| CCC.Vector.CP01 | Embedding Storage | The service always stores high-dimensional vector embeddings, derived from raw input such as text, images, or audio, together with the record they represent. | 1 |
| CCC.Vector.CP02 | Vector Indexing | The service may be configured to build indexes optimized for similarity search, such as HNSW, IVF, or product-quantized structures, with user-selected algorithm and tuning parameters. | 3 |
| CCC.Vector.CP03 | Similarity Search | The service always answers nearest-neighbor queries by taking a query embedding and returning the stored vectors most similar to it. | 1 |
| CCC.Vector.CP04 | Metadata Filtering | The service can apply structured filters on metadata fields alongside a vector similarity query to restrict the candidate set before or after ranking. | 1 |
| CCC.Vector.CP08 | Embedding Format Compatibility | The service can store vector values in standard numeric formats, such as 32-bit floating point or quantized byte and binary representations, so that embeddings produced by any external embedding model can be loaded without transformation. | 1 |
| CCC.Vector.CP09 | Vector Dimension Management | The service always enforces a fixed vector dimensionality per index or field, declared when the index is created, and rejects vectors that do not match it. | 1 |
| CCC.Vector.CP10 | Multi-modal Vector Support | The service can store more than one vector field per record, so that embeddings produced from different modalities (such as text and image) or different models are searchable together. | 1 |
| CCC.Vector.CP11 | Document-Level Access Control | The service may be configured to restrict which stored records and metadata fields a user can retrieve, so that query results are trimmed to the records the requester is authorized to see. | 1 |
| CCC.Vector.CP12 | Approximate or Exact Search Modes | The service can run a query either with an approximate nearest neighbor (ANN) algorithm for speed or with an exhaustive exact search for precision-critical applications. | 1 |
| CCC.Vector.CP13 | Integrated Embedding Generation | The service may be configured to call an embedding model to vectorize content at ingestion or query time, so that raw text or media is sent to a model endpoint instead of pre-computed vectors. | 2 |