RAG.io

Retrieval-Augmented Generation.

Build with

Current Features

  • Intelligent Document Search : ChromaDB-powered semantic search with adjustable retrieval parameters
  • Multi-Provider LLM Support : Seamless integration with OpenAI, Claude, Gemini, Ollama, and 10+ providers
  • Temperature Control : Per-conversation adjustment (0.0-2.0)
  • Project-Based Organization : Isolate document collections and conversations by project
  • Real-Time Streaming : Server-Sent Events for progressive responses
  • Fine-Grained Control : Per-conversation temperature, top-k, and context window management
  • Enterprise Security : JWT authentication, AES-256 encryption, GDPR compliance

Advanced Features

  • Supported Formats : PDF, DOCX, TXT, MD, HTML, CSV, JSON (50+ file types)
  • Smart Chunking : Adaptive chunk size (100-2000 tokens) with configurable overlap
  • Metadata Extraction : Automatic filename, page number, and document type tagging
  • Token Tracking : Real-time token counting for cost estimation
  • Batch Processing : Background async processing with progress tracking

Providers Supported

  • OpenAI : GPT-4o, GPT-4-turbo, o1-preview, o1-mini.
  • Anthropic Claude : Claude 3.5 Sonnet, Claude 3 Opus
  • Google Gemini : Gemini 1.5 Pro/Flash, Gemini 2.0
  • OpenRouter : 200+ models (free + paid)
  • xAI Grok : Grok-3, Grok-3-mini, Grok-3-vision
  • Groq : Mixtral, LLaMA 3, Gemma
  • HuggingFace : Zephyr, Mistral, LLaMA 2
  • Ollama : ollama pull llama3
  • LM Studio : GUI app
  • vLLM : Python + CUDA
  • LMDeploy : Python + TurboMind
  • Oobabooga : Web UI

About

This project is licensed under the MIT License - see the LICENSE file for details.

Contact me

Built with ❤️ for the LLM community

For questions, suggestions, or support, please open an issue or contact the maintainers.@me.