查询公共索引以获取最近邻

Python

def vector_search_find_neighbors(
    project: str,
    location: str,
    index_endpoint_name: str,
    deployed_index_id: str,
    queries: List[List[float]],
    num_neighbors: int,
) -> None:
    """Query the vector search index.

    Args:
        project (str): Required. Project ID
        location (str): Required. The region name
        index_endpoint_name (str): Required. Index endpoint to run the query
        against.
        deployed_index_id (str): Required. The ID of the DeployedIndex to run
        the queries against.
        queries (List[List[float]]): Required. A list of queries. Each query is
        a list of floats, representing a single embedding.
        num_neighbors (int): Required. The number of neighbors to return.
    """
    # Initialize the Vertex AI client
    aiplatform.init(project=project, location=location)

    # Create the index endpoint instance from an existing endpoint.
    my_index_endpoint = aiplatform.MatchingEngineIndexEndpoint(
        index_endpoint_name=index_endpoint_name
    )

    # Query the index endpoint for the nearest neighbors.
    resp = my_index_endpoint.find_neighbors(
        deployed_index_id=deployed_index_id,
        queries=queries,
        num_neighbors=num_neighbors,
    )
    print(resp)

Curl

您可以在部署中找到下面列出的 publicEndpointDomainName。

  $ curl -X POST -H "Content-Type: application/json" -H "Authorization: Bearer `gcloud auth print-access-token`" http://1957880287.us-central1-181224308459.vdb.vertexai.goog/v1/projects/181224308459/locations/us-central1/indexEndpoints/3370566089086861312:findNeighbors -d '{deployed_index_id: "test_index_public1", queries: [{datapoint: {datapoint_id: "0", feature_vector: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}, neighbor_count: 5}]}'
  

此 curl 示例展示了如何从 http(s) 客户端进行调用，虽然公共端点支持 RESTful 和 grpc_cli 的双协议。

  $ curl -X POST -H "Content-Type: application/json" -H "Authorization: Bearer `gcloud auth print-access-token`" http://1957880287.us-central1-181224308459.vdb.vertexai.goog/v1/projects/${PROJECT_ID}/locations/us-central1/indexEndpoints/${INDEX_ENDPOINT_ID}:readIndexDatapoints -d '{deployed_index_id:"test_index_public1", ids: ["606431", "896688"]}'
  

控制台

按照以下说明从控制台查询部署到公共端点的索引。

1. 在 Google Cloud 控制台的 Vertex AI 部分中，前往部署和使用部分。选择 Vector Search

   前往 Vector Search

2. 选择要查询的索引。此时会打开索引信息页面。
3. 向下滚动到已部署的索引部分，然后选择要查询的已部署索引。此时会打开已部署的索引信息页面。
4. 在查询索引部分中，选择查询参数。您可以选择按向量或特定数据点进行查询。
5. 使用提供的 curl 命令或使用 Cloud Shell 运行来执行查询。
6. 如果使用 Cloud Shell，请选择在 Cloud Shell 中运行。
7. 在 Cloud Shell 中运行。
8. 结果会返回最近邻。