langchain-ai/langconnect

A managed RAG API server.

What it solves

LangConnect provides a ready-to-use RAG (Retrieval-Augmented Generation) service that simplifies the process of managing document collections and performing semantic searches via a REST API.

How it works

It uses FastAPI to expose a set of REST endpoints for managing data. For storage, it leverages PostgreSQL with the pgvector extension to store both the documents and their corresponding vector embeddings, allowing for efficient semantic search capabilities.

Who it’s for

Developers who need a scalable, Docker-ready RAG backend that can handle document indexing and retrieval without building the infrastructure from scratch.

Highlights

  • REST API for collection and document management
  • Vector storage powered by PostgreSQL and pgvector
  • Docker and Docker Compose support for rapid deployment
  • Built-in semantic search functionality

Related

  • Project
    danny-avila/rag_api

    An asynchronous FastAPI-based RAG API that uses pgvector or MongoDB to provide ID-based document indexing and retrieval with built-in ownership security.

  • Project
    mudler/LocalRecall

    A lightweight, offline RESTful API for managing vector-based knowledge bases, enabling AI agents to handle local long-term and short-term memory without cloud services.

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

  • Project
    rag-web-ui/rag-web-ui

    An intelligent dialogue system that allows users to build custom Q&A services by combining their own document knowledge bases with LLMs using Retrieval-Augmented Generation.

  • Project
    shinpr/mcp-local-rag

    A local RAG system that indexes private documents (PDF, DOCX, Markdown, TXT) and provides hybrid semantic and keyword search via MCP or CLI without external APIs.