在 RAG 引擎中使用 Vertex AI 特徵儲存庫

from google.cloud import aiplatform
from vertexai.resources.preview import feature_store


def create_optimized_public_feature_online_store_sample(
    project: str,
    location: str,
    feature_online_store_id: str,
):
    aiplatform.init(project=project, location=location)
    fos = feature_store.FeatureOnlineStore.create_optimized_store(
        feature_online_store_id
    )
    return fos

from google.cloud import aiplatform
from vertexai.resources.preview import feature_store


def create_feature_view_from_rag_source(
    project: str,
    location: str,
    existing_feature_online_store_id: str,
    feature_view_id: str,
    bq_table_uri: str,
):
    aiplatform.init(project=project, location=location)
    fos = feature_store.FeatureOnlineStore(existing_feature_online_store_id)
    fv = fos.create_feature_view(
        name=feature_view_id,
        source=feature_store.utils.FeatureViewVertexRagSource(uri=bq_table_uri),
    )
    return fv

import agentplatform
from agentplatform import types

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# feature_view_name = "projects/{PROJECT_ID}/locations/{LOCATION}/featureOnlineStores/{FEATURE_ONLINE_STORE_ID}/featureViews/{FEATURE_VIEW_ID}"
# display_name = "test_corpus"
# description = "Corpus Description"

# Initialize Agent Platform client once per session.
# See https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/rag-engine/rag-overview#supported-regions
client = agentplatform.Client(project=PROJECT_ID, location="us-east5")

# Configure embedding model (Optional)
backend_config = types.RagVectorDbConfig(
    rag_embedding_model_config=types.RagEmbeddingModelConfig(
        vertex_prediction_endpoint=types.RagEmbeddingModelConfigVertexPredictionEndpoint(
            endpoint="publishers/google/models/text-embedding-005"
        ),
    ),
    vertex_feature_store=types.RagVectorDbConfigVertexFeatureStore(
        feature_view_resource_name=feature_view_name
    )
)

corpus = client.rag.create_corpus(
    rag_corpus=types.RagCorpus(
        display_name=display_name,
        description=description,
        rag_vector_db_config=backend_config,
    )
)
print(corpus)
# Example response:
# RagCorpus(name='projects/1234567890/locations/us-central1/ragCorpora/1234567890',
# display_name='test_corpus', description='Corpus Description', embedding_model_config=...
# ...

import agentplatform
from agentplatform import types

from google.genai import types as genai_types

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/{PROJECT_ID}/locations/us-east5/ragCorpora/{rag_corpus_id}"
# paths = ["gs://my_bucket/my_files_dir/*"]

# Initialize Agent Platform client once per session.
# See https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/rag-engine/rag-overview#supported-regions
client = agentplatform.Client(project=PROJECT_ID, location="us-east5")

response = client.rag.import_files(
    name=corpus_name,
    import_config=types.ImportRagFilesConfig(
        gcs_source=genai_types.GcsSource(uris=paths),
        rag_file_transformation_config=types.RagFileTransformationConfig(
            rag_file_chunking_config=types.RagFileChunkingConfig(
                chunk_size=512,
                chunk_overlap=100,
            )
        ),  # optional
        max_embedding_requests_per_min=900,  # optional
    ),
)

print(f"Imported {response.imported_rag_files_count} files.")
# Example response:
# Imported 2 files.

import agentplatform

from agentplatform import types
from google.genai import types as genai_types

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/[PROJECT_ID]/locations/us-east5/ragCorpora/[rag_corpus_id]"

# Initialize Agent Platform client once per session.
# See https://docs.cloud.google.com/gemini-enterprise-agent-platform/build/rag-engine/rag-overview#supported-regions
client = agentplatform.Client(project=PROJECT_ID, location="us-east5")

response = client.rag.retrieve_contexts(
    vertex_rag_store=genai_types.VertexRagStore(
        rag_resources=[
            genai_types.VertexRagStoreRagResource(
                rag_corpus=corpus_name,
                # Optional: supply IDs from `rag.list_files()`.
                # rag_file_ids=["rag-file-1", "rag-file-2", ...],
            )
        ],
    ),
    query=types.RagQuery(
        text="Hello World!",
        rag_retrieval_config=genai_types.RagRetrievalConfig(
            top_k=10,
            filter=genai_types.RagRetrievalConfigFilter(
                vector_distance_threshold=0.5
            ),
        ),
    )
)
print(response)
# Example response:
# contexts {
#   contexts {
#     source_uri: "gs://your-bucket-name/file.txt"
#     text: "....
#   ....

from google import genai
from google.genai import types as genai_types

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/{PROJECT_ID}/locations/us-east5/ragCorpora/{rag_corpus_id}"

rag_retrieval_tool = genai_types.Tool(
    retrieval=genai_types.Retrieval(
        vertex_rag_store=genai_types.VertexRagStore(
            rag_resources=[
                genai_types.VertexRagStoreRagResource(
                    rag_corpus=corpus_name
                )
            ],
            rag_retrieval_config=genai_types.RagRetrievalConfig(
                top_k=10,
                filter=genai_types.RagRetrievalConfigFilter(
                    vector_distance_threshold=0.5
                ),
            ),
        ),
    )
)

# Create a GenAI SDK client to make a generate_content request
genai_client = genai.Client(vertexai=True, project=PROJECT_ID, location="global")

response = genai_client.models.generate_content(
    model="gemini-3.8-flash",
    contents="Why is the sky blue?",
    config=genai_types.GenerateContentConfig(
        tools=[rag_retrieval_tool]
    ),
)
print(response.text)
# Example response:
#   The sky appears blue due to a phenomenon called Rayleigh scattering.
#   Sunlight, which contains all colors of the rainbow, is scattered
#   by the tiny particles in the Earth's atmosphere....
#   ...