PyPI - langflow-base-nightly - Versions diffs - 0.5.0.dev36__py3-none-any.whl → 0.5.0.dev38__py3-none-any.whl - Mend

langflow-base-nightly 0.5.0.dev36py3-none-any.whl → 0.5.0.dev38py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (343) hide show

langflow/initial_setup/starter_projects/Vector Store RAG.json CHANGED Viewed

@@ -2709,7 +2709,7 @@
             "icon": "AstraDB",
             "legacy": false,
             "metadata": {
-              "code_hash": "38a337e89ff4",
+              "code_hash": "23fbe9daca09",
               "module": "langflow.components.vectorstores.astradb.AstraDBVectorStoreComponent"
             },
             "minimized": false,
@@ -2854,7 +2854,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import re\nfrom collections import defaultdict\nfrom dataclasses import asdict, dataclass, field\n\nfrom astrapy import DataAPIClient, Database\nfrom astrapy.data.info.reranking import RerankServiceOptions\nfrom astrapy.info import CollectionDescriptor, CollectionLexicalOptions, CollectionRerankOptions\nfrom langchain_astradb import AstraDBVectorStore, VectorServiceOptions\nfrom langchain_astradb.utils.astradb import HybridSearchMode, _AstraDBCollectionEnvironment\nfrom langchain_core.documents import Document\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom langflow.helpers.data import docs_to_data\nfrom langflow.inputs.inputs import FloatInput, NestedDictInput\nfrom langflow.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    QueryInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.serialization import serialize\nfrom langflow.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.datastax.com/en/langflow/astra-components.html\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    _cached_vector_store: AstraDBVectorStore | None = None\n\n    @dataclass\n    class NewDatabaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_database\",\n                        \"description\": \"Please allow several minutes for creation to complete.\",\n                        \"display_name\": \"Create new database\",\n                        \"field_order\": [\"01_new_database_name\", \"02_cloud_provider\", \"03_region\"],\n                        \"template\": {\n                            \"01_new_database_name\": StrInput(\n                                name=\"new_database_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new database to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_cloud_provider\": DropdownInput(\n                                name=\"cloud_provider\",\n                                display_name=\"Cloud provider\",\n                                info=\"Cloud provider for the new database.\",\n                                options=[],\n                                required=True,\n                                real_time_refresh=True,\n                            ),\n                            \"03_region\": DropdownInput(\n                                name=\"region\",\n                                display_name=\"Region\",\n                                info=\"Region for the new database.\",\n                                options=[],\n                                required=True,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    @dataclass\n    class NewCollectionInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_collection\",\n                        \"description\": \"Please allow several seconds for creation to complete.\",\n                        \"display_name\": \"Create new collection\",\n                        \"field_order\": [\n                            \"01_new_collection_name\",\n                            \"02_embedding_generation_provider\",\n                            \"03_embedding_generation_model\",\n                            \"04_dimension\",\n                        ],\n                        \"template\": {\n                            \"01_new_collection_name\": StrInput(\n                                name=\"new_collection_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new collection to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_embedding_generation_provider\": DropdownInput(\n                                name=\"embedding_generation_provider\",\n                                display_name=\"Embedding generation method\",\n                                info=\"Provider to use for generating embeddings.\",\n                                helper_text=(\n                                    \"To create collections with more embedding provider options, go to \"\n                                    '<a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" '\n                                    'rel=\"noopener noreferrer\">your database in Astra DB</a>'\n                                ),\n                                real_time_refresh=True,\n                                required=True,\n                                options=[],\n                            ),\n                            \"03_embedding_generation_model\": DropdownInput(\n                                name=\"embedding_generation_model\",\n                                display_name=\"Embedding model\",\n                                info=\"Model to use for generating embeddings.\",\n                                real_time_refresh=True,\n                                options=[],\n                            ),\n                            \"04_dimension\": IntInput(\n                                name=\"dimension\",\n                                display_name=\"Dimensions\",\n                                info=\"Dimensions of the embeddings to generate.\",\n                                value=None,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    inputs = [\n        SecretStrInput(\n            name=\"token\",\n            display_name=\"Astra DB Application Token\",\n            info=\"Authentication token for accessing Astra DB.\",\n            value=\"ASTRA_DB_APPLICATION_TOKEN\",\n            required=True,\n            real_time_refresh=True,\n            input_types=[],\n        ),\n        DropdownInput(\n            name=\"environment\",\n            display_name=\"Environment\",\n            info=\"The environment for the Astra DB API Endpoint.\",\n            options=[\"prod\", \"test\", \"dev\"],\n            value=\"prod\",\n            advanced=True,\n            real_time_refresh=True,\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"database_name\",\n            display_name=\"Database\",\n            info=\"The Database name for the Astra DB instance.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewDatabaseInput()),\n            combobox=True,\n        ),\n        StrInput(\n            name=\"api_endpoint\",\n            display_name=\"Astra DB API Endpoint\",\n            info=\"The API Endpoint for the Astra DB instance. Supercedes database selection.\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"keyspace\",\n            display_name=\"Keyspace\",\n            info=\"Optional keyspace within Astra DB to use for the collection.\",\n            advanced=True,\n            options=[],\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"collection_name\",\n            display_name=\"Collection\",\n            info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewCollectionInput()),\n            combobox=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=False,\n        ),\n        *LCVectorStoreComponent.inputs,\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autodetect_collection\",\n            display_name=\"Autodetect Collection\",\n            info=\"Boolean flag to determine whether to autodetect the collection.\",\n            advanced=True,\n            value=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n    ]\n\n    @classmethod\n    def map_cloud_providers(cls):\n        # TODO: Programmatically fetch the regions for each cloud provider\n        return {\n            \"dev\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-west-2\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\", \"europe-west4\"],\n                },\n            },\n            \"test\": {\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\"],\n                },\n            },\n            \"prod\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-east-2\", \"ap-south-1\", \"eu-west-1\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-east1\"],\n                },\n                \"Microsoft Azure\": {\n                    \"id\": \"azure\",\n                    \"regions\": [\"westus3\"],\n                },\n            },\n        }\n\n    @classmethod\n    def get_vectorize_providers(cls, token: str, environment: str | None = None, api_endpoint: str | None = None):\n        try:\n            # Get the admin object\n            client = DataAPIClient(environment=environment)\n            admin_client = client.get_admin()\n            db_admin = admin_client.get_database_admin(api_endpoint, token=token)\n\n            # Get the list of embedding providers\n            embedding_providers = db_admin.find_embedding_providers()\n\n            vectorize_providers_mapping = {}\n            # Map the provider display name to the provider key and models\n            for provider_key, provider_data in embedding_providers.embedding_providers.items():\n                # Get the provider display name and models\n                display_name = provider_data.display_name\n                models = [model.name for model in provider_data.models]\n\n                # Build our mapping\n                vectorize_providers_mapping[display_name] = [provider_key, models]\n\n            # Sort the resulting dictionary\n            return defaultdict(list, dict(sorted(vectorize_providers_mapping.items())))\n        except Exception as _:  # noqa: BLE001\n            return {}\n\n    @classmethod\n    async def create_database_api(\n        cls,\n        new_database_name: str,\n        cloud_provider: str,\n        region: str,\n        token: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n    ):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the environment, set to prod if null like\n        my_env = environment or \"prod\"\n\n        # Raise a value error if name isn't provided\n        if not new_database_name:\n            msg = \"Database name is required to create a new database.\"\n            raise ValueError(msg)\n\n        # Call the create database function\n        return await admin_client.async_create_database(\n            name=new_database_name,\n            cloud_provider=cls.map_cloud_providers()[my_env][cloud_provider][\"id\"],\n            region=region,\n            keyspace=keyspace,\n            wait_until_active=False,\n        )\n\n    @classmethod\n    async def create_collection_api(\n        cls,\n        new_collection_name: str,\n        token: str,\n        api_endpoint: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n        dimension: int | None = None,\n        embedding_generation_provider: str | None = None,\n        embedding_generation_model: str | None = None,\n        reranker: str | None = None,\n    ):\n        # Build vectorize options, if needed\n        vectorize_options = None\n        if not dimension:\n            providers = cls.get_vectorize_providers(token=token, environment=environment, api_endpoint=api_endpoint)\n            vectorize_options = VectorServiceOptions(\n                provider=providers.get(embedding_generation_provider, [None, []])[0],\n                model_name=embedding_generation_model,\n            )\n\n        # Raise a value error if name isn't provided\n        if not new_collection_name:\n            msg = \"Collection name is required to create a new collection.\"\n            raise ValueError(msg)\n\n        # Define the base arguments being passed to the create collection function\n        base_args = {\n            \"collection_name\": new_collection_name,\n            \"token\": token,\n            \"api_endpoint\": api_endpoint,\n            \"keyspace\": keyspace,\n            \"environment\": environment,\n            \"embedding_dimension\": dimension,\n            \"collection_vector_service_options\": vectorize_options,\n        }\n\n        # Add optional arguments if the reranker is set\n        if reranker:\n            # Split the reranker field into a provider a model name\n            provider, _ = reranker.split(\"/\")\n            base_args[\"collection_rerank\"] = CollectionRerankOptions(\n                service=RerankServiceOptions(provider=provider, model_name=reranker),\n            )\n            base_args[\"collection_lexical\"] = CollectionLexicalOptions(analyzer=\"STANDARD\")\n\n        _AstraDBCollectionEnvironment(**base_args)\n\n    @classmethod\n    def get_database_list_static(cls, token: str, environment: str | None = None):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the list of databases\n        db_list = admin_client.list_databases()\n\n        # Generate the api endpoint for each database\n        db_info_dict = {}\n        for db in db_list:\n            try:\n                # Get the API endpoint for the database\n                api_endpoint = db.regions[0].api_endpoint\n\n                # Get the number of collections\n                try:\n                    # Get the number of collections in the database\n                    num_collections = len(\n                        client.get_database(\n                            api_endpoint,\n                            token=token,\n                        ).list_collection_names()\n                    )\n                except Exception:  # noqa: BLE001\n                    if db.status != \"PENDING\":\n                        continue\n                    num_collections = 0\n\n                # Add the database to the dictionary\n                db_info_dict[db.name] = {\n                    \"api_endpoint\": api_endpoint,\n                    \"keyspaces\": db.keyspaces,\n                    \"collections\": num_collections,\n                    \"status\": db.status if db.status != \"ACTIVE\" else None,\n                    \"org_id\": db.org_id if db.org_id else None,\n                }\n            except Exception:  # noqa: BLE001, S110\n                pass\n\n        return db_info_dict\n\n    def get_database_list(self):\n        return self.get_database_list_static(\n            token=self.token,\n            environment=self.environment,\n        )\n\n    @classmethod\n    def get_api_endpoint_static(\n        cls,\n        token: str,\n        environment: str | None = None,\n        api_endpoint: str | None = None,\n        database_name: str | None = None,\n    ):\n        # If the api_endpoint is set, return it\n        if api_endpoint:\n            return api_endpoint\n\n        # Check if the database_name is like a url\n        if database_name and database_name.startswith(\"https://\"):\n            return database_name\n\n        # If the database is not set, nothing we can do.\n        if not database_name:\n            return None\n\n        # Grab the database object\n        db = cls.get_database_list_static(token=token, environment=environment).get(database_name)\n        if not db:\n            return None\n\n        # Otherwise, get the URL from the database list\n        return db.get(\"api_endpoint\")\n\n    def get_api_endpoint(self):\n        return self.get_api_endpoint_static(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=self.api_endpoint,\n            database_name=self.database_name,\n        )\n\n    @classmethod\n    def get_database_id_static(cls, api_endpoint: str) -> str | None:\n        # Pattern matches standard UUID format: 8-4-4-4-12 hexadecimal characters\n        uuid_pattern = r\"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\"\n        match = re.search(uuid_pattern, api_endpoint)\n\n        return match.group(0) if match else None\n\n    def get_database_id(self):\n        return self.get_database_id_static(api_endpoint=self.get_api_endpoint())\n\n    def get_keyspace(self):\n        keyspace = self.keyspace\n\n        if keyspace:\n            return keyspace.strip()\n\n        return \"default_keyspace\"\n\n    def get_database_object(self, api_endpoint: str | None = None):\n        try:\n            client = DataAPIClient(environment=self.environment)\n\n            return client.get_database(\n                api_endpoint or self.get_api_endpoint(),\n                token=self.token,\n                keyspace=self.get_keyspace(),\n            )\n        except Exception as e:\n            msg = f\"Error fetching database object: {e}\"\n            raise ValueError(msg) from e\n\n    def collection_data(self, collection_name: str, database: Database | None = None):\n        try:\n            if not database:\n                client = DataAPIClient(environment=self.environment)\n\n                database = client.get_database(\n                    self.get_api_endpoint(),\n                    token=self.token,\n                    keyspace=self.get_keyspace(),\n                )\n\n            collection = database.get_collection(collection_name)\n\n            return collection.estimated_document_count()\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Error checking collection data: {e}\")\n\n            return None\n\n    def _initialize_database_options(self):\n        try:\n            return [\n                {\n                    \"name\": name,\n                    \"status\": info[\"status\"],\n                    \"collections\": info[\"collections\"],\n                    \"api_endpoint\": info[\"api_endpoint\"],\n                    \"keyspaces\": info[\"keyspaces\"],\n                    \"org_id\": info[\"org_id\"],\n                }\n                for name, info in self.get_database_list().items()\n            ]\n        except Exception as e:\n            msg = f\"Error fetching database options: {e}\"\n            raise ValueError(msg) from e\n\n    @classmethod\n    def get_provider_icon(cls, collection: CollectionDescriptor | None = None, provider_name: str | None = None) -> str:\n        # Get the provider name from the collection\n        provider_name = provider_name or (\n            collection.definition.vector.service.provider\n            if (\n                collection\n                and collection.definition\n                and collection.definition.vector\n                and collection.definition.vector.service\n            )\n            else None\n        )\n\n        # If there is no provider, use the vector store icon\n        if not provider_name or provider_name.lower() == \"bring your own\":\n            return \"vectorstores\"\n\n        # Map provider casings\n        case_map = {\n            \"nvidia\": \"NVIDIA\",\n            \"openai\": \"OpenAI\",\n            \"amazon bedrock\": \"AmazonBedrockEmbeddings\",\n            \"azure openai\": \"AzureOpenAiEmbeddings\",\n            \"cohere\": \"Cohere\",\n            \"jina ai\": \"JinaAI\",\n            \"mistral ai\": \"MistralAI\",\n            \"upstage\": \"Upstage\",\n            \"voyage ai\": \"VoyageAI\",\n        }\n\n        # Adjust the casing on some like nvidia\n        return case_map[provider_name.lower()] if provider_name.lower() in case_map else provider_name.title()\n\n    def _initialize_collection_options(self, api_endpoint: str | None = None):\n        # Nothing to generate if we don't have an API endpoint yet\n        api_endpoint = api_endpoint or self.get_api_endpoint()\n        if not api_endpoint:\n            return []\n\n        # Retrieve the database object\n        database = self.get_database_object(api_endpoint=api_endpoint)\n\n        # Get the list of collections\n        collection_list = database.list_collections(keyspace=self.get_keyspace())\n\n        # Return the list of collections and metadata associated\n        return [\n            {\n                \"name\": col.name,\n                \"records\": self.collection_data(collection_name=col.name, database=database),\n                \"provider\": (\n                    col.definition.vector.service.provider\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n                \"icon\": self.get_provider_icon(collection=col),\n                \"model\": (\n                    col.definition.vector.service.model_name\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n            }\n            for col in collection_list\n        ]\n\n    def reset_provider_options(self, build_config: dict) -> dict:\n        \"\"\"Reset provider options and related configurations in the build_config dictionary.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get vectorize providers\n        vectorize_providers_api = self.get_vectorize_providers(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n        )\n\n        # Create a new dictionary with \"Bring your own\" first\n        vectorize_providers: dict[str, list[list[str]]] = {\"Bring your own\": [[], []]}\n\n        # Add the remaining items (only Nvidia) from the original dictionary\n        vectorize_providers.update(\n            {\n                k: v\n                for k, v in vectorize_providers_api.items()\n                if k.lower() in [\"nvidia\"]  # TODO: Eventually support more\n            }\n        )\n\n        # Set provider options\n        provider_field = \"02_embedding_generation_provider\"\n        template[provider_field][\"options\"] = list(vectorize_providers.keys())\n\n        # Add metadata for each provider option\n        template[provider_field][\"options_metadata\"] = [\n            {\"icon\": self.get_provider_icon(provider_name=provider)} for provider in template[provider_field][\"options\"]\n        ]\n\n        # Get selected embedding provider\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure embedding model field\n        model_field = \"03_embedding_generation_model\"\n        template[model_field].update(\n            {\n                \"options\": vectorize_providers.get(embedding_provider, [[], []])[1],\n                \"placeholder\": \"Bring your own\" if is_bring_your_own else None,\n                \"readonly\": is_bring_your_own,\n                \"required\": not is_bring_your_own,\n                \"value\": None,\n            }\n        )\n\n        # If this is a bring your own, set dimensions to 0\n        return self.reset_dimension_field(build_config)\n\n    def reset_dimension_field(self, build_config: dict) -> dict:\n        \"\"\"Reset dimension field options based on provided configuration.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get selected embedding model\n        provider_field = \"02_embedding_generation_provider\"\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure dimension field\n        dimension_field = \"04_dimension\"\n        dimension_value = 1024 if not is_bring_your_own else None  # TODO: Dynamically figure this out\n        template[dimension_field].update(\n            {\n                \"placeholder\": dimension_value,\n                \"value\": dimension_value,\n                \"readonly\": not is_bring_your_own,\n                \"required\": is_bring_your_own,\n            }\n        )\n\n        return build_config\n\n    def reset_collection_list(self, build_config: dict) -> dict:\n        \"\"\"Reset collection list options based on provided configuration.\"\"\"\n        # Get collection options\n        collection_options = self._initialize_collection_options(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        # Update collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update(\n            {\n                \"options\": [col[\"name\"] for col in collection_options],\n                \"options_metadata\": [{k: v for k, v in col.items() if k != \"name\"} for col in collection_options],\n            }\n        )\n\n        # Reset selected collection if not in options\n        if collection_config[\"value\"] not in collection_config[\"options\"]:\n            collection_config[\"value\"] = \"\"\n\n        # Set advanced status based on database selection\n        collection_config[\"show\"] = bool(build_config[\"database_name\"][\"value\"])\n\n        return build_config\n\n    def reset_database_list(self, build_config: dict) -> dict:\n        \"\"\"Reset database list options and related configurations.\"\"\"\n        # Get database options\n        database_options = self._initialize_database_options()\n\n        # Update cloud provider options\n        env = self.environment\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_cloud_provider\"][\"options\"] = list(self.map_cloud_providers()[env].keys())\n\n        # Update database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update(\n            {\n                \"options\": [db[\"name\"] for db in database_options],\n                \"options_metadata\": [{k: v for k, v in db.items() if k != \"name\"} for db in database_options],\n            }\n        )\n\n        # Reset selections if value not in options\n        if database_config[\"value\"] not in database_config[\"options\"]:\n            database_config[\"value\"] = \"\"\n            build_config[\"api_endpoint\"][\"value\"] = \"\"\n            build_config[\"collection_name\"][\"show\"] = False\n\n        # Set advanced status based on token presence\n        database_config[\"show\"] = bool(build_config[\"token\"][\"value\"])\n\n        return build_config\n\n    def reset_build_config(self, build_config: dict) -> dict:\n        \"\"\"Reset all build configuration options to default empty state.