lfx-nightly 0.1.11.dev0__py3-none-any.whl

lfx/components/logic/run_flow.py

@@ -0,0 +1,71 @@
+from typing import Any
+
+from lfx.base.tools.run_flow import RunFlowBaseComponent
+from lfx.helpers.flow import run_flow
+from lfx.log.logger import logger
+from lfx.schema.dotdict import dotdict
+
+
+class RunFlowComponent(RunFlowBaseComponent):
+    display_name = "Run Flow"
+    description = (
+        "Creates a tool component from a Flow that takes all its inputs and runs it. "
+        " \n **Select a Flow to use the tool mode**"
+    )
+    documentation: str = "https://docs.langflow.org/components-logic#run-flow"
+    beta = True
+    name = "RunFlow"
+    icon = "Workflow"
+
+    inputs = RunFlowBaseComponent.get_base_inputs()
+    outputs = RunFlowBaseComponent.get_base_outputs()
+
+    async def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
+        if field_name == "flow_name_selected":
+            build_config["flow_name_selected"]["options"] = await self.get_flow_names()
+            missing_keys = [key for key in self.default_keys if key not in build_config]
+            if missing_keys:
+                msg = f"Missing required keys in build_config: {missing_keys}"
+                raise ValueError(msg)
+            if field_value is not None:
+                try:
+                    graph = await self.get_graph(field_value)
+                    build_config = self.update_build_config_from_graph(build_config, graph)
+                except Exception as e:
+                    msg = f"Error building graph for flow {field_value}"
+                    await logger.aexception(msg)
+                    raise RuntimeError(msg) from e
+        return build_config
+
+    async def run_flow_with_tweaks(self):
+        tweaks: dict = {}
+
+        flow_name_selected = self._attributes.get("flow_name_selected")
+        parsed_flow_tweak_data = self._attributes.get("flow_tweak_data", {})
+        if not isinstance(parsed_flow_tweak_data, dict):
+            parsed_flow_tweak_data = parsed_flow_tweak_data.dict()
+
+        if parsed_flow_tweak_data != {}:
+            for field in parsed_flow_tweak_data:
+                if "~" in field:
+                    [node, name] = field.split("~")
+                    if node not in tweaks:
+                        tweaks[node] = {}
+                    tweaks[node][name] = parsed_flow_tweak_data[field]
+        else:
+            for field in self._attributes:
+                if field not in self.default_keys and "~" in field:
+                    [node, name] = field.split("~")
+                    if node not in tweaks:
+                        tweaks[node] = {}
+                    tweaks[node][name] = self._attributes[field]
+
+        return await run_flow(
+            inputs=None,
+            output_type="all",
+            flow_id=None,
+            flow_name=flow_name_selected,
+            tweaks=tweaks,
+            user_id=str(self.user_id),
+            session_id=self.graph.session_id or self.session_id,
+        )

