refactor: load components by importing them directly

src/backend/base/langflow/components/amazon/s3_bucket_uploader.py

@@ -1,8 +1,6 @@
 from pathlib import Path
 from typing import Any
 
-import boto3
-
 from langflow.custom.custom_component.component import Component
 from langflow.io import (
     BoolInput,
@@ -175,6 +173,12 @@ def _s3_client(self) -> Any:
         Returns:
             Any: A boto3 S3 client instance.
         """
+        try:
+            import boto3
+        except ImportError as e:
+            msg = "boto3 is not installed. Please install it using `uv pip install boto3`."
+            raise ImportError(msg) from e
+
         return boto3.client(
             "s3",
             aws_access_key_id=self.aws_access_key_id,

src/backend/base/langflow/components/deactivated/amazon_kendra.py

@@ -0,0 +1,66 @@
+# mypy: disable-error-code="attr-defined"
+from langchain_community.retrievers import AmazonKendraRetriever
+
+from langflow.base.vectorstores.model import check_cached_vector_store
+from langflow.custom.custom_component.custom_component import CustomComponent
+from langflow.io import DictInput, IntInput, StrInput
+
+
+class AmazonKendraRetrieverComponent(CustomComponent):
+    display_name: str = "Amazon Kendra Retriever"
+    description: str = "Retriever that uses the Amazon Kendra API."
+    name = "AmazonKendra"
+    icon = "Amazon"
+    legacy = True
+
+    inputs = [
+        StrInput(
+            name="index_id",
+            display_name="Index ID",
+        ),
+        StrInput(
+            name="region_name",
+            display_name="Region Name",
+        ),
+        StrInput(
+            name="credentials_profile_name",
+            display_name="Credentials Profile Name",
+        ),
+        DictInput(
+            name="attribute_filter",
+            display_name="Attribute Filter",
+        ),
+        IntInput(
+            name="top_k",
+            display_name="Top K",
+            value=3,
+        ),
+        DictInput(
+            name="user_context",
+            display_name="User Context",
+        ),
+    ]
+
+    @check_cached_vector_store
+    def build_vector_store(self) -> AmazonKendraRetriever:
+        """Builds the Amazon Kendra Retriever."""
+        try:
+            from langchain_community.retrievers import AmazonKendraRetriever
+        except ImportError as e:
+            msg = "Could not import AmazonKendraRetriever. Please install it with `pip install langchain-community`."
+            raise ImportError(msg) from e
+
+        try:
+            output = AmazonKendraRetriever(
+                index_id=self.index_id,
+                top_k=self.top_k,
+                region_name=self.region_name,
+                credentials_profile_name=self.credentials_profile_name,
+                attribute_filter=self.attribute_filter,
+                user_context=self.user_context,
+            )
+        except Exception as e:
+            msg = "Could not connect to AmazonKendra API."
+            raise ValueError(msg) from e
+
+        return output

src/backend/base/langflow/components/langchain_utilities/json_document_builder.py → src/backend/base/langflow/components/deactivated/json_document_builder.py

@@ -11,25 +11,33 @@
 
 # - **Document:** The Document containing the JSON object.
 
+
 from langchain_core.documents import Document
 
 from langflow.custom.custom_component.custom_component import CustomComponent
+from langflow.io import HandleInput, StrInput
 from langflow.services.database.models.base import orjson_dumps
 
 
 class JSONDocumentBuilder(CustomComponent):
     display_name: str = "JSON Document Builder"
     description: str = "Build a Document containing a JSON object using a key and another Document page content."
     name = "JSONDocumentBuilder"
-    legacy: bool = True
-
-    output_types: list[str] = ["Document"]
     documentation: str = "https://docs.langflow.org/components/utilities#json-document-builder"
-
-    field_config = {
-        "key": {"display_name": "Key"},
-        "document": {"display_name": "Document"},
-    }
+    legacy = True
+
+    inputs = [
+        StrInput(
+            name="key",
+            display_name="Key",
+            required=True,
+        ),
+        HandleInput(
+            name="document",
+            display_name="Document",
+            required=True,
+        ),
+    ]
 
     def build(
         self,
@@ -46,5 +54,6 @@ def build(
         else:
             msg = f"Expected Document or list of Documents, got {type(document)}"
             raise TypeError(msg)
+
         self.repr_value = documents
         return documents

