> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/MicrosoftDocs/azure-ai-docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Index for Agentic Retrieval

> Build search indexes optimized for agentic retrieval workloads.

# Create an Index for Agentic Retrieval

Indexes for agentic retrieval require specific configurations to support multi-query patterns and semantic reranking.

## Requirements

<Steps>
  <Step title="Semantic Configuration">
    Required for semantic reranking of subquery results
  </Step>

  <Step title="Vector Fields">
    Recommended for hybrid search across text and embeddings
  </Step>

  <Step title="Filterable Fields">
    Optional but useful for pre-filtering results
  </Step>

  <Step title="Default Scoring Profile">
    Optional for custom relevance tuning
  </Step>
</Steps>

## Index Schema Example

```json theme={null}
{
  "name": "products-index",
  "fields": [
    {
      "name": "productId",
      "type": "Edm.String",
      "key": true
    },
    {
      "name": "description",
      "type": "Edm.String",
      "searchable": true
    },
    {
      "name": "descriptionVector",
      "type": "Collection(Edm.Single)",
      "searchable": true,
      "dimensions": 1536,
      "vectorSearchProfile": "my-vector-profile"
    }
  ],
  "semantic": {
    "defaultConfiguration": "my-semantic-config",
    "configurations": [
      {
        "name": "my-semantic-config",
        "prioritizedFields": {
          "titleField": {"fieldName": "title"},
          "contentFields": [
            {"fieldName": "description"}
          ]
        }
      }
    ]
  }
}
```

## Best Practices

* Use descriptive field names
* Include both text and vector fields for hybrid search
* Configure semantic ranking on most important fields
* Add filters for common query patterns

## Next Steps

<CardGroup cols={2}>
  <Card title="Create Knowledge Source" icon="database" href="/search/agentic/knowledge-sources">
    Wrap your index in a knowledge source
  </Card>

  <Card title="Vector Search" icon="diagram-project" href="/search/concepts/vector-search">
    Add vector capabilities to your index
  </Card>
</CardGroup>