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

langflow/initial_setup/starter_projects/Knowledge Ingestion.json

@@ -339,7 +339,7 @@
             "legacy": false,
             "lf_version": "1.5.0.post1",
             "metadata": {
-              "code_hash": "a81817a7f244",
+              "code_hash": "252132357639",
               "module": "langflow.components.data.url.URLComponent"
             },
             "minimized": false,
@@ -429,7 +429,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\nfrom loguru import logger\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.helpers.data import safe_convert\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\nfrom langflow.services.deps import get_settings_service\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/components-data#url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=\"Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.\",\n            options=[\"Text\", \"HTML\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": get_settings_service().settings.user_agent}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers}\n        extractor = (lambda x: x) if self.format == \"HTML\" else (lambda x: BeautifulSoup(x, \"lxml\").get_text())\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
+                "value": "import re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.helpers.data import safe_convert\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom langflow.logging.logger import logger\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.message import Message\nfrom langflow.services.deps import get_settings_service\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/components-data#url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=\"Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.\",\n            options=[\"Text\", \"HTML\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": get_settings_service().settings.user_agent}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers}\n        extractor = (lambda x: x) if self.format == \"HTML\" else (lambda x: BeautifulSoup(x, \"lxml\").get_text())\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
               },
               "continue_on_failure": {
                 "_input_type": "BoolInput",
@@ -702,7 +702,7 @@
             "last_updated": "2025-08-13T19:45:49.122Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "e1ebcd66ecbc",
+              "code_hash": "6c62063f2c09",
               "module": "langflow.components.data.kb_ingest.KBIngestionComponent"
             },
             "minimized": false,
@@ -795,7 +795,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from __future__ import annotations\n\nimport hashlib\nimport json\nimport re\nimport uuid\nfrom dataclasses import asdict, dataclass, field\nfrom datetime import datetime, timezone\nfrom pathlib import Path\nfrom typing import Any\n\nimport pandas as pd\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom loguru import logger\n\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, DataFrameInput, DropdownInput, IntInput, Output, SecretStrInput, StrInput, TableInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict  # noqa: TC001\nfrom langflow.schema.table import EditMode\nfrom langflow.services.auth.utils import decrypt_api_key, encrypt_api_key\nfrom langflow.services.deps import get_settings_service\n\nHUGGINGFACE_MODEL_NAMES = [\"sentence-transformers/all-MiniLM-L6-v2\", \"sentence-transformers/all-mpnet-base-v2\"]\nCOHERE_MODEL_NAMES = [\"embed-english-v3.0\", \"embed-multilingual-v3.0\"]\n\nsettings = get_settings_service().settings\nknowledge_directory = settings.knowledge_bases_dir\nif not knowledge_directory:\n    msg = \"Knowledge bases directory is not set in the settings.\"\n    raise ValueError(msg)\nKNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n\n\nclass KBIngestionComponent(Component):\n    \"\"\"Create or append to Langflow Knowledge from a DataFrame.\"\"\"\n\n    # ------ UI metadata ---------------------------------------------------\n    display_name = \"Knowledge Ingestion\"\n    description = \"Create or update knowledge in Langflow.\"\n    icon = \"database\"\n    name = \"KBIngestion\"\n\n    @dataclass\n    class NewKnowledgeBaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_knowledge_base\",\n                        \"description\": \"Create new knowledge in Langflow.\",\n                        \"display_name\": \"Create new knowledge\",\n                        \"field_order\": [\"01_new_kb_name\", \"02_embedding_model\", \"03_api_key\"],\n                        \"template\": {\n                            \"01_new_kb_name\": StrInput(\n                                name=\"new_kb_name\",\n                                display_name=\"Knowledge Name\",\n                                info=\"Name of the new knowledge to create.\",\n                                required=True,\n                            ),\n                            \"02_embedding_model\": DropdownInput(\n                                name=\"embedding_model\",\n                                display_name=\"Model Name\",\n                                info=\"Select the embedding model to use for this knowledge base.\",\n                                required=True,\n                                options=OPENAI_EMBEDDING_MODEL_NAMES + HUGGINGFACE_MODEL_NAMES + COHERE_MODEL_NAMES,\n                                options_metadata=[{\"icon\": \"OpenAI\"} for _ in OPENAI_EMBEDDING_MODEL_NAMES]\n                                + [{\"icon\": \"HuggingFace\"} for _ in HUGGINGFACE_MODEL_NAMES]\n                                + [{\"icon\": \"Cohere\"} for _ in COHERE_MODEL_NAMES],\n                            ),\n                            \"03_api_key\": SecretStrInput(\n                                name=\"api_key\",\n                                display_name=\"API Key\",\n                                info=\"Provider API key for embedding model\",\n                                required=True,\n                                load_from_db=True,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    # ------ Inputs --------------------------------------------------------\n    inputs = [\n        DropdownInput(\n            name=\"knowledge_base\",\n            display_name=\"Knowledge\",\n            info=\"Select the knowledge to load data from.\",\n            required=True,\n            options=[\n                str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()\n            ]\n            if KNOWLEDGE_BASES_ROOT_PATH.exists()\n            else [],\n            refresh_button=True,\n            dialog_inputs=asdict(NewKnowledgeBaseInput()),\n        ),\n        DataFrameInput(\n            name=\"input_df\",\n            display_name=\"Data\",\n            info=\"Table with all original columns (already chunked / processed).\",\n            required=True,\n        ),\n        TableInput(\n            name=\"column_config\",\n            display_name=\"Column Configuration\",\n            info=\"Configure column behavior for the knowledge base.\",\n            required=True,\n            table_schema=[\n                {\n                    \"name\": \"column_name\",\n                    \"display_name\": \"Column Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Name of the column in the source DataFrame\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"vectorize\",\n                    \"display_name\": \"Vectorize\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Create embeddings for this column\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"identifier\",\n                    \"display_name\": \"Identifier\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Use this column as unique identifier\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"column_name\": \"text\",\n                    \"vectorize\": True,\n                    \"identifier\": True,\n                },\n            ],\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=\"Batch size for processing embeddings\",\n            advanced=True,\n            value=1000,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Embedding Provider API Key\",\n            info=\"API key for the embedding provider to generate embeddings.\",\n            advanced=True,\n            required=False,\n        ),\n        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            info=\"Allow duplicate rows in the knowledge base\",\n            advanced=True,\n            value=False,\n        ),\n    ]\n\n    # ------ Outputs -------------------------------------------------------\n    outputs = [Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"build_kb_info\")]\n\n    # ------ Internal helpers ---------------------------------------------\n    def _get_kb_root(self) -> Path:\n        \"\"\"Return the root directory for knowledge bases.\"\"\"\n        return KNOWLEDGE_BASES_ROOT_PATH\n\n    def _validate_column_config(self, df_source: pd.DataFrame) -> list[dict[str, Any]]:\n        \"\"\"Validate column configuration using Structured Output patterns.\"\"\"\n        if not self.column_config:\n            msg = \"Column configuration cannot be empty\"\n            raise ValueError(msg)\n\n        # Convert table input to list of dicts (similar to Structured Output)\n        config_list = self.column_config if isinstance(self.column_config, list) else []\n\n        # Validate column names exist in DataFrame\n        df_columns = set(df_source.columns)\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            if col_name not in df_columns:\n                msg = f\"Column '{col_name}' not found in DataFrame. Available columns: {sorted(df_columns)}\"\n                raise ValueError(msg)\n\n        return config_list\n\n    def _get_embedding_provider(self, embedding_model: str) -> str:\n        \"\"\"Get embedding provider by matching model name to lists.\"\"\"\n        if embedding_model in OPENAI_EMBEDDING_MODEL_NAMES:\n            return \"OpenAI\"\n        if embedding_model in HUGGINGFACE_MODEL_NAMES:\n            return \"HuggingFace\"\n        if embedding_model in COHERE_MODEL_NAMES:\n            return \"Cohere\"\n        return \"Custom\"\n\n    def _build_embeddings(self, embedding_model: str, api_key: str):\n        \"\"\"Build embedding model using provider patterns.\"\"\"\n        # Get provider by matching model name to lists\n        provider = self._get_embedding_provider(embedding_model)\n\n        # Validate provider and model\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required when using OpenAI provider\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=embedding_model,\n                api_key=api_key,\n                chunk_size=self.chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=embedding_model,\n            )\n        if provider == \"Cohere\":\n            from langchain_cohere import CohereEmbeddings\n\n            if not api_key:\n                msg = \"Cohere API key is required when using Cohere provider\"\n                raise ValueError(msg)\n            return CohereEmbeddings(\n                model=embedding_model,\n                cohere_api_key=api_key,\n            )\n        if provider == \"Custom\":\n            # For custom embedding models, we would need additional configuration\n            msg = \"Custom embedding models not yet supported\"\n            raise NotImplementedError(msg)\n        msg = f\"Unknown provider: {provider}\"\n        raise ValueError(msg)\n\n    def _build_embedding_metadata(self, embedding_model, api_key) -> dict[str, Any]:\n        \"\"\"Build embedding model metadata.\"\"\"\n        # Get provider by matching model name to lists\n        embedding_provider = self._get_embedding_provider(embedding_model)\n\n        api_key_to_save = None\n        if api_key and hasattr(api_key, \"get_secret_value\"):\n            api_key_to_save = api_key.get_secret_value()\n        elif isinstance(api_key, str):\n            api_key_to_save = api_key\n\n        encrypted_api_key = None\n        if api_key_to_save:\n            settings_service = get_settings_service()\n            try:\n                encrypted_api_key = encrypt_api_key(api_key_to_save, settings_service=settings_service)\n            except (TypeError, ValueError) as e:\n                self.log(f\"Could not encrypt API key: {e}\")\n                logger.error(f\"Could not encrypt API key: {e}\")\n\n        return {\n            \"embedding_provider\": embedding_provider,\n            \"embedding_model\": embedding_model,\n            \"api_key\": encrypted_api_key,\n            \"api_key_used\": bool(api_key),\n            \"chunk_size\": self.chunk_size,\n            \"created_at\": datetime.now(timezone.utc).isoformat(),\n        }\n\n    def _save_embedding_metadata(self, kb_path: Path, embedding_model: str, api_key: str) -> None:\n        \"\"\"Save embedding model metadata.\"\"\"\n        embedding_metadata = self._build_embedding_metadata(embedding_model, api_key)\n        metadata_path = kb_path / \"embedding_metadata.json\"\n        metadata_path.write_text(json.dumps(embedding_metadata, indent=2))\n\n    def _save_kb_files(\n        self,\n        kb_path: Path,\n        config_list: list[dict[str, Any]],\n    ) -> None:\n        \"\"\"Save KB files using File Component storage patterns.\"\"\"\n        try:\n            # Create directory (following File Component patterns)\n            kb_path.mkdir(parents=True, exist_ok=True)\n\n            # Save column configuration\n            # Only do this if the file doesn't exist already\n            cfg_path = kb_path / \"schema.json\"\n            if not cfg_path.exists():\n                cfg_path.write_text(json.dumps(config_list, indent=2))\n\n        except (OSError, TypeError, ValueError) as e:\n            self.log(f\"Error saving KB files: {e}\")\n\n    def _build_column_metadata(self, config_list: list[dict[str, Any]], df_source: pd.DataFrame) -> dict[str, Any]:\n        \"\"\"Build detailed column metadata.\"\"\"\n        metadata: dict[str, Any] = {\n            \"total_columns\": len(df_source.columns),\n            \"mapped_columns\": len(config_list),\n            \"unmapped_columns\": len(df_source.columns) - len(config_list),\n            \"columns\": [],\n            \"summary\": {\"vectorized_columns\": [], \"identifier_columns\": []},\n        }\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            # Add to columns list\n            metadata[\"columns\"].append(\n                {\n                    \"name\": col_name,\n                    \"vectorize\": vectorize,\n                    \"identifier\": identifier,\n                }\n            )\n\n            # Update summary\n            if vectorize:\n                metadata[\"summary\"][\"vectorized_columns\"].append(col_name)\n            if identifier:\n                metadata[\"summary\"][\"identifier_columns\"].append(col_name)\n\n        return metadata\n\n    def _create_vector_store(\n        self, df_source: pd.DataFrame, config_list: list[dict[str, Any]], embedding_model: str, api_key: str\n    ) -> None:\n        \"\"\"Create vector store following Local DB component pattern.\"\"\"\n        try:\n            # Set up vector store directory\n            base_dir = self._get_kb_root()\n\n            vector_store_dir = base_dir / self.knowledge_base\n            vector_store_dir.mkdir(parents=True, exist_ok=True)\n\n            # Create embeddings model\n            embedding_function = self._build_embeddings(embedding_model, api_key)\n\n            # Convert DataFrame to Data objects (following Local DB pattern)\n            data_objects = self._convert_df_to_data_objects(df_source, config_list)\n\n            # Create vector store\n            chroma = Chroma(\n                persist_directory=str(vector_store_dir),\n                embedding_function=embedding_function,\n                collection_name=self.knowledge_base,\n            )\n\n            # Convert Data objects to LangChain Documents\n            documents = []\n            for data_obj in data_objects:\n                doc = data_obj.to_lc_document()\n                documents.append(doc)\n\n            # Add documents to vector store\n            if documents:\n                chroma.add_documents(documents)\n                self.log(f\"Added {len(documents)} documents to vector store '{self.knowledge_base}'\")\n\n        except (OSError, ValueError, RuntimeError) as e:\n            self.log(f\"Error creating vector store: {e}\")\n\n    def _convert_df_to_data_objects(self, df_source: pd.DataFrame, config_list: list[dict[str, Any]]) -> list[Data]:\n        \"\"\"Convert DataFrame to Data objects for vector store.\"\"\"\n        data_objects: list[Data] = []\n\n        # Set up vector store directory\n        base_dir = self._get_kb_root()\n\n        # If we don't allow duplicates, we need to get the existing hashes\n        chroma = Chroma(\n            persist_directory=str(base_dir / self.knowledge_base),\n            collection_name=self.knowledge_base,\n        )\n\n        # Get all documents and their metadata\n        all_docs = chroma.get()\n\n        # Extract all _id values from metadata\n        id_list = [metadata.get(\"_id\") for metadata in all_docs[\"metadatas\"] if metadata.get(\"_id\")]\n\n        # Get column roles\n        content_cols = []\n        identifier_cols = []\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            if vectorize:\n                content_cols.append(col_name)\n            elif identifier:\n                identifier_cols.append(col_name)\n\n        # Convert each row to a Data object\n        for _, row in df_source.iterrows():\n            # Build content text from identifier columns using list comprehension\n            identifier_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]\n\n            # Join all parts into a single string\n            page_content = \" \".join(identifier_parts)\n\n            # Build metadata from NON-vectorized columns only (simple key-value pairs)\n            data_dict = {\n                \"text\": page_content,  # Main content for vectorization\n            }\n\n            # Add identifier columns if they exist\n            if identifier_cols:\n                identifier_parts = [str(row[col]) for col in identifier_cols if col in row and pd.notna(row[col])]\n                page_content = \" \".join(identifier_parts)\n\n            # Add metadata columns as simple key-value pairs\n            for col in df_source.columns:\n                if col not in content_cols and col in row and pd.notna(row[col]):\n                    # Convert to simple types for Chroma metadata\n                    value = row[col]\n                    data_dict[col] = str(value)  # Convert complex types to string\n\n            # Hash the page_content for unique ID\n            page_content_hash = hashlib.sha256(page_content.encode()).hexdigest()\n            data_dict[\"_id\"] = page_content_hash\n\n            # If duplicates are disallowed, and hash exists, prevent adding this row\n            if not self.allow_duplicates and page_content_hash in id_list:\n                self.log(f\"Skipping duplicate row with hash {page_content_hash}\")\n                continue\n\n            # Create Data object - everything except \"text\" becomes metadata\n            data_obj = Data(data=data_dict)\n            data_objects.append(data_obj)\n\n        return data_objects\n\n    def is_valid_collection_name(self, name, min_length: int = 3, max_length: int = 63) -> bool:\n        \"\"\"Validates collection name against conditions 1-3.