Vertex AI Vector Search

Overview

Vector search engine with semantic search capabilities. Through Langdock’s integration, you can access and manage Vertex AI Vector Search directly from your conversations.

Authentication: Service Account Category: AI & Search Availability: All workspace plans

Available Actions

Search vector index

vertexaivectorsearch.searchvectorindex

Searches the database for the most relevant information based on the query provided

Requires Confirmation: No

Parameters:

• query (VECTOR, Required): The search query for vector similarity search

  • publicDomainName (TEXT, Required): The public domain name of the vector index you want to query can be found in Google Cloud Console: Vertex AI → Vector Search → Index Endpoints → [Your Endpoint] → Endpoint info

  • projectIdNumber (TEXT, Required): The id is the “name” of your google project, number is the associated number, you can find both in the Google Cloud Console -> click the settings at utilities in the top right -> in open menu click “Project Settings” -> you’ll see both Project ID and Project Number listed

  • region (TEXT, Required): The region of the index / vector database you want to query, can be found in Google Cloud Console: Vertex AI → Vector Search → Index Endpoints → [Your Endpoint] → Endpoint info, example format: us-central1

  • indexEndpointId (TEXT, Required): The unique identifier of your Index / vector database, can be found in Google Cloud Console: Vertex AI → Vector Search → Index Endpoints → [Your Endpoint] → Endpoint info

  • deployedIndexId (TEXT, Required): The deployment name of your Index / vector database, can be found in Google Cloud Console: Vertex AI → Vector Search → Index Endpoints → [Your Endpoint] → Endpoint info -> Deployed index column in the table

Output: Returns the most relevant search results from the vector index

---

Common Use Cases

• Data Management Manage and organize your Vertex AI Vector Search data

• Automation Automate workflows with Vertex AI Vector Search

• Reporting Generate insights and reports

• Integration Connect Vertex AI Vector Search with other tools

Best Practices

1

Getting Started

• Enable the Vertex AI Vector Search integration in your workspace settings

• Authenticate using Service Account

• Test the connection with a simple read operation

• Explore available actions for your use case

2

Important Considerations

• Ensure proper authentication credentials

• Respect rate limits and API quotas

• Review data privacy settings

• Test operations in a safe environment first

Troubleshooting

Issue	Solution
Authentication failed	Verify your Service Account credentials
Rate limit exceeded	Reduce request frequency
Data not found	Check permissions and data availability
Connection timeout	Verify network connectivity

Support

For additional help with the Vertex AI Vector Search integration, contact [email protected]