lfx/components/logic/sub_flow.py

@@ -0,0 +1,114 @@
+from typing import Any
+
+from lfx.base.flow_processing.utils import build_data_from_result_data
+from lfx.custom.custom_component.component import Component
+from lfx.graph.graph.base import Graph
+from lfx.graph.vertex.base import Vertex
+from lfx.helpers.flow import get_flow_inputs
+from lfx.io import DropdownInput, Output
+from lfx.log.logger import logger
+from lfx.schema.data import Data
+from lfx.schema.dotdict import dotdict
+
+
+class SubFlowComponent(Component):
+    display_name = "Sub Flow [Deprecated]"
+    description = "Generates a Component from a Flow, with all of its inputs, and "
+    name = "SubFlow"
+    legacy: bool = True
+    icon = "Workflow"
+
+    async def get_flow_names(self) -> list[str]:
+        flow_data = await self.alist_flows()
+        return [flow_data.data["name"] for flow_data in flow_data]
+
+    async def get_flow(self, flow_name: str) -> Data | None:
+        flow_datas = await self.alist_flows()
+        for flow_data in flow_datas:
+            if flow_data.data["name"] == flow_name:
+                return flow_data
+        return None
+
+    async def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
+        if field_name == "flow_name":
+            build_config["flow_name"]["options"] = await self.get_flow_names()
+
+        for key in list(build_config.keys()):
+            if key not in [x.name for x in self.inputs] + ["code", "_type", "get_final_results_only"]:
+                del build_config[key]
+        if field_value is not None and field_name == "flow_name":
+            try:
+                flow_data = await self.get_flow(field_value)
+            except Exception:  # noqa: BLE001
+                await logger.aexception(f"Error getting flow {field_value}")
+            else:
+                if not flow_data:
+                    msg = f"Flow {field_value} not found."
+                    await logger.aerror(msg)
+                else:
+                    try:
+                        graph = Graph.from_payload(flow_data.data["data"])
+                        # Get all inputs from the graph
+                        inputs = get_flow_inputs(graph)
+                        # Add inputs to the build config
+                        build_config = self.add_inputs_to_build_config(inputs, build_config)
+                    except Exception:  # noqa: BLE001
+                        await logger.aexception(f"Error building graph for flow {field_value}")
+
+        return build_config
+
+    def add_inputs_to_build_config(self, inputs_vertex: list[Vertex], build_config: dotdict):
+        new_fields: list[dotdict] = []
+
+        for vertex in inputs_vertex:
+            new_vertex_inputs = []
+            field_template = vertex.data["node"]["template"]
+            for inp in field_template:
+                if inp not in {"code", "_type"}:
+                    field_template[inp]["display_name"] = (
+                        vertex.display_name + " - " + field_template[inp]["display_name"]
+                    )
+                    field_template[inp]["name"] = vertex.id + "|" + inp
+                    new_vertex_inputs.append(field_template[inp])
+            new_fields += new_vertex_inputs
+        for field in new_fields:
+            build_config[field["name"]] = field
+        return build_config
+
+    inputs = [
+        DropdownInput(
+            name="flow_name",
+            display_name="Flow Name",
+            info="The name of the flow to run.",
+            options=[],
+            refresh_button=True,
+            real_time_refresh=True,
+        ),
+    ]
+
+    outputs = [Output(name="flow_outputs", display_name="Flow Outputs", method="generate_results")]
+
+    async def generate_results(self) -> list[Data]:
+        tweaks: dict = {}
+        for field in self._attributes:
+            if field != "flow_name" and "|" in field:
+                [node, name] = field.split("|")
+                if node not in tweaks:
+                    tweaks[node] = {}
+                tweaks[node][name] = self._attributes[field]
+        flow_name = self._attributes.get("flow_name")
+        run_outputs = await self.run_flow(
+            tweaks=tweaks,
+            flow_name=flow_name,
+            output_type="all",
+        )
+        data: list[Data] = []
+        if not run_outputs:
+            return data
+        run_output = run_outputs[0]
+
+        if run_output is not None:
+            for output in run_output.outputs:
+                if output:
+                    data.extend(build_data_from_result_data(output))
+        return data

lfx/components/maritalk/__init__.py

@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from lfx.components._importing import import_mod
+
+if TYPE_CHECKING:
+    from lfx.components.maritalk.maritalk import MaritalkModelComponent
+
+_dynamic_imports = {
+    "MaritalkModelComponent": "maritalk",
+}
+
+__all__ = ["MaritalkModelComponent"]
+
+
+def __getattr__(attr_name: str) -> Any:
+    """Lazily import maritalk components on attribute access."""
+    if attr_name not in _dynamic_imports:
+        msg = f"module '{__name__}' has no attribute '{attr_name}'"
+        raise AttributeError(msg)
+    try:
+        result = import_mod(attr_name, _dynamic_imports[attr_name], __spec__.parent)
+    except (ModuleNotFoundError, ImportError, AttributeError) as e:
+        msg = f"Could not import '{attr_name}' from '{__name__}': {e}"
+        raise AttributeError(msg) from e
+    globals()[attr_name] = result
+    return result
+
+
+def __dir__() -> list[str]:
+    return list(__all__)

