You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: SUPPORTED_MODELS.md
+3Lines changed: 3 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -49,6 +49,9 @@ K8sGPT supports a variety of AI/LLM providers (backends). Some providers have a
49
49
- us.amazon.nova-lite-v1:0
50
50
- anthropic.claude-3-haiku-20240307-v1:0
51
51
52
+
> **Note:**
53
+
> If you use an AWS Bedrock inference profile ARN (e.g., `arn:aws:bedrock:us-east-1:<account>:application-inference-profile/<id>`) as the model, you must still provide a valid modelId (e.g., `anthropic.claude-3-sonnet-20240229-v1:0`). K8sGPT will automatically set the required `X-Amzn-Bedrock-Inference-Profile-ARN` header for you when making requests to Bedrock.
54
+
52
55
### Amazon SageMaker
53
56
-**Model:** User-configurable (any model deployed in your SageMaker endpoint)
return"", fmt.Errorf("AWS credentials are invalid or missing. Please check your AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables or AWS config. Details: %v", err)
0 commit comments