mcp-oi-wiki
35
The 'mcp-oi-wiki' project is designed to enhance large language models by integrating OI-Wiki content using vector embeddings. It supports querying through a database of semantic vectors, offering efficient access to summarized information from OI-Wiki.
mcp-oi-wiki
Empowers large models with OI-Wiki enhancements. It uses Deepseek-V3 to summarize OI-Wiki's 462 pages, embedding the summaries as semantic vectors in a database. When querying, it finds the closest vector in the database and returns the corresponding wiki markdown.
Usage
- Ensure you have
uv. - Clone the repository and modify your MCP configuration file to link with the server.
Update
- Generate your
db/oi-wiki.db. - Place the Silicon flow API key in
api.key. - Run scripts to generate a new database.
Thanks
- Thanks to milvus-io for a lightweight vector database and qdrant for fast embedding.