\"\"\"\n        # Reset database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n        build_config[\"api_endpoint\"][\"value\"] = \"\"\n\n        # Reset collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n\n        return build_config\n\n    def _handle_hybrid_search_options(self, build_config: dict) -> dict:\n        \"\"\"Set hybrid search options in the build configuration.\"\"\"\n        # Detect what hybrid options are available\n        # Get the admin object\n        client = DataAPIClient(environment=self.environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        # We will try to get the reranking providers to see if its hybrid emabled\n        try:\n            providers = db_admin.find_reranking_providers()\n            build_config[\"reranker\"][\"options\"] = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            build_config[\"reranker\"][\"options_metadata\"] = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Set the default search field to hybrid search\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Hybrid Search\"\n        except Exception as _:  # noqa: BLE001\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n            # Set the default search field to vector search\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n\n        # Set reranker and lexical terms options based on search method\n        build_config[\"reranker\"][\"toggle_value\"] = True\n        build_config[\"reranker\"][\"show\"] = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        build_config[\"reranker\"][\"toggle_disable\"] = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        if build_config[\"reranker\"][\"show\"]:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Update build configuration based on field name and value.\"\"\"\n        # Early return if no token provided\n        if not self.token:\n            return self.reset_build_config(build_config)\n\n        # Database creation callback\n        if field_name == \"database_name\" and isinstance(field_value, dict):\n            if \"01_new_database_name\" in field_value:\n                await self._create_new_database(build_config, field_value)\n                return self.reset_collection_list(build_config)\n            return self._update_cloud_regions(build_config, field_value)\n\n        # Collection creation callback\n        if field_name == \"collection_name\" and isinstance(field_value, dict):\n            # Case 1: New collection creation\n            if \"01_new_collection_name\" in field_value:\n                await self._create_new_collection(build_config, field_value)\n                return build_config\n\n            # Case 2: Update embedding provider options\n            if \"02_embedding_generation_provider\" in field_value:\n                return self.reset_provider_options(build_config)\n\n            # Case 3: Update dimension field\n            if \"03_embedding_generation_model\" in field_value:\n                return self.reset_dimension_field(build_config)\n\n        # Initial execution or token/environment change\n        first_run = field_name == \"collection_name\" and not field_value and not build_config[\"database_name\"][\"options\"]\n        if first_run or field_name in {\"token\", \"environment\"}:\n            return self.reset_database_list(build_config)\n\n        # Database selection change\n        if field_name == \"database_name\" and not isinstance(field_value, dict):\n            return self._handle_database_selection(build_config, field_value)\n\n        # Keyspace selection change\n        if field_name == \"keyspace\":\n            return self.reset_collection_list(build_config)\n\n        # Collection selection change\n        if field_name == \"collection_name\" and not isinstance(field_value, dict):\n            return self._handle_collection_selection(build_config, field_value)\n\n        # Search method selection change\n        if field_name == \"search_method\":\n            is_vector_search = field_value == \"Vector Search\"\n            is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n            # Configure lexical terms (same for both cases)\n            build_config[\"lexical_terms\"][\"show\"] = not is_vector_search\n            build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n            # Disable reranker disabling if hybrid search is selected\n            build_config[\"reranker\"][\"toggle_disable\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_value\"] = True\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Toggle search type and score threshold based on search method\n            build_config[\"search_type\"][\"show\"] = is_vector_search\n            build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n            # Make sure the search_type is set to \"Similarity\"\n            if not is_vector_search or is_autodetect:\n                build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def _create_new_database(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new database and update build config options.\"\"\"\n        try:\n            await self.create_database_api(\n                new_database_name=field_value[\"01_new_database_name\"],\n                token=self.token,\n                keyspace=self.get_keyspace(),\n                environment=self.environment,\n                cloud_provider=field_value[\"02_cloud_provider\"],\n                region=field_value[\"03_region\"],\n            )\n        except Exception as e:\n            msg = f\"Error creating database: {e}\"\n            raise ValueError(msg) from e\n\n        build_config[\"database_name\"][\"options\"].append(field_value[\"01_new_database_name\"])\n        build_config[\"database_name\"][\"options_metadata\"].append(\n            {\n                \"status\": \"PENDING\",\n                \"collections\": 0,\n                \"api_endpoint\": None,\n                \"keyspaces\": [self.get_keyspace()],\n                \"org_id\": None,\n            }\n        )\n\n    def _update_cloud_regions(self, build_config: dict, field_value: dict) -> dict:\n        \"\"\"Update cloud provider regions in build config.\"\"\"\n        env = self.environment\n        cloud_provider = field_value[\"02_cloud_provider\"]\n\n        # Update the region options based on the selected cloud provider\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"03_region\"][\"options\"] = self.map_cloud_providers()[env][cloud_provider][\"regions\"]\n\n        # Reset the the 03_region value if it's not in the new options\n        if template[\"03_region\"][\"value\"] not in template[\"03_region\"][\"options\"]:\n            template[\"03_region\"][\"value\"] = None\n\n        return build_config\n\n    async def _create_new_collection(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new collection and update build config options.\"\"\"\n        embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n        try:\n            await self.create_collection_api(\n                new_collection_name=field_value[\"01_new_collection_name\"],\n                token=self.token,\n                api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n                environment=self.environment,\n                keyspace=self.get_keyspace(),\n                dimension=field_value.get(\"04_dimension\") if embedding_provider == \"Bring your own\" else None,\n                embedding_generation_provider=embedding_provider,\n                embedding_generation_model=field_value.get(\"03_embedding_generation_model\"),\n                reranker=self.reranker,\n            )\n        except Exception as e:\n            msg = f\"Error creating collection: {e}\"\n            raise ValueError(msg) from e\n\n        provider = embedding_provider.lower() if embedding_provider and embedding_provider != \"Bring your own\" else None\n        build_config[\"collection_name\"].update(\n            {\n                \"value\": field_value[\"01_new_collection_name\"],\n                \"options\": build_config[\"collection_name\"][\"options\"] + [field_value[\"01_new_collection_name\"]],\n            }\n        )\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n        build_config[\"collection_name\"][\"options_metadata\"].append(\n            {\n                \"records\": 0,\n                \"provider\": provider,\n                \"icon\": self.get_provider_icon(provider_name=provider),\n                \"model\": field_value.get(\"03_embedding_generation_model\"),\n            }\n        )\n\n        # Make sure we always show the reranker options if the collection is hybrid enabled\n        # And right now they always are\n        build_config[\"lexical_terms\"][\"show\"] = True\n\n    def _handle_database_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle database selection and update related configurations.\"\"\"\n        build_config = self.reset_database_list(build_config)\n\n        # Reset collection list if database selection changes\n        if field_value not in build_config[\"database_name\"][\"options\"]:\n            build_config[\"database_name\"][\"value\"] = \"\"\n            return build_config\n\n        # Get the api endpoint for the selected database\n        index = build_config[\"database_name\"][\"options\"].index(field_value)\n        build_config[\"api_endpoint\"][\"value\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"api_endpoint\"]\n\n        # Get the org_id for the selected database\n        org_id = build_config[\"database_name\"][\"options_metadata\"][index][\"org_id\"]\n        if not org_id:\n            return build_config\n\n        # Update the list of keyspaces based on the db info\n        build_config[\"keyspace\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"keyspaces\"]\n        build_config[\"keyspace\"][\"value\"] = (\n            build_config[\"keyspace\"][\"options\"] and build_config[\"keyspace\"][\"options\"][0]\n            if build_config[\"keyspace\"][\"value\"] not in build_config[\"keyspace\"][\"options\"]\n            else build_config[\"keyspace\"][\"value\"]\n        )\n\n        # Get the database id for the selected database\n        db_id = self.get_database_id_static(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        keyspace = self.get_keyspace()\n\n        # Update the helper text for the embedding provider field\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_embedding_generation_provider\"][\"helper_text\"] = (\n            \"To create collections with more embedding provider options, go to \"\n            f'<a class=\"underline\" target=\"_blank\" rel=\"noopener noreferrer\" '\n            f'href=\"https://astra.datastax.com/org/{org_id}/database/{db_id}/data-explorer?createCollection=1&namespace={keyspace}\">'\n            \"your database in Astra DB</a>.\"\n        )\n\n        # Reset provider options\n        build_config = self.reset_provider_options(build_config)\n\n        # Handle hybrid search options\n        build_config = self._handle_hybrid_search_options(build_config)\n\n        return self.reset_collection_list(build_config)\n\n    def _handle_collection_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle collection selection and update embedding options.\"\"\"\n        build_config[\"autodetect_collection\"][\"value\"] = True\n        build_config = self.reset_collection_list(build_config)\n\n        # Reset embedding model if collection selection changes\n        if field_value and field_value not in build_config[\"collection_name\"][\"options\"]:\n            build_config[\"collection_name\"][\"options\"].append(field_value)\n            build_config[\"collection_name\"][\"options_metadata\"].append(\n                {\n                    \"records\": 0,\n                    \"provider\": None,\n                    \"icon\": \"vectorstores\",\n                    \"model\": None,\n                }\n            )\n            build_config[\"autodetect_collection\"][\"value\"] = False\n\n        if not field_value:\n            return build_config\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(field_value)\n\n        # Set the provider of the selected collection\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Grab the collection object\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=field_value,\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        # Check if hybrid and lexical are enabled\n        col_options = collection.options()\n        hyb_enabled = col_options.rerank and col_options.rerank.enabled\n        lex_enabled = col_options.lexical and col_options.lexical.enabled\n        user_hyb_enabled = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n\n        # Show lexical terms if the collection is hybrid enabled\n        build_config[\"lexical_terms\"][\"show\"] = hyb_enabled and lex_enabled and user_hyb_enabled\n\n        return build_config\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except Exception as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except Exception as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except Exception as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except Exception as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except Exception as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
+                "value": "import re\nfrom collections import defaultdict\nfrom dataclasses import asdict, dataclass, field\n\nfrom astrapy import DataAPIClient, Database\nfrom astrapy.data.info.reranking import RerankServiceOptions\nfrom astrapy.info import CollectionDescriptor, CollectionLexicalOptions, CollectionRerankOptions\nfrom langchain_astradb import AstraDBVectorStore, VectorServiceOptions\nfrom langchain_astradb.utils.astradb import HybridSearchMode, _AstraDBCollectionEnvironment\nfrom langchain_core.documents import Document\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom langflow.helpers.data import docs_to_data\nfrom langflow.inputs.inputs import FloatInput, NestedDictInput\nfrom langflow.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    QueryInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.serialization import serialize\nfrom langflow.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.datastax.com/en/langflow/astra-components.html\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    _cached_vector_store: AstraDBVectorStore | None = None\n\n    @dataclass\n    class NewDatabaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_database\",\n                        \"description\": \"Please allow several minutes for creation to complete.\",\n                        \"display_name\": \"Create new database\",\n                        \"field_order\": [\"01_new_database_name\", \"02_cloud_provider\", \"03_region\"],\n                        \"template\": {\n                            \"01_new_database_name\": StrInput(\n                                name=\"new_database_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new database to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_cloud_provider\": DropdownInput(\n                                name=\"cloud_provider\",\n                                display_name=\"Cloud provider\",\n                                info=\"Cloud provider for the new database.\",\n                                options=[],\n                                required=True,\n                                real_time_refresh=True,\n                            ),\n                            \"03_region\": DropdownInput(\n                                name=\"region\",\n                                display_name=\"Region\",\n                                info=\"Region for the new database.\",\n                                options=[],\n                                required=True,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    @dataclass\n    class NewCollectionInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_collection\",\n                        \"description\": \"Please allow several seconds for creation to complete.\",\n                        \"display_name\": \"Create new collection\",\n                        \"field_order\": [\n                            \"01_new_collection_name\",\n                            \"02_embedding_generation_provider\",\n                            \"03_embedding_generation_model\",\n                            \"04_dimension\",\n                        ],\n                        \"template\": {\n                            \"01_new_collection_name\": StrInput(\n                                name=\"new_collection_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new collection to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_embedding_generation_provider\": DropdownInput(\n                                name=\"embedding_generation_provider\",\n                                display_name=\"Embedding generation method\",\n                                info=\"Provider to use for generating embeddings.\",\n                                helper_text=(\n                                    \"To create collections with more embedding provider options, go to \"\n                                    '<a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" '\n                                    'rel=\"noopener noreferrer\">your database in Astra DB</a>'\n                                ),\n                                real_time_refresh=True,\n                                required=True,\n                                options=[],\n                            ),\n                            \"03_embedding_generation_model\": DropdownInput(\n                                name=\"embedding_generation_model\",\n                                display_name=\"Embedding model\",\n                                info=\"Model to use for generating embeddings.\",\n                                real_time_refresh=True,\n                                options=[],\n                            ),\n                            \"04_dimension\": IntInput(\n                                name=\"dimension\",\n                                display_name=\"Dimensions\",\n                                info=\"Dimensions of the embeddings to generate.\",\n                                value=None,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    inputs = [\n        SecretStrInput(\n            name=\"token\",\n            display_name=\"Astra DB Application Token\",\n            info=\"Authentication token for accessing Astra DB.\",\n            value=\"ASTRA_DB_APPLICATION_TOKEN\",\n            required=True,\n            real_time_refresh=True,\n            input_types=[],\n        ),\n        DropdownInput(\n            name=\"environment\",\n            display_name=\"Environment\",\n            info=\"The environment for the Astra DB API Endpoint.\",\n            options=[\"prod\", \"test\", \"dev\"],\n            value=\"prod\",\n            advanced=True,\n            real_time_refresh=True,\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"database_name\",\n            display_name=\"Database\",\n            info=\"The Database name for the Astra DB instance.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewDatabaseInput()),\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"api_endpoint\",\n            display_name=\"Astra DB API Endpoint\",\n            info=\"The API Endpoint for the Astra DB instance. Supercedes database selection.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"keyspace\",\n            display_name=\"Keyspace\",\n            info=\"Optional keyspace within Astra DB to use for the collection.\",\n            advanced=True,\n            options=[],\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"collection_name\",\n            display_name=\"Collection\",\n            info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewCollectionInput()),\n            combobox=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=False,\n        ),\n        *LCVectorStoreComponent.inputs,\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autodetect_collection\",\n            display_name=\"Autodetect Collection\",\n            info=\"Boolean flag to determine whether to autodetect the collection.\",\n            advanced=True,\n            value=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n    ]\n\n    @classmethod\n    def map_cloud_providers(cls):\n        # TODO: Programmatically fetch the regions for each cloud provider\n        return {\n            \"dev\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-west-2\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\", \"europe-west4\"],\n                },\n            },\n            \"test\": {\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\"],\n                },\n            },\n            \"prod\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-east-2\", \"ap-south-1\", \"eu-west-1\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-east1\"],\n                },\n                \"Microsoft Azure\": {\n                    \"id\": \"azure\",\n                    \"regions\": [\"westus3\"],\n                },\n            },\n        }\n\n    @classmethod\n    def get_vectorize_providers(cls, token: str, environment: str | None = None, api_endpoint: str | None = None):\n        try:\n            # Get the admin object\n            client = DataAPIClient(environment=environment)\n            admin_client = client.get_admin()\n            db_admin = admin_client.get_database_admin(api_endpoint, token=token)\n\n            # Get the list of embedding providers\n            embedding_providers = db_admin.find_embedding_providers()\n\n            vectorize_providers_mapping = {}\n            # Map the provider display name to the provider key and models\n            for provider_key, provider_data in embedding_providers.embedding_providers.items():\n                # Get the provider display name and models\n                display_name = provider_data.display_name\n                models = [model.name for model in provider_data.models]\n\n                # Build our mapping\n                vectorize_providers_mapping[display_name] = [provider_key, models]\n\n            # Sort the resulting dictionary\n            return defaultdict(list, dict(sorted(vectorize_providers_mapping.items())))\n        except Exception as _:  # noqa: BLE001\n            return {}\n\n    @classmethod\n    async def create_database_api(\n        cls,\n        new_database_name: str,\n        cloud_provider: str,\n        region: str,\n        token: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n    ):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the environment, set to prod if null like\n        my_env = environment or \"prod\"\n\n        # Raise a value error if name isn't provided\n        if not new_database_name:\n            msg = \"Database name is required to create a new database.\"\n            raise ValueError(msg)\n\n        # Call the create database function\n        return await admin_client.async_create_database(\n            name=new_database_name,\n            cloud_provider=cls.map_cloud_providers()[my_env][cloud_provider][\"id\"],\n            region=region,\n            keyspace=keyspace,\n            wait_until_active=False,\n        )\n\n    @classmethod\n    async def create_collection_api(\n        cls,\n        new_collection_name: str,\n        token: str,\n        api_endpoint: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n        dimension: int | None = None,\n        embedding_generation_provider: str | None = None,\n        embedding_generation_model: str | None = None,\n        reranker: str | None = None,\n    ):\n        # Build vectorize options, if needed\n        vectorize_options = None\n        if not dimension:\n            providers = cls.get_vectorize_providers(token=token, environment=environment, api_endpoint=api_endpoint)\n            vectorize_options = VectorServiceOptions(\n                provider=providers.get(embedding_generation_provider, [None, []])[0],\n                model_name=embedding_generation_model,\n            )\n\n        # Raise a value error if name isn't provided\n        if not new_collection_name:\n            msg = \"Collection name is required to create a new collection.