Editing Troubleshooting of Google Vertex AI Search

Resolving Issues with [https://cloud.google.com/enterprise-search?hl=en_us Google Vertex AI Search] and its API

{{LanguageSwitcher | content = [[Troubleshooting of Google Vertex AI API | EN]], [[Troubleshooting of Google Vertex AI Search in Mandarin | 漢字]] }}

== Issues ==

=== Troubleshooting: Vertex AI Search: Data Repository Requires Enterprise Features ===
'''Error:'''
When creating an application, encountered the error message "This application cannot currently use 4 data stores are..."
Expanding the data repository list shows "Website data repository can only be linked to Enterprise version of Vertex AI Search applications"

'''Solution:'''
When creating the application, enable "[https://cloud.google.com/generative-ai-app-builder/docs/about-advanced-features?_gl=1*3htbzk*_ga*ODY1NjExNjI5LjE3MzUyMDY5NDM.*_ga_WH2QY8WWF5*MTczNTYyODg5MS40LjEuMTczNTYyOTQ5Ny4xMS4wLjA. Enterprise Edition Features]"

=== Troubleshooting: SearchLite API Blocked" Error in Discovery Engine ===

'''Issue Description''': When attempting to retrieve search results using Google Vertex AI API<ref>[https://cloud.google.com/generative-ai-app-builder/docs/preview-search-results Get search results  |  Vertex AI Agent Builder  |  Google Cloud]</ref>, the following error occurs:

<pre>
curl -X POST -H "Content-Type: application/json" \
"https://discoveryengine.googleapis.com/v1/projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search:searchLite?key=API_KEY" \
-d '{
"servingConfig": "projects/PROJECT_ID/locations/global/collections/default_collection/engines/APP_ID/servingConfigs/default_search",
"query": "QUERY",
}'
</pre>

Met the error
<pre>
{
  "code" : 403,
  "message" : "Requests to this API discoveryengine.googleapis.com method google.cloud.discoveryengine.v1.SearchService.SearchLite are blocked.",
  "status" : "PERMISSION_DENIED",
  "details" : [
    {
      "@type" : "type.googleapis.com/google.rpc.ErrorInfo",
      "reason" : "API_KEY_SERVICE_BLOCKED",
      "domain" : "googleapis.com",
      "metadata" : {
        "service" : "discoveryengine.googleapis.com",
        "methodName" : "google.cloud.discoveryengine.v1.SearchService.SearchLite",
        "apiName" : "discoveryengine.googleapis.com",
        "consumer" : "projects/xxx"
      }
    },
    {
      "@type" : "type.googleapis.com/google.rpc.LocalizedMessage",
      "locale" : "en-US",
      "message" : "Requests to this API discoveryengine.googleapis.com method google.cloud.discoveryengine.v1.SearchService.SearchLite are blocked."
    }
  ]
}
</pre>

'''Resolution Steps''': Check API Key Restrictions

* Verify if the key is restricted to specific APIs:
*# Navigate to the API Key Management page in Google Cloud Console.
*# Locate the API key being used and check if it is restricted to specific APIs. If the restriction includes discoveryengine.googleapis.com, ensure it is correctly configured.
*# Remove unnecessary restrictions: If the key is restricted to unrelated IP addresses or applications, remove those restrictions.
* Enable the {{kbd | key=Discovery Engine API}}
*# Go to the API & Services page in Google Cloud Console.
*# Search for Discovery Engine API and ensure it is enabled.

