Skip to main content

Azure OpenAI Embedding

Azure OpenAI Embeddings are a way to convert text data into numerical representations that capture semantic meaning. This allows you to find similar text content or compare documents based on their ideas, even if the wording differs.

Getting started with Azure OpenAI Embedding​

Quicksteps- How to use Azure OpenAI Embedding​

  1. Submit the Azure OpenAI Registration form

  2. Create an instance in Azure portal.

  3. Use Azure OpenAI studio to deploy the model.

Detailed steps to create Azure OpenAI Embedding​

  1. Azure openAI requires registration and is currently only available to approved enterprise customers and partners.Submit the Registration form for approval.

  2. Once the submitted form is approved, Navigate to Azure Portal and login.

  3. Search for Azure OpenAI resource and click on create. If the resource is not listed,search in more services.

    img Azure OpenAI LLM

    img Azure OpenAI LLM

  4. Fill all the mandatory fields in Basic section as shown below.

    img Azure OpenAI LLM

  5. Choose the preferred option in the Network section as shown below.

    img Azure OpenAI LLM

  6. Enter the tag name if required, it's an option section.

    img Azure OpenAI LLM

  7. Review the terms and create the resource.

    img Azure OpenAI LLM

  8. After the creation of OpenAI resource, click on Go to Resource

    img Azure OpenAI LLM

  9. Click on Click here to view Endpoints and get the Endpoint and the API Key.

    img Azure OpenAI LLM img Azure OpenAI LLM

  10. To enable to resource, at least one model should be created. Click on the Alert message shown 🞂 Manage Deployments, which navigates to Azure OpenAI Studio. img Azure OpenAI LLM img Azure OpenAI LLM

  11. Create new Deployment as shown below.

    img Azure OpenAI LLM img Azure OpenAI LLM

  12. Get the Model Name and Deployment Name.

    img Azure OpenAI LLM

Setting up the Azure OpenAI connector in Unstract​

Now that we have all the required details, we can use it to set up an embedding profile on the Unstract platform. For this:

  • Sign in to the Unstract Platform

  • From the side navigation menu, choose Settings 🞂 Embedding

  • Click on the New Embedding Profile button.

  • From the list of LLMs, choose AzureOpenAIEmbedding. You should see a dialog box where you enter details.

    img Azure OpenAI LLM

  • For Name, enter a name for this connector

  • For Models, enter the LLM model name used in the deployment.Refer step 12.

  • For Deployment Name, enter the name provided for LLM deployment.Refer step 12.

  • In API Key, enter the key created in the above section.Refer step 9.

  • Leave Max retries, Timeout, API Version to their default values.

  • In Azure Endpoint, enter the LLM deployed endpoint. Refer step 9.

  • Click on Test Connection and ensure it succeeds. You can finally click on Submit and that should create a new Embedding Profile for use in your Unstract projects.