\"\n            raise ValueError(msg)\n\n        # Define the base arguments being passed to the create collection function\n        base_args = {\n            \"collection_name\": new_collection_name,\n            \"token\": token,\n            \"api_endpoint\": api_endpoint,\n            \"keyspace\": keyspace,\n            \"environment\": environment,\n            \"embedding_dimension\": dimension,\n            \"collection_vector_service_options\": vectorize_options,\n        }\n\n        # Add optional arguments if the reranker is set\n        if reranker:\n            # Split the reranker field into a provider a model name\n            provider, _ = reranker.split(\"/\")\n            base_args[\"collection_rerank\"] = CollectionRerankOptions(\n                service=RerankServiceOptions(provider=provider, model_name=reranker),\n            )\n            base_args[\"collection_lexical\"] = CollectionLexicalOptions(analyzer=\"STANDARD\")\n\n        _AstraDBCollectionEnvironment(**base_args)\n\n    @classmethod\n    def get_database_list_static(cls, token: str, environment: str | None = None):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the list of databases\n        db_list = admin_client.list_databases()\n\n        # Generate the api endpoint for each database\n        db_info_dict = {}\n        for db in db_list:\n            try:\n                # Get the API endpoint for the database\n                api_endpoints = [db_reg.api_endpoint for db_reg in db.regions]\n\n                # Get the number of collections\n                try:\n                    # Get the number of collections in the database\n                    num_collections = len(\n                        client.get_database(\n                            api_endpoints[0],\n                            token=token,\n                        ).list_collection_names()\n                    )\n                except Exception:  # noqa: BLE001\n                    if db.status != \"PENDING\":\n                        continue\n                    num_collections = 0\n\n                # Add the database to the dictionary\n                db_info_dict[db.name] = {\n                    \"api_endpoints\": api_endpoints,\n                    \"keyspaces\": db.keyspaces,\n                    \"collections\": num_collections,\n                    \"status\": db.status if db.status != \"ACTIVE\" else None,\n                    \"org_id\": db.org_id if db.org_id else None,\n                }\n            except Exception:  # noqa: BLE001, S110\n                pass\n\n        return db_info_dict\n\n    def get_database_list(self):\n        return self.get_database_list_static(\n            token=self.token,\n            environment=self.environment,\n        )\n\n    @classmethod\n    def get_api_endpoint_static(\n        cls,\n        token: str,\n        environment: str | None = None,\n        api_endpoint: str | None = None,\n        database_name: str | None = None,\n    ):\n        # If the api_endpoint is set, return it\n        if api_endpoint:\n            return api_endpoint\n\n        # Check if the database_name is like a url\n        if database_name and database_name.startswith(\"https://\"):\n            return database_name\n\n        # If the database is not set, nothing we can do.\n        if not database_name:\n            return None\n\n        # Grab the database object\n        db = cls.get_database_list_static(token=token, environment=environment).get(database_name)\n        if not db:\n            return None\n\n        # Otherwise, get the URL from the database list\n        endpoints = db.get(\"api_endpoints\") or []\n        return endpoints[0] if endpoints else None\n\n    def get_api_endpoint(self):\n        return self.get_api_endpoint_static(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=self.api_endpoint,\n            database_name=self.database_name,\n        )\n\n    @classmethod\n    def get_database_id_static(cls, api_endpoint: str) -> str | None:\n        # Pattern matches standard UUID format: 8-4-4-4-12 hexadecimal characters\n        uuid_pattern = r\"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\"\n        match = re.search(uuid_pattern, api_endpoint)\n\n        return match.group(0) if match else None\n\n    def get_database_id(self):\n        return self.get_database_id_static(api_endpoint=self.get_api_endpoint())\n\n    def get_keyspace(self):\n        keyspace = self.keyspace\n\n        if keyspace:\n            return keyspace.strip()\n\n        return \"default_keyspace\"\n\n    def get_database_object(self, api_endpoint: str | None = None):\n        try:\n            client = DataAPIClient(environment=self.environment)\n\n            return client.get_database(\n                api_endpoint or self.get_api_endpoint(),\n                token=self.token,\n                keyspace=self.get_keyspace(),\n            )\n        except Exception as e:\n            msg = f\"Error fetching database object: {e}\"\n            raise ValueError(msg) from e\n\n    def collection_data(self, collection_name: str, database: Database | None = None):\n        try:\n            if not database:\n                client = DataAPIClient(environment=self.environment)\n\n                database = client.get_database(\n                    self.get_api_endpoint(),\n                    token=self.token,\n                    keyspace=self.get_keyspace(),\n                )\n\n            collection = database.get_collection(collection_name)\n\n            return collection.estimated_document_count()\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Error checking collection data: {e}\")\n\n            return None\n\n    def _initialize_database_options(self):\n        try:\n            return [\n                {\n                    \"name\": name,\n                    \"status\": info[\"status\"],\n                    \"collections\": info[\"collections\"],\n                    \"api_endpoints\": info[\"api_endpoints\"],\n                    \"keyspaces\": info[\"keyspaces\"],\n                    \"org_id\": info[\"org_id\"],\n                }\n                for name, info in self.get_database_list().items()\n            ]\n        except Exception as e:\n            msg = f\"Error fetching database options: {e}\"\n            raise ValueError(msg) from e\n\n    @classmethod\n    def get_provider_icon(cls, collection: CollectionDescriptor | None = None, provider_name: str | None = None) -> str:\n        # Get the provider name from the collection\n        provider_name = provider_name or (\n            collection.definition.vector.service.provider\n            if (\n                collection\n                and collection.definition\n                and collection.definition.vector\n                and collection.definition.vector.service\n            )\n            else None\n        )\n\n        # If there is no provider, use the vector store icon\n        if not provider_name or provider_name.lower() == \"bring your own\":\n            return \"vectorstores\"\n\n        # Map provider casings\n        case_map = {\n            \"nvidia\": \"NVIDIA\",\n            \"openai\": \"OpenAI\",\n            \"amazon bedrock\": \"AmazonBedrockEmbeddings\",\n            \"azure openai\": \"AzureOpenAiEmbeddings\",\n            \"cohere\": \"Cohere\",\n            \"jina ai\": \"JinaAI\",\n            \"mistral ai\": \"MistralAI\",\n            \"upstage\": \"Upstage\",\n            \"voyage ai\": \"VoyageAI\",\n        }\n\n        # Adjust the casing on some like nvidia\n        return case_map[provider_name.lower()] if provider_name.lower() in case_map else provider_name.title()\n\n    def _initialize_collection_options(self, api_endpoint: str | None = None):\n        # Nothing to generate if we don't have an API endpoint yet\n        api_endpoint = api_endpoint or self.get_api_endpoint()\n        if not api_endpoint:\n            return []\n\n        # Retrieve the database object\n        database = self.get_database_object(api_endpoint=api_endpoint)\n\n        # Get the list of collections\n        collection_list = database.list_collections(keyspace=self.get_keyspace())\n\n        # Return the list of collections and metadata associated\n        return [\n            {\n                \"name\": col.name,\n                \"records\": self.collection_data(collection_name=col.name, database=database),\n                \"provider\": (\n                    col.definition.vector.service.provider\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n                \"icon\": self.get_provider_icon(collection=col),\n                \"model\": (\n                    col.definition.vector.service.model_name\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n            }\n            for col in collection_list\n        ]\n\n    def reset_provider_options(self, build_config: dict) -> dict:\n        \"\"\"Reset provider options and related configurations in the build_config dictionary.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get vectorize providers\n        vectorize_providers_api = self.get_vectorize_providers(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n        )\n\n        # Create a new dictionary with \"Bring your own\" first\n        vectorize_providers: dict[str, list[list[str]]] = {\"Bring your own\": [[], []]}\n\n        # Add the remaining items (only Nvidia) from the original dictionary\n        vectorize_providers.update(\n            {\n                k: v\n                for k, v in vectorize_providers_api.items()\n                if k.lower() in [\"nvidia\"]  # TODO: Eventually support more\n            }\n        )\n\n        # Set provider options\n        provider_field = \"02_embedding_generation_provider\"\n        template[provider_field][\"options\"] = list(vectorize_providers.keys())\n\n        # Add metadata for each provider option\n        template[provider_field][\"options_metadata\"] = [\n            {\"icon\": self.get_provider_icon(provider_name=provider)} for provider in template[provider_field][\"options\"]\n        ]\n\n        # Get selected embedding provider\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure embedding model field\n        model_field = \"03_embedding_generation_model\"\n        template[model_field].update(\n            {\n                \"options\": vectorize_providers.get(embedding_provider, [[], []])[1],\n                \"placeholder\": \"Bring your own\" if is_bring_your_own else None,\n                \"readonly\": is_bring_your_own,\n                \"required\": not is_bring_your_own,\n                \"value\": None,\n            }\n        )\n\n        # If this is a bring your own, set dimensions to 0\n        return self.reset_dimension_field(build_config)\n\n    def reset_dimension_field(self, build_config: dict) -> dict:\n        \"\"\"Reset dimension field options based on provided configuration.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get selected embedding model\n        provider_field = \"02_embedding_generation_provider\"\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure dimension field\n        dimension_field = \"04_dimension\"\n        dimension_value = 1024 if not is_bring_your_own else None  # TODO: Dynamically figure this out\n        template[dimension_field].update(\n            {\n                \"placeholder\": dimension_value,\n                \"value\": dimension_value,\n                \"readonly\": not is_bring_your_own,\n                \"required\": is_bring_your_own,\n            }\n        )\n\n        return build_config\n\n    def reset_collection_list(self, build_config: dict) -> dict:\n        \"\"\"Reset collection list options based on provided configuration.\"\"\"\n        # Get collection options\n        collection_options = self._initialize_collection_options(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        # Update collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update(\n            {\n                \"options\": [col[\"name\"] for col in collection_options],\n                \"options_metadata\": [{k: v for k, v in col.items() if k != \"name\"} for col in collection_options],\n            }\n        )\n\n        # Reset selected collection if not in options\n        if collection_config[\"value\"] not in collection_config[\"options\"]:\n            collection_config[\"value\"] = \"\"\n\n        # Set advanced status based on database selection\n        collection_config[\"show\"] = bool(build_config[\"database_name\"][\"value\"])\n\n        return build_config\n\n    def reset_database_list(self, build_config: dict) -> dict:\n        \"\"\"Reset database list options and related configurations.\"\"\"\n        # Get database options\n        database_options = self._initialize_database_options()\n\n        # Update cloud provider options\n        env = self.environment\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_cloud_provider\"][\"options\"] = list(self.map_cloud_providers()[env].keys())\n\n        # Update database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update(\n            {\n                \"options\": [db[\"name\"] for db in database_options],\n                \"options_metadata\": [{k: v for k, v in db.items() if k != \"name\"} for db in database_options],\n            }\n        )\n\n        # Reset selections if value not in options\n        if database_config[\"value\"] not in database_config[\"options\"]:\n            database_config[\"value\"] = \"\"\n            build_config[\"api_endpoint\"][\"options\"] = []\n            build_config[\"api_endpoint\"][\"value\"] = \"\"\n            build_config[\"collection_name\"][\"show\"] = False\n\n        # Set advanced status based on token presence\n        database_config[\"show\"] = bool(build_config[\"token\"][\"value\"])\n\n        return build_config\n\n    def reset_build_config(self, build_config: dict) -> dict:\n        \"\"\"Reset all build configuration options to default empty state.\"\"\"\n        # Reset database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n        build_config[\"api_endpoint\"][\"options\"] = []\n        build_config[\"api_endpoint\"][\"value\"] = \"\"\n\n        # Reset collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n\n        return build_config\n\n    def _handle_hybrid_search_options(self, build_config: dict) -> dict:\n        \"\"\"Set hybrid search options in the build configuration.\"\"\"\n        # Detect what hybrid options are available\n        # Get the admin object\n        client = DataAPIClient(environment=self.environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        # We will try to get the reranking providers to see if its hybrid emabled\n        try:\n            providers = db_admin.find_reranking_providers()\n            build_config[\"reranker\"][\"options\"] = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            build_config[\"reranker\"][\"options_metadata\"] = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Set the default search field to hybrid search\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Hybrid Search\"\n        except Exception as _:  # noqa: BLE001\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n            # Set the default search field to vector search\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n\n        return build_config\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Update build configuration based on field name and value.\"\"\"\n        # Early return if no token provided\n        if not self.token:\n            return self.reset_build_config(build_config)\n\n        # Database creation callback\n        if field_name == \"database_name\" and isinstance(field_value, dict):\n            if \"01_new_database_name\" in field_value:\n                await self._create_new_database(build_config, field_value)\n                return self.reset_collection_list(build_config)\n            return self._update_cloud_regions(build_config, field_value)\n\n        # Collection creation callback\n        if field_name == \"collection_name\" and isinstance(field_value, dict):\n            # Case 1: New collection creation\n            if \"01_new_collection_name\" in field_value:\n                await self._create_new_collection(build_config, field_value)\n                return build_config\n\n            # Case 2: Update embedding provider options\n            if \"02_embedding_generation_provider\" in field_value:\n                return self.reset_provider_options(build_config)\n\n            # Case 3: Update dimension field\n            if \"03_embedding_generation_model\" in field_value:\n                return self.reset_dimension_field(build_config)\n\n        # Initial execution or token/environment change\n        first_run = field_name == \"collection_name\" and not field_value and not build_config[\"database_name\"][\"options\"]\n        if first_run or field_name in {\"token\", \"environment\"}:\n            return self.reset_database_list(build_config)\n\n        # Database selection change\n        if field_name == \"database_name\" and not isinstance(field_value, dict):\n            return self._handle_database_selection(build_config, field_value)\n\n        # Keyspace selection change\n        if field_name == \"keyspace\":\n            return self.reset_collection_list(build_config)\n\n        # Collection selection change\n        if field_name == \"collection_name\" and not isinstance(field_value, dict):\n            return self._handle_collection_selection(build_config, field_value)\n\n        # Search method selection change\n        if field_name == \"search_method\":\n            is_vector_search = field_value == \"Vector Search\"\n            is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n            # Configure lexical terms (same for both cases)\n            build_config[\"lexical_terms\"][\"show\"] = not is_vector_search\n            build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n            # Disable reranker disabling if hybrid search is selected\n            build_config[\"reranker\"][\"show\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_disable\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_value\"] = True\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Toggle search type and score threshold based on search method\n            build_config[\"search_type\"][\"show\"] = is_vector_search\n            build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n            # Make sure the search_type is set to \"Similarity\"\n            if not is_vector_search or is_autodetect:\n                build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def _create_new_database(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new database and update build config options.\"\"\"\n        try:\n            await self.create_database_api(\n                new_database_name=field_value[\"01_new_database_name\"],\n                token=self.token,\n                keyspace=self.get_keyspace(),\n                environment=self.environment,\n                cloud_provider=field_value[\"02_cloud_provider\"],\n                region=field_value[\"03_region\"],\n            )\n        except Exception as e:\n            msg = f\"Error creating database: {e}\"\n            raise ValueError(msg) from e\n\n        build_config[\"database_name\"][\"options\"].append(field_value[\"01_new_database_name\"])\n        build_config[\"database_name\"][\"options_metadata\"].append(\n            {\n                \"status\": \"PENDING\",\n                \"collections\": 0,\n                \"api_endpoints\": [],\n                \"keyspaces\": [self.get_keyspace()],\n                \"org_id\": None,\n            }\n        )\n\n    def _update_cloud_regions(self, build_config: dict, field_value: dict) -> dict:\n        \"\"\"Update cloud provider regions in build config.\"\"\"\n        env = self.environment\n        cloud_provider = field_value[\"02_cloud_provider\"]\n\n        # Update the region options based on the selected cloud provider\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"03_region\"][\"options\"] = self.map_cloud_providers()[env][cloud_provider][\"regions\"]\n\n        # Reset the the 03_region value if it's not in the new options\n        if template[\"03_region\"][\"value\"] not in template[\"03_region\"][\"options\"]:\n            template[\"03_region\"][\"value\"] = None\n\n        return build_config\n\n    async def _create_new_collection(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new collection and update build config options.\"\"\"\n        embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n        try:\n            await self.create_collection_api(\n                new_collection_name=field_value[\"01_new_collection_name\"],\n                token=self.token,\n                api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n                environment=self.environment,\n                keyspace=self.get_keyspace(),\n                dimension=field_value.get(\"04_dimension\") if embedding_provider == \"Bring your own\" else None,\n                embedding_generation_provider=embedding_provider,\n                embedding_generation_model=field_value.get(\"03_embedding_generation_model\"),\n                reranker=self.reranker,\n            )\n        except Exception as e:\n            msg = f\"Error creating collection: {e}\"\n            raise ValueError(msg) from e\n\n        provider = embedding_provider.lower() if embedding_provider and embedding_provider != \"Bring your own\" else None\n        build_config[\"collection_name\"].update(\n            {\n                \"value\": field_value[\"01_new_collection_name\"],\n                \"options\": build_config[\"collection_name\"][\"options\"] + [field_value[\"01_new_collection_name\"]],\n            }\n        )\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n        build_config[\"collection_name\"][\"options_metadata\"].append(\n            {\n                \"records\": 0,\n                \"provider\": provider,\n                \"icon\": self.get_provider_icon(provider_name=provider),\n                \"model\": field_value.get(\"03_embedding_generation_model\"),\n            }\n        )\n\n        # Make sure we always show the reranker options if the collection is hybrid enabled\n        # And right now they always are\n        build_config[\"lexical_terms\"][\"show\"] = True\n\n    def _handle_database_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle database selection and update related configurations.\"\"\"\n        build_config = self.reset_database_list(build_config)\n\n        # Reset collection list if database selection changes\n        if field_value not in build_config[\"database_name\"][\"options\"]:\n            build_config[\"database_name\"][\"value\"] = \"\"\n            return build_config\n\n        # Get the api endpoint for the selected database\n        index = build_config[\"database_name\"][\"options\"].index(field_value)\n        build_config[\"api_endpoint\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\n            \"api_endpoints\"\n        ]\n        build_config[\"api_endpoint\"][\"value\"] = build_config[\"database_name\"][\"options_metadata\"][index][\n            \"api_endpoints\"\n        ][0]\n\n        # Get the org_id for the selected database\n        org_id = build_config[\"database_name\"][\"options_metadata\"][index][\"org_id\"]\n        if not org_id:\n            return build_config\n\n        # Update the list of keyspaces based on the db info\n        build_config[\"keyspace\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"keyspaces\"]\n        build_config[\"keyspace\"][\"value\"] = (\n            build_config[\"keyspace\"][\"options\"] and build_config[\"keyspace\"][\"options\"][0]\n            if build_config[\"keyspace\"][\"value\"] not in build_config[\"keyspace\"][\"options\"]\n            else build_config[\"keyspace\"][\"value\"]\n        )\n\n        # Get the database id for the selected database\n        db_id = self.get_database_id_static(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        keyspace = self.get_keyspace()\n\n        # Update the helper text for the embedding provider field\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_embedding_generation_provider\"][\"helper_text\"] = (\n            \"To create collections with more embedding provider options, go to \"\n            f'<a class=\"underline\" target=\"_blank\" rel=\"noopener noreferrer\" '\n            f'href=\"https://astra.datastax.com/org/{org_id}/database/{db_id}/data-explorer?createCollection=1&namespace={keyspace}\">'\n            \"your database in Astra DB</a>.\"\n        )\n\n        # Reset provider options\n        build_config = self.reset_provider_options(build_config)\n\n        # Handle hybrid search options\n        build_config = self._handle_hybrid_search_options(build_config)\n\n        return self.reset_collection_list(build_config)\n\n    def _handle_collection_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle collection selection and update embedding options.\"\"\"\n        build_config[\"autodetect_collection\"][\"value\"] = True\n        build_config = self.reset_collection_list(build_config)\n\n        # Reset embedding model if collection selection changes\n        if field_value and field_value not in build_config[\"collection_name\"][\"options\"]:\n            build_config[\"collection_name\"][\"options\"].append(field_value)\n            build_config[\"collection_name\"][\"options_metadata\"].append(\n                {\n                    \"records\": 0,\n                    \"provider\": None,\n                    \"icon\": \"vectorstores\",\n                    \"model\": None,\n                }\n            )\n            build_config[\"autodetect_collection\"][\"value\"] = False\n\n        if not field_value:\n            return build_config\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(field_value)\n\n        # Set the provider of the selected collection\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Grab the collection object\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=field_value,\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        # Check if hybrid and lexical are enabled\n        col_options = collection.options()\n        hyb_enabled = col_options.rerank and col_options.rerank.enabled\n        lex_enabled = col_options.lexical and col_options.lexical.enabled\n        user_hyb_enabled = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n\n        # Reranker visible when both the collection supports it and the user selected Hybrid\n        hybrid_active = bool(hyb_enabled and user_hyb_enabled)\n        build_config[\"reranker\"][\"show\"] = hybrid_active\n        build_config[\"reranker\"][\"toggle_value\"] = hybrid_active\n        build_config[\"reranker\"][\"toggle_disable\"] = False  # allow user to toggle if visible\n\n        # If hybrid is active, lock search_type to \"Similarity\"\n        if hybrid_active:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        # Show the lexical terms option only if the collection enables lexical search\n        build_config[\"lexical_terms\"][\"show\"] = bool(lex_enabled)\n\n        return build_config\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except Exception as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except Exception as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except Exception as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except Exception as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except Exception as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