\n\n        1. Contains 3-63 characters\n        2. Starts and ends with alphanumeric character\n        3. Contains only alphanumeric characters, underscores, or hyphens.\n\n        Args:\n            name (str): Collection name to validate\n            min_length (int): Minimum length of the name\n            max_length (int): Maximum length of the name\n\n        Returns:\n            bool: True if valid, False otherwise\n        \"\"\"\n        # Check length (condition 1)\n        if not (min_length <= len(name) <= max_length):\n            return False\n\n        # Check start/end with alphanumeric (condition 2)\n        if not (name[0].isalnum() and name[-1].isalnum()):\n            return False\n\n        # Check allowed characters (condition 3)\n        return re.match(r\"^[a-zA-Z0-9_-]+$\", name) is not None\n\n    # ---------------------------------------------------------------------\n    #                         OUTPUT METHODS\n    # ---------------------------------------------------------------------\n    def build_kb_info(self) -> Data:\n        \"\"\"Main ingestion routine → returns a dict with KB metadata.\"\"\"\n        try:\n            # Get source DataFrame\n            df_source: pd.DataFrame = self.input_df\n\n            # Validate column configuration (using Structured Output patterns)\n            config_list = self._validate_column_config(df_source)\n            column_metadata = self._build_column_metadata(config_list, df_source)\n\n            # Prepare KB folder (using File Component patterns)\n            kb_root = self._get_kb_root()\n            kb_path = kb_root / self.knowledge_base\n\n            # Read the embedding info from the knowledge base folder\n            metadata_path = kb_path / \"embedding_metadata.json\"\n\n            # If the API key is not provided, try to read it from the metadata file\n            if metadata_path.exists():\n                settings_service = get_settings_service()\n                metadata = json.loads(metadata_path.read_text())\n                embedding_model = metadata.get(\"embedding_model\")\n                try:\n                    api_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                except (InvalidToken, TypeError, ValueError) as e:\n                    logger.error(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n\n            # Check if a custom API key was provided, update metadata if so\n            if self.api_key:\n                api_key = self.api_key\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=embedding_model,\n                    api_key=api_key,\n                )\n\n            # Create vector store following Local DB component pattern\n            self._create_vector_store(df_source, config_list, embedding_model=embedding_model, api_key=api_key)\n\n            # Save KB files (using File Component storage patterns)\n            self._save_kb_files(kb_path, config_list)\n\n            # Build metadata response\n            meta: dict[str, Any] = {\n                \"kb_id\": str(uuid.uuid4()),\n                \"kb_name\": self.knowledge_base,\n                \"rows\": len(df_source),\n                \"column_metadata\": column_metadata,\n                \"path\": str(kb_path),\n                \"config_columns\": len(config_list),\n                \"timestamp\": datetime.now(tz=timezone.utc).isoformat(),\n            }\n\n            # Set status message\n            self.status = f\"✅ KB **{self.knowledge_base}** saved · {len(df_source)} chunks.\"\n\n            return Data(data=meta)\n\n        except (OSError, ValueError, RuntimeError, KeyError) as e:\n            self.log(f\"Error in KB ingestion: {e}\")\n            self.status = f\"❌ KB ingestion failed: {e}\"\n            return Data(data={\"error\": str(e), \"kb_name\": self.knowledge_base})\n\n    def _get_knowledge_bases(self) -> list[str]:\n        \"\"\"Retrieve a list of available knowledge bases.\n\n        Returns:\n            A list of knowledge base names.\n        \"\"\"\n        # Return the list of directories in the knowledge base root path\n        kb_root_path = self._get_kb_root()\n\n        if not kb_root_path.exists():\n            return []\n\n        return [str(d.name) for d in kb_root_path.iterdir() if not d.name.startswith(\".\") and d.is_dir()]\n\n    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None) -> dotdict:\n        \"\"\"Update build configuration based on provider selection.\"\"\"\n        # Create a new knowledge base\n        if field_name == \"knowledge_base\":\n            if isinstance(field_value, dict) and \"01_new_kb_name\" in field_value:\n                # Validate the knowledge base name - Make sure it follows these rules:\n                if not self.is_valid_collection_name(field_value[\"01_new_kb_name\"]):\n                    msg = f\"Invalid knowledge base name: {field_value['01_new_kb_name']}\"\n                    raise ValueError(msg)\n\n                # We need to test the API Key one time against the embedding model\n                embed_model = self._build_embeddings(\n                    embedding_model=field_value[\"02_embedding_model\"], api_key=field_value[\"03_api_key\"]\n                )\n\n                # Try to generate a dummy embedding to validate the API key\n                embed_model.embed_query(\"test\")\n\n                # Create the new knowledge base directory\n                kb_path = KNOWLEDGE_BASES_ROOT_PATH / field_value[\"01_new_kb_name\"]\n                kb_path.mkdir(parents=True, exist_ok=True)\n\n                # Save the embedding metadata\n                build_config[\"knowledge_base\"][\"value\"] = field_value[\"01_new_kb_name\"]\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=field_value[\"02_embedding_model\"],\n                    api_key=field_value[\"03_api_key\"],\n                )\n\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = self._get_knowledge_bases()\n            if build_config[\"knowledge_base\"][\"value\"] not in build_config[\"knowledge_base\"][\"options\"]:\n                build_config[\"knowledge_base\"][\"value\"] = None\n\n        return build_config\n"
+                "value": "from __future__ import annotations\n\nimport asyncio\nimport contextlib\nimport hashlib\nimport json\nimport re\nimport uuid\nfrom dataclasses import asdict, dataclass, field\nfrom datetime import datetime, timezone\nfrom pathlib import Path\nfrom typing import Any\n\nimport pandas as pd\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom loguru import logger\n\nfrom langflow.base.data.kb_utils import get_knowledge_bases\nfrom langflow.base.models.openai_constants import OPENAI_EMBEDDING_MODEL_NAMES\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, DataFrameInput, DropdownInput, IntInput, Output, SecretStrInput, StrInput, TableInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict  # noqa: TC001\nfrom langflow.schema.table import EditMode\nfrom langflow.services.auth.utils import decrypt_api_key, encrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom langflow.services.deps import get_settings_service, get_variable_service, session_scope\n\nHUGGINGFACE_MODEL_NAMES = [\"sentence-transformers/all-MiniLM-L6-v2\", \"sentence-transformers/all-mpnet-base-v2\"]\nCOHERE_MODEL_NAMES = [\"embed-english-v3.0\", \"embed-multilingual-v3.0\"]\n\nsettings = get_settings_service().settings\nknowledge_directory = settings.knowledge_bases_dir\nif not knowledge_directory:\n    msg = \"Knowledge bases directory is not set in the settings.\"\n    raise ValueError(msg)\nKNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n\n\nclass KBIngestionComponent(Component):\n    \"\"\"Create or append to Langflow Knowledge from a DataFrame.\"\"\"\n\n    # ------ UI metadata ---------------------------------------------------\n    display_name = \"Knowledge Ingestion\"\n    description = \"Create or update knowledge in Langflow.\"\n    icon = \"database\"\n    name = \"KBIngestion\"\n\n    def __init__(self, *args, **kwargs) -> None:\n        super().__init__(*args, **kwargs)\n        self._cached_kb_path: Path | None = None\n\n    @dataclass\n    class NewKnowledgeBaseInput:\n        functionality: str = \"create\"\n        fields: dict[str, dict] = field(\n            default_factory=lambda: {\n                \"data\": {\n                    \"node\": {\n                        \"name\": \"create_knowledge_base\",\n                        \"description\": \"Create new knowledge in Langflow.\",\n                        \"display_name\": \"Create new knowledge\",\n                        \"field_order\": [\"01_new_kb_name\", \"02_embedding_model\", \"03_api_key\"],\n                        \"template\": {\n                            \"01_new_kb_name\": StrInput(\n                                name=\"new_kb_name\",\n                                display_name=\"Knowledge Name\",\n                                info=\"Name of the new knowledge to create.\",\n                                required=True,\n                            ),\n                            \"02_embedding_model\": DropdownInput(\n                                name=\"embedding_model\",\n                                display_name=\"Model Name\",\n                                info=\"Select the embedding model to use for this knowledge base.\",\n                                required=True,\n                                options=OPENAI_EMBEDDING_MODEL_NAMES + HUGGINGFACE_MODEL_NAMES + COHERE_MODEL_NAMES,\n                                options_metadata=[{\"icon\": \"OpenAI\"} for _ in OPENAI_EMBEDDING_MODEL_NAMES]\n                                + [{\"icon\": \"HuggingFace\"} for _ in HUGGINGFACE_MODEL_NAMES]\n                                + [{\"icon\": \"Cohere\"} for _ in COHERE_MODEL_NAMES],\n                            ),\n                            \"03_api_key\": SecretStrInput(\n                                name=\"api_key\",\n                                display_name=\"API Key\",\n                                info=\"Provider API key for embedding model\",\n                                required=True,\n                                load_from_db=False,\n                            ),\n                        },\n                    },\n                }\n            }\n        )\n\n    # ------ Inputs --------------------------------------------------------\n    inputs = [\n        DropdownInput(\n            name=\"knowledge_base\",\n            display_name=\"Knowledge\",\n            info=\"Select the knowledge to load data from.\",\n            required=True,\n            options=[],\n            refresh_button=True,\n            dialog_inputs=asdict(NewKnowledgeBaseInput()),\n        ),\n        DataFrameInput(\n            name=\"input_df\",\n            display_name=\"Data\",\n            info=\"Table with all original columns (already chunked / processed).\",\n            required=True,\n        ),\n        TableInput(\n            name=\"column_config\",\n            display_name=\"Column Configuration\",\n            info=\"Configure column behavior for the knowledge base.\",\n            required=True,\n            table_schema=[\n                {\n                    \"name\": \"column_name\",\n                    \"display_name\": \"Column Name\",\n                    \"type\": \"str\",\n                    \"description\": \"Name of the column in the source DataFrame\",\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"vectorize\",\n                    \"display_name\": \"Vectorize\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Create embeddings for this column\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n                {\n                    \"name\": \"identifier\",\n                    \"display_name\": \"Identifier\",\n                    \"type\": \"boolean\",\n                    \"description\": \"Use this column as unique identifier\",\n                    \"default\": False,\n                    \"edit_mode\": EditMode.INLINE,\n                },\n            ],\n            value=[\n                {\n                    \"column_name\": \"text\",\n                    \"vectorize\": True,\n                    \"identifier\": True,\n                },\n            ],\n        ),\n        IntInput(\n            name=\"chunk_size\",\n            display_name=\"Chunk Size\",\n            info=\"Batch size for processing embeddings\",\n            advanced=True,\n            value=1000,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Embedding Provider API Key\",\n            info=\"API key for the embedding provider to generate embeddings.\",\n            advanced=True,\n            required=False,\n        ),\n        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            info=\"Allow duplicate rows in the knowledge base\",\n            advanced=True,\n            value=False,\n        ),\n    ]\n\n    # ------ Outputs -------------------------------------------------------\n    outputs = [Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"build_kb_info\")]\n\n    # ------ Internal helpers ---------------------------------------------\n    def _get_kb_root(self) -> Path:\n        \"\"\"Return the root directory for knowledge bases.\"\"\"\n        return KNOWLEDGE_BASES_ROOT_PATH\n\n    def _validate_column_config(self, df_source: pd.DataFrame) -> list[dict[str, Any]]:\n        \"\"\"Validate column configuration using Structured Output patterns.\"\"\"\n        if not self.column_config:\n            msg = \"Column configuration cannot be empty\"\n            raise ValueError(msg)\n\n        # Convert table input to list of dicts (similar to Structured Output)\n        config_list = self.column_config if isinstance(self.column_config, list) else []\n\n        # Validate column names exist in DataFrame\n        df_columns = set(df_source.columns)\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            if col_name not in df_columns:\n                msg = f\"Column '{col_name}' not found in DataFrame. Available columns: {sorted(df_columns)}\"\n                raise ValueError(msg)\n\n        return config_list\n\n    def _get_embedding_provider(self, embedding_model: str) -> str:\n        \"\"\"Get embedding provider by matching model name to lists.\"\"\"\n        if embedding_model in OPENAI_EMBEDDING_MODEL_NAMES:\n            return \"OpenAI\"\n        if embedding_model in HUGGINGFACE_MODEL_NAMES:\n            return \"HuggingFace\"\n        if embedding_model in COHERE_MODEL_NAMES:\n            return \"Cohere\"\n        return \"Custom\"\n\n    def _build_embeddings(self, embedding_model: str, api_key: str):\n        \"\"\"Build embedding model using provider patterns.\"\"\"\n        # Get provider by matching model name to lists\n        provider = self._get_embedding_provider(embedding_model)\n\n        # Validate provider and model\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required when using OpenAI provider\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=embedding_model,\n                api_key=api_key,\n                chunk_size=self.chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=embedding_model,\n            )\n        if provider == \"Cohere\":\n            from langchain_cohere import CohereEmbeddings\n\n            if not api_key:\n                msg = \"Cohere API key is required when using Cohere provider\"\n                raise ValueError(msg)\n            return CohereEmbeddings(\n                model=embedding_model,\n                cohere_api_key=api_key,\n            )\n        if provider == \"Custom\":\n            # For custom embedding models, we would need additional configuration\n            msg = \"Custom embedding models not yet supported\"\n            raise NotImplementedError(msg)\n        msg = f\"Unknown provider: {provider}\"\n        raise ValueError(msg)\n\n    def _build_embedding_metadata(self, embedding_model, api_key) -> dict[str, Any]:\n        \"\"\"Build embedding model metadata.\"\"\"\n        # Get provider by matching model name to lists\n        embedding_provider = self._get_embedding_provider(embedding_model)\n\n        api_key_to_save = None\n        if api_key and hasattr(api_key, \"get_secret_value\"):\n            api_key_to_save = api_key.get_secret_value()\n        elif isinstance(api_key, str):\n            api_key_to_save = api_key\n\n        encrypted_api_key = None\n        if api_key_to_save:\n            settings_service = get_settings_service()\n            try:\n                encrypted_api_key = encrypt_api_key(api_key_to_save, settings_service=settings_service)\n            except (TypeError, ValueError) as e:\n                self.log(f\"Could not encrypt API key: {e}\")\n                logger.error(f\"Could not encrypt API key: {e}\")\n\n        return {\n            \"embedding_provider\": embedding_provider,\n            \"embedding_model\": embedding_model,\n            \"api_key\": encrypted_api_key,\n            \"api_key_used\": bool(api_key),\n            \"chunk_size\": self.chunk_size,\n            \"created_at\": datetime.now(timezone.utc).isoformat(),\n        }\n\n    def _save_embedding_metadata(self, kb_path: Path, embedding_model: str, api_key: str) -> None:\n        \"\"\"Save embedding model metadata.