🚀 Try Zilliz Cloud, the fully managed Milvus, for free—experience 10x faster performance! Try Now>>

Milvus
Zilliz
Home
  • User Guide
    • Indexes
  • Home
  • Docs
  • User Guide

  • Indexes

  • Binary Vector Indexes

  • BIN_IVF_FLAT

BIN_IVF_FLAT

The BIN_IVF_FLAT index is a variant of the IVF_FLAT index exclusively for binary embeddings. It enhances query efficiency by first partitioning the vector data into multiple clusters (nlist units) and then comparing the target input vector to the center of each cluster. BIN_IVF_FLAT significantly reduces query time while allowing users to fine-tune the balance between accuracy and speed. For more information, refer to IVF_FLAT.

Build index

To build a BIN_IVF_FLAT index on a vector field in Milvus, use the add_index() method, specifying the index_type, metric_type, and additional parameters for the index.

from pymilvus import MilvusClient

# Prepare index building params
index_params = MilvusClient.prepare_index_params()

index_params.add_index(
    field_name="your_binary_vector_field_name", # Name of the vector field to be indexed
    index_type="BIN_IVF_FLAT", # Type of the index to create
    index_name="vector_index", # Name of the index to create
    metric_type="HAMMING", # Metric type used to measure similarity
    params={
        "nlist": 64, # Number of clusters for the index
    } # Index building params
)

In this configuration:

  • index_type: The type of index to be built. In this example, set the value to BIN_IVF_FLAT.

  • metric_type: The method used to calculate the distance between vectors. Supported values for binary embeddings include HAMMING (default) and JACCARD. For details, refer to Metric Types.

  • params: Additional configuration options for building the index.

    • nlist: Number of clusters to divide the dataset.

    To learn more building parameters available for the BIN_IVF_FLAT index, refer to Index building params.

Once the index parameters are configured, you can create the index by using the create_index() method directly or passing the index params in the create_collection method. For details, refer to Create Collection.

Search on index

Once the index is built and entities are inserted, you can perform similarity searches on the index.

search_params = {
    "params": {
        "nprobe": 10, # Number of clusters to search
    }
}

res = MilvusClient.search(
    collection_name="your_collection_name", # Collection name
    anns_field="binary_vector_field",  # Binary vector field
    data=[query_binary_vector],  # Query binary vector
    limit=3,  # TopK results to return
    search_params=search_params
)

In this configuration:

  • params: Additional configuration options for searching on the index.

    • nprobe: Number of clusters to search for.

    To learn more search parameters available for the BIN_IVF_FLAT index, refer to Index-specific search params.

Index params

This section provides an overview of the parameters used for building an index and performing searches on the index.

Index building params

The following table lists the parameters that can be configured in params when building an index.

Parameter

Description

Value Range

Tuning Suggestion

nlist

The number of clusters to create using the k-means algorithm during index building. Each cluster, represented by a centroid, stores a list of vectors. Increasing this parameter reduces the number of vectors in each cluster, creating smaller, more focused partitions.

Type: Integer Range: [1, 65536]

Default value: 128

Larger nlist values improve recall by creating more refined clusters but increase index building time. Optimize based on dataset size and available resources. In most cases, we recommend you set a value within this range: [32, 4096].

Index-specific search params

The following table lists the parameters that can be configured in search_params.params when searching on the index.

Parameter

Description

Value Range

Tuning Suggestion

nprobe

The number of clusters to search for candidates. Higher values allow more clusters to be searched, improving recall by expanding the search scope but at the cost of increased query latency.

Type: Integer Range: [1, nlist]

Default value: 8

Increasing this value improves recall but may slow down the search. Set nprobe proportionally to nlist to balance speed and accuracy.

In most cases, we recommend you set a value within this range: [1, nlist].

Try Managed Milvus for Free

Zilliz Cloud is hassle-free, powered by Milvus and 10x faster.

Get Started
Feedback

Was this page helpful?