从 Vector Search 1.0 迁移

为了简化从 Vector Search 1.0 的过渡，ImportDataObjects API 中引入了一项新功能。

迁移过程涉及三个关键步骤：

  1. 创建具有匹配架构的集合。 在导入之前，您必须先创建集合。其数据架构必须经过结构化处理，以适应转换后的 Vector Search 1.0 数据。

  2. 启动导入流程。 调用 ImportDataObjects API，指定 Vector Search 1.0 数据的 Cloud Storage 位置，并启用转换标志 detect_and_convert_vs1_json。

  3. 了解数据转换。 熟悉 Vector Search 1.0 数据字段如何映射到新的数据对象结构。

创建集合

首先，创建一个集合，其数据架构应与 Vector Search 1.0 数据结构相符。

curl -X POST \
  'https://vectorsearch.googleapis.com/v1alpha/projects/PROJECT_ID/locations/LOCATION/collections?collection_id=movies' \
  -H 'Bearer $(gcloud auth print-access-token)' \
  -H 'Content-Type: application/json' \
  -d '{ \
    "data_schema": { \
      "$schema": "http://json-schema.org/draft-07/schema#", \
      "type": "object", \
      "properties": { \
        "restricts": { \
          "type": "object", \
          "properties": { \
            "genres": { \
              "type": "array", \
              "items": { \
                "type": "string" \
              } \
            }, \
            "director": { \
              "type": "array", \
              "items": { \
                "type": "string" \
              } \
            } \
          } \
        }, \
        "restricts_deny": { \
          "type": "object", \
          "properties": { \
            "genres": { \
              "type": "array", \
              "items": { \
                "type": "string" \
              } \
            } \
          } \
        }, \
        "numeric_restricts": { \
          "type": "object", \
          "properties": { \
            "year": { \
              "type": "integer" \
            }, \
            "imdb_rating": { \
              "type": "number", \
              "format": "float" \
            } \
          } \
        }, \
        "embedding_metadata": { \
          "type": "object", \
          "properties": { \
            "plot": { \
              "type": "string" \
            }, \
            "customers_review_summary": { \
              "type": "string" \
            }, \
            "critics_review_summary": { \
              "type": "string" \
            } \
          }, \
        } \
      } \
    }, \
    "vector_schema": { \
      "embedding": { \
        "dense_vector": { \
          "dimensions": 768 \
        } \
      }, \
      "sparse_embedding": { \
        "sparse_vector": {} \
      } \
    } \
  }'

导入 Vector Search 1.0 数据

接下来，对新创建的集合使用 ImportDataObjects API。 将其指向包含 Vector Search 1.0 数据的 Cloud Storage 存储桶。

curl -X POST \
"https://vectorsearch.googleapis.com/v1main/projects/PROJECT_ID/locations/LOCATION/collections/COLLECTION_ID:importDataObjects" \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  -d '{ \
    "gcs_import": { \
      "contents_uri": "gs://your-bucket/path/to/your-data.jsonl", \
      "error_uri": "gs://your-bucket/path/to/import-errors/" \
    } \
  }'

数据转换

在导入过程中，Vector Search 1.0 数据将转换为 Vector Search 2.0 数据对象。以下示例展示了字段的映射方式。

Vector Search 1.0 Cloud Storage 文件格式

{
    "id": "movie-789",
    "embedding": [-0.23, 0.88, 0.11, ...],
    "sparse_embedding": {"values": [0.1, 0.2], "dimensions": [1, 4]},
    "restricts": [
        {"namespace": "genres", "allow": ["science-fiction", "action"], "deny": ["horror"]},
        {"namespace": "director", "allow": ["Christopher Nolan"]}
    ],
    "numeric_restricts": [
        {"namespace": "year", "value_int": 2010},
        {"namespace": "imdb_rating", "value_float": 8.8}
    ],
    "embedding_metadata": {
        "plot": "...",
        "customers_review_summary": "...",
        "critics_review_summary": "..."
    }
}

转换后的 Vector Search 2.0 数据对象

DataObject(
    name="/.../movie-789",
    data={
        "restricts": {
            "genres": ["science-fiction", "action"],
            "director": ["Christopher Nolan"],
        },
        "restricts_deny": {
            "genres": ["horror"]
        },
        "numeric_restricts": {
            "year": 2010,
            "imdb_rating": 8.8,
        },
        "embedding_metadata": {
            "plot": "...",
            "customers_review_summary": "...",
            "critics_review_summary": "...",
        }
    },
    vectors={
        "embedding": {"dense_vector": {"values": [-0.23, 0.88, 0.11, ...]}},
        "sparse_embedding": {"sparse_vector": {"values": [0.1, 0.2], "indices": [1, 4]}},
    }
)