\"\"\"\n        embedding_metadata = self._build_embedding_metadata(embedding_model, api_key)\n        metadata_path = kb_path / \"embedding_metadata.json\"\n        metadata_path.write_text(json.dumps(embedding_metadata, indent=2))\n\n    def _save_kb_files(\n        self,\n        kb_path: Path,\n        config_list: list[dict[str, Any]],\n    ) -> None:\n        \"\"\"Save KB files using File Component storage patterns.\"\"\"\n        try:\n            # Create directory (following File Component patterns)\n            kb_path.mkdir(parents=True, exist_ok=True)\n\n            # Save column configuration\n            # Only do this if the file doesn't exist already\n            cfg_path = kb_path / \"schema.json\"\n            if not cfg_path.exists():\n                cfg_path.write_text(json.dumps(config_list, indent=2))\n\n        except (OSError, TypeError, ValueError) as e:\n            self.log(f\"Error saving KB files: {e}\")\n\n    def _build_column_metadata(self, config_list: list[dict[str, Any]], df_source: pd.DataFrame) -> dict[str, Any]:\n        \"\"\"Build detailed column metadata.\"\"\"\n        metadata: dict[str, Any] = {\n            \"total_columns\": len(df_source.columns),\n            \"mapped_columns\": len(config_list),\n            \"unmapped_columns\": len(df_source.columns) - len(config_list),\n            \"columns\": [],\n            \"summary\": {\"vectorized_columns\": [], \"identifier_columns\": []},\n        }\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            # Add to columns list\n            metadata[\"columns\"].append(\n                {\n                    \"name\": col_name,\n                    \"vectorize\": vectorize,\n                    \"identifier\": identifier,\n                }\n            )\n\n            # Update summary\n            if vectorize:\n                metadata[\"summary\"][\"vectorized_columns\"].append(col_name)\n            if identifier:\n                metadata[\"summary\"][\"identifier_columns\"].append(col_name)\n\n        return metadata\n\n    async def _create_vector_store(\n        self, df_source: pd.DataFrame, config_list: list[dict[str, Any]], embedding_model: str, api_key: str\n    ) -> None:\n        \"\"\"Create vector store following Local DB component pattern.\"\"\"\n        try:\n            # Set up vector store directory\n            vector_store_dir = await self._kb_path()\n            if not vector_store_dir:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            vector_store_dir.mkdir(parents=True, exist_ok=True)\n\n            # Create embeddings model\n            embedding_function = self._build_embeddings(embedding_model, api_key)\n\n            # Convert DataFrame to Data objects (following Local DB pattern)\n            data_objects = await self._convert_df_to_data_objects(df_source, config_list)\n\n            # Create vector store\n            chroma = Chroma(\n                persist_directory=str(vector_store_dir),\n                embedding_function=embedding_function,\n                collection_name=self.knowledge_base,\n            )\n\n            # Convert Data objects to LangChain Documents\n            documents = []\n            for data_obj in data_objects:\n                doc = data_obj.to_lc_document()\n                documents.append(doc)\n\n            # Add documents to vector store\n            if documents:\n                chroma.add_documents(documents)\n                self.log(f\"Added {len(documents)} documents to vector store '{self.knowledge_base}'\")\n\n        except (OSError, ValueError, RuntimeError) as e:\n            self.log(f\"Error creating vector store: {e}\")\n\n    async def _convert_df_to_data_objects(\n        self, df_source: pd.DataFrame, config_list: list[dict[str, Any]]\n    ) -> list[Data]:\n        \"\"\"Convert DataFrame to Data objects for vector store.\"\"\"\n        data_objects: list[Data] = []\n\n        # Set up vector store directory\n        kb_path = await self._kb_path()\n\n        # If we don't allow duplicates, we need to get the existing hashes\n        chroma = Chroma(\n            persist_directory=str(kb_path),\n            collection_name=self.knowledge_base,\n        )\n\n        # Get all documents and their metadata\n        all_docs = chroma.get()\n\n        # Extract all _id values from metadata\n        id_list = [metadata.get(\"_id\") for metadata in all_docs[\"metadatas\"] if metadata.get(\"_id\")]\n\n        # Get column roles\n        content_cols = []\n        identifier_cols = []\n\n        for config in config_list:\n            col_name = config.get(\"column_name\")\n            vectorize = config.get(\"vectorize\") == \"True\" or config.get(\"vectorize\") is True\n            identifier = config.get(\"identifier\") == \"True\" or config.get(\"identifier\") is True\n\n            if vectorize:\n                content_cols.append(col_name)\n            elif identifier:\n                identifier_cols.append(col_name)\n\n        # Convert each row to a Data object\n        for _, row in df_source.iterrows():\n            # Build content text from identifier columns using list comprehension\n            identifier_parts = [str(row[col]) for col in content_cols if col in row and pd.notna(row[col])]\n\n            # Join all parts into a single string\n            page_content = \" \".join(identifier_parts)\n\n            # Build metadata from NON-vectorized columns only (simple key-value pairs)\n            data_dict = {\n                \"text\": page_content,  # Main content for vectorization\n            }\n\n            # Add identifier columns if they exist\n            if identifier_cols:\n                identifier_parts = [str(row[col]) for col in identifier_cols if col in row and pd.notna(row[col])]\n                page_content = \" \".join(identifier_parts)\n\n            # Add metadata columns as simple key-value pairs\n            for col in df_source.columns:\n                if col not in content_cols and col in row and pd.notna(row[col]):\n                    # Convert to simple types for Chroma metadata\n                    value = row[col]\n                    data_dict[col] = str(value)  # Convert complex types to string\n\n            # Hash the page_content for unique ID\n            page_content_hash = hashlib.sha256(page_content.encode()).hexdigest()\n            data_dict[\"_id\"] = page_content_hash\n\n            # If duplicates are disallowed, and hash exists, prevent adding this row\n            if not self.allow_duplicates and page_content_hash in id_list:\n                self.log(f\"Skipping duplicate row with hash {page_content_hash}\")\n                continue\n\n            # Create Data object - everything except \"text\" becomes metadata\n            data_obj = Data(data=data_dict)\n            data_objects.append(data_obj)\n\n        return data_objects\n\n    def is_valid_collection_name(self, name, min_length: int = 3, max_length: int = 63) -> bool:\n        \"\"\"Validates collection name against conditions 1-3.\n\n        1. Contains 3-63 characters\n        2. Starts and ends with alphanumeric character\n        3. Contains only alphanumeric characters, underscores, or hyphens.\n\n        Args:\n            name (str): Collection name to validate\n            min_length (int): Minimum length of the name\n            max_length (int): Maximum length of the name\n\n        Returns:\n            bool: True if valid, False otherwise\n        \"\"\"\n        # Check length (condition 1)\n        if not (min_length <= len(name) <= max_length):\n            return False\n\n        # Check start/end with alphanumeric (condition 2)\n        if not (name[0].isalnum() and name[-1].isalnum()):\n            return False\n\n        # Check allowed characters (condition 3)\n        return re.match(r\"^[a-zA-Z0-9_-]+$\", name) is not None\n\n    async def _kb_path(self) -> Path | None:\n        # Check if we already have the path cached\n        cached_path = getattr(self, \"_cached_kb_path\", None)\n        if cached_path is not None:\n            return cached_path\n\n        # If not cached, compute it\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching knowledge base path.\"\n                raise ValueError(msg)\n            current_user = await get_user_by_id(db, self.user_id)\n            if not current_user:\n                msg = f\"User with ID {self.user_id} not found.\"\n                raise ValueError(msg)\n            kb_user = current_user.username\n\n        kb_root = self._get_kb_root()\n\n        # Cache the result\n        self._cached_kb_path = kb_root / kb_user / self.knowledge_base\n\n        return self._cached_kb_path\n\n    # ---------------------------------------------------------------------\n    #                         OUTPUT METHODS\n    # ---------------------------------------------------------------------\n    async def build_kb_info(self) -> Data:\n        \"\"\"Main ingestion routine → returns a dict with KB metadata.\"\"\"\n        try:\n            # Get source DataFrame\n            df_source: pd.DataFrame = self.input_df\n\n            # Validate column configuration (using Structured Output patterns)\n            config_list = self._validate_column_config(df_source)\n            column_metadata = self._build_column_metadata(config_list, df_source)\n\n            # Read the embedding info from the knowledge base folder\n            kb_path = await self._kb_path()\n            if not kb_path:\n                msg = \"Knowledge base path is not set. Please create a new knowledge base first.\"\n                raise ValueError(msg)\n            metadata_path = kb_path / \"embedding_metadata.json\"\n\n            # If the API key is not provided, try to read it from the metadata file\n            if metadata_path.exists():\n                settings_service = get_settings_service()\n                metadata = json.loads(metadata_path.read_text())\n                embedding_model = metadata.get(\"embedding_model\")\n                try:\n                    api_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                except (InvalidToken, TypeError, ValueError) as e:\n                    logger.error(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n\n            # Check if a custom API key was provided, update metadata if so\n            if self.api_key:\n                api_key = self.api_key\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=embedding_model,\n                    api_key=api_key,\n                )\n\n            # Create vector store following Local DB component pattern\n            await self._create_vector_store(df_source, config_list, embedding_model=embedding_model, api_key=api_key)\n\n            # Save KB files (using File Component storage patterns)\n            self._save_kb_files(kb_path, config_list)\n\n            # Build metadata response\n            meta: dict[str, Any] = {\n                \"kb_id\": str(uuid.uuid4()),\n                \"kb_name\": self.knowledge_base,\n                \"rows\": len(df_source),\n                \"column_metadata\": column_metadata,\n                \"path\": str(kb_path),\n                \"config_columns\": len(config_list),\n                \"timestamp\": datetime.now(tz=timezone.utc).isoformat(),\n            }\n\n            # Set status message\n            self.status = f\"✅ KB **{self.knowledge_base}** saved · {len(df_source)} chunks.\"\n\n            return Data(data=meta)\n\n        except (OSError, ValueError, RuntimeError, KeyError) as e:\n            self.log(f\"Error in KB ingestion: {e}\")\n            self.status = f\"❌ KB ingestion failed: {e}\"\n            return Data(data={\"error\": str(e), \"kb_name\": self.knowledge_base})\n\n    async def _get_api_key_variable(self, field_value: dict[str, Any]):\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching global variables.\"\n                raise ValueError(msg)\n            current_user = await get_user_by_id(db, self.user_id)\n            if not current_user:\n                msg = f\"User with ID {self.user_id} not found.\"\n                raise ValueError(msg)\n            variable_service = get_variable_service()\n\n            # Process the api_key field variable\n            return await variable_service.get_variable(\n                user_id=current_user.id,\n                name=field_value[\"03_api_key\"],\n                field=\"\",\n                session=db,\n            )\n\n    async def update_build_config(\n        self,\n        build_config: dotdict,\n        field_value: Any,\n        field_name: str | None = None,\n    ) -> dotdict:\n        \"\"\"Update build configuration based on provider selection.\"\"\"\n        # Create a new knowledge base\n        if field_name == \"knowledge_base\":\n            async with session_scope() as db:\n                if not self.user_id:\n                    msg = \"User ID is required for fetching knowledge base list.\"\n                    raise ValueError(msg)\n                current_user = await get_user_by_id(db, self.user_id)\n                if not current_user:\n                    msg = f\"User with ID {self.user_id} not found.\"\n                    raise ValueError(msg)\n                kb_user = current_user.username\n            if isinstance(field_value, dict) and \"01_new_kb_name\" in field_value:\n                # Validate the knowledge base name - Make sure it follows these rules:\n                if not self.is_valid_collection_name(field_value[\"01_new_kb_name\"]):\n                    msg = f\"Invalid knowledge base name: {field_value['01_new_kb_name']}\"\n                    raise ValueError(msg)\n\n                api_key = field_value.get(\"03_api_key\", None)\n                with contextlib.suppress(Exception):\n                    # If the API key is a variable, resolve it\n                    api_key = await self._get_api_key_variable(field_value)\n\n                # Make sure api_key is a string\n                if not isinstance(api_key, str):\n                    msg = \"API key must be a string.\"\n                    raise ValueError(msg)\n\n                # We need to test the API Key one time against the embedding model\n                embed_model = self._build_embeddings(embedding_model=field_value[\"02_embedding_model\"], api_key=api_key)\n\n                # Try to generate a dummy embedding to validate the API key without blocking the event loop\n                try:\n                    await asyncio.wait_for(\n                        asyncio.to_thread(embed_model.embed_query, \"test\"),\n                        timeout=10,\n                    )\n                except TimeoutError as e:\n                    msg = \"Embedding validation timed out. Please verify network connectivity and key.\"\n                    raise ValueError(msg) from e\n                except Exception as e:\n                    msg = f\"Embedding validation failed: {e!s}\"\n                    raise ValueError(msg) from e\n\n                # Create the new knowledge base directory\n                kb_path = KNOWLEDGE_BASES_ROOT_PATH / kb_user / field_value[\"01_new_kb_name\"]\n                kb_path.mkdir(parents=True, exist_ok=True)\n\n                # Save the embedding metadata\n                build_config[\"knowledge_base\"][\"value\"] = field_value[\"01_new_kb_name\"]\n                self._save_embedding_metadata(\n                    kb_path=kb_path,\n                    embedding_model=field_value[\"02_embedding_model\"],\n                    api_key=api_key,\n                )\n\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n                KNOWLEDGE_BASES_ROOT_PATH,\n                user_id=self.user_id,\n            )\n\n            # If the selected knowledge base is not available, reset it\n            if build_config[\"knowledge_base\"][\"value\"] not in build_config[\"knowledge_base\"][\"options\"]:\n                build_config[\"knowledge_base\"][\"value\"] = None\n\n        return build_config\n"
               },
               "column_config": {
                 "_input_type": "TableInput",

langflow/initial_setup/starter_projects/Knowledge Retrieval.json

@@ -532,7 +532,7 @@
             "last_updated": "2025-08-14T17:19:22.182Z",
             "legacy": false,
             "metadata": {
-              "code_hash": "ee2b66958f09",
+              "code_hash": "6fcf86be1aca",
               "module": "langflow.components.data.kb_retrieval.KBRetrievalComponent"
             },
             "minimized": false,
