如何通过 Python SDK 在 Collection 中进行相似性检索

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 dashvectorimport 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',  # 按document_id字段的值分组    group_count=2,  # 返回2个分组    group_topk=2,   # 每个分组最多返回2个doc)# 判断是否成功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)

query_group_by success4------------------------group key: paper-01 - {"id": "2", "fields": {"document_id": "paper-01", "chunk_id": 2, "content": "xxxB"}, "score": 0.6807} - {"id": "1", "fields": {"document_id": "paper-01", "chunk_id": 1, "content": "xxxA"}, "score": 0.4289}group key: paper-02 - {"id": "3", "fields": {"document_id": "paper-02", "chunk_id": 1, "content": "xxxC"}, "score": 0.6553} - {"id": "5", "fields": {"document_id": "paper-02", "chunk_id": 3, "content": "xxxE"}, "score": 0.4401}

ret = collection.query_group_by(    id='1',    group_by_field='name',)# 判断query接口是否成功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)

# 根据向量或者主键进行分组相似性检索 + 条件过滤ret = collection.query_group_by(    vector=[0.1, 0.2, 0.3, 0.4],   # 向量检索，也可设置主键检索    group_by_field='name',    filter='age > 18',             # 条件过滤，仅对age > 18的Doc进行相似性检索    output_fields=['name', 'age'], # 仅返回name、age这2个Field    include_vector=True)

# 根据向量进行分组相似性检索 + 稀疏向量ret = collection.query_group_by(    vector=[0.1, 0.2, 0.3, 0.4],   # 向量检索    sparse_vector={1: 0.3, 20: 0.7},    group_by_field='name',)