web-app

Vertex AI Search Demo

NOTE: Some of the features in this demo require allowlist access. If you would like early access, apply to become a Trusted Tester for Google Cloud Generative AI.

This demo illustrates how to search through a corpus of documents using Vertex AI Search (formerly known as Enterprise Search).

Additional features include how to search the public Cloud Knowledge Graph using the Enterprise Knowledge Graph API.

Architecture

Google Cloud Products Used

• Vertex AI Search
• Vertex AI Search: Recommendations
• Cloud Run
• Enterprise Knowledge Graph

Setup

• Follow steps in Get started with Vertex AI Search for Unstructured Data.

  • Sample Data Sources used in the deployed demo:
    • Contract Understanding Atticus Dataset (CUAD)
      • gs://cloud-samples-data/gen-app-builder/search/CUAD_v1
    • Alphabet Earnings Reports
      • gs://cloud-samples-data/gen-app-builder/search/alphabet-investor-pdfs

• Follow steps in Get started with Vertex AI Search for Websites

  • Google Cloud site
    • https://cloud.google.com

• Follow steps in Get started with Recommendations for Unstructured Data.

  • Sample Data Sources used in the deployed demo:
    • Natural language papers from ArXiv
      • gs://cloud-samples-data/gen-app-builder/search/arxiv

Dependencies

1. Install Python
2. Install the Google Cloud SDK
3. Install the prerequisites:
   • pip install -r requirements.txt
4. Run gcloud init, create a new project, and enable billing
5. Enable the Vertex AI Search API:
   • gcloud services enable discoveryengine.googleapis.com
6. Enable the Enterprise Knowledge Graph API:
   • gcloud services enable enterpriseknowledgegraph.googleapis.com
7. Enable Cloud Run:
   • gcloud services enable run.googleapis.com
8. Setup application default authentication, run:
   • gcloud auth application-default login

Demo Deployment

1. Update the consts.py file with your own PROJECT_ID and LOCATION.

2. Configure Vertex AI Search

   • To use the prebuilt widget provided in the Cloud Console for Enterprise, Copy the configId from the <gen-search-widget> in the Integration > Widget tab.
     • 
     • Be sure to set authorization type as Public Access and add your web application url to the Allowed Domains once it's deployed.
     • Add the configId for your Search Engines to WIDGET_CONFIGS in consts.py
   • To use the Custom UI, add the datastore id for your search engine to CUSTOM_UI_DATASTORE_IDS in consts.py
     • This is the string after /engines/ in the Cloud Console URL.
       • https://console.cloud.google.com/gen-app-builder/engines/website-search-engine_1681248733152/...
       • Datastore ID is website-search-engine_1681248733152

3. Configure Recommendations

   • Add the datastore id and engine id for your recommendations engine to RECOMMENDATIONS_DATASTORE_IDs in consts.py.
   • The datastore id is visible on the Data > Details page.
   • The engine id is the string after /engines/ in the Cloud Console URL.
     • https://console.cloud.google.com/gen-app-builder/engines/contracts-personalize_1687884886933/data/records
     • Engine ID is contracts-personalize_1687884886933

4. Configure Image Search

   • Follow the instructions in the documentation to enable image search for a website search engine.
     • NOTE: You must enable Advanced Website Indexing which requires domain verification.
   • Add the datastore id for your search engine to IMAGE_SEARCH_DATASTORE_IDs in consts.py.

5. Deploy the Cloud Run app in your project.

   • gcloud run deploy vertex-ai-search-demo --source .

   • To test locally: flask --app main run

6. Visit the deployed web page

   • Example: https://vertex-ai-search-demo-lnppzg3rxa-uc.a.run.app

---

Copyright 2023 Google LLC Author: Holt Skinner @holtskinner