src/backend/base/langflow/components/deactivated/metal.py

@@ -0,0 +1,54 @@
+# mypy: disable-error-code="attr-defined"
+from langchain_community.retrievers import MetalRetriever
+
+from langflow.base.vectorstores.model import check_cached_vector_store
+from langflow.custom.custom_component.custom_component import CustomComponent
+from langflow.io import DictInput, SecretStrInput, StrInput
+
+
+class MetalRetrieverComponent(CustomComponent):
+    display_name: str = "Metal Retriever"
+    description: str = "Retriever that uses the Metal API."
+    name = "MetalRetriever"
+    legacy = True
+
+    inputs = [
+        SecretStrInput(
+            name="api_key",
+            display_name="API Key",
+            required=True,
+        ),
+        SecretStrInput(
+            name="client_id",
+            display_name="Client ID",
+            required=True,
+        ),
+        StrInput(
+            name="index_id",
+            display_name="Index ID",
+            required=True,
+        ),
+        DictInput(
+            name="params",
+            display_name="Parameters",
+            required=False,
+        ),
+    ]
+
+    @check_cached_vector_store
+    def build_vector_store(self) -> MetalRetriever:
+        """Builds the Metal Retriever."""
+        try:
+            from langchain_community.retrievers import MetalRetriever
+            from metal_sdk.metal import Metal
+        except ImportError as e:
+            msg = "Could not import Metal. Please install it with `pip install metal-sdk langchain-community`."
+            raise ImportError(msg) from e
+
+        try:
+            metal = Metal(api_key=self.api_key, client_id=self.client_id, index_id=self.index_id)
+        except Exception as e:
+            msg = "Could not connect to Metal API."
+            raise ValueError(msg) from e
+
+        return MetalRetriever(client=metal, params=self.params or {})

src/backend/base/langflow/components/deactivated/multi_query.py

@@ -0,0 +1,59 @@
+from langchain.prompts import PromptTemplate
+from langchain.retrievers import MultiQueryRetriever
+
+from langflow.custom.custom_component.custom_component import CustomComponent
+from langflow.field_typing import BaseRetriever, LanguageModel, Text
+from langflow.inputs.inputs import HandleInput, StrInput
+
+
+class MultiQueryRetrieverComponent(CustomComponent):
+    display_name = "MultiQueryRetriever"
+    description = "Initialize from llm using default template."
+    documentation = "https://python.langchain.com/docs/modules/data_connection/retrievers/how_to/MultiQueryRetriever"
+    name = "MultiQueryRetriever"
+    legacy = True
+
+    inputs = [
+        HandleInput(
+            name="llm",
+            display_name="LLM",
+            input_types=["LanguageModel"],
+            required=True,
+        ),
+        HandleInput(
+            name="retriever",
+            display_name="Retriever",
+            input_types=["BaseRetriever"],
+            required=True,
+        ),
+        StrInput(
+            name="prompt",
+            display_name="Prompt",
+            value="You are an AI language model assistant. Your task is \n"
+            "to generate 3 different versions of the given user \n"
+            "question to retrieve relevant documents from a vector database. \n"
+            "By generating multiple perspectives on the user question, \n"
+            "your goal is to help the user overcome some of the limitations \n"
+            "of distance-based similarity search. Provide these alternative \n"
+            "questions separated by newlines. Original question: {question}",
+            required=False,
+        ),
+        StrInput(
+            name="parser_key",
+            display_name="Parser Key",
+            value="lines",
+            required=False,
+        ),
+    ]
+
+    def build(
+        self,
+        llm: LanguageModel,
+        retriever: BaseRetriever,
+        prompt: Text | None = None,
+        parser_key: str = "lines",
+    ) -> MultiQueryRetriever:
+        if not prompt:
+            return MultiQueryRetriever.from_llm(llm=llm, retriever=retriever, parser_key=parser_key)
+        prompt_template = PromptTemplate.from_template(prompt)
+        return MultiQueryRetriever.from_llm(llm=llm, retriever=retriever, prompt=prompt_template, parser_key=parser_key)

src/backend/base/langflow/components/langchain_utilities/retriever.py → src/backend/base/langflow/components/deactivated/retriever.py

