policy.xml

<policies>
    <inbound>
        <base />
        <!-- Getting the main variable where we keep the list of backends -->
        <cache-lookup-value key="listBackends" variable-name="listBackends" />
        <!-- If we can't find the variable, initialize it -->
        <choose>
            <when condition="@(context.Variables.ContainsKey("listBackends") == false)">
                <!-- Variable with the load balancer config stored in a named value -->
                <set-variable name="loadBalancerConfig" value="{{openai-lb-config}}" />
                <set-variable name="listBackends" value="@{
                    // -------------------------------------------------
                    // ------- Explanation of backend properties -------
                    // -------------------------------------------------
                    // "name":         Name of the backend
                    // "priority":     Lower value means higher priority over other backends.
                    //                 If you have more one or more Priority 1 backends, they will always be used instead
                    //                 of Priority 2 or higher. Higher values backends will only be used if your lower values (top priority) are all throttling.
                    // "isThrottling": Indicates if this endpoint is returning 429 (Too many requests) currently
                    // "retryAfter":   We use it to know when to mark this endpoint as healthy again after we received a 429 response

                    var openAIConfig = JArray.Parse((string)context.Variables["loadBalancerConfig"]);
                    JArray backends = new JArray();
                    foreach (JObject config in openAIConfig)
                    {
                        backends.Add(new JObject()
                        {
                            { "name", config.GetValue("name").ToString() },
                            { "priority", config.GetValue("priority").Value<int>() },
                            { "weight", config.GetValue("weight").Value<int>() },
                            { "isThrottling", false },
                            { "retryAfter", DateTime.MinValue }
                        });
                    }
                    return backends;
                }" />
                <!-- And store the variable into cache again -->
                <cache-store-value key="listBackends" value="@((JArray)context.Variables["listBackends"])" duration="60" />
            </when>
        </choose>
        <set-variable name="backendIndex" value="-1" />
        <set-variable name="remainingBackends" value="1" />
        <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>
    </inbound>
    <backend>
        <retry condition="@(context.Response != null && (context.Response.StatusCode == 429 || context.Response.StatusCode >= 500) && (Convert.ToInt32(context.Variables["remainingBackends"]) > 0))" count="50" interval="0">
            <!-- Before picking the backend, let's verify if there is any that should be set to not throttling anymore -->
            <set-variable name="listBackends" value="@{
                JArray backends = (JArray)context.Variables["listBackends"];

                for (int i = 0; i < backends.Count; i++)
                {
                    JObject backend = (JObject)backends[i];

                    if (backend.Value<bool>("isThrottling") && DateTime.Now >= backend.Value<DateTime>("retryAfter"))
                    {
                        backend["isThrottling"] = false;
                        backend["retryAfter"] = DateTime.MinValue;
                    }
                }

                return backends;
            }" />
            <cache-store-value key="listBackends" value="@((JArray)context.Variables["listBackends"])" duration="60" />
            <!-- This is the main logic to pick the backend to be used -->
            <set-variable name="backendIndex" value="@{
                JArray backends = (JArray)context.Variables["listBackends"];

                int selectedPriority = Int32.MaxValue;
                List<int> availableBackends = new List<int>();

                for (int i = 0; i < backends.Count; i++)
                {
                    JObject backend = (JObject)backends[i];

                    if (!backend.Value<bool>("isThrottling"))
                    {
                        int backendPriority = backend.Value<int>("priority");

                        if (backendPriority < selectedPriority)
                        {
                            selectedPriority = backendPriority;
                            availableBackends.Clear();
                            availableBackends.Add(i);
                        }
                        else if (backendPriority == selectedPriority)
                        {
                            availableBackends.Add(i);
                        }
                    }
                }

                if (availableBackends.Count == 1)
                {
                    return availableBackends[0];
                }

                if (availableBackends.Count > 0)
                {
                    //Returns a random backend from the list if we have more than one available with the same priority
                    return availableBackends[new Random().Next(0, availableBackends.Count)];
                }
                else
                {
                    //If there are no available backends, the request will be sent to the first one
                    return 0;
                }
                }" />
            <set-backend-service backend-id="@(((JObject)((JArray)context.Variables["listBackends"])[(Int32)context.Variables["backendIndex"]]).Value<string>("name"))" />
            <forward-request buffer-request-body="true" />
            <choose>
                <!-- In case we got 429 or 5xx from a backend, update the list with its status -->
                <when condition="@(context.Response != null && (context.Response.StatusCode == 429 || context.Response.StatusCode >= 500) )">
                    <cache-lookup-value key="listBackends" variable-name="listBackends" />
                    <set-variable name="listBackends" value="@{
                        JArray backends = (JArray)context.Variables["listBackends"];
                        int currentBackendIndex = context.Variables.GetValueOrDefault<int>("backendIndex");
                        int retryAfter = Convert.ToInt32(context.Response.Headers.GetValueOrDefault("Retry-After", "-1"));

                        if (retryAfter == -1)
                        {
                            retryAfter = Convert.ToInt32(context.Response.Headers.GetValueOrDefault("x-ratelimit-reset-requests", "-1"));
                        }

                        if (retryAfter == -1)
                        {
                            retryAfter = Convert.ToInt32(context.Response.Headers.GetValueOrDefault("x-ratelimit-reset-tokens", "10"));
                        }

                        JObject backend = (JObject)backends[currentBackendIndex];
                        backend["isThrottling"] = true;
                        backend["retryAfter"] = DateTime.Now.AddSeconds(retryAfter);

                        return backends;
                    }" />
                    <cache-store-value key="listBackends" value="@((JArray)context.Variables["listBackends"])" duration="60" />
                    <set-variable name="remainingBackends" value="@{
                        JArray backends = (JArray)context.Variables["listBackends"];

                        int remainingBackends = 0;

                        for (int i = 0; i < backends.Count; i++)
                        {
                            JObject backend = (JObject)backends[i];

                            if (!backend.Value<bool>("isThrottling"))
                            {
                                remainingBackends++;
                            }
                        }

                        return remainingBackends;
                    }" />
                </when>
            </choose>
        </retry>
    </backend>
    <outbound>
        <base />
        <!-- This will return the used backend URL in the HTTP header response. Remove it if you don't want to expose this data -->
        <set-header name="x-ms-openai" exists-action="override">
            <value>@(((JObject)((JArray)context.Variables["listBackends"])[(Int32)context.Variables["backendIndex"]]).Value<string>("name"))</value>
        </set-header>
    </outbound>
    <on-error>
        <base />
    </on-error>
</policies>