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
Browse through the questions and answers listed below or filter and sort to narrow down your results.
164 results
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?
2
answers
0
votes
53
views
asked 6 days ago
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...
1
answers
0
votes
18
views
asked 8 days ago
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...
1
answers
0
votes
145
views
asked 22 days ago
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...
1
answers
0
votes
79
views
asked 23 days ago
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...
1
answers
0
votes
41
views
asked a month ago
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...
2
answers
0
votes
44
views
asked a month ago
how many tokens are served in 1 "Model unit"-hour of Llama 3.1 8B in US West?
1
answers
0
votes
33
views
asked a month ago
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...
1
answers
0
votes
233
views
asked a month ago
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...
2
answers
0
votes
65
views
asked 3 months ago
How can I make nova sonic model start the conversation with some welcome message, instead of waiting for user to speak?
I tried adding USER textInput immediately after the SYSTEM prompt - but it seems...
1
answers
0
votes
146
views
asked 3 months ago
Hello, I cannot launch on demand p3.8xlarge instance on Oregon us-west-2. I have a 32 vCPU limit so it should work but get the error "The requested configuration is currently not supported. Please che...
2
answers
0
votes
101
views
asked 3 months ago
I have my time-series data on InfluxDB. I want to retrieve the data from InfluxDB for a given time period and send it to Bedrock model along with a system prompt to generate a response. I want to avoi...
2
answers
0
votes
133
views
asked 4 months ago