Scalar Quantization (SQ)

Compression by Default

Starting with v1.33, Weaviate enables 8-bit RQ quantization by default when creating new collections to ensure efficient resource utilization and faster performance. This behavior can be changed through the DEFAULT_QUANTIZATION environment variable. Note that once enabled, quantization can't be disabled for a collection. Default quantization only applies for the HNSW vector index type.

Scalar quantization (SQ) is a vector compression technique that can reduce the size of a vector.

To use SQ, enable it in the collection definition, then add data to the collection.

Enable compression for new collection

SQ can be enabled at collection creation time through the collection definition:

PythonGoJava v6 (Beta)JavaC# (Beta)

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    name="MyCollection",
    vector_config=Configure.Vectors.text2vec_openai(
        name="default",
        quantizer=Configure.VectorIndex.Quantizer.sq(),
    ),
)

// Define the configuration for SQ. Setting 'enabled' to true
sq_config := map[string]interface{}{
  "enabled": true,
}

// Define the class schema
class := &models.Class{
  Class:      className,
  Vectorizer: "text2vec-openai",
  // Assign the SQ configuration to the vector index config
  VectorIndexConfig: map[string]interface{}{
  	"sq": sq_config,
  },
}

// Create the collection in Weaviate
err = client.Schema().ClassCreator().
  WithClass(class).
  Do(context.Background())

client.collections.create("MyCollection",
    col -> col.vectorConfig(VectorConfig.text2vecTransformers(vc -> vc
        .quantization(Quantization.sq())
    )).properties(Property.text("title")));

WeaviateClass myCollection = WeaviateClass.builder()
    .className("MyCollection")
    .vectorizer("text2vec-openai")
    .vectorIndexConfig(VectorIndexConfig.builder()
        .sq(SQConfig.builder()
            .enabled(true)
            .build())
        .build())
    .properties(Arrays.asList(
        Property.builder()
            .name("title")
            .dataType(Arrays.asList(DataType.TEXT))
            .build()))
    .build();

Result<Boolean> createResult = client.schema().classCreator()
    .withClass(myCollection)
    .run();

await client.Collections.Create(new CollectionConfig
{
    Name = "MyCollection",
    Properties = [Property.Text("title")],
    VectorConfig = new VectorConfig(
        "default",
        new Vectorizer.Text2VecTransformers(),
        new VectorIndex.HNSW
        {
            Quantizer = new VectorIndex.Quantizers.SQ()
        }
    )
});

Enable compression for existing collection

Added in v1.31

The ability to enable SQ compression after collection creation was added in Weaviate v1.31.

SQ can also be enabled for an existing collection by updating the collection definition:

PythonGoJava v6 (Beta)JavaC# (Beta)

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Reconfigure

collection = client.collections.use("MyCollection")
collection.config.update(
    vector_config=Reconfigure.Vectors.update(
        name="default",
        vector_index_config=Reconfigure.VectorIndex.hnsw(
            quantizer=Reconfigure.VectorIndex.Quantizer.sq(
                rescore_limit=20
            ),
        )
    )
)

// Get the existing collection configuration
class, err := client.Schema().ClassGetter().
  WithClassName(className).Do(context.Background())

if err != nil {
  log.Fatalf("get class for vec idx cfg update: %v", err)
}

// Get the current vector index configuration
cfg := class.VectorIndexConfig.(map[string]interface{})

// Add SQ configuration to enable scalar quantization
cfg["sq"] = map[string]interface{}{
  "enabled":       true,
  "rescoreLimit":  200,   // Optional: number of candidates to fetch before rescoring
  "trainingLimit": 50000, // Optional: number of vectors to use for training
  "cache":         true,  // Optional: enable caching of quantized vectors
}

// Update the class configuration
class.VectorIndexConfig = cfg

// Apply the updated configuration to the collection
err = client.Schema().ClassUpdater().
  WithClass(class).Do(context.Background())

if err != nil {
  log.Fatalf("update class to use sq: %v", err)
}

CollectionHandle<Map<String, Object>> collection =
    client.collections.use("MyCollection");
collection.config.update(c -> c.vectorConfig(VectorConfig
    .text2vecTransformers(vc -> vc.quantization(Quantization.sq()))));

WeaviateClass updatedCollection = WeaviateClass.builder()
    .className("MyCollection")
    .description("Updated collection with SQ compression")
    .properties(Arrays.asList(
        Property.builder()
            .name("title")
            .dataType(Arrays.asList(DataType.TEXT))
            .build()))
    .vectorizer("text2vec-openai")
    .vectorIndexConfig(VectorIndexConfig.builder()
        .sq(SQConfig.builder()
            .enabled(true)
            .rescoreLimit(10L)
            .build())
        .build())
    .build();

Result<Boolean> updateResult = client.schema().classUpdater()
    .withClass(updatedCollection)
    .run();

await collection.Config.Update(c =>
{
    var vectorConfig = c.VectorConfig["default"];
    vectorConfig.VectorIndexConfig.UpdateHNSW(h => h.Quantizer = new VectorIndex.Quantizers.SQ());
});

SQ parameters

To tune SQ, set these vectorIndexConfig parameters.

