mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-12 12:06:29 +03:00
39 lines
1.6 KiB
Markdown
39 lines
1.6 KiB
Markdown
# LangChain — LLM Application Framework
|
|
|
|
An expert-level skill for building LLM-powered applications with LangChain — the most widely adopted LLM orchestration framework. LCEL chains, RAG pipelines, agents, LangSmith observability, and LangServe deployment.
|
|
|
|
## Why Install This Skill
|
|
|
|
When your agent loads this skill, it becomes a **LangChain expert** who can:
|
|
|
|
- **Build chains with LCEL** — `prompt | model | parser` composition with the Runnable interface
|
|
- **Create agents** — `create_agent` with tools (not legacy AgentExecutor)
|
|
- **Implement RAG pipelines** — document loading, splitting, embedding, retrieval, generation
|
|
- **Add observability** — LangSmith tracing for production debugging
|
|
- **Deploy with LangServe** — REST API deployment for production
|
|
|
|
## What You Get
|
|
|
|
| Directory | Purpose |
|
|
|-----------|---------|
|
|
| `SKILL.md` | Core principles, pipeline modes, where-to-start table, quick reference |
|
|
| `references/` | LCEL reference, RAG strategies, agent patterns, LangSmith, LangServe, framework comparisons |
|
|
|
|
## Framework Comparison
|
|
|
|
LangChain is the broadest LLM framework with 1000+ integrations. Its agents now run on LangGraph underneath. Use LangChain for rapid prototyping and broad integration support; drop to LangGraph when you need full state-machine control.
|
|
|
|
## Requirements
|
|
|
|
Python 3.8+ with `langchain`, `langchain-community`, and provider-specific packages.
|
|
|
|
|
|
## Quick Start
|
|
|
|
Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.
|
|
|
|
|
|
## Triggers
|
|
|
|
Use this skill for the task types and keywords described in its SKILL.md description.
|