=== Troubleshooting: "Requested Entity Already Exists" Error When Saving Data Stores ===

'''Error:'''
When saving site indexing, the following error message appears<ref>[https://cloud.google.com/datastore/docs/concepts/errors Errors and Error Handling  |  Cloud Datastore Documentation  |  Google Cloud]</ref>:
<pre>
Failed to save sites
Requested entity already exists
Tracking number: <mix of English and numeric characters>
</pre>

'''Root Cause:'''
Conflicting URL patterns exist simultaneously in "Specify URL patterns to index":
<pre>
example.com
</pre>
and
<pre>
*.example.com/*
</pre>

These two patterns conflict with each other, causing the system to treat them as duplicate entities. The detailed linking rules are mentioned in the official documentation:
<pre>
You can use the operations listed below
Entire site: www.mysite.com/*
Parts of site: www.mysite.com/faq/*
Entire domain: *.mysite.com/*
Quotes for exact match: "www.mysite.com/faq"
Sites without quotes will match any path after the specified address:
www.mysite.com/faq → www.mysite.com/faq*.
</pre>

'''Solution:'''
Simply remove one of the patterns to resolve the issue. It's recommended to keep the broader pattern <code>*.example.com/*</code> as it already includes <code>example.com</code>.

=== Troubleshooting: "Quota exceeded for Search lite requests" Error in Discovery Engine ===

'''Issue Description''':  
When using Discovery Engine API to retrieve search results, the following error occurs:

<pre>
{
  "error" : {
    "code" : 429,
    "message" : "Quota exceeded for quota metric 'Search lite requests' and limit 'Search lite requests per minute' of service 'discoveryengine.googleapis.com' for consumer 'project_number:XXX'.",
    "status" : "RESOURCE_EXHAUSTED",
    ...
  }
}
</pre>

'''Root cause:'''

The metadata in the error response has indicated that the quota value is '''100 requests per minute'''

'''Resolution Steps''': Resolve API Quota Limit Exceedance

Option 1: Increase the delay time between requests

# Implement this timing delay in your code to prevent 429 errors. 60 seconds ÷ 100 requests = 0.6 seconds per request e.g. Add a 0.6 ~ 1 second pause between each request to stay within rate limits
# Adjust the delay time as needed based on your quota and request patterns

Option 2: Increase quota limit

# Go to the Quotas page in Google Cloud Console and find "Search lite requests per minute"
# Select the relevant quota, click "EDIT QUOTAS", and submit a request for a higher limit
# Wait for Google Cloud Support to review and approve

Option 3: Implement exponential backoff retry mechanism

# Detect HTTP 429 errors in your application and set an initial delay (e.g., 1 second)
# Increase the delay time with each failed retry (e.g., 2 seconds, 4 seconds, 8 seconds, etc.)
# Continue retrying until the request succeeds or maximum retry count is reached


=== Troubleshooting: Vertex AI Search: Engine Not Found Error ===

'''Error:'''
When using Vertex AI Search API, encountering a 404 error:
<pre>
{
  "error": {
    "code": 404,
    "message": "Engine projects/<YOUR_PROJECT_ID>/locations/global/collections/default_collection/engines/<YOUR_APP_ID> not found.",
    "status": "NOT_FOUND"
  }
}
</pre>

'''Solution:'''

1. Verify the correct APP ID (Engine ID):
Open your browser and replace {{kbd | key=<nowiki><YOUR_APP_ID></nowiki>}} in the URL with the actual APP ID:
<pre>
https://console.cloud.google.com/gen-app-builder/locations/global/engines/<YOUR_APP_ID>/overview
</pre>

2. Update the app_id in your code:

3. Validate the API endpoint: Ensure the curl request uses the correct engine ID:

<pre>
curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
"https://discoveryengine.googleapis.com/v1alpha/projects/<YOUR_PROJECT_ID>/locations/global/collections/default_collection/engines/<YOUR_APP_ID>/servingConfigs/default_search:search" \
-d '{"query":"<QUERY>","pageSize":10,"queryExpansionSpec":{"condition":"AUTO"},"spellCorrectionSpec":{"mode":"AUTO"},"languageCode":"zh-TW","userInfo":{"timeZone":"Asia/Taipei"}}'
</pre>


=== Troubleshooting: Vertex AI Search: Path Format Error When Enabling Grounding ===