               },
               "collection_name": {
                 "_input_type": "DropdownInput",
@@ -3485,7 +3485,7 @@
             "icon": "AstraDB",
             "legacy": false,
             "metadata": {
-              "code_hash": "38a337e89ff4",
+              "code_hash": "23fbe9daca09",
               "module": "langflow.components.vectorstores.astradb.AstraDBVectorStoreComponent"
             },
             "minimized": false,
@@ -3629,7 +3629,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import re\nfrom collections import defaultdict\nfrom dataclasses import asdict, dataclass, field\n\nfrom astrapy import DataAPIClient, Database\nfrom astrapy.data.info.reranking import RerankServiceOptions\nfrom astrapy.info import CollectionDescriptor, CollectionLexicalOptions, CollectionRerankOptions\nfrom langchain_astradb import AstraDBVectorStore, VectorServiceOptions\nfrom langchain_astradb.utils.astradb import HybridSearchMode, _AstraDBCollectionEnvironment\nfrom langchain_core.documents import Document\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom langflow.helpers.data import docs_to_data\nfrom langflow.inputs.inputs import FloatInput, NestedDictInput\nfrom langflow.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    QueryInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.serialization import serialize\nfrom langflow.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.datastax.com/en/langflow/astra-components.html\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    _cached_vector_store: AstraDBVectorStore | None = None\n\n    @dataclass\n    class NewDatabaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_database\",\n                        \"description\": \"Please allow several minutes for creation to complete.\",\n                        \"display_name\": \"Create new database\",\n                        \"field_order\": [\"01_new_database_name\", \"02_cloud_provider\", \"03_region\"],\n                        \"template\": {\n                            \"01_new_database_name\": StrInput(\n                                name=\"new_database_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new database to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_cloud_provider\": DropdownInput(\n                                name=\"cloud_provider\",\n                                display_name=\"Cloud provider\",\n                                info=\"Cloud provider for the new database.\",\n                                options=[],\n                                required=True,\n                                real_time_refresh=True,\n                            ),\n                            \"03_region\": DropdownInput(\n                                name=\"region\",\n                                display_name=\"Region\",\n                                info=\"Region for the new database.\",\n                                options=[],\n                                required=True,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    @dataclass\n    class NewCollectionInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_collection\",\n                        \"description\": \"Please allow several seconds for creation to complete.\",\n                        \"display_name\": \"Create new collection\",\n                        \"field_order\": [\n                            \"01_new_collection_name\",\n                            \"02_embedding_generation_provider\",\n                            \"03_embedding_generation_model\",\n                            \"04_dimension\",\n                        ],\n                        \"template\": {\n                            \"01_new_collection_name\": StrInput(\n                                name=\"new_collection_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new collection to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_embedding_generation_provider\": DropdownInput(\n                                name=\"embedding_generation_provider\",\n                                display_name=\"Embedding generation method\",\n                                info=\"Provider to use for generating embeddings.\",\n                                helper_text=(\n                                    \"To create collections with more embedding provider options, go to \"\n                                    '<a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" '\n                                    'rel=\"noopener noreferrer\">your database in Astra DB</a>'\n                                ),\n                                real_time_refresh=True,\n                                required=True,\n                                options=[],\n                            ),\n                            \"03_embedding_generation_model\": DropdownInput(\n                                name=\"embedding_generation_model\",\n                                display_name=\"Embedding model\",\n                                info=\"Model to use for generating embeddings.\",\n                                real_time_refresh=True,\n                                options=[],\n                            ),\n                            \"04_dimension\": IntInput(\n                                name=\"dimension\",\n                                display_name=\"Dimensions\",\n                                info=\"Dimensions of the embeddings to generate.\",\n                                value=None,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    inputs = [\n        SecretStrInput(\n            name=\"token\",\n            display_name=\"Astra DB Application Token\",\n            info=\"Authentication token for accessing Astra DB.\",\n            value=\"ASTRA_DB_APPLICATION_TOKEN\",\n            required=True,\n            real_time_refresh=True,\n            input_types=[],\n        ),\n        DropdownInput(\n            name=\"environment\",\n            display_name=\"Environment\",\n            info=\"The environment for the Astra DB API Endpoint.\",\n            options=[\"prod\", \"test\", \"dev\"],\n            value=\"prod\",\n            advanced=True,\n            real_time_refresh=True,\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"database_name\",\n            display_name=\"Database\",\n            info=\"The Database name for the Astra DB instance.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewDatabaseInput()),\n            combobox=True,\n        ),\n        StrInput(\n            name=\"api_endpoint\",\n            display_name=\"Astra DB API Endpoint\",\n            info=\"The API Endpoint for the Astra DB instance. Supercedes database selection.\",\n            show=False,\n        ),\n        DropdownInput(\n            name=\"keyspace\",\n            display_name=\"Keyspace\",\n            info=\"Optional keyspace within Astra DB to use for the collection.\",\n            advanced=True,\n            options=[],\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"collection_name\",\n            display_name=\"Collection\",\n            info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewCollectionInput()),\n            combobox=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=False,\n        ),\n        *LCVectorStoreComponent.inputs,\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autodetect_collection\",\n            display_name=\"Autodetect Collection\",\n            info=\"Boolean flag to determine whether to autodetect the collection.\",\n            advanced=True,\n            value=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n    ]\n\n    @classmethod\n    def map_cloud_providers(cls):\n        # TODO: Programmatically fetch the regions for each cloud provider\n        return {\n            \"dev\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-west-2\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\", \"europe-west4\"],\n                },\n            },\n            \"test\": {\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\"],\n                },\n            },\n            \"prod\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-east-2\", \"ap-south-1\", \"eu-west-1\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-east1\"],\n                },\n                \"Microsoft Azure\": {\n                    \"id\": \"azure\",\n                    \"regions\": [\"westus3\"],\n                },\n            },\n        }\n\n    @classmethod\n    def get_vectorize_providers(cls, token: str, environment: str | None = None, api_endpoint: str | None = None):\n        try:\n            # Get the admin object\n            client = DataAPIClient(environment=environment)\n            admin_client = client.get_admin()\n            db_admin = admin_client.get_database_admin(api_endpoint, token=token)\n\n            # Get the list of embedding providers\n            embedding_providers = db_admin.find_embedding_providers()\n\n            vectorize_providers_mapping = {}\n            # Map the provider display name to the provider key and models\n            for provider_key, provider_data in embedding_providers.embedding_providers.items():\n                # Get the provider display name and models\n                display_name = provider_data.display_name\n                models = [model.name for model in provider_data.models]\n\n                # Build our mapping\n                vectorize_providers_mapping[display_name] = [provider_key, models]\n\n            # Sort the resulting dictionary\n            return defaultdict(list, dict(sorted(vectorize_providers_mapping.items())))\n        except Exception as _:  # noqa: BLE001\n            return {}\n\n    @classmethod\n    async def create_database_api(\n        cls,\n        new_database_name: str,\n        cloud_provider: str,\n        region: str,\n        token: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n    ):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the environment, set to prod if null like\n        my_env = environment or \"prod\"\n\n        # Raise a value error if name isn't provided\n        if not new_database_name:\n            msg = \"Database name is required to create a new database.\"\n            raise ValueError(msg)\n\n        # Call the create database function\n        return await admin_client.async_create_database(\n            name=new_database_name,\n            cloud_provider=cls.map_cloud_providers()[my_env][cloud_provider][\"id\"],\n            region=region,\n            keyspace=keyspace,\n            wait_until_active=False,\n        )\n\n    @classmethod\n    async def create_collection_api(\n        cls,\n        new_collection_name: str,\n        token: str,\n        api_endpoint: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n        dimension: int | None = None,\n        embedding_generation_provider: str | None = None,\n        embedding_generation_model: str | None = None,\n        reranker: str | None = None,\n    ):\n        # Build vectorize options, if needed\n        vectorize_options = None\n        if not dimension:\n            providers = cls.get_vectorize_providers(token=token, environment=environment, api_endpoint=api_endpoint)\n            vectorize_options = VectorServiceOptions(\n                provider=providers.get(embedding_generation_provider, [None, []])[0],\n                model_name=embedding_generation_model,\n            )\n\n        # Raise a value error if name isn't provided\n        if not new_collection_name:\n            msg = \"Collection name is required to create a new collection.\"\n            raise ValueError(msg)\n\n        # Define the base arguments being passed to the create collection function\n        base_args = {\n            \"collection_name\": new_collection_name,\n            \"token\": token,\n            \"api_endpoint\": api_endpoint,\n            \"keyspace\": keyspace,\n            \"environment\": environment,\n            \"embedding_dimension\": dimension,\n            \"collection_vector_service_options\": vectorize_options,\n        }\n\n        # Add optional arguments if the reranker is set\n        if reranker:\n            # Split the reranker field into a provider a model name\n            provider, _ = reranker.split(\"/\")\n            base_args[\"collection_rerank\"] = CollectionRerankOptions(\n                service=RerankServiceOptions(provider=provider, model_name=reranker),\n            )\n            base_args[\"collection_lexical\"] = CollectionLexicalOptions(analyzer=\"STANDARD\")\n\n        _AstraDBCollectionEnvironment(**base_args)\n\n    @classmethod\n    def get_database_list_static(cls, token: str, environment: str | None = None):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the list of databases\n        db_list = admin_client.list_databases()\n\n        # Generate the api endpoint for each database\n        db_info_dict = {}\n        for db in db_list:\n            try:\n                # Get the API endpoint for the database\n                api_endpoint = db.regions[0].api_endpoint\n\n                # Get the number of collections\n                try:\n                    # Get the number of collections in the database\n                    num_collections = len(\n                        client.get_database(\n                            api_endpoint,\n                            token=token,\n                        ).list_collection_names()\n                    )\n                except Exception:  # noqa: BLE001\n                    if db.status != \"PENDING\":\n                        continue\n                    num_collections = 0\n\n                # Add the database to the dictionary\n                db_info_dict[db.name] = {\n                    \"api_endpoint\": api_endpoint,\n                    \"keyspaces\": db.keyspaces,\n                    \"collections\": num_collections,\n                    \"status\": db.status if db.status != \"ACTIVE\" else None,\n                    \"org_id\": db.org_id if db.org_id else None,\n                }\n            except Exception:  # noqa: BLE001, S110\n                pass\n\n        return db_info_dict\n\n    def get_database_list(self):\n        return self.get_database_list_static(\n            token=self.token,\n            environment=self.environment,\n        )\n\n    @classmethod\n    def get_api_endpoint_static(\n        cls,\n        token: str,\n        environment: str | None = None,\n        api_endpoint: str | None = None,\n        database_name: str | None = None,\n    ):\n        # If the api_endpoint is set, return it\n        if api_endpoint:\n            return api_endpoint\n\n        # Check if the database_name is like a url\n        if database_name and database_name.startswith(\"https://\"):\n            return database_name\n\n        # If the database is not set, nothing we can do.\n        if not database_name:\n            return None\n\n        # Grab the database object\n        db = cls.get_database_list_static(token=token, environment=environment).get(database_name)\n        if not db:\n            return None\n\n        # Otherwise, get the URL from the database list\n        return db.get(\"api_endpoint\")\n\n    def get_api_endpoint(self):\n        return self.get_api_endpoint_static(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=self.api_endpoint,\n            database_name=self.database_name,\n        )\n\n    @classmethod\n    def get_database_id_static(cls, api_endpoint: str) -> str | None:\n        # Pattern matches standard UUID format: 8-4-4-4-12 hexadecimal characters\n        uuid_pattern = r\"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\"\n        match = re.search(uuid_pattern, api_endpoint)\n\n        return match.group(0) if match else None\n\n    def get_database_id(self):\n        return self.get_database_id_static(api_endpoint=self.get_api_endpoint())\n\n    def get_keyspace(self):\n        keyspace = self.keyspace\n\n        if keyspace:\n            return keyspace.strip()\n\n        return \"default_keyspace\"\n\n    def get_database_object(self, api_endpoint: str | None = None):\n        try:\n            client = DataAPIClient(environment=self.environment)\n\n            return client.get_database(\n                api_endpoint or self.get_api_endpoint(),\n                token=self.token,\n                keyspace=self.get_keyspace(),\n            )\n        except Exception as e:\n            msg = f\"Error fetching database object: {e}\"\n            raise ValueError(msg) from e\n\n    def collection_data(self, collection_name: str, database: Database | None = None):\n        try:\n            if not database:\n                client = DataAPIClient(environment=self.environment)\n\n                database = client.get_database(\n                    self.get_api_endpoint(),\n                    token=self.token,\n                    keyspace=self.get_keyspace(),\n                )\n\n            collection = database.get_collection(collection_name)\n\n            return collection.estimated_document_count()\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Error checking collection data: {e}\")\n\n            return None\n\n    def _initialize_database_options(self):\n        try:\n            return [\n                {\n                    \"name\": name,\n                    \"status\": info[\"status\"],\n                    \"collections\": info[\"collections\"],\n                    \"api_endpoint\": info[\"api_endpoint\"],\n                    \"keyspaces\": info[\"keyspaces\"],\n                    \"org_id\": info[\"org_id\"],\n                }\n                for name, info in self.get_database_list().items()\n            ]\n        except Exception as e:\n            msg = f\"Error fetching database options: {e}\"\n            raise ValueError(msg) from e\n\n    @classmethod\n    def get_provider_icon(cls, collection: CollectionDescriptor | None = None, provider_name: str | None = None) -> str:\n        # Get the provider name from the collection\n        provider_name = provider_name or (\n            collection.definition.vector.service.provider\n            if (\n                collection\n                and collection.definition\n                and collection.definition.vector\n                and collection.definition.vector.service\n            )\n            else None\n        )\n\n        # If there is no provider, use the vector store icon\n        if not provider_name or provider_name.lower() == \"bring your own\":\n            return \"vectorstores\"\n\n        # Map provider casings\n        case_map = {\n            \"nvidia\": \"NVIDIA\",\n            \"openai\": \"OpenAI\",\n            \"amazon bedrock\": \"AmazonBedrockEmbeddings\",\n            \"azure openai\": \"AzureOpenAiEmbeddings\",\n            \"cohere\": \"Cohere\",\n            \"jina ai\": \"JinaAI\",\n            \"mistral ai\": \"MistralAI\",\n            \"upstage\": \"Upstage\",\n            \"voyage ai\": \"VoyageAI\",\n        }\n\n        # Adjust the casing on some like nvidia\n        return case_map[provider_name.lower()] if provider_name.lower() in case_map else provider_name.title()\n\n    def _initialize_collection_options(self, api_endpoint: str | None = None):\n        # Nothing to generate if we don't have an API endpoint yet\n        api_endpoint = api_endpoint or self.get_api_endpoint()\n        if not api_endpoint:\n            return []\n\n        # Retrieve the database object\n        database = self.get_database_object(api_endpoint=api_endpoint)\n\n        # Get the list of collections\n        collection_list = database.list_collections(keyspace=self.get_keyspace())\n\n        # Return the list of collections and metadata associated\n        return [\n            {\n                \"name\": col.name,\n                \"records\": self.collection_data(collection_name=col.name, database=database),\n                \"provider\": (\n                    col.definition.vector.service.provider\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n                \"icon\": self.get_provider_icon(collection=col),\n                \"model\": (\n                    col.definition.vector.service.model_name\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n            }\n            for col in collection_list\n        ]\n\n    def reset_provider_options(self, build_config: dict) -> dict:\n        \"\"\"Reset provider options and related configurations in the build_config dictionary.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get vectorize providers\n        vectorize_providers_api = self.get_vectorize_providers(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n        )\n\n        # Create a new dictionary with \"Bring your own\" first\n        vectorize_providers: dict[str, list[list[str]]] = {\"Bring your own\": [[], []]}\n\n        # Add the remaining items (only Nvidia) from the original dictionary\n        vectorize_providers.update(\n            {\n                k: v\n                for k, v in vectorize_providers_api.items()\n                if k.lower() in [\"nvidia\"]  # TODO: Eventually support more\n            }\n        )\n\n        # Set provider options\n        provider_field = \"02_embedding_generation_provider\"\n        template[provider_field][\"options\"] = list(vectorize_providers.keys())\n\n        # Add metadata for each provider option\n        template[provider_field][\"options_metadata\"] = [\n            {\"icon\": self.get_provider_icon(provider_name=provider)} for provider in template[provider_field][\"options\"]\n        ]\n\n        # Get selected embedding provider\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure embedding model field\n        model_field = \"03_embedding_generation_model\"\n        template[model_field].update(\n            {\n                \"options\": vectorize_providers.get(embedding_provider, [[], []])[1],\n                \"placeholder\": \"Bring your own\" if is_bring_your_own else None,\n                \"readonly\": is_bring_your_own,\n                \"required\": not is_bring_your_own,\n                \"value\": None,\n            }\n        )\n\n        # If this is a bring your own, set dimensions to 0\n        return self.reset_dimension_field(build_config)\n\n    def reset_dimension_field(self, build_config: dict) -> dict:\n        \"\"\"Reset dimension field options based on provided configuration.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get selected embedding model\n        provider_field = \"02_embedding_generation_provider\"\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure dimension field\n        dimension_field = \"04_dimension\"\n        dimension_value = 1024 if not is_bring_your_own else None  # TODO: Dynamically figure this out\n        template[dimension_field].update(\n            {\n                \"placeholder\": dimension_value,\n                \"value\": dimension_value,\n                \"readonly\": not is_bring_your_own,\n                \"required\": is_bring_your_own,\n            }\n        )\n\n        return build_config\n\n    def reset_collection_list(self, build_config: dict) -> dict:\n        \"\"\"Reset collection list options based on provided configuration.