@@ -2,26 +2,37 @@
 
 from langflow.custom.custom_component.custom_component import CustomComponent
 from langflow.field_typing import BaseRetriever, Tool
+from langflow.io import HandleInput, StrInput
 
 
 class RetrieverToolComponent(CustomComponent):
     display_name = "RetrieverTool"
     description = "Tool for interacting with retriever"
     name = "RetrieverTool"
-    legacy = True
     icon = "LangChain"
+    legacy = True
 
-    def build_config(self):
-        return {
-            "retriever": {
-                "display_name": "Retriever",
-                "info": "Retriever to interact with",
-                "type": BaseRetriever,
-                "input_types": ["Retriever"],
-            },
-            "name": {"display_name": "Name", "info": "Name of the tool"},
-            "description": {"display_name": "Description", "info": "Description of the tool"},
-        }
+    inputs = [
+        HandleInput(
+            name="retriever",
+            display_name="Retriever",
+            info="Retriever to interact with",
+            input_types=["Retriever"],
+            required=True,
+        ),
+        StrInput(
+            name="name",
+            display_name="Name",
+            info="Name of the tool",
+            required=True,
+        ),
+        StrInput(
+            name="description",
+            display_name="Description",
+            info="Description of the tool",
+            required=True,
+        ),
+    ]
 
     def build(self, retriever: BaseRetriever, name: str, description: str, **kwargs) -> Tool:
         _ = kwargs

src/backend/base/langflow/components/deactivated/vectara_self_query.py

@@ -0,0 +1,76 @@
+# mypy: disable-error-code="attr-defined"
+import json
+
+from langchain.chains.query_constructor.base import AttributeInfo
+from langchain.retrievers.self_query.base import SelfQueryRetriever
+
+from langflow.base.vectorstores.model import check_cached_vector_store
+from langflow.custom.custom_component.custom_component import CustomComponent
+from langflow.io import HandleInput, StrInput
+
+
+class VectaraSelfQueryRetriverComponent(CustomComponent):
+    """A custom component for implementing Vectara Self Query Retriever using a vector store."""
+
+    display_name: str = "Vectara Self Query Retriever"
+    description: str = "Implementation of Vectara Self Query Retriever"
+    name = "VectaraSelfQueryRetriver"
+    icon = "Vectara"
+    legacy = True
+
+    inputs = [
+        HandleInput(
+            name="vectorstore",
+            display_name="Vector Store",
+            info="Input Vectara Vector Store",
+        ),
+        HandleInput(
+            name="llm",
+            display_name="LLM",
+            info="For self query retriever",
+        ),
+        StrInput(
+            name="document_content_description",
+            display_name="Document Content Description",
+            info="For self query retriever",
+        ),
+        StrInput(
+            name="metadata_field_info",
+            display_name="Metadata Field Info",
+            info="Each metadata field info is a string in the form of key value pair dictionary containing "
+            "additional search metadata.\n"
+            'Example input: {"name":"speech","description":"what name of the speech","type":'
+            '"string or list[string]"}.\n'
+            "The keys should remain constant(name, description, type)",
+        ),
+    ]
+
+    @check_cached_vector_store
+    def build_vector_store(self):
+        """Builds the Vectara Self Query Retriever."""
+        try:
+            from langchain_community.vectorstores import Vectara  # noqa: F401
+        except ImportError as e:
+            msg = "Could not import Vectara. Please install it with `pip install langchain-community`."
+            raise ImportError(msg) from e
+
+        metadata_field_obj = []
+        for meta in self.metadata_field_info:
+            meta_obj = json.loads(meta)
+            if "name" not in meta_obj or "description" not in meta_obj or "type" not in meta_obj:
+                msg = "Incorrect metadata field info format."
+                raise ValueError(msg)
+            attribute_info = AttributeInfo(
+                name=meta_obj["name"],
+                description=meta_obj["description"],
+                type=meta_obj["type"],
+            )
+            metadata_field_obj.append(attribute_info)
+
+        return SelfQueryRetriever.from_llm(
+            self.llm,  # noqa: ignore[attr-defined]
+            self.vectorstore,  # noqa: ignore[attr-defined]
+            self.document_content_description,  # noqa: ignore[attr-defined]
+            metadata_field_obj,
+            verbose=True,
+        )