Bermigrasi dari Vector Search 1.0

Untuk menyederhanakan transisi dari Vector Search 1.0, fitur baru telah diperkenalkan ke ImportDataObjects API.

Proses migrasi melibatkan tiga langkah utama:

  1. Buat Kumpulan dengan skema yang cocok. Sebelum mengimpor, Anda harus membuat Koleksi. Skema datanya harus terstruktur untuk mengakomodasi data Vector Search 1.0 yang telah diubah.

  2. Mulai proses impor. Panggil API ImportDataObjects, dengan menentukan lokasi Cloud Storage data Vector Search 1.0 Anda dan mengaktifkan tanda konversi detect_and_convert_vs1_json.

  3. Memahami transformasi data. Pahami cara kolom data Vector Search 1.0 dipetakan ke struktur Objek Data baru.

Buat Koleksi

Pertama, buat Koleksi dengan skema data yang mencerminkan struktur data Vector Search 1.0 Anda.

curl -X POST \
  'https://vectorsearch.googleapis.com/v1beta/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": {} \
      } \
    } \
  }'

Mengimpor data Vector Search 1.0

Selanjutnya, gunakan ImportDataObjects API pada koleksi yang baru dibuat. Arahkan ke bucket Cloud Storage yang berisi data Vector Search 1.0 Anda.

curl -X POST \
"https://vectorsearch.googleapis.com/v1beta/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/" \
    } \
  }'

Transformasi data

Selama proses impor, data Penelusuran Vektor 1.0 Anda akan diubah menjadi Objek Data Penelusuran Vektor 2.0. Contoh berikut menggambarkan cara kolom dipetakan.

Format file Cloud Storage Vector Search 1.0

{
    "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": "..."
    }
}

Objek Data Vector Search 2.0 yang Ditransformasi

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]}},
    }
)