\"\"\"\n        # Get collection options\n        collection_options = self._initialize_collection_options(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        # Update collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update(\n            {\n                \"options\": [col[\"name\"] for col in collection_options],\n                \"options_metadata\": [{k: v for k, v in col.items() if k != \"name\"} for col in collection_options],\n            }\n        )\n\n        # Reset selected collection if not in options\n        if collection_config[\"value\"] not in collection_config[\"options\"]:\n            collection_config[\"value\"] = \"\"\n\n        # Set advanced status based on database selection\n        collection_config[\"show\"] = bool(build_config[\"database_name\"][\"value\"])\n\n        return build_config\n\n    def reset_database_list(self, build_config: dict) -> dict:\n        \"\"\"Reset database list options and related configurations.\"\"\"\n        # Get database options\n        database_options = self._initialize_database_options()\n\n        # Update cloud provider options\n        env = self.environment\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_cloud_provider\"][\"options\"] = list(self.map_cloud_providers()[env].keys())\n\n        # Update database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update(\n            {\n                \"options\": [db[\"name\"] for db in database_options],\n                \"options_metadata\": [{k: v for k, v in db.items() if k != \"name\"} for db in database_options],\n            }\n        )\n\n        # Reset selections if value not in options\n        if database_config[\"value\"] not in database_config[\"options\"]:\n            database_config[\"value\"] = \"\"\n            build_config[\"api_endpoint\"][\"value\"] = \"\"\n            build_config[\"collection_name\"][\"show\"] = False\n\n        # Set advanced status based on token presence\n        database_config[\"show\"] = bool(build_config[\"token\"][\"value\"])\n\n        return build_config\n\n    def reset_build_config(self, build_config: dict) -> dict:\n        \"\"\"Reset all build configuration options to default empty state.\"\"\"\n        # Reset database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n        build_config[\"api_endpoint\"][\"value\"] = \"\"\n\n        # Reset collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n\n        return build_config\n\n    def _handle_hybrid_search_options(self, build_config: dict) -> dict:\n        \"\"\"Set hybrid search options in the build configuration.\"\"\"\n        # Detect what hybrid options are available\n        # Get the admin object\n        client = DataAPIClient(environment=self.environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        # We will try to get the reranking providers to see if its hybrid emabled\n        try:\n            providers = db_admin.find_reranking_providers()\n            build_config[\"reranker\"][\"options\"] = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            build_config[\"reranker\"][\"options_metadata\"] = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Set the default search field to hybrid search\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Hybrid Search\"\n        except Exception as _:  # noqa: BLE001\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n            # Set the default search field to vector search\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n\n        # Set reranker and lexical terms options based on search method\n        build_config[\"reranker\"][\"toggle_value\"] = True\n        build_config[\"reranker\"][\"show\"] = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        build_config[\"reranker\"][\"toggle_disable\"] = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n        if build_config[\"reranker\"][\"show\"]:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Update build configuration based on field name and value.\"\"\"\n        # Early return if no token provided\n        if not self.token:\n            return self.reset_build_config(build_config)\n\n        # Database creation callback\n        if field_name == \"database_name\" and isinstance(field_value, dict):\n            if \"01_new_database_name\" in field_value:\n                await self._create_new_database(build_config, field_value)\n                return self.reset_collection_list(build_config)\n            return self._update_cloud_regions(build_config, field_value)\n\n        # Collection creation callback\n        if field_name == \"collection_name\" and isinstance(field_value, dict):\n            # Case 1: New collection creation\n            if \"01_new_collection_name\" in field_value:\n                await self._create_new_collection(build_config, field_value)\n                return build_config\n\n            # Case 2: Update embedding provider options\n            if \"02_embedding_generation_provider\" in field_value:\n                return self.reset_provider_options(build_config)\n\n            # Case 3: Update dimension field\n            if \"03_embedding_generation_model\" in field_value:\n                return self.reset_dimension_field(build_config)\n\n        # Initial execution or token/environment change\n        first_run = field_name == \"collection_name\" and not field_value and not build_config[\"database_name\"][\"options\"]\n        if first_run or field_name in {\"token\", \"environment\"}:\n            return self.reset_database_list(build_config)\n\n        # Database selection change\n        if field_name == \"database_name\" and not isinstance(field_value, dict):\n            return self._handle_database_selection(build_config, field_value)\n\n        # Keyspace selection change\n        if field_name == \"keyspace\":\n            return self.reset_collection_list(build_config)\n\n        # Collection selection change\n        if field_name == \"collection_name\" and not isinstance(field_value, dict):\n            return self._handle_collection_selection(build_config, field_value)\n\n        # Search method selection change\n        if field_name == \"search_method\":\n            is_vector_search = field_value == \"Vector Search\"\n            is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n            # Configure lexical terms (same for both cases)\n            build_config[\"lexical_terms\"][\"show\"] = not is_vector_search\n            build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n            # Disable reranker disabling if hybrid search is selected\n            build_config[\"reranker\"][\"toggle_disable\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_value\"] = True\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Toggle search type and score threshold based on search method\n            build_config[\"search_type\"][\"show\"] = is_vector_search\n            build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n            # Make sure the search_type is set to \"Similarity\"\n            if not is_vector_search or is_autodetect:\n                build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def _create_new_database(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new database and update build config options.\"\"\"\n        try:\n            await self.create_database_api(\n                new_database_name=field_value[\"01_new_database_name\"],\n                token=self.token,\n                keyspace=self.get_keyspace(),\n                environment=self.environment,\n                cloud_provider=field_value[\"02_cloud_provider\"],\n                region=field_value[\"03_region\"],\n            )\n        except Exception as e:\n            msg = f\"Error creating database: {e}\"\n            raise ValueError(msg) from e\n\n        build_config[\"database_name\"][\"options\"].append(field_value[\"01_new_database_name\"])\n        build_config[\"database_name\"][\"options_metadata\"].append(\n            {\n                \"status\": \"PENDING\",\n                \"collections\": 0,\n                \"api_endpoint\": None,\n                \"keyspaces\": [self.get_keyspace()],\n                \"org_id\": None,\n            }\n        )\n\n    def _update_cloud_regions(self, build_config: dict, field_value: dict) -> dict:\n        \"\"\"Update cloud provider regions in build config.\"\"\"\n        env = self.environment\n        cloud_provider = field_value[\"02_cloud_provider\"]\n\n        # Update the region options based on the selected cloud provider\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"03_region\"][\"options\"] = self.map_cloud_providers()[env][cloud_provider][\"regions\"]\n\n        # Reset the the 03_region value if it's not in the new options\n        if template[\"03_region\"][\"value\"] not in template[\"03_region\"][\"options\"]:\n            template[\"03_region\"][\"value\"] = None\n\n        return build_config\n\n    async def _create_new_collection(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new collection and update build config options.\"\"\"\n        embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n        try:\n            await self.create_collection_api(\n                new_collection_name=field_value[\"01_new_collection_name\"],\n                token=self.token,\n                api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n                environment=self.environment,\n                keyspace=self.get_keyspace(),\n                dimension=field_value.get(\"04_dimension\") if embedding_provider == \"Bring your own\" else None,\n                embedding_generation_provider=embedding_provider,\n                embedding_generation_model=field_value.get(\"03_embedding_generation_model\"),\n                reranker=self.reranker,\n            )\n        except Exception as e:\n            msg = f\"Error creating collection: {e}\"\n            raise ValueError(msg) from e\n\n        provider = embedding_provider.lower() if embedding_provider and embedding_provider != \"Bring your own\" else None\n        build_config[\"collection_name\"].update(\n            {\n                \"value\": field_value[\"01_new_collection_name\"],\n                \"options\": build_config[\"collection_name\"][\"options\"] + [field_value[\"01_new_collection_name\"]],\n            }\n        )\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n        build_config[\"collection_name\"][\"options_metadata\"].append(\n            {\n                \"records\": 0,\n                \"provider\": provider,\n                \"icon\": self.get_provider_icon(provider_name=provider),\n                \"model\": field_value.get(\"03_embedding_generation_model\"),\n            }\n        )\n\n        # Make sure we always show the reranker options if the collection is hybrid enabled\n        # And right now they always are\n        build_config[\"lexical_terms\"][\"show\"] = True\n\n    def _handle_database_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle database selection and update related configurations.\"\"\"\n        build_config = self.reset_database_list(build_config)\n\n        # Reset collection list if database selection changes\n        if field_value not in build_config[\"database_name\"][\"options\"]:\n            build_config[\"database_name\"][\"value\"] = \"\"\n            return build_config\n\n        # Get the api endpoint for the selected database\n        index = build_config[\"database_name\"][\"options\"].index(field_value)\n        build_config[\"api_endpoint\"][\"value\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"api_endpoint\"]\n\n        # Get the org_id for the selected database\n        org_id = build_config[\"database_name\"][\"options_metadata\"][index][\"org_id\"]\n        if not org_id:\n            return build_config\n\n        # Update the list of keyspaces based on the db info\n        build_config[\"keyspace\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"keyspaces\"]\n        build_config[\"keyspace\"][\"value\"] = (\n            build_config[\"keyspace\"][\"options\"] and build_config[\"keyspace\"][\"options\"][0]\n            if build_config[\"keyspace\"][\"value\"] not in build_config[\"keyspace\"][\"options\"]\n            else build_config[\"keyspace\"][\"value\"]\n        )\n\n        # Get the database id for the selected database\n        db_id = self.get_database_id_static(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        keyspace = self.get_keyspace()\n\n        # Update the helper text for the embedding provider field\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_embedding_generation_provider\"][\"helper_text\"] = (\n            \"To create collections with more embedding provider options, go to \"\n            f'<a class=\"underline\" target=\"_blank\" rel=\"noopener noreferrer\" '\n            f'href=\"https://astra.datastax.com/org/{org_id}/database/{db_id}/data-explorer?createCollection=1&namespace={keyspace}\">'\n            \"your database in Astra DB</a>.\"\n        )\n\n        # Reset provider options\n        build_config = self.reset_provider_options(build_config)\n\n        # Handle hybrid search options\n        build_config = self._handle_hybrid_search_options(build_config)\n\n        return self.reset_collection_list(build_config)\n\n    def _handle_collection_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle collection selection and update embedding options.\"\"\"\n        build_config[\"autodetect_collection\"][\"value\"] = True\n        build_config = self.reset_collection_list(build_config)\n\n        # Reset embedding model if collection selection changes\n        if field_value and field_value not in build_config[\"collection_name\"][\"options\"]:\n            build_config[\"collection_name\"][\"options\"].append(field_value)\n            build_config[\"collection_name\"][\"options_metadata\"].append(\n                {\n                    \"records\": 0,\n                    \"provider\": None,\n                    \"icon\": \"vectorstores\",\n                    \"model\": None,\n                }\n            )\n            build_config[\"autodetect_collection\"][\"value\"] = False\n\n        if not field_value:\n            return build_config\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(field_value)\n\n        # Set the provider of the selected collection\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Grab the collection object\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=field_value,\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        # Check if hybrid and lexical are enabled\n        col_options = collection.options()\n        hyb_enabled = col_options.rerank and col_options.rerank.enabled\n        lex_enabled = col_options.lexical and col_options.lexical.enabled\n        user_hyb_enabled = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n\n        # Show lexical terms if the collection is hybrid enabled\n        build_config[\"lexical_terms\"][\"show\"] = hyb_enabled and lex_enabled and user_hyb_enabled\n\n        return build_config\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except Exception as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except Exception as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except Exception as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except Exception as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except Exception as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
+                "value": "import re\nfrom collections import defaultdict\nfrom dataclasses import asdict, dataclass, field\n\nfrom astrapy import DataAPIClient, Database\nfrom astrapy.data.info.reranking import RerankServiceOptions\nfrom astrapy.info import CollectionDescriptor, CollectionLexicalOptions, CollectionRerankOptions\nfrom langchain_astradb import AstraDBVectorStore, VectorServiceOptions\nfrom langchain_astradb.utils.astradb import HybridSearchMode, _AstraDBCollectionEnvironment\nfrom langchain_core.documents import Document\n\nfrom langflow.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom langflow.base.vectorstores.vector_store_connection_decorator import vector_store_connection\nfrom langflow.helpers.data import docs_to_data\nfrom langflow.inputs.inputs import FloatInput, NestedDictInput\nfrom langflow.io import (\n    BoolInput,\n    DropdownInput,\n    HandleInput,\n    IntInput,\n    QueryInput,\n    SecretStrInput,\n    StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.serialization import serialize\nfrom langflow.utils.version import get_version_info\n\n\n@vector_store_connection\nclass AstraDBVectorStoreComponent(LCVectorStoreComponent):\n    display_name: str = \"Astra DB\"\n    description: str = \"Ingest and search documents in Astra DB\"\n    documentation: str = \"https://docs.datastax.com/en/langflow/astra-components.html\"\n    name = \"AstraDB\"\n    icon: str = \"AstraDB\"\n\n    _cached_vector_store: AstraDBVectorStore | None = None\n\n    @dataclass\n    class NewDatabaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_database\",\n                        \"description\": \"Please allow several minutes for creation to complete.\",\n                        \"display_name\": \"Create new database\",\n                        \"field_order\": [\"01_new_database_name\", \"02_cloud_provider\", \"03_region\"],\n                        \"template\": {\n                            \"01_new_database_name\": StrInput(\n                                name=\"new_database_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new database to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_cloud_provider\": DropdownInput(\n                                name=\"cloud_provider\",\n                                display_name=\"Cloud provider\",\n                                info=\"Cloud provider for the new database.\",\n                                options=[],\n                                required=True,\n                                real_time_refresh=True,\n                            ),\n                            \"03_region\": DropdownInput(\n                                name=\"region\",\n                                display_name=\"Region\",\n                                info=\"Region for the new database.\",\n                                options=[],\n                                required=True,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    @dataclass\n    class NewCollectionInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_collection\",\n                        \"description\": \"Please allow several seconds for creation to complete.\",\n                        \"display_name\": \"Create new collection\",\n                        \"field_order\": [\n                            \"01_new_collection_name\",\n                            \"02_embedding_generation_provider\",\n                            \"03_embedding_generation_model\",\n                            \"04_dimension\",\n                        ],\n                        \"template\": {\n                            \"01_new_collection_name\": StrInput(\n                                name=\"new_collection_name\",\n                                display_name=\"Name\",\n                                info=\"Name of the new collection to create in Astra DB.\",\n                                required=True,\n                            ),\n                            \"02_embedding_generation_provider\": DropdownInput(\n                                name=\"embedding_generation_provider\",\n                                display_name=\"Embedding generation method\",\n                                info=\"Provider to use for generating embeddings.\",\n                                helper_text=(\n                                    \"To create collections with more embedding provider options, go to \"\n                                    '<a class=\"underline\" href=\"https://astra.datastax.com/\" target=\" _blank\" '\n                                    'rel=\"noopener noreferrer\">your database in Astra DB</a>'\n                                ),\n                                real_time_refresh=True,\n                                required=True,\n                                options=[],\n                            ),\n                            \"03_embedding_generation_model\": DropdownInput(\n                                name=\"embedding_generation_model\",\n                                display_name=\"Embedding model\",\n                                info=\"Model to use for generating embeddings.\",\n                                real_time_refresh=True,\n                                options=[],\n                            ),\n                            \"04_dimension\": IntInput(\n                                name=\"dimension\",\n                                display_name=\"Dimensions\",\n                                info=\"Dimensions of the embeddings to generate.\",\n                                value=None,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    inputs = [\n        SecretStrInput(\n            name=\"token\",\n            display_name=\"Astra DB Application Token\",\n            info=\"Authentication token for accessing Astra DB.\",\n            value=\"ASTRA_DB_APPLICATION_TOKEN\",\n            required=True,\n            real_time_refresh=True,\n            input_types=[],\n        ),\n        DropdownInput(\n            name=\"environment\",\n            display_name=\"Environment\",\n            info=\"The environment for the Astra DB API Endpoint.\",\n            options=[\"prod\", \"test\", \"dev\"],\n            value=\"prod\",\n            advanced=True,\n            real_time_refresh=True,\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"database_name\",\n            display_name=\"Database\",\n            info=\"The Database name for the Astra DB instance.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewDatabaseInput()),\n            combobox=True,\n        ),\n        DropdownInput(\n            name=\"api_endpoint\",\n            display_name=\"Astra DB API Endpoint\",\n            info=\"The API Endpoint for the Astra DB instance. Supercedes database selection.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"keyspace\",\n            display_name=\"Keyspace\",\n            info=\"Optional keyspace within Astra DB to use for the collection.\",\n            advanced=True,\n            options=[],\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"collection_name\",\n            display_name=\"Collection\",\n            info=\"The name of the collection within Astra DB where the vectors will be stored.\",\n            required=True,\n            refresh_button=True,\n            real_time_refresh=True,\n            dialog_inputs=asdict(NewCollectionInput()),\n            combobox=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"embedding_model\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            info=\"Specify the Embedding Model. Not required for Astra Vectorize collections.\",\n            required=False,\n            show=False,\n        ),\n        *LCVectorStoreComponent.inputs,\n        DropdownInput(\n            name=\"search_method\",\n            display_name=\"Search Method\",\n            info=(\n                \"Determine how your content is matched: Vector finds semantic similarity, \"\n                \"and Hybrid Search (suggested) combines both approaches \"\n                \"with a reranker.\"\n            ),\n            options=[\"Hybrid Search\", \"Vector Search\"],  # TODO: Restore Lexical Search?\n            options_metadata=[{\"icon\": \"SearchHybrid\"}, {\"icon\": \"SearchVector\"}],\n            value=\"Vector Search\",\n            advanced=True,\n            real_time_refresh=True,\n        ),\n        DropdownInput(\n            name=\"reranker\",\n            display_name=\"Reranker\",\n            info=\"Post-retrieval model that re-scores results for optimal relevance ranking.\",\n            show=False,\n            toggle=True,\n        ),\n        QueryInput(\n            name=\"lexical_terms\",\n            display_name=\"Lexical Terms\",\n            info=\"Add additional terms/keywords to augment search precision.\",\n            placeholder=\"Enter terms to search...\",\n            separator=\" \",\n            show=False,\n            value=\"\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Search Results\",\n            info=\"Number of search results to return.