# 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.

- **Type:** Skill
- **Install:** `agentstack add skill-ultroncore-claude-skill-vault-langchain`
- **Verified:** Pending review
- **Seller:** [UltronCore](https://agentstack.voostack.com/s/ultroncore)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [UltronCore](https://github.com/UltronCore)
- **Source:** https://github.com/UltronCore/claude-skill-vault/tree/main/skills/ai-ml/langchain

## Install

```sh
agentstack add skill-ultroncore-claude-skill-vault-langchain
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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=["\n\n", "\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

## Related Skills
- `langgraph` — stateful agent workflows
- `rag-pipeline` — RAG with LangChain
- `llm-caching-strategies` — caching in LangChain

## GitNexus Index
This skill is indexed by GitNexus for knowledge graph traversal.
Index path: /Users/localuser/.claude/skills/langchain/.gitnexus
Last indexed: 2026-05-23

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [UltronCore](https://github.com/UltronCore)
- **Source:** [UltronCore/claude-skill-vault](https://github.com/UltronCore/claude-skill-vault)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** yes

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ultroncore-claude-skill-vault-langchain
- Seller: https://agentstack.voostack.com/s/ultroncore
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.