Merge pull request #356 from Portkey-AI/chore/inference-profiles

Author: vrushankportkey

integrations/llms/bedrock/aws-bedrock.mdx

@@ -631,6 +631,27 @@ Note that you will have to set [`strict_open_ai_compliance=False`](/product/ai-g
     ```
 </CodeGroup>
 
+## Inference Profiles
+
+[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:
+```json
+            "Effect": "Allow",
+            "Action": [
+                "bedrock:GetInferenceProfile"
+            ],
+            "Resource": [
+                "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.
+
+For reference, see the following documentation:
+https://docs.aws.amazon.com/bedrock/latest/userguide/inference-profiles-prereq.html
+
+
 ## Bedrock Converse API
 
 Portkey uses the [AWS Converse API](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_Converse.html) internally for making chat completions requests.