[ PROMPT_NODE_22207 ]
Langchain
[ SKILL_DOCUMENTATION ]
# 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
```bash
# Core library (Python 3.10+)
pip install -U langchain
# With OpenAI
pip install langchain-openai
# With Anthropic
pip install langchain-anthropic
# Common extras
pip install langchain-community # 500+ integrations
pip install langchain-chroma # Vector store
```
### Basic LLM usage
```python
from langchain_anthropic import ChatAnthropic
# Initialize model
llm = ChatAnthropic(model="claude-sonnet-4-5-20250929")
# Simple completion
response = llm.invoke("Explain quantum computing in 2 sentences")
print(response.content)
```
### Create an agent (ReAct pattern)
```python
from langchain.agents import create_agent
from langchain_anthropic import ChatAnthropic
# Define tools
def get_weather(city: str) -> str:
"""Get current weather for a city."""
return f"It's sunny in {city}, 72°F"
def search_web(query: str) -> str:
"""Search the web for information."""
return f"Search results for: {query}"
# Create agent ( str:
"""Perform a risky operation that might fail."""
try:
# Your operation here
result = perform_operation(query)
return f"Success: {result}"
except Exception as e:
return f"Error: {str(e)}"
# Agent handles errors gracefully
agent = create_agent(model=llm, tools=[risky_operation])
```
### LangSmith observability
```python
import os
# Enable tracing
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = "your-api-key"
os.environ["LANGCHAIN_PROJECT"] = "my-project"
# All chains/agents automatically traced
agent = create_agent(model=llm, tools=[calculator])
result = agent.invoke({"input": "Calculate 123 * 456"})
# View traces at smith.langchain.com
```
## Vector stores
### Chroma (local)
```python
from langchain_chroma import Chroma
vectorstore = Chroma.from_documents(
documents=docs,
embedding=OpenAIEmbeddings(),
persist_directory="./chroma_db"
)
```
### Pinecone (cloud)
```python
from langchain_pinecone import PineconeVectorStore
vectorstore = PineconeVectorStore.from_documents(
documents=docs,
embedding=OpenAIEmbeddings(),
index_name="my-index"
)
```
### FAISS (similarity search)
```python
from langchain_community.vectorstores import FAISS
vectorstore = FAISS.from_documents(docs, OpenAIEmbeddings())
vectorstore.save_local("faiss_index")
# Load later
vectorstore = FAISS.load_local("faiss_index", OpenAIEmbeddings())
```
## Document loaders
```python
# Web pages
from langchain_community.document_loaders import WebBaseLoader
loader = WebBaseLoader("https://example.com")
# PDFs
from langchain_community.document_loaders import PyPDFLoader
loader = PyPDFLoader("paper.pdf")
# GitHub
from langchain_community.document_loaders import GithubFileLoader
loader = GithubFileLoader(repo="user/repo", file_filter=lambda x: x.endswith(".py"))
# CSV
from langchain_community.document_loaders import CSVLoader
loader = CSVLoader("data.csv")
```
## Text splitters
```python
# Recursive (recommended for general text)
from langchain.text_splitter import RecursiveCharacterTextSplitter
splitter = RecursiveCharacterTextSplitter(
chunk_size=1000,
chunk_overlap=200,
separators=["nn", "n", " ", ""]
)
# Code-aware
from langchain.text_splitter import PythonCodeTextSplitter
splitter = PythonCodeTextSplitter(chunk_size=500)
# Semantic (by meaning)
from langchain_experimental.text_splitter import SemanticChunker
splitter = SemanticChunker(OpenAIEmbeddings())
```
## Best practices
1. **Start simple** - Use `create_agent()` 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. **Monitor costs** - Track token usage with LangSmith
## Performance benchmarks
| Operation | Latency | Notes |
|-----------|---------|-------|
| Simple LLM call | ~1-2s | Depends on provider |
| Agent with 1 tool | ~3-5s | ReAct reasoning overhead |
| RAG retrieval | ~0.5-1s | Vector search + LLM |
| Embedding 1000 docs | ~10-30s | Depends on model |
## LangChain vs LangGraph
| Feature | LangChain | LangGraph |
|---------|-----------|-----------|
| **Best for** | Quick agents, RAG | Complex workflows |
| **Abstraction level** | High | Low |
| **Code to start** | <10 lines | ~30 lines |
| **Control** | Simple | Full control |
| **Stateful workflows** | Limited | Native |
| **Cyclic graphs** | No | Yes |
| **Human-in-loop** | Basic | Advanced |
**Use LangGraph when:**
- Need stateful workflows with cycles
- Require fine-grained control
- Building multi-agent systems
- Production apps with complex logic
## References
- **[Agents Guide](references/agents.md)** - ReAct, tool calling, streaming
- **[RAG Guide](references/rag.md)** - Document loaders, retrievers, QA chains
- **[Integration Guide](references/integration.md)** - Vector stores, LangSmith, deployment
## Resources
- **GitHub**: https://github.com/langchain-ai/langchain ⭐ 119,000+
- **Docs**: https://docs.langchain.com
- **API Reference**: https://reference.langchain.com/python
- **LangSmith**: https://smith.langchain.com (observability)
- **Version**: 0.3+ (stable)
- **License**: MIT
Source: claude-code-templates (MIT). See About Us for full credits.