lfx/components/maritalk/maritalk.py

@@ -0,0 +1,52 @@
+from langchain_community.chat_models import ChatMaritalk
+
+from lfx.base.models.model import LCModelComponent
+from lfx.field_typing import LanguageModel
+from lfx.field_typing.range_spec import RangeSpec
+from lfx.inputs.inputs import DropdownInput, FloatInput, IntInput, SecretStrInput
+
+
+class MaritalkModelComponent(LCModelComponent):
+    display_name = "MariTalk"
+    description = "Generates text using MariTalk LLMs."
+    icon = "Maritalk"
+    name = "Maritalk"
+    inputs = [
+        *LCModelComponent.get_base_inputs(),
+        IntInput(
+            name="max_tokens",
+            display_name="Max Tokens",
+            advanced=True,
+            value=512,
+            info="The maximum number of tokens to generate. Set to 0 for unlimited tokens.",
+        ),
+        DropdownInput(
+            name="model_name",
+            display_name="Model Name",
+            advanced=False,
+            options=["sabia-2-small", "sabia-2-medium"],
+            value=["sabia-2-small"],
+        ),
+        SecretStrInput(
+            name="api_key",
+            display_name="MariTalk API Key",
+            info="The MariTalk API Key to use for authentication.",
+            advanced=False,
+        ),
+        FloatInput(name="temperature", display_name="Temperature", value=0.1, range_spec=RangeSpec(min=0, max=1)),
+    ]
+
+    def build_model(self) -> LanguageModel:  # type: ignore[type-var]
+        # self.output_schea is a list of dictionarie s
+        # let's convert it to a dictionary
+        api_key = self.api_key
+        temperature = self.temperature
+        model_name: str = self.model_name
+        max_tokens = self.max_tokens
+
+        return ChatMaritalk(
+            max_tokens=max_tokens,
+            model=model_name,
+            api_key=api_key,
+            temperature=temperature or 0.1,
+        )

lfx/components/mem0/__init__.py

@@ -0,0 +1,3 @@
+from .mem0_chat_memory import Mem0MemoryComponent
+
+__all__ = ["Mem0MemoryComponent"]

lfx/components/mem0/mem0_chat_memory.py

@@ -0,0 +1,136 @@
+import os
+
+from mem0 import Memory, MemoryClient
+
+from lfx.base.memory.model import LCChatMemoryComponent
+from lfx.inputs.inputs import DictInput, HandleInput, MessageTextInput, NestedDictInput, SecretStrInput
+from lfx.io import Output
+from lfx.log.logger import logger
+from lfx.schema.data import Data
+
+
+class Mem0MemoryComponent(LCChatMemoryComponent):
+    display_name = "Mem0 Chat Memory"
+    description = "Retrieves and stores chat messages using Mem0 memory storage."
+    name = "mem0_chat_memory"
+    icon: str = "Mem0"
+    inputs = [
+        NestedDictInput(
+            name="mem0_config",
+            display_name="Mem0 Configuration",
+            info="""Configuration dictionary for initializing Mem0 memory instance.
+                    Example:
+                    {
+                        "graph_store": {
+                            "provider": "neo4j",
+                            "config": {
+                                "url": "neo4j+s://your-neo4j-url",
+                                "username": "neo4j",
+                                "password": "your-password"
+                            }
+                        },
+                        "version": "v1.1"
+                    }""",
+            input_types=["Data"],
+        ),
+        MessageTextInput(
+            name="ingest_message",
+            display_name="Message to Ingest",
+            info="The message content to be ingested into Mem0 memory.",
+        ),
+        HandleInput(
+            name="existing_memory",
+            display_name="Existing Memory Instance",
+            input_types=["Memory"],
