py-mcp-qdrant-rag

Metadata-Version: 2.2 Name: pyragdoc Version: 0.1.0 Summary: A Model Context Protocol server for RAG with documentation Home-page: https://github.com/yourusername/pyragdoc Author: Aekanun Author-email: your.email@example.com Classifier: Programming Language :: Python :: 3 Classifier: License :: OSI Approved :: MIT License Classifier: Operating System :: OS Independent Requires-Python: >=3.10 Description-Content-Type: text/markdown Requires-Dist: qdrant-client>=1.7.0 Requires-Dist: openai>=1.12.0 Requires-Dist: ollama>=0.1.0 Requires-Dist: PyPDF2>=3.0.0 Requires-Dist: pymupdf>=1.23.0 Requires-Dist: beautifulsoup4>=4.12.0 Requires-Dist: playwright>=1.40.0 Requires-Dist: requests>=2.31.0 Requires-Dist: fastapi>=0.109.0 Requires-Dist: uvicorn>=0.27.0 Requires-Dist: pydantic>=2.5.0 Requires-Dist: python-dotenv>=1.0.0 Requires-Dist: numpy>=1.26.0 Requires-Dist: tqdm>=4.66.0 Dynamic: author Dynamic: author-email Dynamic: classifier Dynamic: description Dynamic: description-content-type Dynamic: home-page Dynamic: requires-dist Dynamic: requires-python Dynamic: summary # PyRAGDoc A Python implementation of a Retrieval Augmented Generation system for documentation. ## Description PyRAGDoc is a Model Context Protocol server for fetching and storing documentation in a vector database, enabling semantic search and retrieval to augment LLM capabilities with relevant documentation context. ## Features - Add documentation from URLs - Process local files and directories - Support for PDF, HTML, and text-based documents - Vector search using Qdrant - Embedding generation with OpenAI or Ollama - MCP integration for LLM tools ## Installation ```bash pip install -e . ``` ## Usage ### Environment Variables - `OLLAMA_URL`: URL for Ollama API (default: http://localhost:11434) - `QDRANT_URL`: URL for Qdrant server (default: http://127.0.0.1:6333) - `EMBEDDING_PROVIDER`: Provider for embeddings (ollama or openai) - `EMBEDDING_MODEL`: Model to use for embeddings - `OPENAI_API_KEY`: API key for OpenAI (if using OpenAI provider) ### Running the Server #### MCP Server Mode ```bash pyragdoc --mode mcp ``` #### HTTP API Server Mode ```bash pyragdoc --mode http ``` ## License MIT