Binary Quantization (compression)

Added in v1.23

BQ is available for the flat index type from v1.23 onwards and for the hnsw index type from v1.24.

Binary quantization (BQ) is a vector compression technique that can reduce the size of a vector.

To use BQ, enable it as shown below and add data to the collection.

Additional information

• How to set the index type

Simple BQ configuration

Each collection can be configured to use BQ compression. BQ must be enabled at collection creation time, before data is added to it.

This can be done by setting the vector_index_config of the collection to enable BQ compression.

Python (v4)

import weaviate.classes.config as wc

client.collections.create(
    name="YourCollection",
    vectorizer_config=wc.Configure.Vectorizer.text2vec_openai(),
    vector_index_config=wc.Configure.VectorIndex.flat(
        quantizer=wc.Configure.VectorIndex.Quantizer.bq()
    ),
)

client.close()

Python (v3)

class_definition = {
    "class": "YourCollection",
    "vectorizer": "text2vec-openai",  # Can be any vectorizer
    "vectorIndexType": "flat",
    "vectorIndexConfig": {
        "bq": {
            "enabled": True,
        },
    },
    #  Remainder not shown
}

client.schema.create_class(class_definition)

JS/TS (Beta)

import { configure } from 'weaviate-client';

const collection = await client.collections.create({
  name: collectionName,
  vectorizer: [
    configure.namedVectorizer(
      "default",
      {
        vectorIndexConfig: configure.vectorIndex.hnsw({
          quantizer: configure.vectorIndex.quantizer.bq()
        })
      }
    )
  ]
})

JS/TS

async function enableBQ() {
  const classObj = {
    class: 'YourCollection',
    vectorizer: 'text2vec-openai', // Can be any vectorizer
    vectorIndexType: 'flat',
    vectorIndexConfig: {
      bq: {
        enabled: true,
      },
    },
    //  Remainder not shown
  };
  const res = await client.schema.classCreator().withClass(classObj).do();
  console.log(res);
}

await enableBQ();

Go

simple_bq := map[string]interface{}{
  "enabled":	true,
}
class := &models.Class{
  Class:      "YourCollection",
  Vectorizer: "text2vec-openai",
  VectorIndexConfig: map[string]interface{}{
  	"bq": simple_bq,
  },
  // Remainder not shown
}

err = client.Schema().ClassCreator().
  WithClass(class).Do(context.Background())

if err != nil {
  log.Fatalf("create class: %v", err)
}

Java

// Coming soon

BQ with custom settings

The following parameters are available for BQ compression, under vectorIndexConfig:

Parameter	Type	Default	Details
bq : enabled	boolean	false	Enable BQ. Weaviate uses binary quantization (BQ) compression when true. The Python client v4 does not use the enabled parameter. To enable BQ with the v4 client, set a quantizer in the collection definition.
bq : rescoreLimit	integer	-1	The minimum number of candidates to fetch before rescoring.
bq : cache	boolean	false	Whether to use the vector cache.
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.

For example:

Python (v4)

import weaviate.classes.config as wc

client.collections.create(
    name="YourCollection",
    vectorizer_config=wc.Configure.Vectorizer.text2vec_openai(),
    vector_index_config=wc.Configure.VectorIndex.flat(
        distance_metric=wc.VectorDistances.COSINE,
        vector_cache_max_objects=100000,
        quantizer=wc.Configure.VectorIndex.Quantizer.bq(
            rescore_limit=200,
            cache=True
        )
    ),
)

client.close()

Python (v3)

class_definition = {
    "class": "YourCollection",
    "vectorizer": "text2vec-openai",  # Can be any vectorizer
    "vectorIndexType": "flat",
    "vectorIndexConfig": {
        "bq": {
            "enabled": True,
            "rescoreLimit": 200,  # The minimum number of candidates to fetch before rescoring
            "cache": True,  # Default: False
        },
        "vectorCacheMaxObjects": 100000,  # Cache size (used if `cache` enabled)
    },
    # Remainder not shown
}

client.schema.create_class(class_definition)

JS/TS (Beta)

import { configure } from 'weaviate-client';

const collection = await client.collections.create({
  name: collectionName,
  vectorizer: [
    configure.namedVectorizer(
      "default",
      {
        vectorIndexConfig: configure.vectorIndex.hnsw({
          quantizer: configure.vectorIndex.quantizer.bq({
            cache: true,  // Enable caching
            rescoreLimit: 200,  // The minimum number of candidates to fetch before rescoring
          }),
          vectorCacheMaxObjects: 100000,  // Cache size (used if `cache` enabled)
        })
      }
    )
  ]
})

JS/TS

async function bqWithOptions() {
  const classObj = {
    class: 'YourCollection',
    vectorizer: 'text2vec-openai', // Can be any vectorizer
    vectorIndexType: 'flat',
    vectorIndexConfig: {
      bq: {
        enabled: true,
        rescoreLimit: 200, // The minimum number of candidates to fetch before rescoring
        cache: true, // Default: false
      },
      vectorCacheMaxObjects: 100000, // Cache size (used if `cache` enabled)
    },
    //  Remainder not shown
  };
  const res = await client.schema.classCreator().withClass(classObj).do();
  console.log(res);
}

await bqWithOptions();

Go

custom_bq := map[string]interface{}{
  "enabled":      true,
  "rescoreLimit": 200,
  "cache":        true,
}
class := &models.Class{
  Class:      "YourCollection",
  Vectorizer: "text2vec-openai",
  VectorIndexConfig: map[string]interface{}{
  	"bq": custom_bq,
  	"vectorCacheMaxObjects": 100_000,
  },
  // Remainder not shown
}

err = client.Schema().ClassCreator().
  WithClass(class).Do(context.Background())

if err != nil {
  log.Fatalf("create class: %v", err)
}

Java

// Coming soon

Multiple vectors

Added in v1.24.0

Weaviate collections support multiple, named vectors.

Collections can have multiple, named vectors. Each vector is independent. Each vector space has its own index, its own compression, and its own vectorizer. This means you can create vectors for properties, use different vectorization models, and apply different metrics to the same object.

You do not have to use multiple vectors in your collections, but if you do, you need to adjust your queries to specify a target vector for vector or hybrid queries.

Similarly, compression must be enabled independently for each vector. The procedure varies slightly by client language, but in each case the idea is the same. Each vector is independent and can use PQ, BQ, or no compression.

Related pages

• Configuration: Vector index
• Concepts: Vector index
• Concepts: Vector quantization
• Tutorial: Schema

Questions and feedback

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

• Technical questions
• Documentation feedback