# Vector Retrieval

A RAG system based on Python code analysis. It parses the code structure through AST and stores it in the Weaviate vector database, providing code query, natural language Q&A, and visualization functions, and supporting multi-codebase management and dependency analysis.

The WindTools MCP Server is a code assistant service based on ChromaDB and sentence transformers, providing document embedding and retrieval functions, and supporting codebase indexing and semantic search.

This project is a document processing server based on the Model Context Protocol (MCP) standard. By building a vector database and an MCP interface, it enables AI assistants to access external document resources and break through the knowledge limitations of large language models. The project includes two major components: a document processing pipeline and an MCP server. It supports multiple embedding models and file formats and can be applied to scenarios such as querying the latest technical documents and understanding private code libraries.

This project implements a server based on the MCP protocol, integrating the FAISS vector database and RAG technology, supporting the extraction of Move files from GitHub and building a knowledge base, and providing document retrieval and enhanced generation functions.

The Tacitbase MCP Server provides advanced search functions, combining native search and Typesense to enhance search capabilities.

A demonstration of a RAG application integrated with an MCP server, featuring document retrieval, context-aware prompt generation, and LLM API integration.

A serverless MCP service based on LanceDB, providing document storage, retrieval, and table information query functions

This project provides an MCP server for connecting Claude to the Qdrant vector database, enabling remote access through Docker deployment.