Metadata-Version: 2.4
Name: rag_server
Version: 0.0.1
Summary: A FastMCP-based RAG server for dynamic document ingestion
Project-URL: Homepage, https://github.com/synehq/mcp-hybrid-rag
Project-URL: Bug Tracker, https://github.com/synehq/mcp-hybrid-rag/issues
Author-email: SyneHQ <human@synehq.com>
License-Expression: MIT
Requires-Python: >=3.10
Requires-Dist: faiss-cpu
Requires-Dist: fastmcp
Requires-Dist: numpy
Requires-Dist: openai
Requires-Dist: pypdf2
Requires-Dist: python-docx
Requires-Dist: requests
Requires-Dist: scikit-learn
Requires-Dist: textract
Description-Content-Type: text/markdown

# RAG Server

A FastMCP-based Retrieval-Augmented Generation server for dynamically ingesting public documents and querying them on-the-fly.

## Installation

```bash
pip install -r requirements.txt
```

Ensure you set your OpenAI API key:

```bash
export OPENAI_API_KEY=your_key_here
```

## Running the server

```bash
python -m rag_server.server
```

## API Tools

- ingest_urls(urls: List[str], session_id: Optional[str]) -> session_id
- query_knowledge(session_id: str, question: str) -> answer
