Kb provides a Model Context Protocol (MCP) server implementation powered by txtai, offering semantic search, knowledge graph capabilities, and AI-driven text processing through a standardized interface. It leverages txtai's unified embeddings database to combine vector indexes, graph networks, and relational databases. Users can build knowledge bases from various sources, export them as portable archives, and serve them through the MCP server for semantic search, knowledge graph querying, and text processing pipelines.
Key Features
01Knowledge graph querying and visualization
02AI-driven text processing pipelines
03Semantic search capabilities leveraging txtai
04Portable knowledge bases via compressed archives
05Causal boosting mechanism for enhanced relevance scoring
