# Pharos

> Self-hosted, open-source RAG system with multi-format document ingestion, hybrid retrieval, enterprise ACL, and dual HTTP + MCP exits for team knowledge bases.

- **Category:** AI
- **Licence:** MIT
- **Latest version:** 0.3.0
- **Open source:** oss
- **Languages:** Python
- **Platforms:** Docker Compose, pip, Systemd
- **Tags:** Mcp, Knowledge Base, Local First, LLM, Rag, Deepseek, Retrieval Augmented Generation, Hybrid Search, Python, Docker Compose, Acl, Fastapi, Self Hosted, Embeddings, Model Context Protocol, Systemd, Qdrant, Agentic rag, Citations, Document Ingestion, Mineru

## Description

Pharos is a local-first agentic RAG system for team document libraries. It ingests multi-format documents (PDF, scans, docx, pptx, xlsx) via MinerU parsing, provides hybrid retrieval combining dense embeddings, sparse BM25, and reranking, and enforces enterprise-grade access control (ACL) with multi-tenant identities and principals. It offers two consumption modes: an HTTP API (/v1/ask) for closed-pipeline QA with citations, and an MCP exit for agentic RAG where the agent drives retrieval. The system runs as a resident daemon (via systemd or Docker Compose) that owns the GPU models and Qdrant vector store, with a three-tier architecture (inference, pharos app, Qdrant) for horizontal scaling. Documentation is primarily in Chinese with a 12-part learning series.

## Links

- [Homepage](https://github.com/laurent00tt/pharosrag)
- [GitHub Repository](https://github.com/Laurent00TT/PharosRAG)
- [Documentation (Chinese)](https://github.com/Laurent00TT/PharosRAG/tree/main/docs)
- [RAG Learning Series (12 parts, Chinese)](https://github.com/Laurent00TT/PharosRAG/tree/main/docs/learning)
- [Operations Manual](https://github.com/Laurent00TT/PharosRAG/blob/main/docs/OPERATIONS.md)
- [API Reference](https://github.com/Laurent00TT/PharosRAG/blob/main/docs/API.md)
- [Scale-out Guide](https://github.com/Laurent00TT/PharosRAG/blob/main/docs/SCALE_OUT.md)
- [Design Document](https://github.com/Laurent00TT/PharosRAG/blob/main/docs/DESIGN.md)

---
Source: https://selfhost.directory/project/pharosrag