Langchain

Langchain

Quick Start

# Install LangChain ecosystem
pip install langchain langchain-openai langchain-community langchain-core

# Install vector store dependencies
pip install chromadb faiss-cpu

# Install document loaders
pip install unstructured pypdf docx2txt

# Set API key
export OPENAI_API_KEY="your-api-key"

When to Use This Skill

USE when:

• Building complex LLM applications with multiple components
• Need agents that can use tools and make autonomous decisions
• Implementing RAG (Retrieval Augmented Generation) systems
• Integrating with various LLM providers (OpenAI, Anthropic, local models)
• Building chatbots with conversation memory
• Processing and querying document collections
• Need streaming responses for real-time applications
• Orchestrating multi-step reasoning workflows

DON'T USE when:

• Simple single-prompt LLM calls (use direct API)
• Optimizing prompts programmatically (use DSPy instead)
• Building UI-focused chat applications (use Streamlit/Gradio directly)
• Need minimal dependencies and maximum control
• Performance-critical applications requiring custom optimizations

Prerequisites

# Core installation
pip install langchain>=0.2.0 langchain-openai>=0.1.0 langchain-core>=0.2.0

# For RAG applications
pip install chromadb>=0.4.0 faiss-cpu>=1.7.0

# For document processing
pip install unstructured>=0.10.0 pypdf>=3.0.0

# For web search and tools
pip install duckduckgo-search wikipedia arxiv

# Optional: Local LLMs
pip install langchain-community ollama

# Environment setup
export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."

Complete Examples

Example 1: Engineering Documentation Assistant

from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_community.document_loaders import DirectoryLoader, PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.runnables import RunnablePassthrough
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_community.chat_message_histories import ChatMessageHistory
from pathlib import Path

*See sub-skills for full details.*
### Example 2: Multi-Tool Research Agent

```python
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.tools import tool
from langchain_community.tools import DuckDuckGoSearchRun, WikipediaQueryRun
from langchain_community.utilities import WikipediaAPIWrapper
from pydantic import BaseModel, Field
from typing import List, Optional
import json

*See sub-skills for full details.*

## Integration Patterns

### LangServe Deployment

```python
from fastapi import FastAPI
from langserve import add_routes
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser

# Create app
app = FastAPI(
    title="Engineering Assistant API",

*See sub-skills for full details.*
### LangSmith Tracing

```python
import os
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

# Enable LangSmith tracing
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = "your-langsmith-api-key"
os.environ["LANGCHAIN_PROJECT"] = "engineering-assistant"

# All chain invocations are now traced
chain = ChatPromptTemplate.from_template("{input}") | ChatOpenAI()
response = chain.invoke({"input": "Hello"})

Resources

• LangChain Documentation: https://python.langchain.com/docs/
• LangChain Expression Language: https://python.langchain.com/docs/expression_language/
• LangSmith: https://smith.langchain.com/
• LangServe: https://python.langchain.com/docs/langserve/

Version History

• 1.0.0 (2026-01-17): Initial release with chains, agents, memory, RAG, and streaming

Sub-Skills

• 1. Basic Chain Composition
• 2. Agent with Tools
• 3. Conversation Memory
• 4. RAG (Retrieval Augmented Generation)
• 5. Document Processing
• 6. Streaming Responses
• 1. Error Handling (+2)
• Rate Limit Errors (+2)