实现 LangChain 集成 - Docs by LangChain

Integration packages are Python packages that users can install for use in their projects. They implement one or more components that adhere to the LangChain interface standards. LangChain components are subclasses of base classes in langchain-core. Examples include chat models, tools, retrievers, and more. Your integration package will typically implement a subclass of at least one of these components. Expand the tabs below to see details on each.

Chat models are subclasses of the BaseChatModel class. They implement methods for generating chat completions, handling message formatting, and managing model parameters.

The chat model integration guide is currently WIP. In the meantime, read the chat model conceptual guide 了解详情 on how LangChain chat models function. You may also refer to existing integrations in the LangChain repo

Embedding models are subclasses of the Embeddings class.

The embedding model integration guide is currently WIP. In the meantime, read the embedding model conceptual guide 了解详情 on how LangChain embedding models function.

Tools are used in 2 main ways:

To define an “input schema” or “args schema” to pass to a chat model’s tool calling feature along with a text request, such that the chat model can generate a “tool call”, or parameters to call the tool with.
To take a “tool call” as generated above, and take some action and return a response that can be passed back to the chat model as a ToolMessage.

The Tools class must inherit from the BaseTool base class. This interface has 3 properties and 2 methods that should be implemented in a subclass.

The tools integration guide is currently WIP. In the meantime, read the tools conceptual guide 了解详情 on how LangChain tools function.

Middleware lets you customize agent behavior by hooking into model calls, tool calls, and agent lifecycle events. Middleware classes subclass the AgentMiddleware base class.Read the custom middleware guide to understand hooks, state updates, and middleware patterns before building an integration.Middleware integrations typically fall into two categories:

Type	Description	Examples
Provider-specific	Leverages a provider’s unique capabilities	Prompt caching, native tool execution, content moderation
Cross-provider	Works with any model or tool	Rate limiting, PII detection, logging, guardrails

Provider-specific middleware lives in the provider’s integration package (例如 langchain-anthropic). Cross-provider middleware can be published as a standalone package.You can also use these existing middleware integrations as reference:

Anthropic middleware

Multiple middleware classes for prompt caching, tools, memory, and file search.

Custom middleware guide

Full reference for hooks, state updates, and patterns.

连接这些文档到 Claude、VSCode 等，通过 MCP 获取实时答案。

在 GitHub 上编辑此页面或提交 Issue.