Welcome to OpenRAG 🚀
OpenRAG is a complete, modular, and production-ready RAG (Retrieval-Augmented Generation) solution. It allows you to query your documents using advanced language models with precise and relevant context.What is a RAG system?
A RAG system combines information retrieval with text generation to provide accurate answers based on your own documents:- Retrieval: Finds relevant passages in your document base
- Augmented: Enriches the query with the found context
- Generation: Generates a coherent response with an LLM
RAG Workflow
Main Features
Document Upload
PDF, DOCX, TXT, Markdown - Automatic processing
Semantic Search
Advanced vector search with Qdrant
Answer Generation
Ollama, OpenAI, Anthropic Claude
Modular Architecture
Decoupled microservices with Docker
Main Components
OpenRAG consists of 10 Docker services:| Service | Port | Role |
|---|---|---|
| frontend-user | 8501 | User chat interface (Streamlit) |
| frontend-admin | 8502 | Admin panel, upload, stats (Streamlit) |
| api | 8000 | REST API (FastAPI) |
| orchestrator | 8001 | RAG workflow coordination |
| embedding | 8002 | Embeddings generation (sentence-transformers) |
| ollama | 11434 | Local LLM server |
| qdrant | 6333 | Vector database |
| postgres | 5432 | Metadata and history |
| redis | 6379 | Cache and queues |
| minio | 9000/9001 | File storage (S3-compatible) |
Use Cases
Enterprise Knowledge Base
Enterprise Knowledge Base
Create an AI assistant that knows all your internal documents, procedures, and company policies.
Legal Assistance
Legal Assistance
Quickly query contracts, case law, and legal documents with precise citations.
Customer Support
Customer Support
Automatically answer questions based on your product documentation and FAQ.
Academic Research
Academic Research
Explore and synthesize large collections of scientific research papers.
Quick Start
Open Chat Interface
Navigate to http://localhost:8501 and ask your first question!
First time? Initial startup takes 10-15 minutes (downloading Docker images + 4.9 GB LLM model)
Next Steps
Quick Start Guide
Complete installation in 5 minutes
Detailed Architecture
Understand the internal workings
System Requirements
Minimum configuration: 16 GB RAM, optional GPU
API Reference
Complete REST API documentation
Technical Characteristics
Performance
Performance
- With GPU: 1-3s per query
- Without GPU: 5-15s per query (after warm-up)
- Vector search: 100-200ms
- Indexing: 10-30s per PDF document
Scalability
Scalability
- Horizontally scalable microservices architecture
- Support for millions of documents
- Redis for distributed cache
- PostgreSQL for metadata
- Qdrant for high-performance vector search
Security
Security
- Data stored locally (no third-party cloud)
- Docker service isolation
- Support for local LLMs (Ollama) for total privacy
- Compatible with cloud LLMs (OpenAI, Claude) if desired
Extensibility
Extensibility
- Easy integration of new document formats
- Multi-LLM support (Ollama, OpenAI, Anthropic)
- REST API for integration into your applications
- Multiple collections for document segmentation
Support and Contributions
- 🐛 Issues: GitHub Issues
- 💻 Source Code: github.com/3ntrop1a/openrag
- 📖 Documentation: This Mintlify documentation