Skip to content
By using AWS re:Post, you agree to the AWS re:Post Terms of Use
AWS re:Postre:Post
About re:Post

Questions tagged with Generative AI on AWS

Innovate faster to reinvent customer experiences and applications

Content language: English

Filter questions
Select tags to filter
Sort by
Sort by most recent
Filter Questions by:

Browse through the questions and answers listed below or filter and sort to narrow down your results.

167 results

why doesn't the LLM of Novasonic understand the conversation...

Here, in the conversation of words, why doesn't the LLM of Novasonic understand? **logs-1: Conversation History** ``` Assistant: Hello! This is Sarah calling from ABC Company. Is this a good time to ...
Amazon Nova Foundation ModelsAmazon BedrockMachine Learning & AIGenerative AI on AWS
1
answers
0
votes
11
views
asked 3 days ago

Bedrock invoke_model returning two JSONs separated by <|eot_...

I'm using invoke_model in Bedrock with Llama 4 Maverick. My prompt format looks like this (as per the docs): <|begin_of_text|> <|start_header_id|>system<|end_header_id|> ...system prompt...<|eot_id|...
Amazon BedrockMachine Learning & AIGenerative AI on AWSAnalyticsMeta Llama in Amazon Bedrock
2
answers
0
votes
50
views
asked 23 days ago

Qwen3 32B Thinking Model on Bedrock Truncates Output

I'm setting up Bedrock with the Qwen3 32B model with thinking enabled, but I'm noticing that the response gets truncated fairly consistently. Is there some sort of setting that I'm missing or is this ...
Amazon BedrockMachine Learning & AIGenerative AI on AWS
1
answers
0
votes
75
views
asked a month ago

Observing Bedrock Model Performance and Cost

We are deploying multiple foundation models through Bedrock. How can we monitor their performance, token usage, and cost impact in production to optimize usage and prevent overspending?
Accepted AnswerAmazon BedrockCost OptimizationMonitoringAmazon CloudWatchGenerative AI on AWS
2
answers
0
votes
162
views
asked a month ago

StrandsAgent support for exceptions in system prompt

Hi, Recently we deploy some ai agents using stands SDK to shutdown some of ec2 instances after office hours. The ai agent will run daily but on some days we want to set exception not shutting ec2 ins...
Generative AI on AWS
1
answers
0
votes
44
views
asked a month ago

Intermittent "Too many connections" errors with Claude Sonne...

We experienced intermittent ServiceUnavailableException errors on October 16, 2025 (09:00-15:00 UTC) when calling the ConverseStream operation for Claude Sonnet 4.5. **Error Message:** "ServiceUnavai...
Amazon BedrockGenerative AI on AWS
1
answers
0
votes
428
views
asked 2 months ago

Bedrock Agent Core AtlassianOAuth2 credential provider confl...

When using the Bedrock Agent Core AtlassianOAuth2 credential provider, the service generates a dynamic, one-time redirect_uri with a unique suffix for each authorization request. This conflicts with A...
Amazon Bedrock AgentCoreGenerative AI on AWSAmazon Bedrock
1
answers
0
votes
170
views
asked 2 months ago

GenAI Architect Cloud Quest challenge Generative AI App for ...

For this challenge, I don't understand if the issue comes from me or from the streamlit application. I've done everything required but the creation of image is still not working. I tried different kin...
Generative AI on AWS
1
answers
0
votes
66
views
asked 2 months ago

How reliable has Amazon Q Developer CLI been for you in CDK ...

I’ve been using Amazon Q Developer CLI with a serverless AWS CDK TypeScript setup and keep running into a few patterns: * Updates sometimes break things that were working before. * Integration with A...
ServerlessAmazon QGenerative AI on AWSAWS Cloud Development Kit (CDK)
2
answers
0
votes
83
views
asked 2 months ago

how many tokens are served in 1 "Model unit"-hour of Llama 3...

how many tokens are served in 1 "Model unit"-hour of Llama 3.1 8B in US West?
ComputeGenerative AI on AWSMachine Learning & AIMeta Llama in Amazon Bedrock
1
answers
0
votes
61
views
asked 2 months ago

Strands Agents tools invocation passing on the whole context...

I am building the GenAI application using bedrock and strands agent running in lambda. Agent is using the strands-native calculator tool. In the processing of the single request, there is anumber of t...
Amazon BedrockGenerative AI on AWS
1
answers
0
votes
550
views
asked 3 months ago

Is this Generative model "Kling" hosted on AWS cloud?

I'd like to deploy the Kling model listed on the following Marketplace: https://aws.amazon.com/marketplace/pp/prodview-6636lqgc4tu2w?ref_=unifiedsearch This model appears sold by Kling AI. To clarif...
Generative AI on AWSAWS Marketplace
2
answers
0
votes
84
views
asked 4 months ago
  • 1
  • 2
  • 3
  • 4
  • 5
  • •••
  • 14
  • Page size
    12 / page