Cloud Quest Generative AI Practitioner: Issue with "Explore the Amazon Bedrock Playgrounds" Lab

Question

Hello,

First post on here, hoping someone knows how to resolve this, please.

I've completed all of the content on the Cloud Quest Generative AI Practitioner course, aside from "Explore the Amazon Bedrock Playgrounds". I've tried this in two different sessions, with the same result: I cannot validate the DIY section, despite following the steps precisely and checking that all of the models are enabled.

Whilst testing some prompts to compare the Mistral 7B model with Amazon Titan and Nova, I continually see a pop-up that states "Access denied to bedrock:ListCustomModelDeployments". I tried diagnosing this with Q, which responded with "You don't have sufficient permissions to Diagnose with Amazon Q". I've also triple-checked that I have the correct model ID for the validation form, which is "mistral.mistral-7b-instruct-v0:2".

When I enter this model ID and click 'Validate', I get the message "The models in the Practice section have not been enabled. Check the practice steps and try again".

I've tried enabling all of the Amazon and Mistral models, have tried varying the model ID by entering e.g. "mistral-7b-instruct-v0:2". I also tried to see if this needed the Image playground. I've cleared cookies on my browser, running it in Private Browsing mode (both Edge and Firefox) and still can't get the validation step to work.

Has anyone else encountered this issue? I'd be very grateful for any advice, I'd really like to finish this and get the badge! Thanks.

PJG999 · Accepted Answer

OK, I've just returned to the last exercise in the "Cloud Quest: Generative AI Practitioner" training, and have now completed the course and received the badge.

The "Access denied to bedrock:ListCustomModelDeployments" message didn't appear, so I'm going to assume that a very kind and helpful AWS person read my post and the permissions issue got passed on to the devs, and they fixed it. So I'd just like to say **thank you very much indeed for your help**, really appreciated!

re:Post Agent · Answer

I understand your frustration with completing the Cloud Quest Generative AI Practitioner course. Based on the information provided, it appears you're encountering permission issues when trying to validate the "Explore the Amazon Bedrock Playgrounds" lab.

For AWS Cloud Quest: Generative AI Practitioner, you need to work with various AI models including Amazon Titan, Amazon Nova, Meta's Llama, and Mistral AI models. The course is designed to provide hands-on experience with these foundation models through a game-based learning environment.

Regarding your specific error about "Access denied to bedrock:ListCustomModelDeployments" - this suggests there might be an IAM permission issue in the lab environment. For Amazon Bedrock models, accessing foundation models requires completing a subscription flow and agreeing to the End User License Agreement (EULA).

For the Mistral model specifically, you mentioned using "mistral.mistral-7b-instruct-v0:2" as the model ID. This appears to be the correct format, but the validation system might be looking for something specific in terms of which models are enabled.

Here are some suggestions to troubleshoot:

1. Make sure you've enabled all required models in the Amazon Bedrock console within the lab environment, particularly focusing on Amazon Titan, Amazon Nova, and Mistral AI models.

2. Double-check that you've completed all the prerequisite steps in the lab instructions, as the validation might be checking for completion of specific actions.

3. Try restarting the lab completely (not just refreshing the browser) to ensure you have a fresh environment with the proper permissions.

4. If possible, check if there are any specific instructions about model access or permissions that need to be configured as part of the lab.

If these steps don't resolve the issue, it might be worth reaching out directly to AWS Training and Certification support, as this could be a technical issue with the Cloud Quest environment itself.  
**Sources**  
[Learn generative AI with AWS Cloud Quest: Generative AI Practitioner | AWS Training and Certification Blog](https://aws.amazon.com/blogs/training-and-certification/learn-generative-ai-with-aws-cloud-quest-generative-ai-practitioner/)  
[Configuring Bedrock Foundation Model Access in GovCloud: A Step-by-Step Guide | AWS re:Post](https://repost.aws/articles/AR0fhULr83SSaaDn58aazMZw/configuring-bedrock-foundation-model-access-in-govcloud-a-step-by-step-guide)

Cloud Quest Generative AI Practitioner: Issue with "Explore the Amazon Bedrock Playgrounds" Lab

Add your answer

Relevant content