@@ -589,7 +589,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nfrom pathlib import Path\nfrom typing import Any\n\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom loguru import logger\n\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SecretStrInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.services.auth.utils import decrypt_api_key\nfrom langflow.services.deps import get_settings_service\n\nsettings = get_settings_service().settings\nknowledge_directory = settings.knowledge_bases_dir\nif not knowledge_directory:\n    msg = \"Knowledge bases directory is not set in the settings.\"\n    raise ValueError(msg)\nKNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n\n\nclass KBRetrievalComponent(Component):\n    display_name = \"Knowledge Retrieval\"\n    description = \"Search and retrieve data from knowledge.\"\n    icon = \"database\"\n    name = \"KBRetrieval\"\n\n    inputs = [\n        DropdownInput(\n            name=\"knowledge_base\",\n            display_name=\"Knowledge\",\n            info=\"Select the knowledge to load data from.\",\n            required=True,\n            options=[\n                str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()\n            ]\n            if KNOWLEDGE_BASES_ROOT_PATH.exists()\n            else [],\n            refresh_button=True,\n            real_time_refresh=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Embedding Provider API Key\",\n            info=\"API key for the embedding provider to generate embeddings.\",\n            advanced=True,\n            required=False,\n        ),\n        MessageTextInput(\n            name=\"search_query\",\n            display_name=\"Search Query\",\n            info=\"Optional search query to filter knowledge base data.\",\n        ),\n        IntInput(\n            name=\"top_k\",\n            display_name=\"Top K Results\",\n            info=\"Number of top results to return from the knowledge base.\",\n            value=5,\n            advanced=True,\n            required=False,\n        ),\n        BoolInput(\n            name=\"include_metadata\",\n            display_name=\"Include Metadata\",\n            info=\"Whether to include all metadata and embeddings in the output. If false, only content is returned.\",\n            value=True,\n            advanced=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            name=\"chroma_kb_data\",\n            display_name=\"Results\",\n            method=\"get_chroma_kb_data\",\n            info=\"Returns the data from the selected knowledge base.\",\n        ),\n    ]\n\n    def _get_knowledge_bases(self) -> list[str]:\n        \"\"\"Retrieve a list of available knowledge bases.\n\n        Returns:\n            A list of knowledge base names.\n        \"\"\"\n        if not KNOWLEDGE_BASES_ROOT_PATH.exists():\n            return []\n\n        return [str(d.name) for d in KNOWLEDGE_BASES_ROOT_PATH.iterdir() if not d.name.startswith(\".\") and d.is_dir()]\n\n    def update_build_config(self, build_config, field_value, field_name=None):  # noqa: ARG002\n        if field_name == \"knowledge_base\":\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = self._get_knowledge_bases()\n\n            # If the selected knowledge base is not available, reset it\n            if build_config[\"knowledge_base\"][\"value\"] not in build_config[\"knowledge_base\"][\"options\"]:\n                build_config[\"knowledge_base\"][\"value\"] = None\n\n        return build_config\n\n    def _get_kb_metadata(self, kb_path: Path) -> dict:\n        \"\"\"Load and process knowledge base metadata.\"\"\"\n        metadata: dict[str, Any] = {}\n        metadata_file = kb_path / \"embedding_metadata.json\"\n        if not metadata_file.exists():\n            logger.warning(f\"Embedding metadata file not found at {metadata_file}\")\n            return metadata\n\n        try:\n            with metadata_file.open(\"r\", encoding=\"utf-8\") as f:\n                metadata = json.load(f)\n        except json.JSONDecodeError:\n            logger.error(f\"Error decoding JSON from {metadata_file}\")\n            return {}\n\n        # Decrypt API key if it exists\n        if \"api_key\" in metadata and metadata.get(\"api_key\"):\n            settings_service = get_settings_service()\n            try:\n                decrypted_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                metadata[\"api_key\"] = decrypted_key\n            except (InvalidToken, TypeError, ValueError) as e:\n                logger.error(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n                metadata[\"api_key\"] = None\n        return metadata\n\n    def _build_embeddings(self, metadata: dict):\n        \"\"\"Build embedding model from metadata.\"\"\"\n        provider = metadata.get(\"embedding_provider\")\n        model = metadata.get(\"embedding_model\")\n        api_key = metadata.get(\"api_key\")\n        chunk_size = metadata.get(\"chunk_size\")\n\n        # If user provided a key in the input, it overrides the stored one.\n        if self.api_key and self.api_key.get_secret_value():\n            api_key = self.api_key.get_secret_value()\n\n        # Handle various providers\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required. Provide it in the component's advanced settings.\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=model,\n                api_key=api_key,\n                chunk_size=chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=model,\n            )\n        if provider == \"Cohere\":\n            from langchain_cohere import CohereEmbeddings\n\n            if not api_key:\n                msg = \"Cohere API key is required when using Cohere provider\"\n                raise ValueError(msg)\n            return CohereEmbeddings(\n                model=model,\n                cohere_api_key=api_key,\n            )\n        if provider == \"Custom\":\n            # For custom embedding models, we would need additional configuration\n            msg = \"Custom embedding models not yet supported\"\n            raise NotImplementedError(msg)\n        # Add other providers here if they become supported in ingest\n        msg = f\"Embedding provider '{provider}' is not supported for retrieval.\"\n        raise NotImplementedError(msg)\n\n    def get_chroma_kb_data(self) -> DataFrame:\n        \"\"\"Retrieve data from the selected knowledge base by reading the Chroma collection.\n\n        Returns:\n            A DataFrame containing the data rows from the knowledge base.\n        \"\"\"\n        kb_path = KNOWLEDGE_BASES_ROOT_PATH / self.knowledge_base\n\n        metadata = self._get_kb_metadata(kb_path)\n        if not metadata:\n            msg = f\"Metadata not found for knowledge base: {self.knowledge_base}. Ensure it has been indexed.\"\n            raise ValueError(msg)\n\n        # Build the embedder for the knowledge base\n        embedding_function = self._build_embeddings(metadata)\n\n        # Load vector store\n        chroma = Chroma(\n            persist_directory=str(kb_path),\n            embedding_function=embedding_function,\n            collection_name=self.knowledge_base,\n        )\n\n        # If a search query is provided, perform a similarity search\n        if self.search_query:\n            # Use the search query to perform a similarity search\n            logger.info(f\"Performing similarity search with query: {self.search_query}\")\n            results = chroma.similarity_search_with_score(\n                query=self.search_query or \"\",\n                k=self.top_k,\n            )\n        else:\n            results = chroma.similarity_search(\n                query=self.search_query or \"\",\n                k=self.top_k,\n            )\n\n            # For each result, make it a tuple to match the expected output format\n            results = [(doc, 0) for doc in results]  # Assign a dummy score of 0\n\n        # If metadata is enabled, get embeddings for the results\n        id_to_embedding = {}\n        if self.include_metadata and results:\n            doc_ids = [doc[0].metadata.get(\"_id\") for doc in results if doc[0].metadata.get(\"_id\")]\n\n            # Only proceed if we have valid document IDs\n            if doc_ids:\n                # Access underlying client to get embeddings\n                collection = chroma._client.get_collection(name=self.knowledge_base)\n                embeddings_result = collection.get(where={\"_id\": {\"$in\": doc_ids}}, include=[\"embeddings\", \"metadatas\"])\n\n                # Create a mapping from document ID to embedding\n                for i, metadata in enumerate(embeddings_result.get(\"metadatas\", [])):\n                    if metadata and \"_id\" in metadata:\n                        id_to_embedding[metadata[\"_id\"]] = embeddings_result[\"embeddings\"][i]\n\n        # Build output data based on include_metadata setting\n        data_list = []\n        for doc in results:\n            if self.include_metadata:\n                # Include all metadata, embeddings, and content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                    **doc[0].metadata,\n                }\n                if self.search_query:\n                    kwargs[\"_score\"] = -1 * doc[1]\n                kwargs[\"_embeddings\"] = id_to_embedding.get(doc[0].metadata.get(\"_id\"))\n            else:\n                # Only include content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                }\n\n            data_list.append(Data(**kwargs))\n\n        # Return the DataFrame containing the data\n        return DataFrame(data=data_list)\n"
+                "value": "import json\nfrom pathlib import Path\nfrom typing import Any\n\nfrom cryptography.fernet import InvalidToken\nfrom langchain_chroma import Chroma\nfrom loguru import logger\nfrom pydantic import SecretStr\n\nfrom langflow.base.data.kb_utils import get_knowledge_bases\nfrom langflow.custom import Component\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SecretStrInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.services.auth.utils import decrypt_api_key\nfrom langflow.services.database.models.user.crud import get_user_by_id\nfrom langflow.services.deps import get_settings_service, session_scope\n\nsettings = get_settings_service().settings\nknowledge_directory = settings.knowledge_bases_dir\nif not knowledge_directory:\n    msg = \"Knowledge bases directory is not set in the settings.\"\n    raise ValueError(msg)\nKNOWLEDGE_BASES_ROOT_PATH = Path(knowledge_directory).expanduser()\n\n\nclass KBRetrievalComponent(Component):\n    display_name = \"Knowledge Retrieval\"\n    description = \"Search and retrieve data from knowledge.\"\n    icon = \"database\"\n    name = \"KBRetrieval\"\n\n    inputs = [\n        DropdownInput(\n            name=\"knowledge_base\",\n            display_name=\"Knowledge\",\n            info=\"Select the knowledge to load data from.\",\n            required=True,\n            options=[],\n            refresh_button=True,\n            real_time_refresh=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Embedding Provider API Key\",\n            info=\"API key for the embedding provider to generate embeddings.\",\n            advanced=True,\n            required=False,\n        ),\n        MessageTextInput(\n            name=\"search_query\",\n            display_name=\"Search Query\",\n            info=\"Optional search query to filter knowledge base data.\",\n        ),\n        IntInput(\n            name=\"top_k\",\n            display_name=\"Top K Results\",\n            info=\"Number of top results to return from the knowledge base.\",\n            value=5,\n            advanced=True,\n            required=False,\n        ),\n        BoolInput(\n            name=\"include_metadata\",\n            display_name=\"Include Metadata\",\n            info=\"Whether to include all metadata and embeddings in the output. If false, only content is returned.\",\n            value=True,\n            advanced=False,\n        ),\n    ]\n\n    outputs = [\n        Output(\n            name=\"chroma_kb_data\",\n            display_name=\"Results\",\n            method=\"get_chroma_kb_data\",\n            info=\"Returns the data from the selected knowledge base.\",\n        ),\n    ]\n\n    async def update_build_config(self, build_config, field_value, field_name=None):  # noqa: ARG002\n        if field_name == \"knowledge_base\":\n            # Update the knowledge base options dynamically\n            build_config[\"knowledge_base\"][\"options\"] = await get_knowledge_bases(\n                KNOWLEDGE_BASES_ROOT_PATH,\n                user_id=self.user_id,  # Use the user_id from the component context\n            )\n\n            # If the selected knowledge base is not available, reset it\n            if build_config[\"knowledge_base\"][\"value\"] not in build_config[\"knowledge_base\"][\"options\"]:\n                build_config[\"knowledge_base\"][\"value\"] = None\n\n        return build_config\n\n    def _get_kb_metadata(self, kb_path: Path) -> dict:\n        \"\"\"Load and process knowledge base metadata.\"\"\"\n        metadata: dict[str, Any] = {}\n        metadata_file = kb_path / \"embedding_metadata.json\"\n        if not metadata_file.exists():\n            logger.warning(f\"Embedding metadata file not found at {metadata_file}\")\n            return metadata\n\n        try:\n            with metadata_file.open(\"r\", encoding=\"utf-8\") as f:\n                metadata = json.load(f)\n        except json.JSONDecodeError:\n            logger.error(f\"Error decoding JSON from {metadata_file}\")\n            return {}\n\n        # Decrypt API key if it exists\n        if \"api_key\" in metadata and metadata.get(\"api_key\"):\n            settings_service = get_settings_service()\n            try:\n                decrypted_key = decrypt_api_key(metadata[\"api_key\"], settings_service)\n                metadata[\"api_key\"] = decrypted_key\n            except (InvalidToken, TypeError, ValueError) as e:\n                logger.error(f\"Could not decrypt API key. Please provide it manually. Error: {e}\")\n                metadata[\"api_key\"] = None\n        return metadata\n\n    def _build_embeddings(self, metadata: dict):\n        \"\"\"Build embedding model from metadata.\"\"\"\n        runtime_api_key = self.api_key.get_secret_value() if isinstance(self.api_key, SecretStr) else self.api_key\n        provider = metadata.get(\"embedding_provider\")\n        model = metadata.get(\"embedding_model\")\n        api_key = runtime_api_key or metadata.get(\"api_key\")\n        chunk_size = metadata.get(\"chunk_size\")\n\n        # Handle various providers\n        if provider == \"OpenAI\":\n            from langchain_openai import OpenAIEmbeddings\n\n            if not api_key:\n                msg = \"OpenAI API key is required. Provide it in the component's advanced settings.\"\n                raise ValueError(msg)\n            return OpenAIEmbeddings(\n                model=model,\n                api_key=api_key,\n                chunk_size=chunk_size,\n            )\n        if provider == \"HuggingFace\":\n            from langchain_huggingface import HuggingFaceEmbeddings\n\n            return HuggingFaceEmbeddings(\n                model=model,\n            )\n        if provider == \"Cohere\":\n            from langchain_cohere import CohereEmbeddings\n\n            if not api_key:\n                msg = \"Cohere API key is required when using Cohere provider\"\n                raise ValueError(msg)\n            return CohereEmbeddings(\n                model=model,\n                cohere_api_key=api_key,\n            )\n        if provider == \"Custom\":\n            # For custom embedding models, we would need additional configuration\n            msg = \"Custom embedding models not yet supported\"\n            raise NotImplementedError(msg)\n        # Add other providers here if they become supported in ingest\n        msg = f\"Embedding provider '{provider}' is not supported for retrieval.\"\n        raise NotImplementedError(msg)\n\n    async def get_chroma_kb_data(self) -> DataFrame:\n        \"\"\"Retrieve data from the selected knowledge base by reading the Chroma collection.\n\n        Returns:\n            A DataFrame containing the data rows from the knowledge base.\n        \"\"\"\n        # Get the current user\n        async with session_scope() as db:\n            if not self.user_id:\n                msg = \"User ID is required for fetching Knowledge Base data.\"\n                raise ValueError(msg)\n            current_user = await get_user_by_id(db, self.user_id)\n            if not current_user:\n                msg = f\"User with ID {self.user_id} not found.\"\n                raise ValueError(msg)\n            kb_user = current_user.username\n        kb_path = KNOWLEDGE_BASES_ROOT_PATH / kb_user / self.knowledge_base\n\n        metadata = self._get_kb_metadata(kb_path)\n        if not metadata:\n            msg = f\"Metadata not found for knowledge base: {self.knowledge_base}. Ensure it has been indexed.\"\n            raise ValueError(msg)\n\n        # Build the embedder for the knowledge base\n        embedding_function = self._build_embeddings(metadata)\n\n        # Load vector store\n        chroma = Chroma(\n            persist_directory=str(kb_path),\n            embedding_function=embedding_function,\n            collection_name=self.knowledge_base,\n        )\n\n        # If a search query is provided, perform a similarity search\n        if self.search_query:\n            # Use the search query to perform a similarity search\n            logger.info(f\"Performing similarity search with query: {self.search_query}\")\n            results = chroma.similarity_search_with_score(\n                query=self.search_query or \"\",\n                k=self.top_k,\n            )\n        else:\n            results = chroma.similarity_search(\n                query=self.search_query or \"\",\n                k=self.top_k,\n            )\n\n            # For each result, make it a tuple to match the expected output format\n            results = [(doc, 0) for doc in results]  # Assign a dummy score of 0\n\n        # If metadata is enabled, get embeddings for the results\n        id_to_embedding = {}\n        if self.include_metadata and results:\n            doc_ids = [doc[0].metadata.get(\"_id\") for doc in results if doc[0].metadata.get(\"_id\")]\n\n            # Only proceed if we have valid document IDs\n            if doc_ids:\n                # Access underlying client to get embeddings\n                collection = chroma._client.get_collection(name=self.knowledge_base)\n                embeddings_result = collection.get(where={\"_id\": {\"$in\": doc_ids}}, include=[\"embeddings\", \"metadatas\"])\n\n                # Create a mapping from document ID to embedding\n                for i, metadata in enumerate(embeddings_result.get(\"metadatas\", [])):\n                    if metadata and \"_id\" in metadata:\n                        id_to_embedding[metadata[\"_id\"]] = embeddings_result[\"embeddings\"][i]\n\n        # Build output data based on include_metadata setting\n        data_list = []\n        for doc in results:\n            if self.include_metadata:\n                # Include all metadata, embeddings, and content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                    **doc[0].metadata,\n                }\n                if self.search_query:\n                    kwargs[\"_score\"] = -1 * doc[1]\n                kwargs[\"_embeddings\"] = id_to_embedding.get(doc[0].metadata.get(\"_id\"))\n            else:\n                # Only include content\n                kwargs = {\n                    \"content\": doc[0].page_content,\n                }\n\n            data_list.append(Data(**kwargs))\n\n        # Return the DataFrame containing the data\n        return DataFrame(data=data_list)\n"
               },
               "include_metadata": {
                 "_input_type": "BoolInput",

langflow/initial_setup/starter_projects/Market Research.json

@@ -1190,7 +1190,7 @@
             "legacy": false,
             "lf_version": "1.2.0",
             "metadata": {
-              "code_hash": "6843645056d9",
+              "code_hash": "4c76fb76d395",
               "module": "langflow.components.tavily.tavily_search.TavilySearchComponent"
