Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

OpenRAG

Intelligent Agent-powered document search

Langflow OpenSearch Docling

YouTube Channel GitHub stars GitHub forks

Documentation Ask DeepWiki


OpenRAG is a comprehensive Retrieval-Augmented Generation platform that enables intelligent document search and AI-powered conversations.

Users can upload, process, and query documents through a chat interface backed by large language models and semantic search capabilities. The system utilizes Langflow for document ingestion, retrieval workflows, and intelligent nudges, providing a seamless RAG experience.

Check out the documentation or get started with the quickstart.

Built with FastAPI and Next.js. Powered by OpenSearch, Langflow, and Docling.


OpenRAG Demo

✨ Highlight Features

  • Pre-packaged & ready to run - All core tools are hooked up and ready to go, just install and run
  • Agentic RAG workflows - Advanced orchestration with re-ranking and multi-agent coordination
  • Document ingestion - Handles messy, real-world data with intelligent parsing
  • Drag-and-drop workflow builder - Visual interface powered by Langflow for rapid iteration
  • Modular enterprise add-ons - Extend functionality when you need it
  • Enterprise search at any scale - Powered by OpenSearch for production-grade performance

🔄 How OpenRAG Works

OpenRAG follows a streamlined workflow to transform your documents into intelligent, searchable knowledge:

OpenRAG Workflow Diagram

🚀 Install OpenRAG

To get started with OpenRAG, see the installation guides in the OpenRAG documentation:

✨ Quick Start Workflow

Use uv run openrag to start

1. Launch OpenRAG

↓

Add files or folders as knowledge

2. Add Knowledge

↓

Start Chatting with your knowledge

3. Start Chatting

📦 SDKs

Integrate OpenRAG into your applications with our official SDKs:

Python SDK

pip install openrag-sdk

Quick Example:

import asyncio
from openrag_sdk import OpenRAGClient


async def main():
    async with OpenRAGClient() as client:
        response = await client.chat.create(message="What is RAG?")
        print(response.response)


if __name__ == "__main__":
    asyncio.run(main())

📖 Full Python SDK Documentation

TypeScript/JavaScript SDK

npm install openrag-sdk

Quick Example:

import { OpenRAGClient } from "openrag-sdk";

const client = new OpenRAGClient();
const response = await client.chat.create({ message: "What is RAG?" });
console.log(response.response);

📖 Full TypeScript/JavaScript SDK Documentation

🔌 Model Context Protocol (MCP)

OpenRAG ships a built-in MCP server over streamable HTTP, mounted on your instance at /mcp. Connect AI assistants like Cursor, Claude Desktop, and IBM Bob to your OpenRAG knowledge base — no subprocess and no separate install. Authenticate with the same OpenRAG API key you use for the REST API, passed via the X-API-Key header.

Important: The standalone openrag-mcp PyPI package is deprecated. Connect your MCP client directly to the /mcp endpoint instead.

Quick Example (Cursor/Claude Desktop config):

{
  "mcpServers": {
    "openrag": {
      "url": "http://localhost:3000/mcp",
      "headers": {
        "X-API-Key": "orag_your_api_key_here"
      }
    }
  }
}

The MCP server provides tools for RAG-enhanced chat, semantic search, document ingestion, knowledge filters, and settings management.

📖 Full MCP Documentation

🛠️ Development

For developers who want to contribute to OpenRAG or set up a development environment, see CONTRIBUTING.md.

🛟 Troubleshooting

For assistance with OpenRAG, see Troubleshoot OpenRAG and visit the Discussions page.

To report a bug or submit a feature request, visit the Issues page.

Metadata

Release files for openrag 0.8.1.dev8

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for openrag 0.8.1.dev8
File Size Uploaded Provenance Actions
openrag-0.8.1.dev8.tar.gz 7.7 MB Without provenance Details for openrag-0.8.1.dev8.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for openrag 0.8.1.dev8
File Interpreter ABI Platform Actions
openrag-0.8.1.dev8-py3-none-any.whl Python 3 none any Details for openrag-0.8.1.dev8-py3-none-any.whl

Total release size: 15.4 MB

Release files / openrag-0.8.1.dev8.tar.gz

Download URL openrag-0.8.1.dev8.tar.gz
Size 7.7 MB
Tags Source
SHA-256 checksum
How to use checksums
68e3d93e9c4a0dbfb6d7b9d859252f11442b4238cf4b3340049850579242520d
BLAKE2b-256 checksum
How to use checksums
33a493dbd257c35248e8a060cdf1b92447d25a93e1fed2a244615e262d66e137
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / openrag-0.8.1.dev8-py3-none-any.whl

Download URL openrag-0.8.1.dev8-py3-none-any.whl
Size 7.8 MB
Tags Python 3
SHA-256 checksum
How to use checksums
c4680b6bb06f1f3db8cac688794ebaf0371afcd7fe88d9c18ce1dcc6e8060377
BLAKE2b-256 checksum
How to use checksums
13d0505930875b1e0d0464f11d7f69be9d073e5a5b39984a8ddeab5e6a1cb290
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.13.7 {"installer":{"name":"uv","version":"0.13.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"26.04","id":"resolute","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Security for openrag 0.8.1.dev8

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page