搭配使用 Vertex AI Vector Search 和 Vertex AI RAG 引擎

透過集合功能整理內容 你可以依據偏好儲存及分類內容。

from vertexai import rag
import vertexai

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# vector_search_index_name = "projects/{PROJECT_ID}/locations/{LOCATION}/indexes/{INDEX_ID}"
# vector_search_index_endpoint_name = "projects/{PROJECT_ID}/locations/{LOCATION}/indexEndpoints/{INDEX_ENDPOINT_ID}"
# display_name = "test_corpus"
# description = "Corpus Description"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="us-central1")

# Configure embedding model (Optional)
embedding_model_config = rag.RagEmbeddingModelConfig(
    vertex_prediction_endpoint=rag.VertexPredictionEndpoint(
        publisher_model="publishers/google/models/text-embedding-005"
    )
)

# Configure Vector DB
vector_db = rag.VertexVectorSearch(
    index=vector_search_index_name, index_endpoint=vector_search_index_endpoint_name
)

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

from vertexai import rag
import vertexai

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/{PROJECT_ID}/locations/us-central1/ragCorpora/{rag_corpus_id}"
# paths = ["https://drive.google.com/file/123", "gs://my_bucket/my_files_dir"]  # Supports Google Cloud Storage and Google Drive Links

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="us-central1")

response = rag.import_files(
    corpus_name=corpus_name,
    paths=paths,
    transformation_config=rag.TransformationConfig(
        rag.ChunkingConfig(chunk_size=512, chunk_overlap=100)
    ),
    import_result_sink="gs://sample-existing-folder/sample_import_result_unique.ndjson",  # Optional, this has to be an existing storage bucket folder, and file name has to be unique (non-existent).
    max_embedding_requests_per_min=900,  # Optional
)
print(f"Imported {response.imported_rag_files_count} files.")
# Example response:
# Imported 2 files.

from vertexai import rag
import vertexai

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/[PROJECT_ID]/locations/us-central1/ragCorpora/[rag_corpus_id]"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="us-central1")

response = rag.retrieval_query(
    rag_resources=[
        rag.RagResource(
            rag_corpus=corpus_name,
            # Optional: supply IDs from `rag.list_files()`.
            # rag_file_ids=["rag-file-1", "rag-file-2", ...],
        )
    ],
    text="Hello World!",
    rag_retrieval_config=rag.RagRetrievalConfig(
        top_k=10,
        filter=rag.utils.resources.Filter(vector_distance_threshold=0.5),
    ),
)
print(response)
# Example response:
# contexts {
#   contexts {
#     source_uri: "gs://your-bucket-name/file.txt"
#     text: "....
#   ....

from vertexai import rag
from vertexai.generative_models import GenerativeModel, Tool
import vertexai

# TODO(developer): Update and un-comment below lines
# PROJECT_ID = "your-project-id"
# corpus_name = "projects/{PROJECT_ID}/locations/us-central1/ragCorpora/{rag_corpus_id}"

# Initialize Vertex AI API once per session
vertexai.init(project=PROJECT_ID, location="us-central1")

rag_retrieval_tool = Tool.from_retrieval(
    retrieval=rag.Retrieval(
        source=rag.VertexRagStore(
            rag_resources=[
                rag.RagResource(
                    rag_corpus=corpus_name,
                    # Optional: supply IDs from `rag.list_files()`.
                    # rag_file_ids=["rag-file-1", "rag-file-2", ...],
                )
            ],
            rag_retrieval_config=rag.RagRetrievalConfig(
                top_k=10,
                filter=rag.utils.resources.Filter(vector_distance_threshold=0.5),
            ),
        ),
    )
)

rag_model = GenerativeModel(
    model_name="gemini-2.0-flash-001", tools=[rag_retrieval_tool]
)
response = rag_model.generate_content("Why is the sky blue?")
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....
#   ...