Weaviate

Weaviate is an open-source vector database designed to store, manage, and query vector data, specifically crafted for AI-driven search and recommendation systems. It is easy to integrate, scalable, and capable of handling high-dimensional vectors, high-performance similarity searches, as well as hybrid queries combining traditional structured data.

Weaviate not only stores vectors but also supports real-time vector creation, integration with machine learning models, and visual data analysis. Whether you’re building recommendation systems, search engines, or AI-powered applications, Weaviate provides robust support.

Key Features

• Vector Search: Supports fast similarity queries (nearest neighbor search).
• Multimodal Data Storage: Combines vector and structured data for hybrid queries.
• Contextual Awareness: Stores vector representations for text, images, and other multimodal data types.
• Scalable and High-Performance: Handles billions of data vectors with strong horizontal scaling capabilities.
• Machine Learning Integration: Supports external ML models such as OpenAI, Hugging Face, Cohere, etc., for dynamic vector generation.
• Schema-first: Allows defining clear schema structures to organize and optimize data storage and querying.
• API Support: Access and manipulate data easily through GraphQL and RESTful APIs.

Add Users and API Keys

• Add more apiKeys in AUTHENTICATION_APIKEY_ALLOWED_KEYS
• Add more users after AUTHENTICATION_APIKEY_USERS separated by commas

Example code

      import weaviate
      client = weaviate.connect_to_local(
          host="<host>",
          port=<http_port>,
          grpc_port=<grpc_port>,
          auth_credentials=Auth.api_key("<password>"),
      )