             },
             "minimized": false,
@@ -1268,7 +1268,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import httpx\nfrom loguru import logger\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.inputs.inputs import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.template.field.base import Output\n\n\nclass TavilySearchComponent(Component):\n    display_name = \"Tavily Search API\"\n    description = \"\"\"**Tavily Search** is a search engine optimized for LLMs and RAG, \\\n        aimed at efficient, quick, and persistent search results.\"\"\"\n    icon = \"TavilyIcon\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Tavily API Key\",\n            required=True,\n            info=\"Your Tavily API Key.\",\n        ),\n        MessageTextInput(\n            name=\"query\",\n            display_name=\"Search Query\",\n            info=\"The search query you want to execute with Tavily.\",\n            tool_mode=True,\n        ),\n        DropdownInput(\n            name=\"search_depth\",\n            display_name=\"Search Depth\",\n            info=\"The depth of the search.\",\n            options=[\"basic\", \"advanced\"],\n            value=\"advanced\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"chunks_per_source\",\n            display_name=\"Chunks Per Source\",\n            info=(\"The number of content chunks to retrieve from each source (1-3). Only works with advanced search.\"),\n            value=3,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"topic\",\n            display_name=\"Search Topic\",\n            info=\"The category of the search.\",\n            options=[\"general\", \"news\"],\n            value=\"general\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"days\",\n            display_name=\"Days\",\n            info=\"Number of days back from current date to include. Only available with news topic.\",\n            value=7,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"max_results\",\n            display_name=\"Max Results\",\n            info=\"The maximum number of search results to return.\",\n            value=5,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_answer\",\n            display_name=\"Include Answer\",\n            info=\"Include a short answer to original query.\",\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"time_range\",\n            display_name=\"Time Range\",\n            info=\"The time range back from the current date to filter results.\",\n            options=[\"day\", \"week\", \"month\", \"year\"],\n            value=None,  # Default to None to make it optional\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_images\",\n            display_name=\"Include Images\",\n            info=\"Include a list of query-related images in the response.\",\n            value=True,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"include_domains\",\n            display_name=\"Include Domains\",\n            info=\"Comma-separated list of domains to include in the search results.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"exclude_domains\",\n            display_name=\"Exclude Domains\",\n            info=\"Comma-separated list of domains to exclude from the search results.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_raw_content\",\n            display_name=\"Include Raw Content\",\n            info=\"Include the cleaned and parsed HTML content of each search result.\",\n            value=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"fetch_content_dataframe\"),\n    ]\n\n    def fetch_content(self) -> list[Data]:\n        try:\n            # Only process domains if they're provided\n            include_domains = None\n            exclude_domains = None\n\n            if self.include_domains:\n                include_domains = [domain.strip() for domain in self.include_domains.split(\",\") if domain.strip()]\n\n            if self.exclude_domains:\n                exclude_domains = [domain.strip() for domain in self.exclude_domains.split(\",\") if domain.strip()]\n\n            url = \"https://api.tavily.com/search\"\n            headers = {\n                \"content-type\": \"application/json\",\n                \"accept\": \"application/json\",\n            }\n\n            payload = {\n                \"api_key\": self.api_key,\n                \"query\": self.query,\n                \"search_depth\": self.search_depth,\n                \"topic\": self.topic,\n                \"max_results\": self.max_results,\n                \"include_images\": self.include_images,\n                \"include_answer\": self.include_answer,\n                \"include_raw_content\": self.include_raw_content,\n                \"days\": self.days,\n                \"time_range\": self.time_range,\n            }\n\n            # Only add domains to payload if they exist and have values\n            if include_domains:\n                payload[\"include_domains\"] = include_domains\n            if exclude_domains:\n                payload[\"exclude_domains\"] = exclude_domains\n\n            # Add conditional parameters only if they should be included\n            if self.search_depth == \"advanced\" and self.chunks_per_source:\n                payload[\"chunks_per_source\"] = self.chunks_per_source\n\n            if self.topic == \"news\" and self.days:\n                payload[\"days\"] = int(self.days)  # Ensure days is an integer\n\n            # Add time_range if it's set\n            if hasattr(self, \"time_range\") and self.time_range:\n                payload[\"time_range\"] = self.time_range\n\n            # Add timeout handling\n            with httpx.Client(timeout=90.0) as client:\n                response = client.post(url, json=payload, headers=headers)\n\n            response.raise_for_status()\n            search_results = response.json()\n\n            data_results = []\n\n            if self.include_answer and search_results.get(\"answer\"):\n                data_results.append(Data(text=search_results[\"answer\"]))\n\n            for result in search_results.get(\"results\", []):\n                content = result.get(\"content\", \"\")\n                result_data = {\n                    \"title\": result.get(\"title\"),\n                    \"url\": result.get(\"url\"),\n                    \"content\": content,\n                    \"score\": result.get(\"score\"),\n                }\n                if self.include_raw_content:\n                    result_data[\"raw_content\"] = result.get(\"raw_content\")\n\n                data_results.append(Data(text=content, data=result_data))\n\n            if self.include_images and search_results.get(\"images\"):\n                data_results.append(Data(text=\"Images found\", data={\"images\": search_results[\"images\"]}))\n\n        except httpx.TimeoutException:\n            error_message = \"Request timed out (90s). Please try again or adjust parameters.\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except httpx.HTTPStatusError as exc:\n            error_message = f\"HTTP error occurred: {exc.response.status_code} - {exc.response.text}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except httpx.RequestError as exc:\n            error_message = f\"Request error occurred: {exc}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except ValueError as exc:\n            error_message = f\"Invalid response format: {exc}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        else:\n            self.status = data_results\n            return data_results\n\n    def fetch_content_dataframe(self) -> DataFrame:\n        data = self.fetch_content()\n        return DataFrame(data)\n"
+                "value": "import httpx\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.inputs.inputs import BoolInput, DropdownInput, IntInput, MessageTextInput, SecretStrInput\nfrom langflow.logging.logger import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.template.field.base import Output\n\n\nclass TavilySearchComponent(Component):\n    display_name = \"Tavily Search API\"\n    description = \"\"\"**Tavily Search** is a search engine optimized for LLMs and RAG, \\\n        aimed at efficient, quick, and persistent search results.\"\"\"\n    icon = \"TavilyIcon\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Tavily API Key\",\n            required=True,\n            info=\"Your Tavily API Key.\",\n        ),\n        MessageTextInput(\n            name=\"query\",\n            display_name=\"Search Query\",\n            info=\"The search query you want to execute with Tavily.\",\n            tool_mode=True,\n        ),\n        DropdownInput(\n            name=\"search_depth\",\n            display_name=\"Search Depth\",\n            info=\"The depth of the search.\",\n            options=[\"basic\", \"advanced\"],\n            value=\"advanced\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"chunks_per_source\",\n            display_name=\"Chunks Per Source\",\n            info=(\"The number of content chunks to retrieve from each source (1-3). Only works with advanced search.\"),\n            value=3,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"topic\",\n            display_name=\"Search Topic\",\n            info=\"The category of the search.\",\n            options=[\"general\", \"news\"],\n            value=\"general\",\n            advanced=True,\n        ),\n        IntInput(\n            name=\"days\",\n            display_name=\"Days\",\n            info=\"Number of days back from current date to include. Only available with news topic.\",\n            value=7,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"max_results\",\n            display_name=\"Max Results\",\n            info=\"The maximum number of search results to return.\",\n            value=5,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_answer\",\n            display_name=\"Include Answer\",\n            info=\"Include a short answer to original query.\",\n            value=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"time_range\",\n            display_name=\"Time Range\",\n            info=\"The time range back from the current date to filter results.\",\n            options=[\"day\", \"week\", \"month\", \"year\"],\n            value=None,  # Default to None to make it optional\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_images\",\n            display_name=\"Include Images\",\n            info=\"Include a list of query-related images in the response.\",\n            value=True,\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"include_domains\",\n            display_name=\"Include Domains\",\n            info=\"Comma-separated list of domains to include in the search results.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"exclude_domains\",\n            display_name=\"Exclude Domains\",\n            info=\"Comma-separated list of domains to exclude from the search results.\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"include_raw_content\",\n            display_name=\"Include Raw Content\",\n            info=\"Include the cleaned and parsed HTML content of each search result.\",\n            value=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"DataFrame\", name=\"dataframe\", method=\"fetch_content_dataframe\"),\n    ]\n\n    def fetch_content(self) -> list[Data]:\n        try:\n            # Only process domains if they're provided\n            include_domains = None\n            exclude_domains = None\n\n            if self.include_domains:\n                include_domains = [domain.strip() for domain in self.include_domains.split(\",\") if domain.strip()]\n\n            if self.exclude_domains:\n                exclude_domains = [domain.strip() for domain in self.exclude_domains.split(\",\") if domain.strip()]\n\n            url = \"https://api.tavily.com/search\"\n            headers = {\n                \"content-type\": \"application/json\",\n                \"accept\": \"application/json\",\n            }\n\n            payload = {\n                \"api_key\": self.api_key,\n                \"query\": self.query,\n                \"search_depth\": self.search_depth,\n                \"topic\": self.topic,\n                \"max_results\": self.max_results,\n                \"include_images\": self.include_images,\n                \"include_answer\": self.include_answer,\n                \"include_raw_content\": self.include_raw_content,\n                \"days\": self.days,\n                \"time_range\": self.time_range,\n            }\n\n            # Only add domains to payload if they exist and have values\n            if include_domains:\n                payload[\"include_domains\"] = include_domains\n            if exclude_domains:\n                payload[\"exclude_domains\"] = exclude_domains\n\n            # Add conditional parameters only if they should be included\n            if self.search_depth == \"advanced\" and self.chunks_per_source:\n                payload[\"chunks_per_source\"] = self.chunks_per_source\n\n            if self.topic == \"news\" and self.days:\n                payload[\"days\"] = int(self.days)  # Ensure days is an integer\n\n            # Add time_range if it's set\n            if hasattr(self, \"time_range\") and self.time_range:\n                payload[\"time_range\"] = self.time_range\n\n            # Add timeout handling\n            with httpx.Client(timeout=90.0) as client:\n                response = client.post(url, json=payload, headers=headers)\n\n            response.raise_for_status()\n            search_results = response.json()\n\n            data_results = []\n\n            if self.include_answer and search_results.get(\"answer\"):\n                data_results.append(Data(text=search_results[\"answer\"]))\n\n            for result in search_results.get(\"results\", []):\n                content = result.get(\"content\", \"\")\n                result_data = {\n                    \"title\": result.get(\"title\"),\n                    \"url\": result.get(\"url\"),\n                    \"content\": content,\n                    \"score\": result.get(\"score\"),\n                }\n                if self.include_raw_content:\n                    result_data[\"raw_content\"] = result.get(\"raw_content\")\n\n                data_results.append(Data(text=content, data=result_data))\n\n            if self.include_images and search_results.get(\"images\"):\n                data_results.append(Data(text=\"Images found\", data={\"images\": search_results[\"images\"]}))\n\n        except httpx.TimeoutException:\n            error_message = \"Request timed out (90s). Please try again or adjust parameters.\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except httpx.HTTPStatusError as exc:\n            error_message = f\"HTTP error occurred: {exc.response.status_code} - {exc.response.text}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except httpx.RequestError as exc:\n            error_message = f\"Request error occurred: {exc}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        except ValueError as exc:\n            error_message = f\"Invalid response format: {exc}\"\n            logger.error(error_message)\n            return [Data(text=error_message, data={\"error\": error_message})]\n        else:\n            self.status = data_results\n            return data_results\n\n    def fetch_content_dataframe(self) -> DataFrame:\n        data = self.fetch_content()\n        return DataFrame(data)\n"
               },
               "days": {
                 "_input_type": "IntInput",
@@ -2213,7 +2213,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def message_response(self) -> Message:\n        try:\n            # Get LLM model and validate\n            llm_model, display_name = self.get_llm()\n            if llm_model is None:\n                msg = \"No language model selected. Please choose a model to proceed.\"\n                raise ValueError(msg)\n            self.model_name = get_model_name(llm_model, display_name=display_name)\n\n            # Get memory data\n            self.chat_history = await self.get_memory_data()\n            if isinstance(self.chat_history, Message):\n                self.chat_history = [self.chat_history]\n\n            # Add current date tool if enabled\n            if self.add_current_date_tool:\n                if not isinstance(self.tools, list):  # type: ignore[has-type]\n                    self.tools = []\n                current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n                if not isinstance(current_date_tool, StructuredTool):\n                    msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                    raise TypeError(msg)\n                self.tools.append(current_date_tool)\n            # note the tools are not required to run the agent, hence the validation removed.\n\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n            # return result\n\n        except (ValueError, TypeError, KeyError) as e:\n            logger.error(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            logger.error(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        except Exception as e:\n            logger.error(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output.\"\"\"\n        # Run the regular message response first to get the result\n        if not hasattr(self, \"_agent_result\"):\n            await self.message_response()\n\n        result = self._agent_result\n\n        # Extract content from result\n        if hasattr(result, \"content\"):\n            content = result.content\n        elif hasattr(result, \"text\"):\n            content = result.text\n        else:\n            content = str(result)\n\n        # Try to parse as JSON\n        try:\n            json_data = json.loads(content)\n            return Data(data=json_data)\n        except json.JSONDecodeError:\n            # If it's not valid JSON, try to extract JSON from the content\n            json_match = re.search(r\"\\{.*\\}\", content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                    return Data(data=json_data)\n                except json.JSONDecodeError:\n                    pass\n\n            # If we can't extract JSON, return the raw content as data\n            return Data(data={\"content\": content, \"error\": \"Could not parse as JSON\"})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except Exception as e:\n            logger.error(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
