langchain-retrieval
Document Q&A with RAG using Supabase pgvector store.
When & Why to Use This Skill
This Claude skill enables advanced Document Q&A capabilities using Retrieval-Augmented Generation (RAG). By integrating LangChain.js with Supabase pgvector, it allows users to transform static documents into a dynamic, searchable knowledge base. It solves the problem of AI hallucinations by grounding Claude's responses in specific, uploaded datasets, ensuring high accuracy and context-awareness for complex information retrieval tasks.
Use Cases
- Internal Corporate Wikis: Transform employee handbooks, SOPs, and internal documentation into an interactive assistant that provides instant answers to staff queries.
- Customer Support Automation: Power self-service support portals by allowing customers to ask questions directly against product manuals and troubleshooting guides.
- Legal and Compliance Analysis: Efficiently query large volumes of legal contracts or regulatory documents to find specific clauses or verify compliance requirements.
- Academic and Technical Research: Enable researchers to upload collections of papers or technical specifications to quickly synthesize information and extract data points through semantic search.
| name | langchain-retrieval |
|---|---|
| description | Document Q&A with RAG using Supabase pgvector store. |
LangChain Retrieval
Document Q&A with RAG (Retrieval Augmented Generation) using Supabase vector store.
Tech Stack
- Framework: Next.js
- AI: LangChain.js, 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.git .
If the directory is not empty:
git clone --depth 1 https://github.com/Eng0AI/langchain-retrieval.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
Create .env with required variables:
SUPABASE_URL- Supabase project URLSUPABASE_PRIVATE_KEY- Supabase service role keyOPENAI_API_KEY- For embeddings and LLMSUPABASE_DB_URL- Direct PostgreSQL connection URL
5. Setup Vector Store
Initialize pgvector extension and create documents table in Supabase.
Build
pnpm build
Development
pnpm dev