Integrate a Custom Embedding Model

Connect your own embedding model to control how Search AI vectorizes text, enabling domain-specific embeddings or compliance with data privacy requirements.

Supported Vector Dimensions

Your embedding model must output one of these vector sizes:

Supported Sizes
128, 256, 384, 512, 768, 1024, 1028, 1536, 2048, 3072

Integration Steps

Step 1: Configure the Model

1. Go to Generative AI Tools > Model Library
2. Click +New Model and select Custom Integration
3. In the Configurations tab, provide:

Field	Description
Integration Name	Unique identifier for this integration
Model Name	Your model name (e.g., text-embedding-ada-002)
Endpoint	API endpoint that returns embeddings
Auth	Authorization profile (if required)
Headers	Any required request headers

4. Click Next and enter your Request Prompt (the payload sent to the model):

{
  "input": "The food was delicious and the waiter...",
  "model": "text-embedding-ada-002",
  "encoding_format": "float"
}

5. Click Test to verify the response, then Save

Step 2: Create a Custom Prompt

1. Go to Generative AI Tools > Prompt Library
2. Click +New Prompt and configure:

Field	Description
Name	Unique identifier for this prompt
Feature	Select Vector Generation
Model	Select your custom model from Step 1

3. Define the Request using the {{embedding_input}} variable:

{
  "input": "{{embedding_input}}",
  "model": "text-embedding-ada-002",
  "encoding_format": "float"
}

4. Enter sample values and click Test
5. In the Response, double-click the field containing the embeddings array to set the Text Response Path

The selected field must contain an array of numbers:

{
  "data": [
    {
      "embedding": [-0.022822052, 0.01614314, 0.008042404, ...]
    }
  ]
}

6. Click Save

If the response format doesn’t match, use a post-processor script to transform it.

Step 3: Enable the Model

1. Go to GenAI Features
2. For Vector Generation:
   • Select the model from Step 1
   • Select the prompt from Step 2
3. Enable the feature

Search AI now uses your custom embedding model.

Fine-Tuning Embedding Models

For improved relevance, fine-tune embedding models with your domain-specific data using the Fine-Tune Embedding Utility from the Search AI Toolkit.