DashVector:Grouped document search

Collection.query_group_by(
        self,
        vector: Optional[Union[List[Union[int, float]], np.ndarray]] = None,
        *,
        group_by_field: str,
        group_count: int = 10,
        group_topk: int = 10,
        id: Optional[str] = None,
        filter: Optional[str] = None,
        include_vector: bool = False,
        partition: Optional[str] = None,
        output_fields: Optional[List[str]] = None,
        sparse_vector: Optional[Dict[int, float]] = None,
        async_req: bool = False,
    ) -> DashVectorResponse:

import dashvector
import numpy as np

client = dashvector.Client(
    api_key='YOUR_API_KEY',
    endpoint='YOUR_CLUSTER_ENDPOINT'
)
ret = client.create(
    name='group_by_demo',
    dimension=4,
    fields_schema={'document_id': str, 'chunk_id': int}
)
assert ret

collection = client.get(name='group_by_demo')

ret = collection.insert([
    ('1', np.random.rand(4), {'document_id': 'paper-01', 'chunk_id': 1, 'content': 'xxxA'}),
    ('2', np.random.rand(4), {'document_id': 'paper-01', 'chunk_id': 2, 'content': 'xxxB'}),
    ('3', np.random.rand(4), {'document_id': 'paper-02', 'chunk_id': 1, 'content': 'xxxC'}),
    ('4', np.random.rand(4), {'document_id': 'paper-02', 'chunk_id': 2, 'content': 'xxxD'}),
    ('5', np.random.rand(4), {'document_id': 'paper-02', 'chunk_id': 3, 'content': 'xxxE'}),
    ('6', np.random.rand(4), {'document_id': 'paper-03', 'chunk_id': 1, 'content': 'xxxF'}),
])
assert ret

ret = collection.query_group_by(
    vector=[0.1, 0.2, 0.3, 0.4],
    group_by_field='document_id',  # Group return results by the value of the document_id field.
    group_count=2,  # Return two groups.
    group_topk=2,   # Return up to two documents from each group.
)
# Check whether the operation is successful.
if ret:
    print('query_group_by success')
    print(len(ret))
    print('------------------------')
    for group in ret:
        print('group key:', group.group_id)
        for doc in group.docs:
            prefix = ' -'
            print(prefix, doc)

ret = collection.query_group_by(
    id='1',
    group_by_field='name',
)
# Check whether the query method is successfully called.
if ret:
    print('query_group_by success')
    print(len(ret))
    for group in ret:
        print('group:', group.group_id)
        for doc in group.docs:
            print(doc)
            print(doc.id)
            print(doc.vector)
            print(doc.fields)

# Perform a grouped similarity search by using the vector or primary key and a conditional filter.
ret = collection.query(
    vector=[0.1, 0.2, 0.3, 0.4],   # Specify a vector for search. Alternatively, you can specify a primary key for search.
    group_by_field='name',
    filter='age > 18',             # Specify a filter to perform a match query on documents whose value of the age field is greater than 18.
    output_fields=['name', 'age'], # Return only the name and age fields.
    include_vector=True
)

# Perform a grouped similarity search by using both dense and sparse vectors.
ret = collection.query(
    vector=[0.1, 0.2, 0.3, 0.4],   # Specify a vector for search.
    sparse_vector={1: 0.3, 20: 0.7},
    group_by_field='name',
)