Document Indexer
Indexes and provides semantic search for local documents using a vector database and local language models.
Acerca de
The Document Indexer transforms your local files into a searchable knowledge base, allowing for intelligent querying and summarization directly on your machine. It acts as a Python-based Model Context Protocol (MCP) server, automatically monitoring designated folders for new or modified documents. Leveraging LanceDB for vector storage and Ollama for local LLM integration, it provides powerful semantic search capabilities across various file formats, ensuring your data remains private while enabling advanced document retrieval and cataloging.
Características Principales
- Real-time Document Monitoring
- MCP Integration exposing search and catalog tools
- Local LLM Integration (Ollama) for summarization and keyword extraction
- Multi-format Support (PDF, Word, TXT, MD, RTF)
- 4 GitHub stars
- Vector Search for semantic queries using LanceDB
Casos de Uso
- Cataloging and summarizing local files to get an overview of indexed content.
- Searching personal or research document collections using natural language queries.
- Integrating local document search capabilities into AI assistants like Claude Desktop.
Sponsored