+            info="Optional existing Mem0 memory instance. If not provided, a new instance will be created.",
+        ),
+        MessageTextInput(
+            name="user_id", display_name="User ID", info="Identifier for the user associated with the messages."
+        ),
+        MessageTextInput(
+            name="search_query", display_name="Search Query", info="Input text for searching related memories in Mem0."
+        ),
+        SecretStrInput(
+            name="mem0_api_key",
+            display_name="Mem0 API Key",
+            info="API key for Mem0 platform. Leave empty to use the local version.",
+        ),
+        DictInput(
+            name="metadata",
+            display_name="Metadata",
+            info="Additional metadata to associate with the ingested message.",
+            advanced=True,
+        ),
+        SecretStrInput(
+            name="openai_api_key",
+            display_name="OpenAI API Key",
+            required=False,
+            info="API key for OpenAI. Required if using OpenAI Embeddings without a provided configuration.",
+        ),
+    ]
+
+    outputs = [
+        Output(name="memory", display_name="Mem0 Memory", method="ingest_data"),
+        Output(
+            name="search_results",
+            display_name="Search Results",
+            method="build_search_results",
+        ),
+    ]
+
+    def build_mem0(self) -> Memory:
+        """Initializes a Mem0 memory instance based on provided configuration and API keys."""
+        if self.openai_api_key:
+            os.environ["OPENAI_API_KEY"] = self.openai_api_key
+
+        try:
+            if not self.mem0_api_key:
+                return Memory.from_config(config_dict=dict(self.mem0_config)) if self.mem0_config else Memory()
+            if self.mem0_config:
+                return MemoryClient.from_config(api_key=self.mem0_api_key, config_dict=dict(self.mem0_config))
+            return MemoryClient(api_key=self.mem0_api_key)
+        except ImportError as e:
+            msg = "Mem0 is not properly installed. Please install it with 'pip install -U mem0ai'."
+            raise ImportError(msg) from e
+
+    def ingest_data(self) -> Memory:
+        """Ingests a new message into Mem0 memory and returns the updated memory instance."""
+        mem0_memory = self.existing_memory or self.build_mem0()
+
+        if not self.ingest_message or not self.user_id:
+            logger.warning("Missing 'ingest_message' or 'user_id'; cannot ingest data.")
+            return mem0_memory
+
+        metadata = self.metadata or {}
+
+        logger.info("Ingesting message for user_id: %s", self.user_id)
+
+        try:
+            mem0_memory.add(self.ingest_message, user_id=self.user_id, metadata=metadata)
+        except Exception:
+            logger.exception("Failed to add message to Mem0 memory.")
+            raise
+
+        return mem0_memory
+
+    def build_search_results(self) -> Data:
+        """Searches the Mem0 memory for related messages based on the search query and returns the results."""
+        mem0_memory = self.ingest_data()
+        search_query = self.search_query
+        user_id = self.user_id
+
+        logger.info("Search query: %s", search_query)
+
+        try:
+            if search_query:
+                logger.info("Performing search with query.")
+                related_memories = mem0_memory.search(query=search_query, user_id=user_id)
+            else:
+                logger.info("Retrieving all memories for user_id: %s", user_id)
+                related_memories = mem0_memory.get_all(user_id=user_id)
+        except Exception:
+            logger.exception("Failed to retrieve related memories from Mem0.")
+            raise
+
+        logger.info("Related memories retrieved: %s", related_memories)
+        return related_memories

