LangChain Components

Complete reference for the LangChain ecosystem — models, agents, tools, retrieval, memory, middleware, streaming, multi-agent orchestration, LangGraph workflows, Deep Agents, and provider integrations for Python 3.10+.

Component Index

Models & Output

• Models — Chat models, tool calling, multimodal inputs, caching, rate limiting, custom models reference
• Messages — Message types (Human, AI, System, Tool), message operations, serialization, OpenAI format conversion reference

Agents

• Agents — create_agent, tools, structured output, guardrails, human-in-the-loop, context engineering reference
• Multi-Agent — Subagents, handoffs, skills, router, custom workflows, pattern selection reference

Tools & MCP

• Tools — Tool creation (@tool decorator, ToolNode), InjectedState, MCP integration, error handling reference

Retrieval & RAG

• Retrieval — Document loaders, text splitters, embeddings, vector stores, agentic RAG, semantic search reference