docs: add retriever integrations template (#24836)

libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb

@@ -0,0 +1,217 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: __ModuleName__\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# __ModuleName__Retriever\n",
+    "\n",
+    "## Overview\n",
+    "- TODO: Make sure API reference link is correct.\n",
+    "\n",
+    "This will help you getting started with the __ModuleName__ [retriever](/docs/concepts/#retrievers). For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Namespace | Native async | Local |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[__ModuleName__Retriever](https://api.python.langchain.com/en/latest/retrievers/__package_name__.retrievers.__module_name__.__ModuleName__Retriever.html) | __package_name__.retrievers | ❌ | ❌ |\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- TODO: Update with relevant info."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `__package_name__` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our retriever:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "70cc8e65-2a02-408a-bbc6-8ef649057d82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__Retriever\n",
+    "\n",
+    "retriever = __ModuleName__Retriever(\n",
+    "    # ...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c5f2839-4020-424e-9fc9-07777eede442",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51a60dbe-9f2e-4e04-bb62-23968f17164a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"...\"\n",
+    "\n",
+    "retriever.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfe8aad4-8626-4330-98a9-7ea1ca5d2e0e",
+   "metadata": {},
+   "source": [
+    "## Use within a chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23e11cc9-abd6-4855-a7eb-799f45ca01ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d47c37dd-5c11-416c-a3b6-bec413cd70e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"...\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality or considerations specific to this retriever\n",
+    "\n",
+    "Fill in or delete if not relevant."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/cli/langchain_cli/integration_template/integration_template/retrievers.py

@@ -0,0 +1,89 @@
+"""__ModuleName__ retrievers."""
+
+from typing import List
+
+from langchain_core.documents import Document
+from langchain_core.retrievers import BaseRetriever
+
+
+class __ModuleName__Retriever(BaseRetriever):
+    # TODO: Replace all TODOs in docstring. See example docstring:
+    # https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/retrievers/tavily_search_api.py#L17
+    """__ModuleName__ retriever.
+
+    # TODO: Replace with relevant packages, env vars, etc.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args:
+        arg 1: type
+            description
+        arg 2: type
+            description
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
+        .. code-block:: python
+
+            from __package_name__ import __ModuleName__Retriever
+
+            retriever = __ModuleName__Retriever(
+                # ...
+            )
+
+    Usage:
+        .. code-block:: python
+
+            query = "..."
+
+            retriever.invoke(query)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    Use within a chain:
+        .. code-block:: python
+
+            from langchain_core.output_parsers import StrOutputParser
+            from langchain_core.prompts import ChatPromptTemplate
+            from langchain_core.runnables import RunnablePassthrough
+            from langchain_openai import ChatOpenAI
+
+            prompt = ChatPromptTemplate.from_template(
+                \"\"\"Answer the question based only on the context provided.
+
+            Context: {context}
+
+            Question: {question}\"\"\"
+            )
+
+            llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+
+            def format_docs(docs):
+                return "\n\n".join(doc.page_content for doc in docs)
+
+            chain = (
+                {"context": retriever | format_docs, "question": RunnablePassthrough()}
+                | prompt
+                | llm
+                | StrOutputParser()
+            )
+
+            chain.invoke("...")
+
+        .. code-block:: python
+
+             # TODO: Example output.
+
+    """  # noqa: E501
+
+    # TODO: This method must be implemented to retrieve documents.
+    def _get_relevant_documents(self, query: str) -> List[Document]:
+        raise NotImplementedError()

libs/cli/langchain_cli/integration_template/integration_template/toolkits.py

@@ -1,4 +1,4 @@
-"""__ModuleName__ chat models."""
+"""__ModuleName__ toolkits."""
 
 from typing import List
 from langchain_core.tools import BaseTool, BaseToolKit
@@ -6,7 +6,7 @@ from langchain_core.tools import BaseTool, BaseToolKit
 
 class __ModuleName__Toolkit(BaseToolKit):
     # TODO: Replace all TODOs in docstring. See example docstring:
-    # https://github.com/langchain-ai/langchain/blob/a6d1fb4275801a4850e62b6209cfbf096a24f93f/libs/community/langchain_community/agent_toolkits/sql/toolkit.py#L20
+    # https://github.com/langchain-ai/langchain/blob/c123cb2b304f52ab65db4714eeec46af69a861ec/libs/community/langchain_community/agent_toolkits/sql/toolkit.py#L19
     """__ModuleName__ toolkit.
 
     # TODO: Replace with relevant packages, env vars, etc.
@@ -66,6 +66,6 @@ class __ModuleName__Toolkit(BaseToolKit):
 
     """  # noqa: E501
 
-    # TODO: This method must be implemented to generate chat responses.
+    # TODO: This method must be implemented to list tools.
     def get_tools(self) -> List[BaseTool]:
         raise NotImplementedError()