lfx/components/milvus/__init__.py

@@ -0,0 +1,34 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from lfx.components._importing import import_mod
+
+if TYPE_CHECKING:
+    from .milvus import MilvusVectorStoreComponent
+
+_dynamic_imports = {
+    "MilvusVectorStoreComponent": "milvus",
+}
+
+__all__ = [
+    "MilvusVectorStoreComponent",
+]
+
+
+def __getattr__(attr_name: str) -> Any:
+    """Lazily import Milvus components on attribute access."""
+    if attr_name not in _dynamic_imports:
+        msg = f"module '{__name__}' has no attribute '{attr_name}'"
+        raise AttributeError(msg)
+    try:
+        result = import_mod(attr_name, _dynamic_imports[attr_name], __spec__.parent)
+    except (ModuleNotFoundError, ImportError, AttributeError) as e:
+        msg = f"Could not import '{attr_name}' from '{__name__}': {e}"
+        raise AttributeError(msg) from e
+    globals()[attr_name] = result
+    return result
+
+
+def __dir__() -> list[str]:
+    return list(__all__)

lfx/components/milvus/milvus.py

@@ -0,0 +1,115 @@
+from lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store
+from lfx.helpers.data import docs_to_data
+from lfx.io import (
+    BoolInput,
+    DictInput,
+    DropdownInput,
+    FloatInput,
+    HandleInput,
+    IntInput,
+    SecretStrInput,
+    StrInput,
+)
+from lfx.schema.data import Data
+
+
+class MilvusVectorStoreComponent(LCVectorStoreComponent):
+    """Milvus vector store with search capabilities."""
+
+    display_name: str = "Milvus"
+    description: str = "Milvus vector store with search capabilities"
+    name = "Milvus"
+    icon = "Milvus"
+
+    inputs = [
+        StrInput(name="collection_name", display_name="Collection Name", value="langflow"),
+        StrInput(name="collection_description", display_name="Collection Description", value=""),
+        StrInput(
+            name="uri",
+            display_name="Connection URI",
+            value="http://localhost:19530",
+        ),
+        SecretStrInput(
+            name="password",
+            display_name="Token",
+            value="",
+            info="Ignore this field if no token is required to make connection.",
+        ),
+        DictInput(name="connection_args", display_name="Other Connection Arguments", advanced=True),
+        StrInput(name="primary_field", display_name="Primary Field Name", value="pk"),
+        StrInput(name="text_field", display_name="Text Field Name", value="text"),
+        StrInput(name="vector_field", display_name="Vector Field Name", value="vector"),
+        DropdownInput(
+            name="consistency_level",
+            display_name="Consistencey Level",
+            options=["Bounded", "Session", "Strong", "Eventual"],
+            value="Session",
+            advanced=True,
+        ),
+        DictInput(name="index_params", display_name="Index Parameters", advanced=True),
+        DictInput(name="search_params", display_name="Search Parameters", advanced=True),
+        BoolInput(name="drop_old", display_name="Drop Old Collection", value=False, advanced=True),
+        FloatInput(name="timeout", display_name="Timeout", advanced=True),
+        *LCVectorStoreComponent.inputs,
+        HandleInput(name="embedding", display_name="Embedding", input_types=["Embeddings"]),
+        IntInput(
+            name="number_of_results",
+            display_name="Number of Results",
+            info="Number of results to return.",
+            value=4,
+            advanced=True,
+        ),
+    ]
+
+    @check_cached_vector_store
+    def build_vector_store(self):
+        try:
+            from langchain_milvus.vectorstores import Milvus as LangchainMilvus
+        except ImportError as e:
+            msg = "Could not import Milvus integration package. Please install it with `pip install langchain-milvus`."
+            raise ImportError(msg) from e
+        self.connection_args.update(uri=self.uri, token=self.password)
+        milvus_store = LangchainMilvus(
+            embedding_function=self.embedding,
+            collection_name=self.collection_name,
+            collection_description=self.collection_description,
+            connection_args=self.connection_args,
+            consistency_level=self.consistency_level,
+            index_params=self.index_params,
+            search_params=self.search_params,
+            drop_old=self.drop_old,
+            auto_id=True,
+            primary_field=self.primary_field,
+            text_field=self.text_field,
+            vector_field=self.vector_field,
+            timeout=self.timeout,
+        )
+
+        # Convert DataFrame to Data if needed using parent's method
+        self.ingest_data = self._prepare_ingest_data()
+
+        documents = []
+        for _input in self.ingest_data or []:
+            if isinstance(_input, Data):
+                documents.append(_input.to_lc_document())
+            else:
+                documents.append(_input)
+
+        if documents:
+            milvus_store.add_documents(documents)
+
+        return milvus_store
+
+    def search_documents(self) -> list[Data]:
+        vector_store = self.build_vector_store()
+
+        if self.search_query and isinstance(self.search_query, str) and self.search_query.strip():
+            docs = vector_store.similarity_search(
+                query=self.search_query,
+                k=self.number_of_results,
+            )
+
+            data = docs_to_data(docs)
+            self.status = data
+            return data
+        return []

lfx/components/mistral/__init__.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
+
+from lfx.components._importing import import_mod
+
+if TYPE_CHECKING:
+    from .mistral import MistralAIModelComponent
+    from .mistral_embeddings import MistralAIEmbeddingsComponent
+
+_dynamic_imports = {
+    "MistralAIModelComponent": "mistral",
+    "MistralAIEmbeddingsComponent": "mistral_embeddings",
+}
+
+__all__ = [
+    "MistralAIEmbeddingsComponent",
+    "MistralAIModelComponent",
+]
+
+
+def __getattr__(attr_name: str) -> Any:
+    """Lazily import mistral components on attribute access."""
+    if attr_name not in _dynamic_imports:
+        msg = f"module '{__name__}' has no attribute '{attr_name}'"
+        raise AttributeError(msg)
+    try:
+        result = import_mod(attr_name, _dynamic_imports[attr_name], __spec__.parent)
+    except (ModuleNotFoundError, ImportError, AttributeError) as e:
+        msg = f"Could not import '{attr_name}' from '{__name__}': {e}"
+        raise AttributeError(msg) from e
+    globals()[attr_name] = result
+    return result
+
+
+def __dir__() -> list[str]:
+    return list(__all__)