Parameter	Type	Default	Details
sq: enabled	boolean	false	Uses SQ when true. The Python client does not use the enabled parameter. To enable SQ with the v4 client, set a quantizer in the collection definition.
sq: rescoreLimit	integer	-1	The minimum number of candidates to fetch before rescoring.
sq: trainingLimit	integer	100000	The size of the training set to determine scalar bucket boundaries.
vectorCacheMaxObjects	integer	1e12	Maximum number of objects in the memory cache. By default, this limit is set to one trillion (1e12) objects when a new collection is created. For sizing recommendations, see Vector cache considerations.

PythonGoJava v6 (Beta)JavaC# (Beta)

  API docs

More infoCode snippets in the documentation reflect the latest client library and Weaviate Database version. Check the Release notes for specific versions.

If a snippet doesn't work or you have feedback, please open a GitHub issue.

from weaviate.classes.config import Configure

client.collections.create(
    name="MyCollection",
    vector_config=Configure.Vectors.text2vec_openai(
        name="default",
        quantizer=Configure.VectorIndex.Quantizer.sq(
            rescore_limit=200,
            training_limit=50000,
            cache=True,
        ),
        vector_index_config=Configure.VectorIndex.hnsw(
            vector_cache_max_objects=100000,
        ),
    ),
)

// Define a custom configuration for SQ.
sq_with_options_config := map[string]interface{}{
  "enabled":       true,
  "rescoreLimit":  200,   // The number of candidates to fetch before rescoring
  "trainingLimit": 50000, // The number of vectors to use for training the quantizer
  "cache":         true,  // Enable caching of quantized vectors
}

// Define the class schema with the custom SQ config and other HNSW settings
class_with_options := &models.Class{
  Class:      className,
  Vectorizer: "text2vec-openai",
  VectorIndexConfig: map[string]interface{}{
  	"sq": sq_with_options_config,
  	"distance":              "cosine", // Set the distance metric for HNSW
  	"vectorCacheMaxObjects": 100000,   // Configure the vector cache
  },
}

// Create the collection in Weaviate
err = client.Schema().ClassCreator().
  WithClass(class_with_options).
  Do(context.Background())

client.collections.create("MyCollection",
    col -> col.vectorConfig(VectorConfig.text2vecTransformers(vc -> vc
        .quantization(Quantization
            .sq(q -> q.cache(true).trainingLimit(50000).rescoreLimit(200)))
        .vectorIndex(Hnsw.of(c -> c.vectorCacheMaxObjects(100000)))
    )).properties(Property.text("title")));

WeaviateClass myCollection = WeaviateClass.builder()
    .className("MyCollection")
    .vectorizer("text2vec-openai")
    .vectorIndexConfig(VectorIndexConfig.builder()
        .sq(SQConfig.builder()
            .enabled(true)
            .rescoreLimit(20L)
            .build())
        .build())
    .properties(Arrays.asList(
        Property.builder()
            .name("title")
            .dataType(Arrays.asList(DataType.TEXT))
            .build()))
    .build();

Result<Boolean> createResult = client.schema().classCreator()
    .withClass(myCollection)
    .run();

await client.Collections.Create(new CollectionConfig
{
    Name = "MyCollection",
    Properties = [Property.Text("title")],
    VectorConfig = new VectorConfig(
        "default",
        new Vectorizer.Text2VecTransformers(),
        new VectorIndex.HNSW
        {
            VectorCacheMaxObjects = 100000,
            Quantizer = new VectorIndex.Quantizers.SQ
            {
                //Cache = true,
                TrainingLimit = 50000,
                RescoreLimit = 200
            }
        }
    )
});

Additional considerations

Multiple vector embeddings (named vectors)

Collections can have multiple named vectors. The vectors in a collection can have their own configurations, and compression must be enabled independently for each vector. Every vector is independent and can use PQ, BQ, RQ, SQ, or no compression.

Multi-vector embeddings (ColBERT, ColPali, etc.)

Added in v1.30

Multi-vector embeddings (implemented through models like ColBERT, ColPali, or ColQwen) represent each object or query using multiple vectors instead of a single vector. Just like with single vectors, multi-vectors support PQ, BQ, RQ, SQ, or no compression.

During the initial search phase, compressed vectors are used for efficiency. However, when computing the MaxSim operation, uncompressed vectors are utilized to ensure more precise similarity calculations. This approach balances the benefits of compression for search efficiency with the accuracy of uncompressed vectors during final scoring.

Further resources

• Starter guides: Compression
• Reference: Vector index
• Concepts: Vector quantization
• Concepts: Vector index

Questions and feedback

If you have any questions or feedback, let us know in the user forum.

Technical questions

If you have questions feel free to post on our Community forum.

Documentation feedback

Leave feedback by opening a GitHub issue.