Agent skill · software engineering · davila7
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG applications. Best for rapid prototyping and production deployments.
Why this skill is useful
Adds executable scripts and patterns for building LLM applications with agents and RAG that aren't available in public documentation.
What it needs
Requires langchain, langchain-anthropic, langchain-core, langchain-openai installed locally. About 6k tokens when loaded. Last updated 2026-08-06. 30,138 stars on the source repository.
What this skill does
LangChain - Build LLM Applications with Agents & RAG The most popular framework for building LLM-powered applications. When to use LangChain Use LangChain when: Building agents with tool calling and reasoning (ReAct pattern) Implementing RAG (retrieval-augmented generation) pipelines Need to swap LLM providers easily (OpenAI, Anthropic, Google) Creating chatbots with conversation memory Rapid prototyping of LLM applications Production deployments with LangSmith observability Metrics: 119,000+ GitHub stars 272,000+ repositories use LangChain 500+ integrations (models, vector stores, tools) 3,800+ contributors Use alternatives instead: LlamaIndex: RAG-focused, better for document Q&A LangGraph: Complex stateful workflows, more control Haystack: Production search pipelines Semantic Kernel: Microsoft ecosystem Quick start Installation Basic LLM usage Create an agent (ReAct pattern) Core concepts 1. Models - LLM abstraction 2. Chains - Sequential operations 3. Agents - Tool-using reasoning ReAct (Reasoning + Acting) pattern: 4. Memory - Conversation history RAG (Retrieval-Augmented Generation) Basic RAG pipeline Conversational RAG with memory Advanced agent patterns Structured output Parallel tool execution Streaming agent execution Common patterns Multi-document QA Custom tools with error handling LangSmith observability Vector stores Chroma (local) Pinecone (cloud) FAISS (similarity search) Document loaders Text splitters Best practices 1. Start simple - Use createagent() for most cases 2. Enable streaming - Better UX for long responses 3. Add error handling - Tools can fail, handle gracefully 4. Use LangSmith - Essential for debugging agents 5. Optimize chunk size - 500-1000 chars for RAG 6. Version prompts - Track changes in production 7. Cache embeddings - Expensive, cache when possible 8. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills davila7/agents-langchain