Small change

Author: siddharthsambharia-portkey

images/guardrails/lasso.png

@@ -50,7 +50,7 @@ You can change this behaviour by setting the optional `on_status_codes` param in
 
 ### Respecting provider's retry headers
 
-Portkey can respect the provider's `Retry-After` and `Retry-After-ms` response headers when encountering rate limits. This enables more intelligent retry timing based on the provider's response headers rather than using the default exponential backoff strategy.
+Portkey can respect the provider's `retry-after-ms`, `x-ms-retry-after-ms` and `retry-after`response headers when encountering rate limits. This enables more intelligent retry timing based on the provider's response headers rather than using the default exponential backoff strategy.
 
 To enable this feature, add the `use_retry_after_headers` parameter to your retry config. By default this behaviour is disabled, and `use_retry_after_headers` is set to `false`.
 

product/ai-gateway/automatic-retries.mdx

@@ -7,49 +7,50 @@ Each Guardrail Check has a specific purpose, it's own parameters, supported hook
 ## Partner Guardrails
 
 <CardGroup cols={3}>
-
+  <Card title="Acuvity" href="/product/guardrails/acuvity" img="/images/product/Guardrails/acuvity-logo.png">
+    * Scan Prompts
+    * Scan Responses
+    For PII, toxicity, prompt injection detection, and more.
+  </Card>
   <Card title="Apora" href="/product/guardrails/list-of-guardrail-checks/aporia" img="/images/guardrails/logo-1.avif">
     * Validate Aporia policies
     * Define your Aporia policies on your Aporia dashboard and just pass the project ID in Portkey Guardrail check.
   </Card>
-
-  <Card title="Pillar" href="/product/guardrails/list-of-guardrail-checks/pillar" img="/images/guardrails/logo-2.avif">
-    * Scan Prompts
-    * Scan Responses
-     For PII, toxicity, prompt injection detection, and more.
+  <Card title="Azure" href="/product/guardrails/azure-guardrails" img="/images/supported-llm/microsoft-assure.avif" alt="Azure OpenAI">
+   * Detect and Redact PII
+   * Apply Azure's Content Safety checks
   </Card>
-
-  <Card title="Patronus" href="/product/guardrails/list-of-guardrail-checks/patronus-ai" img="/images/guardrails/logo-3.avif">
-
-    * Hallucination detection
-    * Check for conciseness, helpfulness, politeness
-    * Check for gender, racial bias
-    * and more!
+  <Card title="AWS Bedrock" href="/product/guardrails/bedrock-guardrials" img="/images/product/Guardrails/bedrock-logo.jpeg">
+    * Analyze and redact PII to avoid model manipulation
+    * Bring your AWS Guardrails directly inside Portkey
+    and more!
+  </Card>
+  <Card title="Lasso Security" href="/product/guardrails/lasso" img="/images/guardrails/lasso.png">
+    * Scan Content
+    Lasso Security's Deputies analyze content for various security risks including jailbreak attempts, custom policy violations, and more.
+  </Card>
+  <Card title="Mistral" href="/product/guardrails/mistral" img="/images/supported-llm/mistral.avif">
+   * Detect and filter harmful content across multiple dimensions
   </Card>
-
   <Card title="Pangea" href="/product/guardrails/pangea"  img="/images/guardrails/logo-4.png">
     * Text Guard for scanning LLM inputs and outputs
     * Analyze and redact text to avoid model manipulation
     * Detect malicious content and undesirable data transfers
   </Card>
-  <Card title="Acuvity" href="/product/guardrails/acuvity" img="/images/product/Guardrails/acuvity-logo.png">
+  <Card title="Patronus" href="/product/guardrails/list-of-guardrail-checks/patronus-ai" img="/images/guardrails/logo-3.avif">
+    * Hallucination detection
+    * Check for conciseness, helpfulness, politeness
+    * Check for gender, racial bias
+    * and more!
+  </Card>
+  <Card title="Pillar" href="/product/guardrails/list-of-guardrail-checks/pillar" img="/images/guardrails/logo-2.avif">
     * Scan Prompts
     * Scan Responses
-
-    For PII, toxicity, prompt injection detection, and more.
+     For PII, toxicity, prompt injection detection, and more.
   </Card>
-  <Card title="AWS Bedrock" href="/product/guardrails/bedrock-guardrials" img="/images/product/Guardrails/bedrock-logo.jpeg">
-
-    * Analyze and redact PII to avoid model manipulation
+</CardGroup>
 
-    * Bring your AWS Guardrails directly inside Portkey
 
-    and more!
-  </Card>
-  <Card title="Mistral" href="/product/guardrails/mistral" img="/images/supported-llm/mistral.avif">
-   * Detect and filter harmful content across multiple dimensions
-  </Card>
-</CardGroup>
 
 The logic for all of the Guardrail Checks (including Partner Guardrails) is open source.