\",\n            advanced=True,\n            value=4,\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            info=\"Search type to use\",\n            options=[\"Similarity\", \"Similarity with score threshold\", \"MMR (Max Marginal Relevance)\"],\n            value=\"Similarity\",\n            advanced=True,\n        ),\n        FloatInput(\n            name=\"search_score_threshold\",\n            display_name=\"Search Score Threshold\",\n            info=\"Minimum similarity score threshold for search results. \"\n            \"(when using 'Similarity with score threshold')\",\n            value=0,\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"advanced_search_filter\",\n            display_name=\"Search Metadata Filter\",\n            info=\"Optional dictionary of filters to apply to the search query.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autodetect_collection\",\n            display_name=\"Autodetect Collection\",\n            info=\"Boolean flag to determine whether to autodetect the collection.\",\n            advanced=True,\n            value=True,\n        ),\n        StrInput(\n            name=\"content_field\",\n            display_name=\"Content Field\",\n            info=\"Field to use as the text content field for the vector store.\",\n            advanced=True,\n        ),\n        StrInput(\n            name=\"deletion_field\",\n            display_name=\"Deletion Based On Field\",\n            info=\"When this parameter is provided, documents in the target collection with \"\n            \"metadata field values matching the input metadata field value will be deleted \"\n            \"before new data is loaded.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"ignore_invalid_documents\",\n            display_name=\"Ignore Invalid Documents\",\n            info=\"Boolean flag to determine whether to ignore invalid documents at runtime.\",\n            advanced=True,\n        ),\n        NestedDictInput(\n            name=\"astradb_vectorstore_kwargs\",\n            display_name=\"AstraDBVectorStore Parameters\",\n            info=\"Optional dictionary of additional parameters for the AstraDBVectorStore.\",\n            advanced=True,\n        ),\n    ]\n\n    @classmethod\n    def map_cloud_providers(cls):\n        # TODO: Programmatically fetch the regions for each cloud provider\n        return {\n            \"dev\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-west-2\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\", \"europe-west4\"],\n                },\n            },\n            \"test\": {\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-central1\"],\n                },\n            },\n            \"prod\": {\n                \"Amazon Web Services\": {\n                    \"id\": \"aws\",\n                    \"regions\": [\"us-east-2\", \"ap-south-1\", \"eu-west-1\"],\n                },\n                \"Google Cloud Platform\": {\n                    \"id\": \"gcp\",\n                    \"regions\": [\"us-east1\"],\n                },\n                \"Microsoft Azure\": {\n                    \"id\": \"azure\",\n                    \"regions\": [\"westus3\"],\n                },\n            },\n        }\n\n    @classmethod\n    def get_vectorize_providers(cls, token: str, environment: str | None = None, api_endpoint: str | None = None):\n        try:\n            # Get the admin object\n            client = DataAPIClient(environment=environment)\n            admin_client = client.get_admin()\n            db_admin = admin_client.get_database_admin(api_endpoint, token=token)\n\n            # Get the list of embedding providers\n            embedding_providers = db_admin.find_embedding_providers()\n\n            vectorize_providers_mapping = {}\n            # Map the provider display name to the provider key and models\n            for provider_key, provider_data in embedding_providers.embedding_providers.items():\n                # Get the provider display name and models\n                display_name = provider_data.display_name\n                models = [model.name for model in provider_data.models]\n\n                # Build our mapping\n                vectorize_providers_mapping[display_name] = [provider_key, models]\n\n            # Sort the resulting dictionary\n            return defaultdict(list, dict(sorted(vectorize_providers_mapping.items())))\n        except Exception as _:  # noqa: BLE001\n            return {}\n\n    @classmethod\n    async def create_database_api(\n        cls,\n        new_database_name: str,\n        cloud_provider: str,\n        region: str,\n        token: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n    ):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the environment, set to prod if null like\n        my_env = environment or \"prod\"\n\n        # Raise a value error if name isn't provided\n        if not new_database_name:\n            msg = \"Database name is required to create a new database.\"\n            raise ValueError(msg)\n\n        # Call the create database function\n        return await admin_client.async_create_database(\n            name=new_database_name,\n            cloud_provider=cls.map_cloud_providers()[my_env][cloud_provider][\"id\"],\n            region=region,\n            keyspace=keyspace,\n            wait_until_active=False,\n        )\n\n    @classmethod\n    async def create_collection_api(\n        cls,\n        new_collection_name: str,\n        token: str,\n        api_endpoint: str,\n        environment: str | None = None,\n        keyspace: str | None = None,\n        dimension: int | None = None,\n        embedding_generation_provider: str | None = None,\n        embedding_generation_model: str | None = None,\n        reranker: str | None = None,\n    ):\n        # Build vectorize options, if needed\n        vectorize_options = None\n        if not dimension:\n            providers = cls.get_vectorize_providers(token=token, environment=environment, api_endpoint=api_endpoint)\n            vectorize_options = VectorServiceOptions(\n                provider=providers.get(embedding_generation_provider, [None, []])[0],\n                model_name=embedding_generation_model,\n            )\n\n        # Raise a value error if name isn't provided\n        if not new_collection_name:\n            msg = \"Collection name is required to create a new collection.\"\n            raise ValueError(msg)\n\n        # Define the base arguments being passed to the create collection function\n        base_args = {\n            \"collection_name\": new_collection_name,\n            \"token\": token,\n            \"api_endpoint\": api_endpoint,\n            \"keyspace\": keyspace,\n            \"environment\": environment,\n            \"embedding_dimension\": dimension,\n            \"collection_vector_service_options\": vectorize_options,\n        }\n\n        # Add optional arguments if the reranker is set\n        if reranker:\n            # Split the reranker field into a provider a model name\n            provider, _ = reranker.split(\"/\")\n            base_args[\"collection_rerank\"] = CollectionRerankOptions(\n                service=RerankServiceOptions(provider=provider, model_name=reranker),\n            )\n            base_args[\"collection_lexical\"] = CollectionLexicalOptions(analyzer=\"STANDARD\")\n\n        _AstraDBCollectionEnvironment(**base_args)\n\n    @classmethod\n    def get_database_list_static(cls, token: str, environment: str | None = None):\n        client = DataAPIClient(environment=environment)\n\n        # Get the admin object\n        admin_client = client.get_admin(token=token)\n\n        # Get the list of databases\n        db_list = admin_client.list_databases()\n\n        # Generate the api endpoint for each database\n        db_info_dict = {}\n        for db in db_list:\n            try:\n                # Get the API endpoint for the database\n                api_endpoints = [db_reg.api_endpoint for db_reg in db.regions]\n\n                # Get the number of collections\n                try:\n                    # Get the number of collections in the database\n                    num_collections = len(\n                        client.get_database(\n                            api_endpoints[0],\n                            token=token,\n                        ).list_collection_names()\n                    )\n                except Exception:  # noqa: BLE001\n                    if db.status != \"PENDING\":\n                        continue\n                    num_collections = 0\n\n                # Add the database to the dictionary\n                db_info_dict[db.name] = {\n                    \"api_endpoints\": api_endpoints,\n                    \"keyspaces\": db.keyspaces,\n                    \"collections\": num_collections,\n                    \"status\": db.status if db.status != \"ACTIVE\" else None,\n                    \"org_id\": db.org_id if db.org_id else None,\n                }\n            except Exception:  # noqa: BLE001, S110\n                pass\n\n        return db_info_dict\n\n    def get_database_list(self):\n        return self.get_database_list_static(\n            token=self.token,\n            environment=self.environment,\n        )\n\n    @classmethod\n    def get_api_endpoint_static(\n        cls,\n        token: str,\n        environment: str | None = None,\n        api_endpoint: str | None = None,\n        database_name: str | None = None,\n    ):\n        # If the api_endpoint is set, return it\n        if api_endpoint:\n            return api_endpoint\n\n        # Check if the database_name is like a url\n        if database_name and database_name.startswith(\"https://\"):\n            return database_name\n\n        # If the database is not set, nothing we can do.\n        if not database_name:\n            return None\n\n        # Grab the database object\n        db = cls.get_database_list_static(token=token, environment=environment).get(database_name)\n        if not db:\n            return None\n\n        # Otherwise, get the URL from the database list\n        endpoints = db.get(\"api_endpoints\") or []\n        return endpoints[0] if endpoints else None\n\n    def get_api_endpoint(self):\n        return self.get_api_endpoint_static(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=self.api_endpoint,\n            database_name=self.database_name,\n        )\n\n    @classmethod\n    def get_database_id_static(cls, api_endpoint: str) -> str | None:\n        # Pattern matches standard UUID format: 8-4-4-4-12 hexadecimal characters\n        uuid_pattern = r\"[0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{4}-[0-9a-fA-F]{12}\"\n        match = re.search(uuid_pattern, api_endpoint)\n\n        return match.group(0) if match else None\n\n    def get_database_id(self):\n        return self.get_database_id_static(api_endpoint=self.get_api_endpoint())\n\n    def get_keyspace(self):\n        keyspace = self.keyspace\n\n        if keyspace:\n            return keyspace.strip()\n\n        return \"default_keyspace\"\n\n    def get_database_object(self, api_endpoint: str | None = None):\n        try:\n            client = DataAPIClient(environment=self.environment)\n\n            return client.get_database(\n                api_endpoint or self.get_api_endpoint(),\n                token=self.token,\n                keyspace=self.get_keyspace(),\n            )\n        except Exception as e:\n            msg = f\"Error fetching database object: {e}\"\n            raise ValueError(msg) from e\n\n    def collection_data(self, collection_name: str, database: Database | None = None):\n        try:\n            if not database:\n                client = DataAPIClient(environment=self.environment)\n\n                database = client.get_database(\n                    self.get_api_endpoint(),\n                    token=self.token,\n                    keyspace=self.get_keyspace(),\n                )\n\n            collection = database.get_collection(collection_name)\n\n            return collection.estimated_document_count()\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Error checking collection data: {e}\")\n\n            return None\n\n    def _initialize_database_options(self):\n        try:\n            return [\n                {\n                    \"name\": name,\n                    \"status\": info[\"status\"],\n                    \"collections\": info[\"collections\"],\n                    \"api_endpoints\": info[\"api_endpoints\"],\n                    \"keyspaces\": info[\"keyspaces\"],\n                    \"org_id\": info[\"org_id\"],\n                }\n                for name, info in self.get_database_list().items()\n            ]\n        except Exception as e:\n            msg = f\"Error fetching database options: {e}\"\n            raise ValueError(msg) from e\n\n    @classmethod\n    def get_provider_icon(cls, collection: CollectionDescriptor | None = None, provider_name: str | None = None) -> str:\n        # Get the provider name from the collection\n        provider_name = provider_name or (\n            collection.definition.vector.service.provider\n            if (\n                collection\n                and collection.definition\n                and collection.definition.vector\n                and collection.definition.vector.service\n            )\n            else None\n        )\n\n        # If there is no provider, use the vector store icon\n        if not provider_name or provider_name.lower() == \"bring your own\":\n            return \"vectorstores\"\n\n        # Map provider casings\n        case_map = {\n            \"nvidia\": \"NVIDIA\",\n            \"openai\": \"OpenAI\",\n            \"amazon bedrock\": \"AmazonBedrockEmbeddings\",\n            \"azure openai\": \"AzureOpenAiEmbeddings\",\n            \"cohere\": \"Cohere\",\n            \"jina ai\": \"JinaAI\",\n            \"mistral ai\": \"MistralAI\",\n            \"upstage\": \"Upstage\",\n            \"voyage ai\": \"VoyageAI\",\n        }\n\n        # Adjust the casing on some like nvidia\n        return case_map[provider_name.lower()] if provider_name.lower() in case_map else provider_name.title()\n\n    def _initialize_collection_options(self, api_endpoint: str | None = None):\n        # Nothing to generate if we don't have an API endpoint yet\n        api_endpoint = api_endpoint or self.get_api_endpoint()\n        if not api_endpoint:\n            return []\n\n        # Retrieve the database object\n        database = self.get_database_object(api_endpoint=api_endpoint)\n\n        # Get the list of collections\n        collection_list = database.list_collections(keyspace=self.get_keyspace())\n\n        # Return the list of collections and metadata associated\n        return [\n            {\n                \"name\": col.name,\n                \"records\": self.collection_data(collection_name=col.name, database=database),\n                \"provider\": (\n                    col.definition.vector.service.provider\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n                \"icon\": self.get_provider_icon(collection=col),\n                \"model\": (\n                    col.definition.vector.service.model_name\n                    if col.definition.vector and col.definition.vector.service\n                    else None\n                ),\n            }\n            for col in collection_list\n        ]\n\n    def reset_provider_options(self, build_config: dict) -> dict:\n        \"\"\"Reset provider options and related configurations in the build_config dictionary.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get vectorize providers\n        vectorize_providers_api = self.get_vectorize_providers(\n            token=self.token,\n            environment=self.environment,\n            api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n        )\n\n        # Create a new dictionary with \"Bring your own\" first\n        vectorize_providers: dict[str, list[list[str]]] = {\"Bring your own\": [[], []]}\n\n        # Add the remaining items (only Nvidia) from the original dictionary\n        vectorize_providers.update(\n            {\n                k: v\n                for k, v in vectorize_providers_api.items()\n                if k.lower() in [\"nvidia\"]  # TODO: Eventually support more\n            }\n        )\n\n        # Set provider options\n        provider_field = \"02_embedding_generation_provider\"\n        template[provider_field][\"options\"] = list(vectorize_providers.keys())\n\n        # Add metadata for each provider option\n        template[provider_field][\"options_metadata\"] = [\n            {\"icon\": self.get_provider_icon(provider_name=provider)} for provider in template[provider_field][\"options\"]\n        ]\n\n        # Get selected embedding provider\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure embedding model field\n        model_field = \"03_embedding_generation_model\"\n        template[model_field].update(\n            {\n                \"options\": vectorize_providers.get(embedding_provider, [[], []])[1],\n                \"placeholder\": \"Bring your own\" if is_bring_your_own else None,\n                \"readonly\": is_bring_your_own,\n                \"required\": not is_bring_your_own,\n                \"value\": None,\n            }\n        )\n\n        # If this is a bring your own, set dimensions to 0\n        return self.reset_dimension_field(build_config)\n\n    def reset_dimension_field(self, build_config: dict) -> dict:\n        \"\"\"Reset dimension field options based on provided configuration.\"\"\"\n        # Extract template path for cleaner access\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n\n        # Get selected embedding model\n        provider_field = \"02_embedding_generation_provider\"\n        embedding_provider = template[provider_field][\"value\"]\n        is_bring_your_own = embedding_provider and embedding_provider == \"Bring your own\"\n\n        # Configure dimension field\n        dimension_field = \"04_dimension\"\n        dimension_value = 1024 if not is_bring_your_own else None  # TODO: Dynamically figure this out\n        template[dimension_field].update(\n            {\n                \"placeholder\": dimension_value,\n                \"value\": dimension_value,\n                \"readonly\": not is_bring_your_own,\n                \"required\": is_bring_your_own,\n            }\n        )\n\n        return build_config\n\n    def reset_collection_list(self, build_config: dict) -> dict:\n        \"\"\"Reset collection list options based on provided configuration.\"\"\"\n        # Get collection options\n        collection_options = self._initialize_collection_options(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        # Update collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update(\n            {\n                \"options\": [col[\"name\"] for col in collection_options],\n                \"options_metadata\": [{k: v for k, v in col.items() if k != \"name\"} for col in collection_options],\n            }\n        )\n\n        # Reset selected collection if not in options\n        if collection_config[\"value\"] not in collection_config[\"options\"]:\n            collection_config[\"value\"] = \"\"\n\n        # Set advanced status based on database selection\n        collection_config[\"show\"] = bool(build_config[\"database_name\"][\"value\"])\n\n        return build_config\n\n    def reset_database_list(self, build_config: dict) -> dict:\n        \"\"\"Reset database list options and related configurations.\"\"\"\n        # Get database options\n        database_options = self._initialize_database_options()\n\n        # Update cloud provider options\n        env = self.environment\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_cloud_provider\"][\"options\"] = list(self.map_cloud_providers()[env].keys())\n\n        # Update database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update(\n            {\n                \"options\": [db[\"name\"] for db in database_options],\n                \"options_metadata\": [{k: v for k, v in db.items() if k != \"name\"} for db in database_options],\n            }\n        )\n\n        # Reset selections if value not in options\n        if database_config[\"value\"] not in database_config[\"options\"]:\n            database_config[\"value\"] = \"\"\n            build_config[\"api_endpoint\"][\"options\"] = []\n            build_config[\"api_endpoint\"][\"value\"] = \"\"\n            build_config[\"collection_name\"][\"show\"] = False\n\n        # Set advanced status based on token presence\n        database_config[\"show\"] = bool(build_config[\"token\"][\"value\"])\n\n        return build_config\n\n    def reset_build_config(self, build_config: dict) -> dict:\n        \"\"\"Reset all build configuration options to default empty state.\"\"\"\n        # Reset database configuration\n        database_config = build_config[\"database_name\"]\n        database_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n        build_config[\"api_endpoint\"][\"options\"] = []\n        build_config[\"api_endpoint\"][\"value\"] = \"\"\n\n        # Reset collection configuration\n        collection_config = build_config[\"collection_name\"]\n        collection_config.update({\"options\": [], \"options_metadata\": [], \"value\": \"\", \"show\": False})\n\n        return build_config\n\n    def _handle_hybrid_search_options(self, build_config: dict) -> dict:\n        \"\"\"Set hybrid search options in the build configuration.\"\"\"\n        # Detect what hybrid options are available\n        # Get the admin object\n        client = DataAPIClient(environment=self.environment)\n        admin_client = client.get_admin()\n        db_admin = admin_client.get_database_admin(self.get_api_endpoint(), token=self.token)\n\n        # We will try to get the reranking providers to see if its hybrid emabled\n        try:\n            providers = db_admin.find_reranking_providers()\n            build_config[\"reranker\"][\"options\"] = [\n                model.name for provider_data in providers.reranking_providers.values() for model in provider_data.models\n            ]\n            build_config[\"reranker\"][\"options_metadata\"] = [\n                {\"icon\": self.get_provider_icon(provider_name=model.name.split(\"/\")[0])}\n                for provider in providers.reranking_providers.values()\n                for model in provider.models\n            ]\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Set the default search field to hybrid search\n            build_config[\"search_method\"][\"show\"] = True\n            build_config[\"search_method\"][\"options\"] = [\"Hybrid Search\", \"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Hybrid Search\"\n        except Exception as _:  # noqa: BLE001\n            build_config[\"reranker\"][\"options\"] = []\n            build_config[\"reranker\"][\"options_metadata\"] = []\n\n            # Set the default search field to vector search\n            build_config[\"search_method\"][\"show\"] = False\n            build_config[\"search_method\"][\"options\"] = [\"Vector Search\"]\n            build_config[\"search_method\"][\"value\"] = \"Vector Search\"\n\n        return build_config\n\n    async def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None) -> dict:\n        \"\"\"Update build configuration based on field name and value.\"\"\"\n        # Early return if no token provided\n        if not self.token:\n            return self.reset_build_config(build_config)\n\n        # Database creation callback\n        if field_name == \"database_name\" and isinstance(field_value, dict):\n            if \"01_new_database_name\" in field_value:\n                await self._create_new_database(build_config, field_value)\n                return self.reset_collection_list(build_config)\n            return self._update_cloud_regions(build_config, field_value)\n\n        # Collection creation callback\n        if field_name == \"collection_name\" and isinstance(field_value, dict):\n            # Case 1: New collection creation\n            if \"01_new_collection_name\" in field_value:\n                await self._create_new_collection(build_config, field_value)\n                return build_config\n\n            # Case 2: Update embedding provider options\n            if \"02_embedding_generation_provider\" in field_value:\n                return self.reset_provider_options(build_config)\n\n            # Case 3: Update dimension field\n            if \"03_embedding_generation_model\" in field_value:\n                return self.reset_dimension_field(build_config)\n\n        # Initial execution or token/environment change\n        first_run = field_name == \"collection_name\" and not field_value and not build_config[\"database_name\"][\"options\"]\n        if first_run or field_name in {\"token\", \"environment\"}:\n            return self.reset_database_list(build_config)\n\n        # Database selection change\n        if field_name == \"database_name\" and not isinstance(field_value, dict):\n            return self._handle_database_selection(build_config, field_value)\n\n        # Keyspace selection change\n        if field_name == \"keyspace\":\n            return self.reset_collection_list(build_config)\n\n        # Collection selection change\n        if field_name == \"collection_name\" and not isinstance(field_value, dict):\n            return self._handle_collection_selection(build_config, field_value)\n\n        # Search method selection change\n        if field_name == \"search_method\":\n            is_vector_search = field_value == \"Vector Search\"\n            is_autodetect = build_config[\"autodetect_collection\"][\"value\"]\n\n            # Configure lexical terms (same for both cases)\n            build_config[\"lexical_terms\"][\"show\"] = not is_vector_search\n            build_config[\"lexical_terms\"][\"value\"] = \"\" if is_vector_search else build_config[\"lexical_terms\"][\"value\"]\n\n            # Disable reranker disabling if hybrid search is selected\n            build_config[\"reranker\"][\"show\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_disable\"] = not is_vector_search\n            build_config[\"reranker\"][\"toggle_value\"] = True\n            build_config[\"reranker\"][\"value\"] = build_config[\"reranker\"][\"options\"][0]\n\n            # Toggle search type and score threshold based on search method\n            build_config[\"search_type\"][\"show\"] = is_vector_search\n            build_config[\"search_score_threshold\"][\"show\"] = is_vector_search\n\n            # Make sure the search_type is set to \"Similarity\"\n            if not is_vector_search or is_autodetect:\n                build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        return build_config\n\n    async def _create_new_database(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new database and update build config options.