Qdrant
Provides semantic memory capabilities using the Qdrant vector database with configurable embedding models for efficient vector search and retrieval.
Acerca de
Qdrant is a Model Context Protocol (MCP) server designed to offer robust semantic memory functionalities. It leverages the Qdrant vector database to store and retrieve information based on vector similarity, making it ideal for AI applications requiring contextual awareness. The server supports a variety of embedding providers, including OpenAI and Sentence Transformers, allowing users to choose the most suitable model for their needs. With flexible configuration via environment variables and standard MCP tools, it simplifies the integration of sophisticated search capabilities and metadata management into any project.
Características Principales
- 0 GitHub stars
- Custom metadata support for stored content
- Flexible configuration via environment variables
- Semantic search and vector similarity retrieval
- Multiple embedding providers (OpenAI, Sentence Transformers)
- Standard MCP tools for store, find, delete, and list operations
Casos de Uso
- Enhancing AI applications like chatbots or agents with semantic memory
- Building intelligent search systems for large knowledge bases
- Integrating context-aware retrieval into custom software solutions
Advertisement