name

whether to auto generate id, default to True

Name of collection to search

Optional lower bound for dense range search (default: None)

Optional upper bound for dense range search (default: None)

vector dimension, default to 768; for quick setup and will be ignored if fieldschema is provided

Proportion of low-frequency terms to ignore (0.0-1.0) (default: 0.2)

name of the field to index

List of field schema, each element is a dictionary with the following keys:

Filter expression

Optional list of index parameters, each element is a dictionary with the following keys:

index type

The maximum number of results to return (default: 5)

Distance metric (COSINE, L2, IP) (default: "COSINE")

Create a new collection with quick setup or customized schema

Lists detailed information like schema, properties, collection ID, and other metadata of a specific collection.

Perform hybrid search on a collection

Insert data into a collection

List all collections in the database

Load a collection into memory for search and query

Query collection using filter expressions

Release a collection from memory

Search for documents using full text search

Perform text similarity search on a collection

Perform vector similarity search on a collection

Additional keyword arguments for the collection creation

Fields to include in results

name of the primary field, default to "id"; for quick setup and will be ignored if fieldschema is provided

Text to search for

Optional lower bound for range search (default: None)

Optional upper bound for range search (default: None)

Number of replicas (default: 1)

Optional lower bound for sparse range search (default: None)

Optional upper bound for sparse range search (default: None)

Field name for text search

type of the field

Query vector

Field name for vector search (default: "vector")

name of the vector field, default to "vector"; for quick setup and will be ignored if fieldschema is provided