policy.xml

<policies>
    <inbound>
        <base />
        <!-- Check the embeddings in the Redis cache for a cached prompt response according to the score threshold. If successful, the policy automatically moves past the azure-openai-semantic-cache-store policy. -->
        <azure-openai-semantic-cache-lookup score-threshold="0.8" embeddings-backend-id ="embeddings-backend" embeddings-backend-auth ="system-assigned" />
        <authentication-managed-identity resource="https://cognitiveservices.azure.com" output-token-variable-name="managed-id-access-token" ignore-error="false" />
        <set-header name="Authorization" exists-action="override">
            <value>@("Bearer " + (string)context.Variables["managed-id-access-token"])</value>
        </set-header>
        <set-backend-service backend-id="{backend-id}" />
    </inbound>
    <backend>
        <base />
    </backend>
    <outbound>
        <!-- Cache the Gen AI response in Redis for 2 minutes -->
        <azure-openai-semantic-cache-store duration="120" />
        <base />
    </outbound>
    <on-error>
        <base />
    </on-error>
</policies>