Zenn
🐪

Vertex AI Searchを試す

2023/12/02に公開
Google Cloud
Python
Vertex AI
tech

Cloud FunctionsでVertex AI Searchの動作確認を行いました。

ベクトルデータストアには、サンプルでGCSに公開されているGoogleの決算書を登録します。

cloud-samples-data/gen-app-builder/search/alphabet-investor-pdfs

https://cloud.google.com/generative-ai-app-builder/docs/try-enterprise-search

Cloud Functions

requirements.txt
functions-framework==3.*
google-api-core==2.14.0
google-cloud-discoveryengine==0.11.3
search.py
from typing import List

from google.api_core.client_options import ClientOptions
from google.cloud import discoveryengine_v1 as discoveryengine

# TODO(developer): Uncomment these variables before running the sample.
# project_id = "YOUR_PROJECT_ID"
# location = "YOUR_LOCATION"                    # Values: "global", "us", "eu"
# data_store_id = "YOUR_DATA_STORE_ID"
# search_query = "YOUR_SEARCH_QUERY"

def search_sample(
    project_id: str,
    location: str,
    data_store_id: str,
    search_query: str,
) -> List[discoveryengine.SearchResponse]:
    #  For more information, refer to:
    # https://cloud.google.com/generative-ai-app-builder/docs/locations#specify_a_multi-region_for_your_data_store
    client_options = (
        ClientOptions(api_endpoint=f"{location}-discoveryengine.googleapis.com")
        if location != "global"
        else None
    )

    # Create a client
    client = discoveryengine.SearchServiceClient(client_options=client_options)

    # The full resource name of the search engine serving config
    # e.g. projects/{project_id}/locations/{location}/dataStores/{data_store_id}/servingConfigs/{serving_config_id}
    serving_config = client.serving_config_path(
        project=project_id,
        location=location,
        data_store=data_store_id,
        serving_config="default_config",
    )

    # Optional: Configuration options for search
    # Refer to the `ContentSearchSpec` reference for all supported fields:
    # https://cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1.types.SearchRequest.ContentSearchSpec
    content_search_spec = discoveryengine.SearchRequest.ContentSearchSpec(
        # For information about snippets, refer to:
        # https://cloud.google.com/generative-ai-app-builder/docs/snippets
        snippet_spec=discoveryengine.SearchRequest.ContentSearchSpec.SnippetSpec(
            return_snippet=True
        ),
        # For information about search summaries, refer to:
        # https://cloud.google.com/generative-ai-app-builder/docs/get-search-summaries
        summary_spec=discoveryengine.SearchRequest.ContentSearchSpec.SummarySpec(
            summary_result_count=5,
            include_citations=True,
            ignore_adversarial_query=True,
            ignore_non_summary_seeking_query=True,
        ),
    )

    # Refer to the `SearchRequest` reference for all supported fields:
    # https://cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1.types.SearchRequest
    request = discoveryengine.SearchRequest(
        serving_config=serving_config,
        query=search_query,
        page_size=10,
        content_search_spec=content_search_spec,
        query_expansion_spec=discoveryengine.SearchRequest.QueryExpansionSpec(
            condition=discoveryengine.SearchRequest.QueryExpansionSpec.Condition.AUTO,
        ),
        spell_correction_spec=discoveryengine.SearchRequest.SpellCorrectionSpec(
            mode=discoveryengine.SearchRequest.SpellCorrectionSpec.Mode.AUTO
        ),
    )

    response = client.search(request)
    print(response)

    return response
main.py
import functions_framework
from search import search_sample

@functions_framework.http
def hello_http(request):
    search_sample(
        project_id='xxxxx',
        location='global',
        data_store_id='test-data_xxxxxx',
        search_query='google 2013'
    )
    return 'Hello !'

結果
search_query:'google 2013'からデータストア内の、2013Q4_google_earnings_releaseというタイトルのpdfがベクトル値が近いと判定されて、結果が返ってきました。

# responseの結果（長いので一部のみ）
SearchPager<results {
string_value: "2013Q4_google_earnings_release"
}

https://cloud.google.com/generative-ai-app-builder/docs/preview-search-results

Discussion