> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ragen.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction to Ragen AI: Self-Hosted RAG Platform

> Ragen AI turns your company documents into an AI knowledge base with multilingual retrieval, source-traceable answers, and an OpenAI-compatible API.

Ragen AI is a self-hosted, open-source RAG (Retrieval-Augmented Generation) platform that lets your team and customers ask questions of your company's documents and get answers grounded in your actual data — with every answer traceable back to the source. You run it entirely on your own infrastructure: your documents, your database, your vector index, your encryption keys.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Scaffold a working Ragen instance in under 10 minutes with a single command.
  </Card>

  <Card title="Self-Hosting Guide" icon="server" href="/self-hosting">
    Set up Ragen on your own infrastructure with Docker Compose or Kubernetes.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/quickstart">
    Integrate Ragen into your apps with the OpenAI-compatible REST API.
  </Card>

  <Card title="TypeScript SDK" icon="npm" href="/api-reference/typescript-sdk">
    Use the official `@webamigos/ragen-sdk-ts` client for typed, streaming-ready access.
  </Card>
</CardGroup>

## What is Ragen AI?

Ragen connects your existing documents — PDF, DOCX, PPTX, XLSX, CSV, Markdown, images, URLs, and more — to modern language models using Retrieval-Augmented Generation. When a user asks a question, Ragen retrieves the most relevant document chunks and generates an answer that cites those chunks by source, so your team always knows where the information came from.

### Key capabilities

<CardGroup cols={2}>
  <Card title="AI Chat Assistant" icon="comments">
    Internal knowledge platform for your team, with document permissions enforced at retrieval — not just in the UI.
  </Card>

  <Card title="Embeddable Chatbot" icon="robot">
    Customer-facing widget you can embed on any website, backed by your own knowledge base.
  </Card>

  <Card title="OpenAI-Compatible API" icon="plug">
    Drop-in replacement for OpenAI's Chat Completions, Files, Assistants, and Threads APIs.
  </Card>

  <Card title="No Model Lock-In" icon="shuffle">
    Route to OpenAI, Anthropic, Azure, AWS Bedrock, Google Vertex, or models running on your own hardware.
  </Card>

  <Card title="Multilingual Retrieval" icon="language">
    Hybrid dense + sparse (BM25) search with cross-encoder reranking. 92% multilingual benchmark accuracy.
  </Card>

  <Card title="MCP Integrations" icon="link">
    Connect Google Drive, Google Calendar, Gmail, HubSpot, ClickUp, and Slack as live data sources.
  </Card>
</CardGroup>

## How it works

<Steps>
  <Step title="Upload your documents">
    Add PDFs, Word docs, spreadsheets, web pages, or any supported file to a project (knowledge base). Ragen parses, chunks, and embeds them automatically.
  </Step>

  <Step title="Ask a question">
    Users ask questions in the chat interface, via the API, or through an embedded chatbot. Ragen retrieves the most relevant document chunks using hybrid vector + keyword search.
  </Step>

  <Step title="Get a grounded answer">
    The language model generates an answer using only the retrieved content, and Ragen shows which documents and passages it cited — so you can verify every response.
  </Step>
</Steps>

## Deployment options

| Option        | What it means                                                           |
| ------------- | ----------------------------------------------------------------------- |
| Self-hosted   | Docker Compose or Kubernetes on infrastructure you control              |
| Private cloud | Your own cloud account (AWS, Azure, GCP, Scaleway)                      |
| Air-gapped    | Supported by architecture — all model calls can route to local hardware |

<Tip>
  A demo instance is available at [demo.ragen.ai](https://demo.ragen.ai) seeded with sample data. It shows what a Ragen installation looks like — your own data belongs on your own instance.
</Tip>

## Next steps

* **New to Ragen?** Start with the [Quick Start](/quickstart) to get a local instance running in minutes.
* **Ready to deploy?** Follow the [Self-Hosting Guide](/self-hosting) for a production setup.
* **Building an integration?** Jump straight to the [API Reference](/api-reference/quickstart) or [TypeScript SDK](/api-reference/typescript-sdk).
* **Running local models?** See the [Open Models guide](/configuration/open-models) to run completely offline.