------------------------------
Title: Vertex Search and Conversation
[content]
Vertex AI Search is a fully-managed platform, powered by large language models, that lets you build AI-enabled search and recommendation experiences for your public or private websites or mobile applications. For a thorough understanding of the methodology and procedures associated with the creation, deployment, maintenance, and monitoring of a Vertex AI Search instance, please refer to the Vertex AI Search and Conversation documentation.There are many options to DIY a Search/Chat bot … BUT Demos are easy, Production is hard.The following are the steps involved in constructing a Retrieval-Augmented Generation (RAG) search application:The utilization of managed Vertex AI Search by Google Cloud considerably streamlines this process.Follow the simple steps to build your datastores and engines, then load and query the data in GCP Vertex AI Search and Conversation platform.What we are going to BuildDatastores and Engines from TerraformLoad data and query from pythonStep 1:# Create Test DataStoreresource "google_discovery_engine_data_store" "test-ds" {  location = "global"  data_store_id = "test-data-store-id"  display_name = "test-unstructured-datastore"  industry_vertical = "GENERIC"  content_config = "CONTENT_REQUIRED"  solution_types = ["SOLUTION_TYPE_SEARCH"]  create_advanced_site_search = false  project = <PROJECT ID>}# Create Test Serach Engineresource "google_discovery_engine_search_engine" "test-engine" {  engine_id = "test_engine_id"  collection_id = "default_collection"  location = google_discovery_engine_data_store.test-ds.location  display_name = "test-engine"  industry_vertical = "GENERIC"  data_store_ids = [google_discovery_engine_data_store.test-ds.data_store_id]  common_config {  company_name = "Test Company"  }search_engine_config {  search_add_ons = ["SEARCH_ADD_ON_LLM"]  }project = <PROJECT ID>}# Output resource Id'soutput "test_data_store_id" {  value =resource.google_discovery_engine_data_store.test-ds.data_store_id}output "test_engine_id" {  value = resource.google_discovery_engine_search_engine.test-engine.engine_id}RunPlugin project ID in above terraform code and run below commandsterraform initterraform planterraform applyIf you running terraform with your own GCP identity you will run into an error like below.Error: Error creating DataStore: googleapi: Error 403: Your application is authenticating by using local Application Default Credentials. The discoveryengine.googleapis.com API requires a quota project, which is not set by default. To learn how to set your quota project, see https://cloud.google.com/docs/authentication/adc-troubleshooting/user-creds .Add provider block to specify billing project. billing project and project where datastores are created can be same.provider "google" {  project         = <PROJECT ID>  // Your actual GCP project ID  user_project_override = true   billing_project = <BILLING PROJECT ID> // The project used for quota}Once terraform is successful you can login to GCP Console -> Vertex Search and ConversationConfirm an App named “test-engine” is createdConfirm an empty datastore named “test-unstructured-datastore” is createdStep 2:Create load_data.py with below contents. Plug in project Id and Datastore ID (output from terraform)from google.cloud import storagefrom google.api_core.client_options import ClientOptionsfrom google.cloud import discoveryengine_v1alpha as discoveryenginedef import_documents(    project_id: str,    location: str,    data_store_id: str,    gcs_uri: str,):    # Create a client    client_options = (        ClientOptions(            api_endpoint=f"{location}-discoveryengine.googleapis.com")        if location != "global"        else None    )    client = discoveryengine.DocumentServiceClient(        client_options=client_options)    # The full resource name of the search engine branch.    # e.g. projects/{project}/locations/{location}/dataStores/{data_store_id}/branches/{branch}    parent = client.branch_path(        project=project_id,        location=location,        data_store=data_store_id,        branch="default_branch",    )    source_documents = [f"{gcs_uri}/*"]    request = discoveryengine.ImportDocumentsRequest(        parent=parent,        gcs_source=discoveryengine.GcsSource(            input_uris=source_documents, data_schema="content"        ),        # Options: `FULL`, `INCREMENTAL`        reconciliation_mode=discoveryengine.ImportDocumentsRequest.ReconciliationMode.INCREMENTAL,    )    # Make the request    operation = client.import_documents(request=request)    response = operation.result()    # Once the operation is complete,    # get information from operation metadata    metadata = discoveryengine.ImportDocumentsMetadata(operation.metadata)    # Handle the response    return operation.operation.namesource_documents_gs_uri = (    "gs://cloud-samples-data/gen-app-builder/search/alphabet-investor-pdfs")PROJECT_ID = <PROJECT ID>DATASTORE_ID = <DATASTORE ID>LOCATION = "global"print(" Starting loading data into datastore")import_documents(PROJECT_ID, LOCATION, DATASTORE_ID, source_documents_gs_uri)print(" Completed loading data into datastore")Create search_data.py with below contents. Plug in project Id and Datastore ID (output from terraform)from google.cloud import storagefrom google.api_core.client_options import ClientOptionsfrom google.cloud import discoveryengine_v1alpha as discoveryenginefrom typing import Listdef 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)    return responseQUERY = "Who is the CEO of Google?"PROJECT_ID = <PROJECT ID>DATASTORE_ID = <DATASTORE ID>LOCATION = "global"print(search_sample(PROJECT_ID, LOCATION, DATASTORE_ID, QUERY).summary.summary_text)Output of above python script should print the summary for the query.Do create datastores and engines in python refer to this Github ResourceVertex Search and Conversation was originally published in Google Cloud - Community on Medium, where people are continuing the conversation by highlighting and responding to this story.
[/content]

Author: Anita Gutta
PublishedDate: 2024-04-08
Category: Blogs
NewsPaper: Google Cloud - Medium
Tags: google-cloud-platform, gcp-chat-bots, conversational-ai, machine-learning, vertex-search