Chat LangChain

May 13, 2026 · View on GitHub

A simple documentation assistant built with LangGraph.

Overview

This is a documentation assistant agent that helps answer questions about LangChain, LangGraph, and LangSmith. It demonstrates how to build a production-ready agent using:

LangGraph - For agent orchestration and state management
LangChain Agents - For agent creation with middleware support
Guardrails - To keep conversations on-topic

The repo also includes a Next.js frontend in frontend/ for the public chat UI.

Features

Documentation Search - Searches official LangChain docs
Support KB - Searches the Pylon knowledge base for known issues
Link Validation - Verifies URLs before including in responses
Guardrails - Filters off-topic queries

Quick Start

Prerequisites

Python 3.11+
uv (recommended) or pip

Installation

# Clone the repository
git clone https://github.com/langchain-ai/chat-langchain.git
cd chat-langchain

# Install dependencies with uv
uv sync

# Or with pip
pip install -e . "langgraph-cli[inmem]"

Configuration

# Copy environment template
cp .env.example .env

# Edit .env with your API keys

Required Environment Variables

Variable	Description
`ANTHROPIC_API_KEY`	Anthropic API key (or use another provider)
`MINTLIFY_API_URL`	Mintlify API base URL for docs search (e.g. `https://api-dsc.mintlify.com/v1/search/docs.langchain.com`)
`MINTLIFY_API_KEY`	Mintlify API key for docs search
`PYLON_API_KEY`	Pylon API key for support KB
`PYLON_KB_ID`	Pylon knowledge base ID for support articles
`USE_LOCAL_PROMPTS`	Optional. Set to `true` to use local prompt files instead of pulling Prompt Hub prompts

Running Locally

Backend

# Start LangGraph development server
uv run langgraph dev

# Or with pip
langgraph dev

Open LangGraph Studio: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

Frontend

cd frontend
npm ci
npm run dev:local

The frontend expects the LangGraph server at http://127.0.0.1:2024 by default. If you want trace sharing from the UI, set LANGSMITH_API_KEY in frontend/.env.local.

Project Structure

├── src/
│   ├── agent/
│   │   ├── docs_graph.py      # Main docs agent
│   │   └── config.py          # Model configuration
│   ├── tools/
│   │   ├── docs_tools.py      # Documentation search
│   │   ├── pylon_tools.py     # Support KB tools
│   │   └── link_check_tools.py # URL validation
│   ├── prompts/
│   │   └── docs_agent_prompt.py
│   └── middleware/
│       ├── guardrails_middleware.py
│       └── retry_middleware.py
├── frontend/                  # Next.js public chat UI
├── langgraph.json             # LangGraph configuration
└── pyproject.toml             # Python project config

How It Works

The agent uses a docs-first research strategy:

Guardrails Check - Validates the query is LangChain-related
Documentation Search - Searches official docs via Mintlify
Knowledge Base - Searches Pylon for known issues/solutions
Link Validation - Verifies any URLs before including them
Response Generation - Synthesizes a helpful answer