Represents a search query for a specific field in a collection. A `Query` can be constructed for either vector search or full-text search, bu

Represents a retrieved document with optional metadata, fields, and vectors. This immutable data class encapsulates the result of a search or ret

Represents a scalar (non-vector) field in a collection schema. A `FieldSchema` defines the name, data type, nullability, and optional inverte

Represents a vector field in a collection schema. A `VectorSchema` defines the name, data type, dimensionality, and index configuration for a

Defines the structure of a collection in Zvec. A collection schema specifies the name of the collection and its fields, including both scalar

Full-text search query parameters. Attributes: query_string (Optional[str]): FTS query expression (e.g. '+vector -slow "exact

* Quantizer parameters for vector indexes. * Encapsulates quantization-related settings such as enable_rotate. * Designed for future extensibility (

Re-ranker using Sentence Transformer cross-encoder models for semantic re-ranking. This re-ranker leverages pre-trained cross-encoder models to p

! Index Query Meta */

Sparse text embedding function using Qwen (DashScope) API. This class provides text-to-sparse-vector embedding capabilities using Alibaba Clo

Dense text embedding function using OpenAI API. This class provides text-to-vector embedding capabilities using OpenAI's embedding models. It

BM25-based sparse embedding function using DashText SDK. This class provides text-to-sparse-vector embedding capabilities using the DashText

Re-ranker using Reciprocal Rank Fusion (RRF) for multi-vector search. RRF combines results from multiple vector queries without requiring rel

Default local dense embedding using all-MiniLM-L6-v2 model. This is the default implementation for dense text embedding that uses the ``all-M

Re-ranker using Qwen (DashScope) cross-encoder API for semantic re-ranking. This re-ranker leverages DashScope's TextReRank service to perform

Default local sparse embedding using SPLADE model. This class provides sparse vector embedding using the SPLADE (SParse Lexical AnD Expansion

! JSON Value */

Unified query executor that routes based on query count and reranker type.

Re-ranker that combines scores using per-sub-query weights. Each sub-query's score is normalized by metric type (automatic when used via coll

Dense text embedding function using Qwen (DashScope) API. This class provides text-to-vector embedding capabilities using Alibaba Cloud's Das

! AiLego Blob Wrap */

A callable distance handle bound to a quantized query vector. DistanceImpl owns the quantized query bytes and a dispatched DistanceFunc. Invoking `op

! Half-Precision Floating Point */

Re-ranker that delegates to a user-provided callback. The callback receives sub-query results, field schemas, and topn. Args: callba

Neighbor

! Distance module */

HNSW builder (adds one specific field: ef_search)

Deprecated alias for Query. Use Query instead.

Lightweight MemoryBlock for buffer pool mode: release on destruction

! Cube class */

FLAT builder (no extra fields, just inherits base functionality)

HNSW-Rabitq builder (adds ef_search field)

IVF builder (adds specific fields: nprobe, l1QueryParam, l2QueryParam)

! Index Meta */

! JSON String */

Vamana builder (adds ef_search field)

! Location of Vector in Storage Segment */

Iterator over all documents in a collection. Returned by :meth:`Collection.iter_docs`. Supports the iterator protocol, explicit :meth:`close`

! File Stream Writer */

A group value and its matching documents. Attributes: group_by_value (str): String representation of the grouped scalar field value.

! Index Document */

! Index Plugin */

! IVF RaBitQ Builder * Implements the standard IndexBuilder interface (init → train → build → dump) * for IVF RaBitQ indexes. */

! Math Helper */

MultiChunkCluster

Product-Quantization specific params