Automatically apply vector embeddings with Azure OpenAI

The Azure OpenAI Embeddings Generator component allows you to automatically apply vector embeddings to specified properties in your documents. When applied, these embeddings can be used to enhance the accuracy of your search results and provide a better natural-language experience for your users.

By integrating your own AI with AutoClassifier, you agree to the Upland AI Disclaimer. This disclaimer appears on all components with AI functionality in the administration portal.

Prerequisites

Note the following prerequisites before configuring the AI Visual Interpreter component:

Configure the component

To configure you component, do the following:

  1. In the AutoClassifier administration portal, Add a new component to a new or existing pipeline.

  2. When adding your component, select Azure OpenAI Embeddings Generator from the New Component list and provide a name for your component.

  3. Click Add Component.

  4. Select your Azure OpenAI Embeddings Generator component from the list.

  5. In the Endpoint URL field, enter the endpoint URL for your Azure OpenAI service resource.

  6. In the API Key field, enter the API key for your Azure Open AI instance.

  7. In the Embedding Property Mappings field, do the following:

    1. In the Input Property Name field, enter the property name that you want to generate vector embeddings for. For example, if you want to generate embeddings for the Body property of your document, enter Body.

    2. In the Output Metadata Name field, enter a name for the metadata that your vectors embeddings will be generated under. For example, BodyEmbeddings.

  8. To generate embeddings for additional properties, click Add New Property Mapping and repeat step 7.

  9. Click Validate Connection to confirm you have a successful connection to your Open AI instance.

  10. Click Save.

Output details

On the Pipeline Testing page, you can test your component configuration. When you do so, the following output properties will be visible:

Output property Description
<OutputMetadataName> This output property displays the generated vector embeddings for the property that you identified in step 7a.