【Azure AI Studio】如何在Azure AI Studio中构建和使用向量索引

1. If you don't have an existing connection, choose Connect other Azure AI Search service
2. Select the subscription and the service you wish to use.

Select Next after choosing index storage

Configure your Search Settings

1. The Vector settings defaults to true for Add vector search to this search resource. As noted, this enables Hybrid and Hybrid + Semantic search options. Disabling this limits vector search options to Keyword and Semantic.
2. For the hybrid option to work, you need an embedding model. Choose an embedding model from the dropdown.
3. Select the acknowledgment to deploy an embedding model if it doesn't already exist in your resource

If a non-Azure OpenAI model isn't appearing in the dropdown follow these steps:

1. Navigate to the Project settings in Azure AI Studio.
2. Navigate to connections section in the settings tab and select New connection.
3. Select Serverless Model.
4. Type in the name of your embedding model deployment and select Add connection. If the model doesn't appear in the dropdown, select the Enter manually option.
5. Enter the deployment API endpoint, model name, and API key in the corresponding fields. Then add connection.
6. The embedding model should now appear in the dropdown.

Select Next after configuring search settings

In the Index settings

1. Enter a name for your index or use the autopopulated name
2. Schedule updates. You can choose to update the index hourly or daily.
3. Choose the compute where you want to run the jobs to create the index. You can
   
   • Auto select to allow Azure AI to choose an appropriate VM size that is available
   • Choose a VM size from a list of recommended options
   • Choose a VM size from a list of all possible options

Select Next after configuring index settings

Review the details you entered and select Create

You're taken to the index details page where you can see the status of your index creation.

Open your AI Studio project.

Navigate to the Playground tab.

The Select available project index is displayed for existing indexes in the project. If an existing index isn't being used, continue to the next steps.

Select the Add your data dropdown.

If a new index is being created, select the Add your data option. Then follow the steps from Create an index from the Indexes tab to navigate through the wizard to create an index.

1. If there's an external index that is being used, select the Connect external index option.

2. In the Index Source

   1. Select your data source
   2. Select your AI Search Service
   3. Select the index to be used.

   

3. Select Next after configuring search settings.

4. In the Index settings

   1. Enter a name for your index or use the autopopulated name
   2. Schedule updates. You can choose to update the index hourly or daily.
   3. Choose the compute where you want to run the jobs to create the index. You can
      
      • Auto select to allow Azure AI to choose an appropriate VM size that is available
      • Choose a VM size from a list of recommended options
      • Choose a VM size from a list of all possible options

5. Review the details you entered and select Create.

6. The index is now ready to be used in the Playground.

Sign in to Azure AI Studio and select your project.

From the collapsible left menu, select Prompt flow.

Open an existing prompt flow or select + Create to create a new flow.

On the top menu of the flow designer, select More tools, and then select Index Lookup.

Provide a name for your Index Lookup Tool and select Add.

Select the mlindex_content value box, and select your index. After completing this step, enter the queries and query_types to be performed against the index.