+                "value": "import json\nimport re\n\nfrom langchain_core.tools import StructuredTool\n\nfrom langflow.base.agents.agent import LCToolsAgentComponent\nfrom langflow.base.agents.events import ExceptionWithMessageError\nfrom langflow.base.models.model_input_constants import (\n    ALL_PROVIDER_FIELDS,\n    MODEL_DYNAMIC_UPDATE_FIELDS,\n    MODEL_PROVIDERS,\n    MODEL_PROVIDERS_DICT,\n    MODELS_METADATA,\n)\nfrom langflow.base.models.model_utils import get_model_name\nfrom langflow.components.helpers.current_date import CurrentDateComponent\nfrom langflow.components.helpers.memory import MemoryComponent\nfrom langflow.components.langchain_utilities.tool_calling import ToolCallingAgentComponent\nfrom langflow.custom.custom_component.component import _get_component_toolkit\nfrom langflow.custom.utils import update_component_build_config\nfrom langflow.field_typing import Tool\nfrom langflow.io import BoolInput, DropdownInput, IntInput, MultilineInput, Output\nfrom langflow.logging import logger\nfrom langflow.schema.data import Data\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\n\n\ndef set_advanced_true(component_input):\n    component_input.advanced = True\n    return component_input\n\n\nMODEL_PROVIDERS_LIST = [\"Anthropic\", \"Google Generative AI\", \"Groq\", \"OpenAI\"]\n\n\nclass AgentComponent(ToolCallingAgentComponent):\n    display_name: str = \"Agent\"\n    description: str = \"Define the agent's instructions, then enter a task to complete using tools.\"\n    documentation: str = \"https://docs.langflow.org/agents\"\n    icon = \"bot\"\n    beta = False\n    name = \"Agent\"\n\n    memory_inputs = [set_advanced_true(component_input) for component_input in MemoryComponent().inputs]\n\n    # Filter out json_mode from OpenAI inputs since we handle structured output differently\n    openai_inputs_filtered = [\n        input_field\n        for input_field in MODEL_PROVIDERS_DICT[\"OpenAI\"][\"inputs\"]\n        if not (hasattr(input_field, \"name\") and input_field.name == \"json_mode\")\n    ]\n\n    inputs = [\n        DropdownInput(\n            name=\"agent_llm\",\n            display_name=\"Model Provider\",\n            info=\"The provider of the language model that the agent will use to generate responses.\",\n            options=[*MODEL_PROVIDERS_LIST, \"Custom\"],\n            value=\"OpenAI\",\n            real_time_refresh=True,\n            input_types=[],\n            options_metadata=[MODELS_METADATA[key] for key in MODEL_PROVIDERS_LIST] + [{\"icon\": \"brain\"}],\n        ),\n        *openai_inputs_filtered,\n        MultilineInput(\n            name=\"system_prompt\",\n            display_name=\"Agent Instructions\",\n            info=\"System Prompt: Initial instructions and context provided to guide the agent's behavior.\",\n            value=\"You are a helpful assistant that can use tools to answer questions and perform tasks.\",\n            advanced=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Chat History Messages\",\n            value=100,\n            info=\"Number of chat history messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        *LCToolsAgentComponent._base_inputs,\n        # removed memory inputs from agent component\n        # *memory_inputs,\n        BoolInput(\n            name=\"add_current_date_tool\",\n            display_name=\"Current Date\",\n            advanced=True,\n            info=\"If true, will add a tool to the agent that returns the current date.\",\n            value=True,\n        ),\n    ]\n    outputs = [\n        Output(name=\"response\", display_name=\"Response\", method=\"message_response\"),\n        Output(name=\"structured_response\", display_name=\"Structured Response\", method=\"json_response\", tool_mode=False),\n    ]\n\n    async def message_response(self) -> Message:\n        try:\n            # Get LLM model and validate\n            llm_model, display_name = self.get_llm()\n            if llm_model is None:\n                msg = \"No language model selected. Please choose a model to proceed.\"\n                raise ValueError(msg)\n            self.model_name = get_model_name(llm_model, display_name=display_name)\n\n            # Get memory data\n            self.chat_history = await self.get_memory_data()\n            if isinstance(self.chat_history, Message):\n                self.chat_history = [self.chat_history]\n\n            # Add current date tool if enabled\n            if self.add_current_date_tool:\n                if not isinstance(self.tools, list):  # type: ignore[has-type]\n                    self.tools = []\n                current_date_tool = (await CurrentDateComponent(**self.get_base_args()).to_toolkit()).pop(0)\n                if not isinstance(current_date_tool, StructuredTool):\n                    msg = \"CurrentDateComponent must be converted to a StructuredTool\"\n                    raise TypeError(msg)\n                self.tools.append(current_date_tool)\n            # note the tools are not required to run the agent, hence the validation removed.\n\n            # Set up and run agent\n            self.set(\n                llm=llm_model,\n                tools=self.tools or [],\n                chat_history=self.chat_history,\n                input_value=self.input_value,\n                system_prompt=self.system_prompt,\n            )\n            agent = self.create_agent_runnable()\n            result = await self.run_agent(agent)\n\n            # Store result for potential JSON output\n            self._agent_result = result\n            # return result\n\n        except (ValueError, TypeError, KeyError) as e:\n            await logger.aerror(f\"{type(e).__name__}: {e!s}\")\n            raise\n        except ExceptionWithMessageError as e:\n            await logger.aerror(f\"ExceptionWithMessageError occurred: {e}\")\n            raise\n        except Exception as e:\n            await logger.aerror(f\"Unexpected error: {e!s}\")\n            raise\n        else:\n            return result\n\n    async def json_response(self) -> Data:\n        \"\"\"Convert agent response to structured JSON Data output.\"\"\"\n        # Run the regular message response first to get the result\n        if not hasattr(self, \"_agent_result\"):\n            await self.message_response()\n\n        result = self._agent_result\n\n        # Extract content from result\n        if hasattr(result, \"content\"):\n            content = result.content\n        elif hasattr(result, \"text\"):\n            content = result.text\n        else:\n            content = str(result)\n\n        # Try to parse as JSON\n        try:\n            json_data = json.loads(content)\n            return Data(data=json_data)\n        except json.JSONDecodeError:\n            # If it's not valid JSON, try to extract JSON from the content\n            json_match = re.search(r\"\\{.*\\}\", content, re.DOTALL)\n            if json_match:\n                try:\n                    json_data = json.loads(json_match.group())\n                    return Data(data=json_data)\n                except json.JSONDecodeError:\n                    pass\n\n            # If we can't extract JSON, return the raw content as data\n            return Data(data={\"content\": content, \"error\": \"Could not parse as JSON\"})\n\n    async def get_memory_data(self):\n        # TODO: This is a temporary fix to avoid message duplication. We should develop a function for this.\n        messages = (\n            await MemoryComponent(**self.get_base_args())\n            .set(session_id=self.graph.session_id, order=\"Ascending\", n_messages=self.n_messages)\n            .retrieve_messages()\n        )\n        return [\n            message for message in messages if getattr(message, \"id\", None) != getattr(self.input_value, \"id\", None)\n        ]\n\n    def get_llm(self):\n        if not isinstance(self.agent_llm, str):\n            return self.agent_llm, None\n\n        try:\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if not provider_info:\n                msg = f\"Invalid model provider: {self.agent_llm}\"\n                raise ValueError(msg)\n\n            component_class = provider_info.get(\"component_class\")\n            display_name = component_class.display_name\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\", \"\")\n\n            return self._build_llm_model(component_class, inputs, prefix), display_name\n\n        except Exception as e:\n            logger.error(f\"Error building {self.agent_llm} language model: {e!s}\")\n            msg = f\"Failed to initialize language model: {e!s}\"\n            raise ValueError(msg) from e\n\n    def _build_llm_model(self, component, inputs, prefix=\"\"):\n        model_kwargs = {}\n        for input_ in inputs:\n            if hasattr(self, f\"{prefix}{input_.name}\"):\n                model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n        return component.set(**model_kwargs).build_model()\n\n    def set_component_params(self, component):\n        provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n        if provider_info:\n            inputs = provider_info.get(\"inputs\")\n            prefix = provider_info.get(\"prefix\")\n            # Filter out json_mode and only use attributes that exist on this component\n            model_kwargs = {}\n            for input_ in inputs:\n                if hasattr(self, f\"{prefix}{input_.name}\"):\n                    model_kwargs[input_.name] = getattr(self, f\"{prefix}{input_.name}\")\n\n            return component.set(**model_kwargs)\n        return component\n\n    def delete_fields(self, build_config: dotdict, fields: dict | list[str]) -> None:\n        \"\"\"Delete specified fields from build_config.\"\"\"\n        for field in fields:\n            build_config.pop(field, None)\n\n    def update_input_types(self, build_config: dotdict) -> dotdict:\n        \"\"\"Update input types for all fields in build_config.\"\"\"\n        for key, value in build_config.items():\n            if isinstance(value, dict):\n                if value.get(\"input_types\") is None:\n                    build_config[key][\"input_types\"] = []\n            elif hasattr(value, \"input_types\") and value.input_types is None:\n                value.input_types = []\n        return build_config\n\n    async def update_build_config(\n        self, build_config: dotdict, field_value: str, field_name: str | None = None\n    ) -> dotdict:\n        # Iterate over all providers in the MODEL_PROVIDERS_DICT\n        # Existing logic for updating build_config\n        if field_name in (\"agent_llm\",):\n            build_config[\"agent_llm\"][\"value\"] = field_value\n            provider_info = MODEL_PROVIDERS_DICT.get(field_value)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call the component class's update_build_config method\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n\n            provider_configs: dict[str, tuple[dict, list[dict]]] = {\n                provider: (\n                    MODEL_PROVIDERS_DICT[provider][\"fields\"],\n                    [\n                        MODEL_PROVIDERS_DICT[other_provider][\"fields\"]\n                        for other_provider in MODEL_PROVIDERS_DICT\n                        if other_provider != provider\n                    ],\n                )\n                for provider in MODEL_PROVIDERS_DICT\n            }\n            if field_value in provider_configs:\n                fields_to_add, fields_to_delete = provider_configs[field_value]\n\n                # Delete fields from other providers\n                for fields in fields_to_delete:\n                    self.delete_fields(build_config, fields)\n\n                # Add provider-specific fields\n                if field_value == \"OpenAI\" and not any(field in build_config for field in fields_to_add):\n                    build_config.update(fields_to_add)\n                else:\n                    build_config.update(fields_to_add)\n                # Reset input types for agent_llm\n                build_config[\"agent_llm\"][\"input_types\"] = []\n            elif field_value == \"Custom\":\n                # Delete all provider fields\n                self.delete_fields(build_config, ALL_PROVIDER_FIELDS)\n                # Update with custom component\n                custom_component = DropdownInput(\n                    name=\"agent_llm\",\n                    display_name=\"Language Model\",\n                    options=[*sorted(MODEL_PROVIDERS), \"Custom\"],\n                    value=\"Custom\",\n                    real_time_refresh=True,\n                    input_types=[\"LanguageModel\"],\n                    options_metadata=[MODELS_METADATA[key] for key in sorted(MODELS_METADATA.keys())]\n                    + [{\"icon\": \"brain\"}],\n                )\n                build_config.update({\"agent_llm\": custom_component.to_dict()})\n            # Update input types for all fields\n            build_config = self.update_input_types(build_config)\n\n            # Validate required keys\n            default_keys = [\n                \"code\",\n                \"_type\",\n                \"agent_llm\",\n                \"tools\",\n                \"input_value\",\n                \"add_current_date_tool\",\n                \"system_prompt\",\n                \"agent_description\",\n                \"max_iterations\",\n                \"handle_parsing_errors\",\n                \"verbose\",\n            ]\n            missing_keys = [key for key in default_keys if key not in build_config]\n            if missing_keys:\n                msg = f\"Missing required keys in build_config: {missing_keys}\"\n                raise ValueError(msg)\n        if (\n            isinstance(self.agent_llm, str)\n            and self.agent_llm in MODEL_PROVIDERS_DICT\n            and field_name in MODEL_DYNAMIC_UPDATE_FIELDS\n        ):\n            provider_info = MODEL_PROVIDERS_DICT.get(self.agent_llm)\n            if provider_info:\n                component_class = provider_info.get(\"component_class\")\n                component_class = self.set_component_params(component_class)\n                prefix = provider_info.get(\"prefix\")\n                if component_class and hasattr(component_class, \"update_build_config\"):\n                    # Call each component class's update_build_config method\n                    # remove the prefix from the field_name\n                    if isinstance(field_name, str) and isinstance(prefix, str):\n                        field_name = field_name.replace(prefix, \"\")\n                    build_config = await update_component_build_config(\n                        component_class, build_config, field_value, \"model_name\"\n                    )\n        return dotdict({k: v.to_dict() if hasattr(v, \"to_dict\") else v for k, v in build_config.items()})\n\n    async def _get_tools(self) -> list[Tool]:\n        component_toolkit = _get_component_toolkit()\n        tools_names = self._build_tools_names()\n        agent_description = self.get_tool_description()\n        # TODO: Agent Description Depreciated Feature to be removed\n        description = f\"{agent_description}{tools_names}\"\n        tools = component_toolkit(component=self).get_tools(\n            tool_name=\"Call_Agent\", tool_description=description, callbacks=self.get_langchain_callbacks()\n        )\n        if hasattr(self, \"tools_metadata\"):\n            tools = component_toolkit(component=self, metadata=self.tools_metadata).update_tools_metadata(tools=tools)\n        return tools\n"
               },
               "handle_parsing_errors": {
                 "_input_type": "BoolInput",

langflow/initial_setup/starter_projects/Meeting Summary.json

@@ -314,7 +314,7 @@
             "legacy": false,
             "lf_version": "1.1.5",
             "metadata": {
-              "code_hash": "6fd1a65a4904",
+              "code_hash": "3e67a5940263",
               "module": "langflow.components.assemblyai.assemblyai_poll_transcript.AssemblyAITranscriptionJobPoller"
             },
             "minimized": false,
@@ -371,7 +371,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import assemblyai as aai\nfrom loguru import logger\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.io import DataInput, FloatInput, Output, SecretStrInput\nfrom langflow.schema.data import Data\n\n\nclass AssemblyAITranscriptionJobPoller(Component):\n    display_name = \"AssemblyAI Poll Transcript\"\n    description = \"Poll for the status of a transcription job using AssemblyAI\"\n    documentation = \"https://www.assemblyai.com/docs\"\n    icon = \"AssemblyAI\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Assembly API Key\",\n            info=\"Your AssemblyAI API key. You can get one from https://www.assemblyai.com/\",\n            required=True,\n        ),\n        DataInput(\n            name=\"transcript_id\",\n            display_name=\"Transcript ID\",\n            info=\"The ID of the transcription job to poll\",\n            required=True,\n        ),\n        FloatInput(\n            name=\"polling_interval\",\n            display_name=\"Polling Interval\",\n            value=3.0,\n            info=\"The polling interval in seconds\",\n            advanced=True,\n            range_spec=RangeSpec(min=3, max=30),\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Transcription Result\", name=\"transcription_result\", method=\"poll_transcription_job\"),\n    ]\n\n    def poll_transcription_job(self) -> Data:\n        \"\"\"Polls the transcription status until completion and returns the Data.\"\"\"\n        aai.settings.api_key = self.api_key\n        aai.settings.polling_interval = self.polling_interval\n\n        # check if it's an error message from the previous step\n        if self.transcript_id.data.get(\"error\"):\n            self.status = self.transcript_id.data[\"error\"]\n            return self.transcript_id\n\n        try:\n            transcript = aai.Transcript.get_by_id(self.transcript_id.data[\"transcript_id\"])\n        except Exception as e:  # noqa: BLE001\n            error = f\"Getting transcription failed: {e}\"\n            logger.opt(exception=True).debug(error)\n            self.status = error\n            return Data(data={\"error\": error})\n\n        if transcript.status == aai.TranscriptStatus.completed:\n            json_response = transcript.json_response\n            text = json_response.pop(\"text\", None)\n            utterances = json_response.pop(\"utterances\", None)\n            transcript_id = json_response.pop(\"id\", None)\n            sorted_data = {\"text\": text, \"utterances\": utterances, \"id\": transcript_id}\n            sorted_data.update(json_response)\n            data = Data(data=sorted_data)\n            self.status = data\n            return data\n        self.status = transcript.error\n        return Data(data={\"error\": transcript.error})\n"