\"\"\"\n        try:\n            await self.create_database_api(\n                new_database_name=field_value[\"01_new_database_name\"],\n                token=self.token,\n                keyspace=self.get_keyspace(),\n                environment=self.environment,\n                cloud_provider=field_value[\"02_cloud_provider\"],\n                region=field_value[\"03_region\"],\n            )\n        except Exception as e:\n            msg = f\"Error creating database: {e}\"\n            raise ValueError(msg) from e\n\n        build_config[\"database_name\"][\"options\"].append(field_value[\"01_new_database_name\"])\n        build_config[\"database_name\"][\"options_metadata\"].append(\n            {\n                \"status\": \"PENDING\",\n                \"collections\": 0,\n                \"api_endpoints\": [],\n                \"keyspaces\": [self.get_keyspace()],\n                \"org_id\": None,\n            }\n        )\n\n    def _update_cloud_regions(self, build_config: dict, field_value: dict) -> dict:\n        \"\"\"Update cloud provider regions in build config.\"\"\"\n        env = self.environment\n        cloud_provider = field_value[\"02_cloud_provider\"]\n\n        # Update the region options based on the selected cloud provider\n        template = build_config[\"database_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"03_region\"][\"options\"] = self.map_cloud_providers()[env][cloud_provider][\"regions\"]\n\n        # Reset the the 03_region value if it's not in the new options\n        if template[\"03_region\"][\"value\"] not in template[\"03_region\"][\"options\"]:\n            template[\"03_region\"][\"value\"] = None\n\n        return build_config\n\n    async def _create_new_collection(self, build_config: dict, field_value: dict) -> None:\n        \"\"\"Create a new collection and update build config options.\"\"\"\n        embedding_provider = field_value.get(\"02_embedding_generation_provider\")\n        try:\n            await self.create_collection_api(\n                new_collection_name=field_value[\"01_new_collection_name\"],\n                token=self.token,\n                api_endpoint=build_config[\"api_endpoint\"][\"value\"],\n                environment=self.environment,\n                keyspace=self.get_keyspace(),\n                dimension=field_value.get(\"04_dimension\") if embedding_provider == \"Bring your own\" else None,\n                embedding_generation_provider=embedding_provider,\n                embedding_generation_model=field_value.get(\"03_embedding_generation_model\"),\n                reranker=self.reranker,\n            )\n        except Exception as e:\n            msg = f\"Error creating collection: {e}\"\n            raise ValueError(msg) from e\n\n        provider = embedding_provider.lower() if embedding_provider and embedding_provider != \"Bring your own\" else None\n        build_config[\"collection_name\"].update(\n            {\n                \"value\": field_value[\"01_new_collection_name\"],\n                \"options\": build_config[\"collection_name\"][\"options\"] + [field_value[\"01_new_collection_name\"]],\n            }\n        )\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n        build_config[\"collection_name\"][\"options_metadata\"].append(\n            {\n                \"records\": 0,\n                \"provider\": provider,\n                \"icon\": self.get_provider_icon(provider_name=provider),\n                \"model\": field_value.get(\"03_embedding_generation_model\"),\n            }\n        )\n\n        # Make sure we always show the reranker options if the collection is hybrid enabled\n        # And right now they always are\n        build_config[\"lexical_terms\"][\"show\"] = True\n\n    def _handle_database_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle database selection and update related configurations.\"\"\"\n        build_config = self.reset_database_list(build_config)\n\n        # Reset collection list if database selection changes\n        if field_value not in build_config[\"database_name\"][\"options\"]:\n            build_config[\"database_name\"][\"value\"] = \"\"\n            return build_config\n\n        # Get the api endpoint for the selected database\n        index = build_config[\"database_name\"][\"options\"].index(field_value)\n        build_config[\"api_endpoint\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\n            \"api_endpoints\"\n        ]\n        build_config[\"api_endpoint\"][\"value\"] = build_config[\"database_name\"][\"options_metadata\"][index][\n            \"api_endpoints\"\n        ][0]\n\n        # Get the org_id for the selected database\n        org_id = build_config[\"database_name\"][\"options_metadata\"][index][\"org_id\"]\n        if not org_id:\n            return build_config\n\n        # Update the list of keyspaces based on the db info\n        build_config[\"keyspace\"][\"options\"] = build_config[\"database_name\"][\"options_metadata\"][index][\"keyspaces\"]\n        build_config[\"keyspace\"][\"value\"] = (\n            build_config[\"keyspace\"][\"options\"] and build_config[\"keyspace\"][\"options\"][0]\n            if build_config[\"keyspace\"][\"value\"] not in build_config[\"keyspace\"][\"options\"]\n            else build_config[\"keyspace\"][\"value\"]\n        )\n\n        # Get the database id for the selected database\n        db_id = self.get_database_id_static(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        keyspace = self.get_keyspace()\n\n        # Update the helper text for the embedding provider field\n        template = build_config[\"collection_name\"][\"dialog_inputs\"][\"fields\"][\"data\"][\"node\"][\"template\"]\n        template[\"02_embedding_generation_provider\"][\"helper_text\"] = (\n            \"To create collections with more embedding provider options, go to \"\n            f'<a class=\"underline\" target=\"_blank\" rel=\"noopener noreferrer\" '\n            f'href=\"https://astra.datastax.com/org/{org_id}/database/{db_id}/data-explorer?createCollection=1&namespace={keyspace}\">'\n            \"your database in Astra DB</a>.\"\n        )\n\n        # Reset provider options\n        build_config = self.reset_provider_options(build_config)\n\n        # Handle hybrid search options\n        build_config = self._handle_hybrid_search_options(build_config)\n\n        return self.reset_collection_list(build_config)\n\n    def _handle_collection_selection(self, build_config: dict, field_value: str) -> dict:\n        \"\"\"Handle collection selection and update embedding options.\"\"\"\n        build_config[\"autodetect_collection\"][\"value\"] = True\n        build_config = self.reset_collection_list(build_config)\n\n        # Reset embedding model if collection selection changes\n        if field_value and field_value not in build_config[\"collection_name\"][\"options\"]:\n            build_config[\"collection_name\"][\"options\"].append(field_value)\n            build_config[\"collection_name\"][\"options_metadata\"].append(\n                {\n                    \"records\": 0,\n                    \"provider\": None,\n                    \"icon\": \"vectorstores\",\n                    \"model\": None,\n                }\n            )\n            build_config[\"autodetect_collection\"][\"value\"] = False\n\n        if not field_value:\n            return build_config\n\n        # Get the selected collection index\n        index = build_config[\"collection_name\"][\"options\"].index(field_value)\n\n        # Set the provider of the selected collection\n        provider = build_config[\"collection_name\"][\"options_metadata\"][index][\"provider\"]\n        build_config[\"embedding_model\"][\"show\"] = not bool(provider)\n        build_config[\"embedding_model\"][\"required\"] = not bool(provider)\n\n        # Grab the collection object\n        database = self.get_database_object(api_endpoint=build_config[\"api_endpoint\"][\"value\"])\n        collection = database.get_collection(\n            name=field_value,\n            keyspace=build_config[\"keyspace\"][\"value\"],\n        )\n\n        # Check if hybrid and lexical are enabled\n        col_options = collection.options()\n        hyb_enabled = col_options.rerank and col_options.rerank.enabled\n        lex_enabled = col_options.lexical and col_options.lexical.enabled\n        user_hyb_enabled = build_config[\"search_method\"][\"value\"] == \"Hybrid Search\"\n\n        # Reranker visible when both the collection supports it and the user selected Hybrid\n        hybrid_active = bool(hyb_enabled and user_hyb_enabled)\n        build_config[\"reranker\"][\"show\"] = hybrid_active\n        build_config[\"reranker\"][\"toggle_value\"] = hybrid_active\n        build_config[\"reranker\"][\"toggle_disable\"] = False  # allow user to toggle if visible\n\n        # If hybrid is active, lock search_type to \"Similarity\"\n        if hybrid_active:\n            build_config[\"search_type\"][\"value\"] = \"Similarity\"\n\n        # Show the lexical terms option only if the collection enables lexical search\n        build_config[\"lexical_terms\"][\"show\"] = bool(lex_enabled)\n\n        return build_config\n\n    @check_cached_vector_store\n    def build_vector_store(self):\n        try:\n            from langchain_astradb import AstraDBVectorStore\n        except ImportError as e:\n            msg = (\n                \"Could not import langchain Astra DB integration package. \"\n                \"Please install it with `pip install langchain-astradb`.\"\n            )\n            raise ImportError(msg) from e\n\n        # Get the embedding model and additional params\n        embedding_params = {\"embedding\": self.embedding_model} if self.embedding_model else {}\n\n        # Get the additional parameters\n        additional_params = self.astradb_vectorstore_kwargs or {}\n\n        # Get Langflow version and platform information\n        __version__ = get_version_info()[\"version\"]\n        langflow_prefix = \"\"\n        # if os.getenv(\"AWS_EXECUTION_ENV\") == \"AWS_ECS_FARGATE\":  # TODO: More precise way of detecting\n        #     langflow_prefix = \"ds-\"\n\n        # Get the database object\n        database = self.get_database_object()\n        autodetect = self.collection_name in database.list_collection_names() and self.autodetect_collection\n\n        # Bundle up the auto-detect parameters\n        autodetect_params = {\n            \"autodetect_collection\": autodetect,\n            \"content_field\": (\n                self.content_field\n                if self.content_field and embedding_params\n                else (\n                    \"page_content\"\n                    if embedding_params\n                    and self.collection_data(collection_name=self.collection_name, database=database) == 0\n                    else None\n                )\n            ),\n            \"ignore_invalid_documents\": self.ignore_invalid_documents,\n        }\n\n        # Choose HybridSearchMode based on the selected param\n        hybrid_search_mode = HybridSearchMode.DEFAULT if self.search_method == \"Hybrid Search\" else HybridSearchMode.OFF\n\n        # Attempt to build the Vector Store object\n        try:\n            vector_store = AstraDBVectorStore(\n                # Astra DB Authentication Parameters\n                token=self.token,\n                api_endpoint=database.api_endpoint,\n                namespace=database.keyspace,\n                collection_name=self.collection_name,\n                environment=self.environment,\n                # Hybrid Search Parameters\n                hybrid_search=hybrid_search_mode,\n                # Astra DB Usage Tracking Parameters\n                ext_callers=[(f\"{langflow_prefix}langflow\", __version__)],\n                # Astra DB Vector Store Parameters\n                **autodetect_params,\n                **embedding_params,\n                **additional_params,\n            )\n        except Exception as e:\n            msg = f\"Error initializing AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        # Add documents to the vector store\n        self._add_documents_to_vector_store(vector_store)\n\n        return vector_store\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        self.ingest_data = self._prepare_ingest_data()\n\n        documents = []\n        for _input in self.ingest_data or []:\n            if isinstance(_input, Data):\n                documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        documents = [\n            Document(page_content=doc.page_content, metadata=serialize(doc.metadata, to_str=True)) for doc in documents\n        ]\n\n        if documents and self.deletion_field:\n            self.log(f\"Deleting documents where {self.deletion_field}\")\n            try:\n                database = self.get_database_object()\n                collection = database.get_collection(self.collection_name, keyspace=database.keyspace)\n                delete_values = list({doc.metadata[self.deletion_field] for doc in documents})\n                self.log(f\"Deleting documents where {self.deletion_field} matches {delete_values}.\")\n                collection.delete_many({f\"metadata.{self.deletion_field}\": {\"$in\": delete_values}})\n            except Exception as e:\n                msg = f\"Error deleting documents from AstraDBVectorStore based on '{self.deletion_field}': {e}\"\n                raise ValueError(msg) from e\n\n        if documents:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                vector_store.add_documents(documents)\n            except Exception as e:\n                msg = f\"Error adding documents to AstraDBVectorStore: {e}\"\n                raise ValueError(msg) from e\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    def _map_search_type(self) -> str:\n        search_type_mapping = {\n            \"Similarity with score threshold\": \"similarity_score_threshold\",\n            \"MMR (Max Marginal Relevance)\": \"mmr\",\n        }\n\n        return search_type_mapping.get(self.search_type, \"similarity\")\n\n    def _build_search_args(self):\n        # Clean up the search query\n        query = self.search_query if isinstance(self.search_query, str) and self.search_query.strip() else None\n        lexical_terms = self.lexical_terms or None\n\n        # Check if we have a search query, and if so set the args\n        if query:\n            args = {\n                \"query\": query,\n                \"search_type\": self._map_search_type(),\n                \"k\": self.number_of_results,\n                \"score_threshold\": self.search_score_threshold,\n                \"lexical_query\": lexical_terms,\n            }\n        elif self.advanced_search_filter:\n            args = {\n                \"n\": self.number_of_results,\n            }\n        else:\n            return {}\n\n        filter_arg = self.advanced_search_filter or {}\n        if filter_arg:\n            args[\"filter\"] = filter_arg\n\n        return args\n\n    def search_documents(self, vector_store=None) -> list[Data]:\n        vector_store = vector_store or self.build_vector_store()\n\n        self.log(f\"Search input: {self.search_query}\")\n        self.log(f\"Search type: {self.search_type}\")\n        self.log(f\"Number of results: {self.number_of_results}\")\n        self.log(f\"store.hybrid_search: {vector_store.hybrid_search}\")\n        self.log(f\"Lexical terms: {self.lexical_terms}\")\n        self.log(f\"Reranker: {self.reranker}\")\n\n        try:\n            search_args = self._build_search_args()\n        except Exception as e:\n            msg = f\"Error in AstraDBVectorStore._build_search_args: {e}\"\n            raise ValueError(msg) from e\n\n        if not search_args:\n            self.log(\"No search input or filters provided. Skipping search.\")\n            return []\n\n        docs = []\n        search_method = \"search\" if \"query\" in search_args else \"metadata_search\"\n\n        try:\n            self.log(f\"Calling vector_store.{search_method} with args: {search_args}\")\n            docs = getattr(vector_store, search_method)(**search_args)\n        except Exception as e:\n            msg = f\"Error performing {search_method} in AstraDBVectorStore: {e}\"\n            raise ValueError(msg) from e\n\n        self.log(f\"Retrieved documents: {len(docs)}\")\n\n        data = docs_to_data(docs)\n        self.log(f\"Converted documents to data: {len(data)}\")\n        self.status = data\n\n        return data\n\n    def get_retriever_kwargs(self):\n        search_args = self._build_search_args()\n\n        return {\n            \"search_type\": self._map_search_type(),\n            \"search_kwargs\": search_args,\n        }\n"
               },
               "collection_name": {
                 "_input_type": "DropdownInput",
@@ -4284,7 +4284,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from copy import deepcopy\nfrom typing import Any\n\nfrom langflow.base.data.base_file import BaseFileComponent\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom langflow.io import BoolInput, FileInput, IntInput, Output\nfrom langflow.schema.data import Data\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"Handles loading and processing of individual or zipped text files.\n\n    This component supports processing multiple valid files within a zip archive,\n    resolving paths, validating file types, and optionally using multithreading for processing.\n    \"\"\"\n\n    display_name = \"File\"\n    description = \"Loads content from one or more files.\"\n    documentation: str = \"https://docs.langflow.org/components-data#file\"\n    icon = \"file-text\"\n    name = \"File\"\n\n    VALID_EXTENSIONS = TEXT_FILE_TYPES\n\n    _base_inputs = deepcopy(BaseFileComponent._base_inputs)\n\n    for input_item in _base_inputs:\n        if isinstance(input_item, FileInput) and input_item.name == \"path\":\n            input_item.real_time_refresh = True\n            break\n\n    inputs = [\n        *_base_inputs,\n        BoolInput(\n            name=\"use_multithreading\",\n            display_name=\"[Deprecated] Use Multithreading\",\n            advanced=True,\n            value=True,\n            info=\"Set 'Processing Concurrency' greater than 1 to enable multithreading.\",\n        ),\n        IntInput(\n            name=\"concurrency_multithreading\",\n            display_name=\"Processing Concurrency\",\n            advanced=True,\n            info=\"When multiple files are being processed, the number of files to process concurrently.\",\n            value=1,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n    ]\n\n    def update_outputs(self, frontend_node: dict, field_name: str, field_value: Any) -> dict:\n        \"\"\"Dynamically show only the relevant output based on the number of files processed.\"\"\"\n        if field_name == \"path\":\n            # Add outputs based on the number of files in the path\n            if len(field_value) == 0:\n                return frontend_node\n\n            frontend_node[\"outputs\"] = []\n\n            if len(field_value) == 1:\n                # We need to check if the file is structured content\n                file_path = frontend_node[\"template\"][\"path\"][\"file_path\"][0]\n                if file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n                    frontend_node[\"outputs\"].append(\n                        Output(display_name=\"Structured Content\", name=\"dataframe\", method=\"load_files_structured\"),\n                    )\n                elif file_path.endswith(\".json\"):\n                    frontend_node[\"outputs\"].append(\n                        Output(display_name=\"Structured Content\", name=\"json\", method=\"load_files_json\"),\n                    )\n\n                # All files get the raw content and path outputs\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n            else:\n                # For multiple files, we only show the files output\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Files\", name=\"dataframe\", method=\"load_files\"),\n                )\n\n        return frontend_node\n\n    def process_files(self, file_list: list[BaseFileComponent.BaseFile]) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Processes files either sequentially or in parallel, depending on concurrency settings.\n\n        Args:\n            file_list (list[BaseFileComponent.BaseFile]): List of files to process.\n\n        Returns:\n            list[BaseFileComponent.BaseFile]: Updated list of files with merged data.\n        \"\"\"\n\n        def process_file(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            \"\"\"Processes a single file and returns its Data object.\"\"\"\n            try:\n                return parse_text_file_to_data(file_path, silent_errors=silent_errors)\n            except FileNotFoundError as e:\n                msg = f\"File not found: {file_path}. Error: {e}\"\n                self.log(msg)\n                if not silent_errors:\n                    raise\n                return None\n            except Exception as e:\n                msg = f\"Unexpected error processing {file_path}: {e}\"\n                self.log(msg)\n                if not silent_errors:\n                    raise\n                return None\n\n        if not file_list:\n            msg = \"No files to process.\"\n            raise ValueError(msg)\n\n        concurrency = 1 if not self.use_multithreading else max(1, self.concurrency_multithreading)\n        file_count = len(file_list)\n\n        parallel_processing_threshold = 2\n        if concurrency < parallel_processing_threshold or file_count < parallel_processing_threshold:\n            if file_count > 1:\n                self.log(f\"Processing {file_count} files sequentially.\")\n            processed_data = [process_file(str(file.path), silent_errors=self.silent_errors) for file in file_list]\n        else:\n            self.log(f\"Starting parallel processing of {file_count} files with concurrency: {concurrency}.\")\n            file_paths = [str(file.path) for file in file_list]\n            processed_data = parallel_load_data(\n                file_paths,\n                silent_errors=self.silent_errors,\n                load_function=process_file,\n                max_concurrency=concurrency,\n            )\n\n        # Use rollup_basefile_data to merge processed data with BaseFile objects\n        return self.rollup_data(file_list, processed_data)\n"
