LangConnect Client offers a modern, Next.js-based GUI for managing vector databases, specifically those using PostgreSQL with the pgvector extension. It targets developers and researchers working with AI assistants, providing features for document management, advanced search (semantic, keyword, hybrid), and seamless integration with tools like Claude and Cursor via the Model Context Protocol (MCP).

How It Works

The architecture leverages Next.js for the frontend and FastAPI for the backend API, with Supabase handling JWT authentication and token refresh for secure user management. Vector data is stored in PostgreSQL via the pgvector extension. The MCP integration allows AI assistants to interact with the vector database through a defined protocol, enabling features like semantic search and document retrieval within AI workflows.

Quick Start & Requirements

• Install/Run: Clone the repository, copy .env.example to .env, configure Supabase credentials, and run make build then make up.
• Prerequisites: Docker, Docker Compose, Node.js 20+, Python 3.11+, Supabase account, OpenAI API key.
• Setup: Estimated setup time is minimal if prerequisites are met.
• Links: Frontend, API Docs.

Highlighted Details

• MCP Integration: Supports 9+ tools for AI assistants with stdio and SSE transport.
• Authentication: Secure JWT authentication with automatic token refresh and role-based access control via Supabase and NextAuth.js.
• Search: Hybrid search combining semantic (OpenAI embeddings) and keyword (PostgreSQL full-text search) with configurable weights.
• UI: Modern interface built with Next.js and Tailwind CSS, featuring dark/light themes and multi-language support (EN/KO).

Maintenance & Community

The project lists contributors and mentions a "Community Vibe Coding KR Facebook Group." Further community links or roadmap details are not explicitly provided in the README.

Licensing & Compatibility

Licensed under the MIT License, permitting commercial use and integration with closed-source projects.

Limitations & Caveats

The project requires specific versions of Node.js and Python. While it supports multiple document formats, the README does not detail performance benchmarks or limitations on document size or complexity. The MCP integration relies on external AI assistant configurations.