Error encountered when enabling "[https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-vertex-ai-search Grounding with Vertex AI Search]":

'''Error message:'''
<pre>
Path must follow this format: projects/{project_id}/locations/{location}/collections/{collection_name}/dataStores/{datastore_name}
</pre>

'''Solution:''' How to find the correct path parameters:

# Navigate to https://console.cloud.google.com/gen-app-builder/engines
# Select your datastore
# Click the "Integration" tab
# Look for the example command under "Run sample request in Cloud Shell"

Example curl command:
<pre>
curl -X POST -H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
"https://discoveryengine.googleapis.com/v1alpha/projects/987654321000/locations/global/collections/default_collection/engines/vertex-search_123/servingConfigs/default_search:search" \
-d '{"query":"<QUERY>","pageSize":10,"queryExpansionSpec":{"condition":"AUTO"},"spellCorrectionSpec":{"mode":"AUTO"},"languageCode":"zh-TW","userInfo":{"timeZone":"Asia/Taipei"}}'
</pre>

Parameter extraction from the URL:
From the URL path 

{{kbd | key=<nowiki>/projects/987654321000/locations/global/collections/default_collection/engines/vertex-search_123/</nowiki>}}

# {project_id}: `987654321000` (the number after `/projects/`)
# {location}: `global` (the string after `/locations/`) {{exclaim}} Note: Do not enter the [https://cloud.google.com/compute/docs/regions-zones geographic areas] of GCP server. You will met the error message e.g. "Invalid location in serving config: asia-east1"
# {collection_name}: `default_collection` (the string after `/collections/`)
# {datastore_name}: Found on the datastore overview page as "Datastore ID" (e.g., `XXX_1234567890123`) {{exclaim}} Note: The datastore_name is not visible in the engine URL - you need to check the datastore overview page to find the "Datastore ID".


=== Troubleshooting: Vertex AI Discovery Engine: Search Returns No Results ===

Issue encountered when searching with keywords against a Vertex AI Discovery Engine Data Store: the query executes successfully but returns no content.

'''Symptom:'''
The API responds with empty result arrays:
<pre>
{
  "attributionToken" : "xxxx",
  "guidedSearchResult" : [],
  "summary" : [],
  "semanticState" : "DISABLED"
}
</pre>

'''Cause:''' The query syntax is correct, but the target website is outside the indexing scope of the Data Store specified by the Vertex API. For example, attempting to search <code>aaa.com</code> while the Data Store only indexes <code>example.com</code> will return no results, since the engine can only retrieve content it has actually crawled and indexed.

'''Solution:''' Verify and expand the indexed website scope:

# Navigate to https://console.cloud.google.com/gen-app-builder
# Open the Data Store referenced by your Vertex API call
# Check the configured website scope under the "Data" tab
# Confirm whether the target domain (e.g., `aaa.com`) is included

If the target domain is not covered, you must create a dedicated Data Store for it:

# In '''GCP Console → Vertex AI Search''', create a new Data Store for `aaa.com`
# Configure '''website crawling''' for that domain 

{{exclaim}} Note: Each Data Store indexes only its own configured site list — a query cannot reach content outside the Data Store's crawl scope, regardless of how correct the query syntax is.

== Related Pages ==
* [[Customized Search Engine]] written in Mandarin
* [[Troubleshooting of curl errors]] if you are using curl command.
* [[Troubleshooting of HTTP errors]]

== Further readings ==
* [https://www.youtube.com/watch?v=cPJIHHbDdGk&t=1s Building an Enterprise Search app using Vertex AI Search on Google Cloud (Demo) - YouTube]
* [https://cloud.google.com/vertex-ai/generative-ai/docs/grounding/grounding-with-vertex-ai-search Grounding with Vertex AI Search  |  Generative AI on Vertex AI  |  Google Cloud]

== References ==
<references />

[[Category: Search]] [[Category: Google]] [[Category: Revised with LLMs]]