Managed Vector Store

A Managed Vector Store is a specialized data service designed to store, index, and retrieve high-dimensional vector embeddings, enabling similarity search and machine learning inference. These services are used in AI/ML pipelines for use cases such as semantic search, recommendation systems, and generative AI applications. Vector stores support operations like nearest neighbor search using approximate or exact methods and integrate with model-serving and ingestion pipelines. They are optimized for performance, scale, and integration with cloud-native tools.

Release Details

Version:

DEV

Assurance Level:

Release Manager:

Development Build

Contributors

Development Team

Change Log

Development build - no formal changelog available

Capabilities

ID	Title	Description
CCC.Vector.F01	Embedding Storage	Supports storage of high-dimensional vector embeddings derived from raw input data such as text, images, or audio.
CCC.Vector.F02	Vector Indexing	Provides creation and management of indexes optimized for similarity search, such as HNSW, IVF, or PQ.
CCC.Vector.F03	Similarity Search	Enables nearest-neighbor queries using a query embedding to return the most similar vectors from the store.
CCC.Vector.F04	Metadata Filtering	Supports structured filtering on metadata fields alongside vector similarity search queries.
CCC.Vector.F05	Batch Ingestion	Allows for high-throughput batch upload and deletion of vectors and associated metadata.
CCC.Vector.F06	Real-Time Querying	Provides low-latency response to vector similarity queries suitable for interactive applications.
CCC.Vector.F07	Index Lifecycle Management	Enables automated or manual creation, optimization, and removal of vector indexes.
CCC.Vector.F08	Embedding Format Compatibility	Supports standard vector formats and integrates with common embedding generators (e.g., OpenAI, HuggingFace, TensorFlow).
CCC.Vector.F09	Vector Dimension Management	Supports storing and managing vectors of specific or dynamic dimensionality, depending on model needs.
CCC.Vector.F10	Multi-modal Vector Support	Supports storing and searching across vectors derived from multiple modalities (e.g., text, image, audio).
CCC.Vector.F11	Query Access Control	Provides the ability to restrict who can run vector similarity or metadata filter queries, separate from data modification rights.
CCC.Vector.F12	Approximate or Exact Search Modes	Supports both approximate nearest neighbor (ANN) algorithms for speed and exact search modes for precision-critical applications.