+                "value": "import assemblyai as aai\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.field_typing.range_spec import RangeSpec\nfrom langflow.io import DataInput, FloatInput, Output, SecretStrInput\nfrom langflow.logging.logger import logger\nfrom langflow.schema.data import Data\n\n\nclass AssemblyAITranscriptionJobPoller(Component):\n    display_name = \"AssemblyAI Poll Transcript\"\n    description = \"Poll for the status of a transcription job using AssemblyAI\"\n    documentation = \"https://www.assemblyai.com/docs\"\n    icon = \"AssemblyAI\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Assembly API Key\",\n            info=\"Your AssemblyAI API key. You can get one from https://www.assemblyai.com/\",\n            required=True,\n        ),\n        DataInput(\n            name=\"transcript_id\",\n            display_name=\"Transcript ID\",\n            info=\"The ID of the transcription job to poll\",\n            required=True,\n        ),\n        FloatInput(\n            name=\"polling_interval\",\n            display_name=\"Polling Interval\",\n            value=3.0,\n            info=\"The polling interval in seconds\",\n            advanced=True,\n            range_spec=RangeSpec(min=3, max=30),\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Transcription Result\", name=\"transcription_result\", method=\"poll_transcription_job\"),\n    ]\n\n    def poll_transcription_job(self) -> Data:\n        \"\"\"Polls the transcription status until completion and returns the Data.\"\"\"\n        aai.settings.api_key = self.api_key\n        aai.settings.polling_interval = self.polling_interval\n\n        # check if it's an error message from the previous step\n        if self.transcript_id.data.get(\"error\"):\n            self.status = self.transcript_id.data[\"error\"]\n            return self.transcript_id\n\n        try:\n            transcript = aai.Transcript.get_by_id(self.transcript_id.data[\"transcript_id\"])\n        except Exception as e:  # noqa: BLE001\n            error = f\"Getting transcription failed: {e}\"\n            logger.debug(error, exc_info=True)\n            self.status = error\n            return Data(data={\"error\": error})\n\n        if transcript.status == aai.TranscriptStatus.completed:\n            json_response = transcript.json_response\n            text = json_response.pop(\"text\", None)\n            utterances = json_response.pop(\"utterances\", None)\n            transcript_id = json_response.pop(\"id\", None)\n            sorted_data = {\"text\": text, \"utterances\": utterances, \"id\": transcript_id}\n            sorted_data.update(json_response)\n            data = Data(data=sorted_data)\n            self.status = data\n            return data\n        self.status = transcript.error\n        return Data(data={\"error\": transcript.error})\n"
               },
               "polling_interval": {
                 "_input_type": "FloatInput",
@@ -1718,7 +1718,7 @@
             "legacy": false,
             "lf_version": "1.1.5",
             "metadata": {
-              "code_hash": "5ca89b168f3f",
+              "code_hash": "464cc8b8fdd2",
               "module": "langflow.components.helpers.memory.MemoryComponent"
             },
             "minimized": false,
@@ -1772,7 +1772,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from typing import Any, cast\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.inputs.inputs import DropdownInput, HandleInput, IntInput, MessageTextInput, MultilineInput, TabInput\nfrom langflow.memory import aget_messages, astore_message\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.template.field.base import Output\nfrom langflow.utils.component_utils import set_current_fields, set_field_display\nfrom langflow.utils.constants import MESSAGE_SENDER_AI, MESSAGE_SENDER_NAME_AI, MESSAGE_SENDER_USER\n\n\nclass MemoryComponent(Component):\n    display_name = \"Message History\"\n    description = \"Stores or retrieves stored chat messages from Langflow tables or an external memory.\"\n    documentation: str = \"https://docs.langflow.org/components-helpers#message-history\"\n    icon = \"message-square-more\"\n    name = \"Memory\"\n    default_keys = [\"mode\", \"memory\"]\n    mode_config = {\n        \"Store\": [\"message\", \"memory\", \"sender\", \"sender_name\", \"session_id\"],\n        \"Retrieve\": [\"n_messages\", \"order\", \"template\", \"memory\"],\n    }\n\n    inputs = [\n        TabInput(\n            name=\"mode\",\n            display_name=\"Mode\",\n            options=[\"Retrieve\", \"Store\"],\n            value=\"Retrieve\",\n            info=\"Operation mode: Store messages or Retrieve messages.\",\n            real_time_refresh=True,\n        ),\n        MessageTextInput(\n            name=\"message\",\n            display_name=\"Message\",\n            info=\"The chat message to be stored.\",\n            tool_mode=True,\n            dynamic=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"memory\",\n            display_name=\"External Memory\",\n            input_types=[\"Memory\"],\n            info=\"Retrieve messages from an external memory. If empty, it will use the Langflow tables.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"sender_type\",\n            display_name=\"Sender Type\",\n            options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER, \"Machine and User\"],\n            value=\"Machine and User\",\n            info=\"Filter by sender type.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"sender\",\n            display_name=\"Sender\",\n            info=\"The sender of the message. Might be Machine or User. \"\n            \"If empty, the current sender parameter will be used.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"sender_name\",\n            display_name=\"Sender Name\",\n            info=\"Filter by sender name.\",\n            advanced=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Messages\",\n            value=100,\n            info=\"Number of messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MessageTextInput(\n            name=\"session_id\",\n            display_name=\"Session ID\",\n            info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n            value=\"\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"order\",\n            display_name=\"Order\",\n            options=[\"Ascending\", \"Descending\"],\n            value=\"Ascending\",\n            info=\"Order of the messages.\",\n            advanced=True,\n            tool_mode=True,\n            required=True,\n        ),\n        MultilineInput(\n            name=\"template\",\n            display_name=\"Template\",\n            info=\"The template to use for formatting the data. \"\n            \"It can contain the keys {text}, {sender} or any other key in the message data.\",\n            value=\"{sender_name}: {text}\",\n            advanced=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Message\", name=\"messages_text\", method=\"retrieve_messages_as_text\", dynamic=True),\n        Output(display_name=\"Dataframe\", name=\"dataframe\", method=\"retrieve_messages_dataframe\", dynamic=True),\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 selected output type.\"\"\"\n        if field_name == \"mode\":\n            # Start with empty outputs\n            frontend_node[\"outputs\"] = []\n            if field_value == \"Store\":\n                frontend_node[\"outputs\"] = [\n                    Output(\n                        display_name=\"Stored Messages\",\n                        name=\"stored_messages\",\n                        method=\"store_message\",\n                        hidden=True,\n                        dynamic=True,\n                    )\n                ]\n            if field_value == \"Retrieve\":\n                frontend_node[\"outputs\"] = [\n                    Output(\n                        display_name=\"Messages\", name=\"messages_text\", method=\"retrieve_messages_as_text\", dynamic=True\n                    ),\n                    Output(\n                        display_name=\"Dataframe\", name=\"dataframe\", method=\"retrieve_messages_dataframe\", dynamic=True\n                    ),\n                ]\n        return frontend_node\n\n    async def store_message(self) -> Message:\n        message = Message(text=self.message) if isinstance(self.message, str) else self.message\n\n        message.session_id = self.session_id or message.session_id\n        message.sender = self.sender or message.sender or MESSAGE_SENDER_AI\n        message.sender_name = self.sender_name or message.sender_name or MESSAGE_SENDER_NAME_AI\n\n        stored_messages: list[Message] = []\n\n        if self.memory:\n            self.memory.session_id = message.session_id\n            lc_message = message.to_lc_message()\n            await self.memory.aadd_messages([lc_message])\n\n            stored_messages = await self.memory.aget_messages() or []\n\n            stored_messages = [Message.from_lc_message(m) for m in stored_messages] if stored_messages else []\n\n            if message.sender:\n                stored_messages = [m for m in stored_messages if m.sender == message.sender]\n        else:\n            await astore_message(message, flow_id=self.graph.flow_id)\n            stored_messages = (\n                await aget_messages(\n                    session_id=message.session_id, sender_name=message.sender_name, sender=message.sender\n                )\n                or []\n            )\n\n        if not stored_messages:\n            msg = \"No messages were stored. Please ensure that the session ID and sender are properly set.\"\n            raise ValueError(msg)\n\n        stored_message = stored_messages[0]\n        self.status = stored_message\n        return stored_message\n\n    async def retrieve_messages(self) -> Data:\n        sender_type = self.sender_type\n        sender_name = self.sender_name\n        session_id = self.session_id\n        n_messages = self.n_messages\n        order = \"DESC\" if self.order == \"Descending\" else \"ASC\"\n\n        if sender_type == \"Machine and User\":\n            sender_type = None\n\n        if self.memory and not hasattr(self.memory, \"aget_messages\"):\n            memory_name = type(self.memory).__name__\n            err_msg = f\"External Memory object ({memory_name}) must have 'aget_messages' method.\"\n            raise AttributeError(err_msg)\n        # Check if n_messages is None or 0\n        if n_messages == 0:\n            stored = []\n        elif self.memory:\n            # override session_id\n            self.memory.session_id = session_id\n\n            stored = await self.memory.aget_messages()\n            # langchain memories are supposed to return messages in ascending order\n\n            if order == \"DESC\":\n                stored = stored[::-1]\n            if n_messages:\n                stored = stored[-n_messages:] if order == \"ASC\" else stored[:n_messages]\n            stored = [Message.from_lc_message(m) for m in stored]\n            if sender_type:\n                expected_type = MESSAGE_SENDER_AI if sender_type == MESSAGE_SENDER_AI else MESSAGE_SENDER_USER\n                stored = [m for m in stored if m.type == expected_type]\n        else:\n            # For internal memory, we always fetch the last N messages by ordering by DESC\n            stored = await aget_messages(\n                sender=sender_type,\n                sender_name=sender_name,\n                session_id=session_id,\n                limit=10000,\n                order=order,\n            )\n            if n_messages:\n                stored = stored[-n_messages:] if order == \"ASC\" else stored[:n_messages]\n\n        # self.status = stored\n        return cast(Data, stored)\n\n    async def retrieve_messages_as_text(self) -> Message:\n        stored_text = data_to_text(self.template, await self.retrieve_messages())\n        # self.status = stored_text\n        return Message(text=stored_text)\n\n    async def retrieve_messages_dataframe(self) -> DataFrame:\n        \"\"\"Convert the retrieved messages into a DataFrame.\n\n        Returns:\n            DataFrame: A DataFrame containing the message data.\n        \"\"\"\n        messages = await self.retrieve_messages()\n        return DataFrame(messages)\n\n    def update_build_config(\n        self,\n        build_config: dotdict,\n        field_value: Any,  # noqa: ARG002\n        field_name: str | None = None,  # noqa: ARG002\n    ) -> dotdict:\n        return set_current_fields(\n            build_config=build_config,\n            action_fields=self.mode_config,\n            selected_action=build_config[\"mode\"][\"value\"],\n            default_fields=self.default_keys,\n            func=set_field_display,\n        )\n"
+                "value": "from typing import Any, cast\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.helpers.data import data_to_text\nfrom langflow.inputs.inputs import DropdownInput, HandleInput, IntInput, MessageTextInput, MultilineInput, TabInput\nfrom langflow.memory import aget_messages, astore_message\nfrom langflow.schema.data import Data\nfrom langflow.schema.dataframe import DataFrame\nfrom langflow.schema.dotdict import dotdict\nfrom langflow.schema.message import Message\nfrom langflow.template.field.base import Output\nfrom langflow.utils.component_utils import set_current_fields, set_field_display\nfrom langflow.utils.constants import MESSAGE_SENDER_AI, MESSAGE_SENDER_NAME_AI, MESSAGE_SENDER_USER\n\n\nclass MemoryComponent(Component):\n    display_name = \"Message History\"\n    description = \"Stores or retrieves stored chat messages from Langflow tables or an external memory.\"\n    documentation: str = \"https://docs.langflow.org/components-helpers#message-history\"\n    icon = \"message-square-more\"\n    name = \"Memory\"\n    default_keys = [\"mode\", \"memory\"]\n    mode_config = {\n        \"Store\": [\"message\", \"memory\", \"sender\", \"sender_name\", \"session_id\"],\n        \"Retrieve\": [\"n_messages\", \"order\", \"template\", \"memory\"],\n    }\n\n    inputs = [\n        TabInput(\n            name=\"mode\",\n            display_name=\"Mode\",\n            options=[\"Retrieve\", \"Store\"],\n            value=\"Retrieve\",\n            info=\"Operation mode: Store messages or Retrieve messages.\",\n            real_time_refresh=True,\n        ),\n        MessageTextInput(\n            name=\"message\",\n            display_name=\"Message\",\n            info=\"The chat message to be stored.\",\n            tool_mode=True,\n            dynamic=True,\n            show=False,\n        ),\n        HandleInput(\n            name=\"memory\",\n            display_name=\"External Memory\",\n            input_types=[\"Memory\"],\n            info=\"Retrieve messages from an external memory. If empty, it will use the Langflow tables.\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"sender_type\",\n            display_name=\"Sender Type\",\n            options=[MESSAGE_SENDER_AI, MESSAGE_SENDER_USER, \"Machine and User\"],\n            value=\"Machine and User\",\n            info=\"Filter by sender type.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"sender\",\n            display_name=\"Sender\",\n            info=\"The sender of the message. Might be Machine or User. \"\n            \"If empty, the current sender parameter will be used.\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"sender_name\",\n            display_name=\"Sender Name\",\n            info=\"Filter by sender name.\",\n            advanced=True,\n            show=False,\n        ),\n        IntInput(\n            name=\"n_messages\",\n            display_name=\"Number of Messages\",\n            value=100,\n            info=\"Number of messages to retrieve.\",\n            advanced=True,\n            show=True,\n        ),\n        MessageTextInput(\n            name=\"session_id\",\n            display_name=\"Session ID\",\n            info=\"The session ID of the chat. If empty, the current session ID parameter will be used.\",\n            value=\"\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"order\",\n            display_name=\"Order\",\n            options=[\"Ascending\", \"Descending\"],\n            value=\"Ascending\",\n            info=\"Order of the messages.\",\n            advanced=True,\n            tool_mode=True,\n            required=True,\n        ),\n        MultilineInput(\n            name=\"template\",\n            display_name=\"Template\",\n            info=\"The template to use for formatting the data. \"\n            \"It can contain the keys {text}, {sender} or any other key in the message data.\",\n            value=\"{sender_name}: {text}\",\n            advanced=True,\n            show=False,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Message\", name=\"messages_text\", method=\"retrieve_messages_as_text\", dynamic=True),\n        Output(display_name=\"Dataframe\", name=\"dataframe\", method=\"retrieve_messages_dataframe\", dynamic=True),\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 selected output type.