mcpField
L
langchain-retrieval-agent

langchain-retrieval-agent

github.com/rebyteai-templateDocuments1760 installsUpdated 19w ago
Repository

About langchain-retrieval-agent

langchain-retrieval-agent is a LangGraph-based template for developers building document Q&A with RAG. It uses Supabase pgvector for vector storage and a retrieval tool to answer questions about documents.

Key features

  1. 01LangGraph-based agent
  2. 02Document retrieval Q&A
  3. 03Supabase pgvector vector store
  4. 04Next.js project template

Use cases

  1. 01Set up a document RAG Q&A app
  2. 02Store vectors with Supabase pgvector
  3. 03Build a retrieval agent with LangChain.js

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/rebyteai-template/rebyte-skills --skill langchain-retrieval-agent

After installing, type/langchain-retrieval-agentin Claude Code to confirm it loaded.

Details

From the project README

LangChain Retrieval Agent

An AI agent with retrieval tool for document Q&A using RAG, powered by LangGraph.

Tech Stack

  • Framework: Next.js
  • AI: LangChain.js, LangGraph, AI SDK
  • Vector Store: Supabase pgvector
  • Package Manager: pnpm

Prerequisites

  • Supabase project with pgvector extension
  • OpenAI API key

Setup

1. Clone the Template
git clone --depth 1 https://github.com/Eng0AI/langchain-retrieval-agent.git .

If the directory is not empty:

git clone --depth 1 https://github.com/Eng0AI/langchain-retrieval-agent.git _temp_template
mv _temp_template/* _temp_template/.* . 2>/dev/null || true
rm -rf _temp_template
2. Remove Git History (Optional)
rm -rf .git
git init
3. Install Dependencies
pnpm install
4. Setup Environment Variables
  • SUPABASE_URL - Supabase project URL
  • SUPABASE_PRIVATE_KEY - Supabase service role key
  • OPENAI_API_KEY - For embeddings and LLM

Build

pnpm build

Development

pnpm dev

Comments

Markdown supported