Bring your own chunks/vectors from Trieve

Use existing chunks/vectors from Trieve

Vapi supports Trieve as a knowledgebase provider, allowing you to leverage your existing document embeddings and chunks. While Vapi maintains its own storage of documents and vectors, you can seamlessly integrate with your Trieve datasets.

Use Cases

Existing Knowledge Base Migration

If you’ve already invested time in building and organizing your knowledge base in Trieve, you can continue using those vectors without having to reprocess your documents. This is particularly useful for:

  • Large document collections that took significant time to process
  • Carefully curated and cleaned datasets
  • Custom-chunked documents with specific segmentation rules

Parallel Systems

You might want to use both Trieve’s native interface and Vapi simultaneously:

  • Use Trieve’s UI for content management and organization
  • Leverage Vapi’s chat interface and API capabilities
  • Maintain consistency across both platforms

Integration Steps

  1. Configure Trieve Credentials

    • Navigate to the credentials page in your Vapi dashboard
    • Add your Trieve API key for authentication from Trieve

  2. Create a New Knowledge Base

    • When setting up a new knowledge base, provide:
      • Your Trieve datasetId as the vectorStoreProviderId
      • Appropriate search configuration parameters
    • Vapi will then connect to your existing Trieve vectors

    Example configuration:

    1{
    2  "name": "byok-test",
    3  "provider": "trieve",
    4  "vectorStoreSearchPlan": {
    5    "scoreThreshold": 0.2,
    6    "searchType": "semantic"
    7  },
    8  "vectorStoreProviderId": "<Your datasetId from Trieve>"
    9}

Best Practices

  • Ensure your Trieve API key has appropriate permissions
  • Keep track of which datasetIds correspond to which knowledge bases
  • Monitor vector synchronization to ensure consistency
Built with