+                "value": "\"\"\"Enhanced file component v2 with mypy and ruff compliance.\"\"\"\n\nfrom __future__ import annotations\n\nfrom copy import deepcopy\nfrom enum import Enum\nfrom typing import TYPE_CHECKING, Any\n\nfrom langflow.base.data.base_file import BaseFileComponent\nfrom langflow.base.data.utils import TEXT_FILE_TYPES, parallel_load_data, parse_text_file_to_data\nfrom langflow.io import (\n    BoolInput,\n    DropdownInput,\n    FileInput,\n    IntInput,\n    MessageTextInput,\n    Output,\n    StrInput,\n)\nfrom langflow.schema.data import Data\nfrom langflow.schema.message import Message\n\nif TYPE_CHECKING:\n    from langflow.schema import DataFrame\n\n\nclass MockConversionStatus(Enum):\n    \"\"\"Mock ConversionStatus for fallback compatibility.\"\"\"\n\n    SUCCESS = \"success\"\n    FAILURE = \"failure\"\n\n\nclass MockInputFormat(Enum):\n    \"\"\"Mock InputFormat for fallback compatibility.\"\"\"\n\n    PDF = \"pdf\"\n    IMAGE = \"image\"\n\n\nclass MockImageRefMode(Enum):\n    \"\"\"Mock ImageRefMode for fallback compatibility.\"\"\"\n\n    PLACEHOLDER = \"placeholder\"\n    EMBEDDED = \"embedded\"\n\n\nclass DoclingImports:\n    \"\"\"Container for docling imports with type information.\"\"\"\n\n    def __init__(\n        self,\n        conversion_status: type[Enum],\n        input_format: type[Enum],\n        document_converter: type,\n        image_ref_mode: type[Enum],\n        strategy: str,\n    ) -> None:\n        self.conversion_status = conversion_status\n        self.input_format = input_format\n        self.document_converter = document_converter\n        self.image_ref_mode = image_ref_mode\n        self.strategy = strategy\n\n\nclass FileComponent(BaseFileComponent):\n    \"\"\"Enhanced file component v2 that combines standard file loading with optional Docling processing and export.\n\n    This component supports all features of the standard File component, plus an advanced mode\n    that enables Docling document processing and export to various formats (Markdown, HTML, etc.).\n    \"\"\"\n\n    display_name = \"File\"\n    description = \"Loads content from files with optional advanced document processing and export using Docling.\"\n    documentation: str = \"https://docs.langflow.org/components-data#file\"\n    icon = \"file-text\"\n    name = \"File\"\n\n    # Docling supported formats from original component\n    VALID_EXTENSIONS = [\n        \"adoc\",\n        \"asciidoc\",\n        \"asc\",\n        \"bmp\",\n        \"csv\",\n        \"dotx\",\n        \"dotm\",\n        \"docm\",\n        \"docx\",\n        \"htm\",\n        \"html\",\n        \"jpeg\",\n        \"json\",\n        \"md\",\n        \"pdf\",\n        \"png\",\n        \"potx\",\n        \"ppsx\",\n        \"pptm\",\n        \"potm\",\n        \"ppsm\",\n        \"pptx\",\n        \"tiff\",\n        \"txt\",\n        \"xls\",\n        \"xlsx\",\n        \"xhtml\",\n        \"xml\",\n        \"webp\",\n        *TEXT_FILE_TYPES,\n    ]\n\n    # Fixed export settings\n    EXPORT_FORMAT = \"Markdown\"\n    IMAGE_MODE = \"placeholder\"\n\n    _base_inputs = deepcopy(BaseFileComponent._base_inputs)\n\n    for input_item in _base_inputs:\n        if isinstance(input_item, FileInput) and input_item.name == \"path\":\n            input_item.real_time_refresh = True\n            break\n\n    inputs = [\n        *_base_inputs,\n        BoolInput(\n            name=\"advanced_mode\",\n            display_name=\"Advanced Parser\",\n            value=False,\n            real_time_refresh=True,\n            info=(\n                \"Enable advanced document processing and export with Docling for PDFs, images, and office documents. \"\n                \"Available only for single file processing.\"\n            ),\n            show=False,\n        ),\n        DropdownInput(\n            name=\"pipeline\",\n            display_name=\"Pipeline\",\n            info=\"Docling pipeline to use\",\n            options=[\"standard\", \"vlm\"],\n            value=\"standard\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"ocr_engine\",\n            display_name=\"OCR Engine\",\n            info=\"OCR engine to use. Only available when pipeline is set to 'standard'.\",\n            options=[\"\", \"easyocr\"],\n            value=\"\",\n            show=False,\n            advanced=True,\n        ),\n        StrInput(\n            name=\"md_image_placeholder\",\n            display_name=\"Image placeholder\",\n            info=\"Specify the image placeholder for markdown exports.\",\n            value=\"<!-- image -->\",\n            advanced=True,\n            show=False,\n        ),\n        StrInput(\n            name=\"md_page_break_placeholder\",\n            display_name=\"Page break placeholder\",\n            info=\"Add this placeholder between pages in the markdown output.\",\n            value=\"\",\n            advanced=True,\n            show=False,\n        ),\n        MessageTextInput(\n            name=\"doc_key\",\n            display_name=\"Doc Key\",\n            info=\"The key to use for the DoclingDocument column.\",\n            value=\"doc\",\n            advanced=True,\n            show=False,\n        ),\n        BoolInput(\n            name=\"use_multithreading\",\n            display_name=\"[Deprecated] Use Multithreading\",\n            advanced=True,\n            value=True,\n            info=\"Set 'Processing Concurrency' greater than 1 to enable multithreading.\",\n        ),\n        IntInput(\n            name=\"concurrency_multithreading\",\n            display_name=\"Processing Concurrency\",\n            advanced=True,\n            info=\"When multiple files are being processed, the number of files to process concurrently.\",\n            value=1,\n        ),\n        BoolInput(\n            name=\"markdown\",\n            display_name=\"Markdown Export\",\n            info=\"Export processed documents to Markdown format. Only available when advanced mode is enabled.\",\n            value=False,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n    ]\n\n    def _path_value(self, template) -> list[str]:\n        # Get current path value\n        return template.get(\"path\", {}).get(\"file_path\", [])\n\n    def update_build_config(\n        self,\n        build_config: dict[str, Any],\n        field_value: Any,\n        field_name: str | None = None,\n    ) -> dict[str, Any]:\n        \"\"\"Update build configuration to show/hide fields based on file count and advanced_mode.\"\"\"\n        if field_name == \"path\":\n            # Get current path value\n            path_value = self._path_value(build_config)\n            file_path = path_value[0] if len(path_value) > 0 else \"\"\n\n            # Show/hide Advanced Parser based on file count (only for single files)\n            file_count = len(field_value) if field_value else 0\n            if file_count == 1 and not file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n                build_config[\"advanced_mode\"][\"show\"] = True\n            else:\n                build_config[\"advanced_mode\"][\"show\"] = False\n                build_config[\"advanced_mode\"][\"value\"] = False  # Reset to False when hidden\n\n                # Hide all advanced fields when Advanced Parser is not available\n                advanced_fields = [\n                    \"pipeline\",\n                    \"ocr_engine\",\n                    \"doc_key\",\n                    \"md_image_placeholder\",\n                    \"md_page_break_placeholder\",\n                ]\n                for field in advanced_fields:\n                    if field in build_config:\n                        build_config[field][\"show\"] = False\n\n        elif field_name == \"advanced_mode\":\n            # Show/hide advanced fields based on advanced_mode (only if single file)\n            advanced_fields = [\n                \"pipeline\",\n                \"ocr_engine\",\n                \"doc_key\",\n                \"md_image_placeholder\",\n                \"md_page_break_placeholder\",\n            ]\n\n            for field in advanced_fields:\n                if field in build_config:\n                    build_config[field][\"show\"] = field_value\n\n        return build_config\n\n    def update_outputs(self, frontend_node: dict[str, Any], field_name: str, field_value: Any) -> dict[str, Any]:  # noqa: ARG002\n        \"\"\"Dynamically show outputs based on the number of files and their types.\"\"\"\n        if field_name not in [\"path\", \"advanced_mode\"]:\n            return frontend_node\n\n        # Add outputs based on the number of files in the path\n        template = frontend_node.get(\"template\", {})\n        path_value = self._path_value(template)\n        if len(path_value) == 0:\n            return frontend_node\n\n        # Clear existing outputs\n        frontend_node[\"outputs\"] = []\n\n        if len(path_value) == 1:\n            # We need to check if the file is structured content\n            file_path = path_value[0] if field_name == \"path\" else frontend_node[\"template\"][\"path\"][\"file_path\"][0]\n            if file_path.endswith((\".csv\", \".xlsx\", \".parquet\")):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"dataframe\", method=\"load_files_structured\"),\n                )\n            elif file_path.endswith(\".json\"):\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Content\", name=\"json\", method=\"load_files_json\"),\n                )\n\n            # Add outputs based on advanced mode\n            advanced_mode = frontend_node.get(\"template\", {}).get(\"advanced_mode\", {}).get(\"value\", False)\n\n            if advanced_mode:\n                # Advanced mode: Structured Output, Markdown, and File Path\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Structured Output\", name=\"advanced\", method=\"load_files_advanced\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Markdown\", name=\"markdown\", method=\"load_files_markdown\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n            else:\n                # Normal mode: Raw Content and File Path\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"Raw Content\", name=\"message\", method=\"load_files_message\"),\n                )\n                frontend_node[\"outputs\"].append(\n                    Output(display_name=\"File Path\", name=\"path\", method=\"load_files_path\"),\n                )\n        else:\n            # For multiple files, we show the files output (DataFrame format)\n            # Advanced Parser is not available for multiple files\n            frontend_node[\"outputs\"].append(\n                Output(display_name=\"Files\", name=\"dataframe\", method=\"load_files\"),\n            )\n\n        return frontend_node\n\n    def _try_import_docling(self) -> DoclingImports | None:\n        \"\"\"Try different import strategies for docling components.\"\"\"\n        # Try strategy 1: Latest docling structure\n        try:\n            from docling.datamodel.base_models import ConversionStatus, InputFormat  # type: ignore[import-untyped]\n            from docling.document_converter import DocumentConverter  # type: ignore[import-untyped]\n            from docling_core.types.doc import ImageRefMode  # type: ignore[import-untyped]\n\n            self.log(\"Using latest docling import structure\")\n            return DoclingImports(\n                conversion_status=ConversionStatus,\n                input_format=InputFormat,\n                document_converter=DocumentConverter,\n                image_ref_mode=ImageRefMode,\n                strategy=\"latest\",\n            )\n        except ImportError as e:\n            self.log(f\"Latest docling structure failed: {e}\")\n\n        # Try strategy 2: Alternative import paths\n        try:\n            from docling.document_converter import DocumentConverter  # type: ignore[import-untyped]\n            from docling_core.types.doc import ImageRefMode  # type: ignore[import-untyped]\n\n            # Try to get ConversionStatus from different locations\n            conversion_status: type[Enum] = MockConversionStatus\n            input_format: type[Enum] = MockInputFormat\n\n            try:\n                from docling_core.types import ConversionStatus, InputFormat  # type: ignore[import-untyped]\n\n                conversion_status = ConversionStatus\n                input_format = InputFormat\n            except ImportError:\n                try:\n                    from docling.datamodel import ConversionStatus, InputFormat  # type: ignore[import-untyped]\n\n                    conversion_status = ConversionStatus\n                    input_format = InputFormat\n                except ImportError:\n                    # Use mock enums if we can't find them\n                    pass\n\n            self.log(\"Using alternative docling import structure\")\n            return DoclingImports(\n                conversion_status=conversion_status,\n                input_format=input_format,\n                document_converter=DocumentConverter,\n                image_ref_mode=ImageRefMode,\n                strategy=\"alternative\",\n            )\n        except ImportError as e:\n            self.log(f\"Alternative docling structure failed: {e}\")\n\n        # Try strategy 3: Basic converter only\n        try:\n            from docling.document_converter import DocumentConverter  # type: ignore[import-untyped]\n\n            self.log(\"Using basic docling import structure with mocks\")\n            return DoclingImports(\n                conversion_status=MockConversionStatus,\n                input_format=MockInputFormat,\n                document_converter=DocumentConverter,\n                image_ref_mode=MockImageRefMode,\n                strategy=\"basic\",\n            )\n        except ImportError as e:\n            self.log(f\"Basic docling structure failed: {e}\")\n\n        # Strategy 4: Complete fallback - return None to indicate failure\n        return None\n\n    def _create_advanced_converter(self, docling_imports: DoclingImports) -> Any:\n        \"\"\"Create advanced converter with pipeline options if available.\"\"\"\n        try:\n            from docling.datamodel.pipeline_options import PdfPipelineOptions  # type: ignore[import-untyped]\n            from docling.document_converter import PdfFormatOption  # type: ignore[import-untyped]\n\n            document_converter = docling_imports.document_converter\n            input_format = docling_imports.input_format\n\n            # Create basic pipeline options\n            pipeline_options = PdfPipelineOptions()\n\n            # Configure OCR if specified and available\n            if self.ocr_engine:\n                try:\n                    from docling.models.factories import get_ocr_factory  # type: ignore[import-untyped]\n\n                    pipeline_options.do_ocr = True\n                    ocr_factory = get_ocr_factory(allow_external_plugins=False)\n                    ocr_options = ocr_factory.create_options(kind=self.ocr_engine)\n                    pipeline_options.ocr_options = ocr_options\n                    self.log(f\"Configured OCR with engine: {self.ocr_engine}\")\n                except Exception as e:  # noqa: BLE001\n                    self.log(f\"Could not configure OCR: {e}, proceeding without OCR\")\n                    pipeline_options.do_ocr = False\n\n            # Create format options\n            pdf_format_option = PdfFormatOption(pipeline_options=pipeline_options)\n            format_options = {}\n            if hasattr(input_format, \"PDF\"):\n                format_options[input_format.PDF] = pdf_format_option\n            if hasattr(input_format, \"IMAGE\"):\n                format_options[input_format.IMAGE] = pdf_format_option\n\n            return document_converter(format_options=format_options)\n\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Could not create advanced converter: {e}, using basic converter\")\n            return docling_imports.document_converter()\n\n    def _is_docling_compatible(self, file_path: str) -> bool:\n        \"\"\"Check if file is compatible with Docling processing.\"\"\"\n        # All VALID_EXTENSIONS are Docling compatible (except for TEXT_FILE_TYPES which may overlap)\n        docling_extensions = [\n            \".adoc\",\n            \".asciidoc\",\n            \".asc\",\n            \".bmp\",\n            \".csv\",\n            \".dotx\",\n            \".dotm\",\n            \".docm\",\n            \".docx\",\n            \".htm\",\n            \".html\",\n            \".jpeg\",\n            \".json\",\n            \".md\",\n            \".pdf\",\n            \".png\",\n            \".potx\",\n            \".ppsx\",\n            \".pptm\",\n            \".potm\",\n            \".ppsm\",\n            \".pptx\",\n            \".tiff\",\n            \".txt\",\n            \".xls\",\n            \".xlsx\",\n            \".xhtml\",\n            \".xml\",\n            \".webp\",\n        ]\n        return any(file_path.lower().endswith(ext) for ext in docling_extensions)\n\n    def process_files(\n        self,\n        file_list: list[BaseFileComponent.BaseFile],\n    ) -> list[BaseFileComponent.BaseFile]:\n        \"\"\"Process files using standard parsing or Docling based on advanced_mode and file type.\"\"\"\n\n        def process_file_standard(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            \"\"\"Process a single file using standard text parsing.\"\"\"\n            try:\n                return parse_text_file_to_data(file_path, silent_errors=silent_errors)\n            except FileNotFoundError as e:\n                msg = f\"File not found: {file_path}. Error: {e}\"\n                self.log(msg)\n                if not silent_errors:\n                    raise\n                return None\n            except Exception as e:\n                msg = f\"Unexpected error processing {file_path}: {e}\"\n                self.log(msg)\n                if not silent_errors:\n                    raise\n                return None\n\n        def process_file_docling(file_path: str, *, silent_errors: bool = False) -> Data | None:\n            \"\"\"Process a single file using Docling if compatible, otherwise standard processing.\"\"\"\n            # Try Docling first if file is compatible and advanced mode is enabled\n            try:\n                return self._process_with_docling_and_export(file_path)\n            except Exception as e:  # noqa: BLE001\n                self.log(f\"Docling processing failed for {file_path}: {e}, falling back to standard processing\")\n                if not silent_errors:\n                    # Return error data instead of raising\n                    return Data(data={\"error\": f\"Docling processing failed: {e}\", \"file_path\": file_path})\n\n            return None\n\n        if not file_list:\n            msg = \"No files to process.\"\n            raise ValueError(msg)\n\n        file_path = str(file_list[0].path)\n        if self.advanced_mode and self._is_docling_compatible(file_path):\n            processed_data = process_file_docling(file_path)\n            if not processed_data:\n                msg = f\"Failed to process file with Docling: {file_path}\"\n                raise ValueError(msg)\n\n            # Serialize processed data to match Data structure\n            serialized_data = processed_data.serialize_model()\n\n            # Now, if doc is nested, we need to unravel it\n            clean_data: list[Data | None] = [processed_data]\n\n            # This is where we've manually processed the data\n            try:\n                if \"exported_content\" not in serialized_data:\n                    clean_data = [\n                        Data(\n                            data={\n                                \"file_path\": file_path,\n                                **(\n                                    item[\"element\"]\n                                    if \"element\" in item\n                                    else {k: v for k, v in item.items() if k != \"file_path\"}\n                                ),\n                            }\n                        )\n                        for item in serialized_data[\"doc\"]\n                    ]\n            except Exception as _:  # noqa: BLE001\n                raise ValueError(serialized_data) from None\n\n            # Repeat file_list to match the number of processed data elements\n            final_data: list[Data | None] = clean_data\n            return self.rollup_data(file_list, final_data)\n\n        concurrency = 1 if not self.use_multithreading else max(1, self.concurrency_multithreading)\n        file_count = len(file_list)\n\n        self.log(f\"Starting parallel processing of {file_count} files with concurrency: {concurrency}.\")\n        file_paths = [str(file.path) for file in file_list]\n        my_data = parallel_load_data(\n            file_paths,\n            silent_errors=self.silent_errors,\n            load_function=process_file_standard,\n            max_concurrency=concurrency,\n        )\n\n        return self.rollup_data(file_list, my_data)\n\n    def load_files_advanced(self) -> DataFrame:\n        \"\"\"Load files using advanced Docling processing and export to an advanced format.\"\"\"\n        # TODO: Update\n        self.markdown = False\n        return self.load_files()\n\n    def load_files_markdown(self) -> Message:\n        \"\"\"Load files using advanced Docling processing and export to Markdown format.\"\"\"\n        self.markdown = True\n        result = self.load_files()\n        return Message(text=str(result.text[0]))\n\n    def _process_with_docling_and_export(self, file_path: str) -> Data:\n        \"\"\"Process a single file with Docling and export to the specified format.\"\"\"\n        # Import docling components only when needed\n        docling_imports = self._try_import_docling()\n\n        if docling_imports is None:\n            msg = \"Docling not available for advanced processing\"\n            raise ImportError(msg)\n\n        conversion_status = docling_imports.conversion_status\n        document_converter = docling_imports.document_converter\n        image_ref_mode = docling_imports.image_ref_mode\n\n        try:\n            # Create converter based on strategy and pipeline setting\n            if docling_imports.strategy == \"latest\" and self.pipeline == \"standard\":\n                converter = self._create_advanced_converter(docling_imports)\n            else:\n                # Use basic converter for compatibility\n                converter = document_converter()\n                self.log(\"Using basic DocumentConverter for Docling processing\")\n\n            # Process single file\n            result = converter.convert(file_path)\n\n            # Check if conversion was successful\n            success = False\n            if hasattr(result, \"status\"):\n                if hasattr(conversion_status, \"SUCCESS\"):\n                    success = result.status == conversion_status.SUCCESS\n                else:\n                    success = str(result.status).lower() == \"success\"\n            elif hasattr(result, \"document\"):\n                # If no status but has document, assume success\n                success = result.document is not None\n\n            if not success:\n                return Data(data={\"error\": \"Docling conversion failed\", \"file_path\": file_path})\n\n            if self.markdown:\n                self.log(\"Exporting document to Markdown format\")\n                # Export the document to the specified format\n                exported_content = self._export_document(result.document, image_ref_mode)\n\n                return Data(\n                    text=exported_content,\n                    data={\n                        \"exported_content\": exported_content,\n                        \"export_format\": self.EXPORT_FORMAT,\n                        \"file_path\": file_path,\n                    },\n                )\n\n            return Data(\n                data={\n                    \"doc\": self.docling_to_dataframe_simple(result.document.export_to_dict()),\n                    \"export_format\": self.EXPORT_FORMAT,\n                    \"file_path\": file_path,\n                }\n            )\n\n        except Exception as e:  # noqa: BLE001\n            return Data(data={\"error\": f\"Docling processing error: {e!s}\", \"file_path\": file_path})\n\n    def docling_to_dataframe_simple(self, doc):\n        \"\"\"Extract all text elements into a simple DataFrame.\"\"\"\n        return [\n            {\n                \"page_no\": text[\"prov\"][0][\"page_no\"] if text[\"prov\"] else None,\n                \"label\": text[\"label\"],\n                \"text\": text[\"text\"],\n                \"level\": text.get(\"level\", None),  # for headers\n            }\n            for text in doc[\"texts\"]\n        ]\n\n    def _export_document(self, document: Any, image_ref_mode: type[Enum]) -> str:\n        \"\"\"Export document to Markdown format with placeholder images.\"\"\"\n        try:\n            image_mode = (\n                image_ref_mode(self.IMAGE_MODE) if hasattr(image_ref_mode, self.IMAGE_MODE) else self.IMAGE_MODE\n            )\n\n            # Always export to Markdown since it's fixed\n            return document.export_to_markdown(\n                image_mode=image_mode,\n                image_placeholder=self.md_image_placeholder,\n                page_break_placeholder=self.md_page_break_placeholder,\n            )\n\n        except Exception as e:  # noqa: BLE001\n            self.log(f\"Markdown export failed: {e}, using basic text export\")\n            # Fallback to basic text export\n            try:\n                return document.export_to_text()\n            except Exception:  # noqa: BLE001\n                return str(document)\n"
               },
               "concurrency_multithreading": {
                 "_input_type": "IntInput",

langflow-base-nightly 0.5.0.dev36__py3-none-any.whl → 0.5.0.dev38__py3-none-any.whl

langflow-base-nightly 0.5.0.dev36py3-none-any.whl → 0.5.0.dev38py3-none-any.whl