Enables advanced RAG with knowledge graphs, supporting document ingestion, multimodal extraction, and multiple query modes (naive, local, global, hybrid) via the Model Context Protocol.
Implements the Model Context Protocol for managing, ingesting, and querying structured and unstructured data with integration to graph databases, vector search, and LLMs.
Enables querying private knowledge bases through a modular RAG pipeline with features like hybrid retrieval, reranking, and observability, exposed via the Model Context Protocol.
Enables querying medical documents stored in Qdrant using semantic retrieval, allowing users to search PubMed articles through the Model Context Protocol.
Provides AI assistants with persistent graph database memory using Neo4j, enabling task management, relationship understanding, semantic search with embeddings, file indexing, and multi-agent coordination through the Model Context Protocol.