Para optimizar la transición desde Vector Search 1.0, se introdujo una nueva función en la API de ImportDataObjects.
El proceso de migración implica tres pasos clave:
Crea una colección con un esquema coincidente. Antes de importar, debes crear una colección. Su esquema de datos debe estar estructurado para adaptarse a los datos transformados de Vector Search 1.0.
Inicia el proceso de importación. Llama a la API de
ImportDataObjects, especifica la ubicación de Cloud Storage de tus datos de Vector Search 1.0 y habilita la marca de conversióndetect_and_convert_vs1_json.Comprende la transformación de datos. Familiarízate con la forma en que se asignan los campos de datos de Vector Search 1.0 a la nueva estructura de objetos de datos.
Crea una Colección
Primero, crea una colección con un esquema de datos que refleje la estructura de tus datos de Vector Search 1.0.
REST
curl -X POST \
'https://vectorsearch.googleapis.com/v1beta/projects/PROJECT_ID/locations/LOCATION/collections?collection_id=COLLECTION_ID' \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H 'Content-Type: application/json' \
-d '{
"data_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": {}
}
}
}'
Python
from google.cloud import vectorsearch_v1beta
# Create the client
vector_search_service_client = vectorsearch_v1beta.VectorSearchServiceClient()
# The JSON schema for the data
data_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"},
},
},
},
}
# The JSON schema for the vector
vector_schema = {
"embedding": {"dense_vector": {"dimensions": 768}},
"sparse_embedding": {"sparse_vector": {}},
}
collection = vectorsearch_v1beta.Collection(
data_schema=data_schema,
vector_schema=vector_schema,
)
request = vectorsearch_v1beta.CreateCollectionRequest(
parent="projects/PROJECT_ID/locations/LOCATION",
collection_id="COLLECTION_ID",
collection=collection,
)
# Create the collection
operation = vector_search_service_client.create_collection(request=request)
operation.result()
Importa tus datos de Vector Search 1.0
Luego, usa la API de ImportDataObjects en la colección recién creada.
Dirígela al bucket de Cloud Storage que contiene tus datos de Vector Search 1.0.
REST
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/"
}
}'
Python
from google.cloud import vectorsearch_v1beta
# Create the client
vector_search_service_client = vectorsearch_v1beta.VectorSearchServiceClient()
# Initialize request
request = vectorsearch_v1beta.ImportDataObjectsRequest(
name="projects/PROJECT_ID/locations/LOCATION/collections/COLLECTION_ID",
gcs_import={
"contents_uri": "gs://your-bucket/path/to/your-data.jsonl",
"error_uri": "gs://your-bucket/path/to/import-errors/",
},
)
# Make the request
operation = vector_search_service_client.import_data_objects(request=request)
# Wait for the result (note this may take up to several minutes)
operation.result()
Transformación de datos
Durante el proceso de importación, tus datos de Vector Search 1.0 se transformarán en objetos de datos de recuperación del agente. En los siguientes ejemplos, se ilustra cómo se asignan los campos.
Formato de archivo de Cloud Storage de 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": "..."
}
}
Objeto de datos de recuperación del agente transformado
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]}},
}
)