\"\"\"\n        if field_name == \"mode\":\n            # Start with empty outputs\n            frontend_node[\"outputs\"] = []\n            if field_value == \"Store\":\n                frontend_node[\"outputs\"] = [\n                    Output(\n                        display_name=\"Stored Messages\",\n                        name=\"stored_messages\",\n                        method=\"store_message\",\n                        hidden=True,\n                        dynamic=True,\n                    )\n                ]\n            if field_value == \"Retrieve\":\n                frontend_node[\"outputs\"] = [\n                    Output(\n                        display_name=\"Messages\", name=\"messages_text\", method=\"retrieve_messages_as_text\", dynamic=True\n                    ),\n                    Output(\n                        display_name=\"Dataframe\", name=\"dataframe\", method=\"retrieve_messages_dataframe\", dynamic=True\n                    ),\n                ]\n        return frontend_node\n\n    async def store_message(self) -> Message:\n        message = Message(text=self.message) if isinstance(self.message, str) else self.message\n\n        message.session_id = self.session_id or message.session_id\n        message.sender = self.sender or message.sender or MESSAGE_SENDER_AI\n        message.sender_name = self.sender_name or message.sender_name or MESSAGE_SENDER_NAME_AI\n\n        stored_messages: list[Message] = []\n\n        if self.memory:\n            self.memory.session_id = message.session_id\n            lc_message = message.to_lc_message()\n            await self.memory.aadd_messages([lc_message])\n\n            stored_messages = await self.memory.aget_messages() or []\n\n            stored_messages = [Message.from_lc_message(m) for m in stored_messages] if stored_messages else []\n\n            if message.sender:\n                stored_messages = [m for m in stored_messages if m.sender == message.sender]\n        else:\n            await astore_message(message, flow_id=self.graph.flow_id)\n            stored_messages = (\n                await aget_messages(\n                    session_id=message.session_id, sender_name=message.sender_name, sender=message.sender\n                )\n                or []\n            )\n\n        if not stored_messages:\n            msg = \"No messages were stored. Please ensure that the session ID and sender are properly set.\"\n            raise ValueError(msg)\n\n        stored_message = stored_messages[0]\n        self.status = stored_message\n        return stored_message\n\n    async def retrieve_messages(self) -> Data:\n        sender_type = self.sender_type\n        sender_name = self.sender_name\n        session_id = self.session_id\n        n_messages = self.n_messages\n        order = \"DESC\" if self.order == \"Descending\" else \"ASC\"\n\n        if sender_type == \"Machine and User\":\n            sender_type = None\n\n        if self.memory and not hasattr(self.memory, \"aget_messages\"):\n            memory_name = type(self.memory).__name__\n            err_msg = f\"External Memory object ({memory_name}) must have 'aget_messages' method.\"\n            raise AttributeError(err_msg)\n        # Check if n_messages is None or 0\n        if n_messages == 0:\n            stored = []\n        elif self.memory:\n            # override session_id\n            self.memory.session_id = session_id\n\n            stored = await self.memory.aget_messages()\n            # langchain memories are supposed to return messages in ascending order\n\n            if order == \"DESC\":\n                stored = stored[::-1]\n            if n_messages:\n                stored = stored[-n_messages:] if order == \"ASC\" else stored[:n_messages]\n            stored = [Message.from_lc_message(m) for m in stored]\n            if sender_type:\n                expected_type = MESSAGE_SENDER_AI if sender_type == MESSAGE_SENDER_AI else MESSAGE_SENDER_USER\n                stored = [m for m in stored if m.type == expected_type]\n        else:\n            # For internal memory, we always fetch the last N messages by ordering by DESC\n            stored = await aget_messages(\n                sender=sender_type,\n                sender_name=sender_name,\n                session_id=session_id,\n                limit=10000,\n                order=order,\n            )\n            if n_messages:\n                stored = stored[-n_messages:] if order == \"ASC\" else stored[:n_messages]\n\n        # self.status = stored\n        return cast(\"Data\", stored)\n\n    async def retrieve_messages_as_text(self) -> Message:\n        stored_text = data_to_text(self.template, await self.retrieve_messages())\n        # self.status = stored_text\n        return Message(text=stored_text)\n\n    async def retrieve_messages_dataframe(self) -> DataFrame:\n        \"\"\"Convert the retrieved messages into a DataFrame.\n\n        Returns:\n            DataFrame: A DataFrame containing the message data.\n        \"\"\"\n        messages = await self.retrieve_messages()\n        return DataFrame(messages)\n\n    def update_build_config(\n        self,\n        build_config: dotdict,\n        field_value: Any,  # noqa: ARG002\n        field_name: str | None = None,  # noqa: ARG002\n    ) -> dotdict:\n        return set_current_fields(\n            build_config=build_config,\n            action_fields=self.mode_config,\n            selected_action=build_config[\"mode\"][\"value\"],\n            default_fields=self.default_keys,\n            func=set_field_display,\n        )\n"
               },
               "memory": {
                 "_input_type": "HandleInput",
@@ -2466,7 +2466,7 @@
             "key": "AssemblyAITranscriptionJobCreator",
             "legacy": false,
             "metadata": {
-              "code_hash": "03525d13fcc0",
+              "code_hash": "03d20eaf49f4",
               "module": "langflow.components.assemblyai.assemblyai_start_transcript.AssemblyAITranscriptionJobCreator"
             },
             "minimized": false,
@@ -2606,7 +2606,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from pathlib import Path\n\nimport assemblyai as aai\nfrom loguru import logger\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.io import BoolInput, DropdownInput, FileInput, MessageTextInput, Output, SecretStrInput\nfrom langflow.schema.data import Data\n\n\nclass AssemblyAITranscriptionJobCreator(Component):\n    display_name = \"AssemblyAI Start Transcript\"\n    description = \"Create a transcription job for an audio file using AssemblyAI with advanced options\"\n    documentation = \"https://www.assemblyai.com/docs\"\n    icon = \"AssemblyAI\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Assembly API Key\",\n            info=\"Your AssemblyAI API key. You can get one from https://www.assemblyai.com/\",\n            required=True,\n        ),\n        FileInput(\n            name=\"audio_file\",\n            display_name=\"Audio File\",\n            file_types=[\n                \"3ga\",\n                \"8svx\",\n                \"aac\",\n                \"ac3\",\n                \"aif\",\n                \"aiff\",\n                \"alac\",\n                \"amr\",\n                \"ape\",\n                \"au\",\n                \"dss\",\n                \"flac\",\n                \"flv\",\n                \"m4a\",\n                \"m4b\",\n                \"m4p\",\n                \"m4r\",\n                \"mp3\",\n                \"mpga\",\n                \"ogg\",\n                \"oga\",\n                \"mogg\",\n                \"opus\",\n                \"qcp\",\n                \"tta\",\n                \"voc\",\n                \"wav\",\n                \"wma\",\n                \"wv\",\n                \"webm\",\n                \"mts\",\n                \"m2ts\",\n                \"ts\",\n                \"mov\",\n                \"mp2\",\n                \"mp4\",\n                \"m4p\",\n                \"m4v\",\n                \"mxf\",\n            ],\n            info=\"The audio file to transcribe\",\n            required=True,\n        ),\n        MessageTextInput(\n            name=\"audio_file_url\",\n            display_name=\"Audio File URL\",\n            info=\"The URL of the audio file to transcribe (Can be used instead of a File)\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"speech_model\",\n            display_name=\"Speech Model\",\n            options=[\n                \"best\",\n                \"nano\",\n            ],\n            value=\"best\",\n            info=\"The speech model to use for the transcription\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"language_detection\",\n            display_name=\"Automatic Language Detection\",\n            info=\"Enable automatic language detection\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"language_code\",\n            display_name=\"Language\",\n            info=(\n                \"\"\"\n            The language of the audio file. Can be set manually if automatic language detection is disabled.\n            See https://www.assemblyai.com/docs/getting-started/supported-languages \"\"\"\n                \"for a list of supported language codes.\"\n            ),\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"speaker_labels\",\n            display_name=\"Enable Speaker Labels\",\n            info=\"Enable speaker diarization\",\n        ),\n        MessageTextInput(\n            name=\"speakers_expected\",\n            display_name=\"Expected Number of Speakers\",\n            info=\"Set the expected number of speakers (optional, enter a number)\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"punctuate\",\n            display_name=\"Punctuate\",\n            info=\"Enable automatic punctuation\",\n            advanced=True,\n            value=True,\n        ),\n        BoolInput(\n            name=\"format_text\",\n            display_name=\"Format Text\",\n            info=\"Enable text formatting\",\n            advanced=True,\n            value=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Transcript ID\", name=\"transcript_id\", method=\"create_transcription_job\"),\n    ]\n\n    def create_transcription_job(self) -> Data:\n        aai.settings.api_key = self.api_key\n\n        # Convert speakers_expected to int if it's not empty\n        speakers_expected = None\n        if self.speakers_expected and self.speakers_expected.strip():\n            try:\n                speakers_expected = int(self.speakers_expected)\n            except ValueError:\n                self.status = \"Error: Expected Number of Speakers must be a valid integer\"\n                return Data(data={\"error\": \"Error: Expected Number of Speakers must be a valid integer\"})\n\n        language_code = self.language_code or None\n\n        config = aai.TranscriptionConfig(\n            speech_model=self.speech_model,\n            language_detection=self.language_detection,\n            language_code=language_code,\n            speaker_labels=self.speaker_labels,\n            speakers_expected=speakers_expected,\n            punctuate=self.punctuate,\n            format_text=self.format_text,\n        )\n\n        audio = None\n        if self.audio_file:\n            if self.audio_file_url:\n                logger.warning(\"Both an audio file an audio URL were specified. The audio URL was ignored.\")\n\n            # Check if the file exists\n            if not Path(self.audio_file).exists():\n                self.status = \"Error: Audio file not found\"\n                return Data(data={\"error\": \"Error: Audio file not found\"})\n            audio = self.audio_file\n        elif self.audio_file_url:\n            audio = self.audio_file_url\n        else:\n            self.status = \"Error: Either an audio file or an audio URL must be specified\"\n            return Data(data={\"error\": \"Error: Either an audio file or an audio URL must be specified\"})\n\n        try:\n            transcript = aai.Transcriber().submit(audio, config=config)\n        except Exception as e:  # noqa: BLE001\n            logger.opt(exception=True).debug(\"Error submitting transcription job\")\n            self.status = f\"An error occurred: {e}\"\n            return Data(data={\"error\": f\"An error occurred: {e}\"})\n\n        if transcript.error:\n            self.status = transcript.error\n            return Data(data={\"error\": transcript.error})\n        result = Data(data={\"transcript_id\": transcript.id})\n        self.status = result\n        return result\n"
+                "value": "from pathlib import Path\n\nimport assemblyai as aai\n\nfrom langflow.custom.custom_component.component import Component\nfrom langflow.io import BoolInput, DropdownInput, FileInput, MessageTextInput, Output, SecretStrInput\nfrom langflow.logging.logger import logger\nfrom langflow.schema.data import Data\n\n\nclass AssemblyAITranscriptionJobCreator(Component):\n    display_name = \"AssemblyAI Start Transcript\"\n    description = \"Create a transcription job for an audio file using AssemblyAI with advanced options\"\n    documentation = \"https://www.assemblyai.com/docs\"\n    icon = \"AssemblyAI\"\n\n    inputs = [\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"Assembly API Key\",\n            info=\"Your AssemblyAI API key. You can get one from https://www.assemblyai.com/\",\n            required=True,\n        ),\n        FileInput(\n            name=\"audio_file\",\n            display_name=\"Audio File\",\n            file_types=[\n                \"3ga\",\n                \"8svx\",\n                \"aac\",\n                \"ac3\",\n                \"aif\",\n                \"aiff\",\n                \"alac\",\n                \"amr\",\n                \"ape\",\n                \"au\",\n                \"dss\",\n                \"flac\",\n                \"flv\",\n                \"m4a\",\n                \"m4b\",\n                \"m4p\",\n                \"m4r\",\n                \"mp3\",\n                \"mpga\",\n                \"ogg\",\n                \"oga\",\n                \"mogg\",\n                \"opus\",\n                \"qcp\",\n                \"tta\",\n                \"voc\",\n                \"wav\",\n                \"wma\",\n                \"wv\",\n                \"webm\",\n                \"mts\",\n                \"m2ts\",\n                \"ts\",\n                \"mov\",\n                \"mp2\",\n                \"mp4\",\n                \"m4p\",\n                \"m4v\",\n                \"mxf\",\n            ],\n            info=\"The audio file to transcribe\",\n            required=True,\n        ),\n        MessageTextInput(\n            name=\"audio_file_url\",\n            display_name=\"Audio File URL\",\n            info=\"The URL of the audio file to transcribe (Can be used instead of a File)\",\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"speech_model\",\n            display_name=\"Speech Model\",\n            options=[\n                \"best\",\n                \"nano\",\n            ],\n            value=\"best\",\n            info=\"The speech model to use for the transcription\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"language_detection\",\n            display_name=\"Automatic Language Detection\",\n            info=\"Enable automatic language detection\",\n            advanced=True,\n        ),\n        MessageTextInput(\n            name=\"language_code\",\n            display_name=\"Language\",\n            info=(\n                \"\"\"\n            The language of the audio file. Can be set manually if automatic language detection is disabled.\n            See https://www.assemblyai.com/docs/getting-started/supported-languages \"\"\"\n                \"for a list of supported language codes.\"\n            ),\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"speaker_labels\",\n            display_name=\"Enable Speaker Labels\",\n            info=\"Enable speaker diarization\",\n        ),\n        MessageTextInput(\n            name=\"speakers_expected\",\n            display_name=\"Expected Number of Speakers\",\n            info=\"Set the expected number of speakers (optional, enter a number)\",\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"punctuate\",\n            display_name=\"Punctuate\",\n            info=\"Enable automatic punctuation\",\n            advanced=True,\n            value=True,\n        ),\n        BoolInput(\n            name=\"format_text\",\n            display_name=\"Format Text\",\n            info=\"Enable text formatting\",\n            advanced=True,\n            value=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Transcript ID\", name=\"transcript_id\", method=\"create_transcription_job\"),\n    ]\n\n    def create_transcription_job(self) -> Data:\n        aai.settings.api_key = self.api_key\n\n        # Convert speakers_expected to int if it's not empty\n        speakers_expected = None\n        if self.speakers_expected and self.speakers_expected.strip():\n            try:\n                speakers_expected = int(self.speakers_expected)\n            except ValueError:\n                self.status = \"Error: Expected Number of Speakers must be a valid integer\"\n                return Data(data={\"error\": \"Error: Expected Number of Speakers must be a valid integer\"})\n\n        language_code = self.language_code or None\n\n        config = aai.TranscriptionConfig(\n            speech_model=self.speech_model,\n            language_detection=self.language_detection,\n            language_code=language_code,\n            speaker_labels=self.speaker_labels,\n            speakers_expected=speakers_expected,\n            punctuate=self.punctuate,\n            format_text=self.format_text,\n        )\n\n        audio = None\n        if self.audio_file:\n            if self.audio_file_url:\n                logger.warning(\"Both an audio file an audio URL were specified. The audio URL was ignored.\")\n\n            # Check if the file exists\n            if not Path(self.audio_file).exists():\n                self.status = \"Error: Audio file not found\"\n                return Data(data={\"error\": \"Error: Audio file not found\"})\n            audio = self.audio_file\n        elif self.audio_file_url:\n            audio = self.audio_file_url\n        else:\n            self.status = \"Error: Either an audio file or an audio URL must be specified\"\n            return Data(data={\"error\": \"Error: Either an audio file or an audio URL must be specified\"})\n\n        try:\n            transcript = aai.Transcriber().submit(audio, config=config)\n        except Exception as e:  # noqa: BLE001\n            logger.debug(\"Error submitting transcription job\", exc_info=True)\n            self.status = f\"An error occurred: {e}\"\n            return Data(data={\"error\": f\"An error occurred: {e}\"})\n\n        if transcript.error:\n            self.status = transcript.error\n            return Data(data={\"error\": transcript.error})\n        result = Data(data={\"transcript_id\": transcript.id})\n        self.status = result\n        return result\n"
               },
               "format_text": {
                 "_input_type": "BoolInput",