Merge pull request #374 from Portkey-AI/fix/inference-profiles

fix policy statement for inference profiles

Author: vrushankportkey

integrations/llms/bedrock/aws-bedrock.mdx

@@ -635,8 +635,12 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g
 
 [Inference profiles](https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles.html) are a resource in Amazon Bedrock that define a model and one or more Regions to which the inference profile can route model invocation requests.
 
-To use inference profiles, your IAM role needs to have the following permissions:
+To use inference profiles, your IAM role needs to additionally have the following permissions:
 ```json
+{
+    "Version": "2012-10-17",
+    "Statement": [
+        {
             "Effect": "Allow",
             "Action": [
                 "bedrock:GetInferenceProfile"
@@ -645,6 +649,9 @@ To use inference profiles, your IAM role needs to have the following permissions
                 "arn:aws:bedrock:*:*:inference-profile/*",
                 "arn:aws:bedrock:*:*:application-inference-profile/*"
             ]
+        }
+    ]
+}
 ```
 This is a pre-requisite for using inference profiles, as the gateway needs to fetch the foundation model to process the request.