aws-samples/amazon-bedrock-audio-summarizer

eventbridge-bedrock-inference

sanchep2 opened this issue · 2 comments

I follow the step by step guide
and After uploading the file I get transcription folder created but the processed Folder is never created

looking at the /aws/lambda/eventbridge-bedrock-inference Cloudwatch logs I see the following log event

2024-08-14T20:22:05.431Z
[ERROR]	2024-08-14T20:22:05.431Z	930587f4-631c-4afc-81dd-840def9cc233	An error occurred (AccessDeniedException) when calling the InvokeModel operation: You don't have access to the model with the specified model ID.

just after

[INFO]	2024-08-14T20:22:04.916Z	930587f4-631c-4afc-81dd-840def9cc233	## INVOKING MODEL

any Idea how to solve it ?

Hi @sanchep2 -- yes, the error "You don't have access to the model with the specified model ID" means you'll need to request access to the Claude 3 Sonnet model in Bedrock for the script to work. Instructions for requesting access can be found at: https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html

Alternatively, if you already have access to a model you want to try, you could update the code at https://github.com/aws-samples/amazon-bedrock-audio-summarizer/blob/main/lambda/eventbridge-bedrock-inference/lambda_function.py#L199

Thanks
that was the resolution @jbnunn