By using AWS re:Post, you agree to the AWS re:Post Terms of Use

Questions tagged with Generative AI on AWS

Innovate faster to reinvent customer experiences and applications

Content language: English

Select up to 5 tags to filter
Sort by most recent

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

117 results
![Enter image description here](/media/postImages/original/IMrB_bcgc1RBO0_t06yfLlNw) Is there a way to optimize this prompt flow? I'm running into the 20 node limit and I barely got started. A bunch ...
1
answers
0
votes
15
views
asked a day ago
Hello, hope someone can help me with this. I've built an agent with access to my knowledge base, which contains structured data about customer transactions (ie, merchant, amount, date, etc.). I'm tr...
2
answers
0
votes
26
views
asked 8 days ago
Hi, hoping someone can help me. I'm trying to create a prompt where my llm will suggest two relevant questions based on the user's data. However, I'm getting this error when trying to invoke the pro...
1
answers
0
votes
74
views
asked 8 days ago
Hello! I am trying to set up the GenASL solution using the steps available on [https://aws.amazon.com/blogs/machine-learning/genasl-generative-ai-powered-american-sign-language-avatars/]() Once I rea...
2
answers
0
votes
26
views
asked 13 days ago
Is there any native vector database present in AWS for production ready solution?
1
answers
0
votes
29
views
asked 20 days ago
For an API connection I need the sessionID. I found the AgentID & AliasID, but where do you find the sessionID in AWS Bedrock? Thanks in advance!
1
answers
0
votes
39
views
asked a month ago
Hi! I've been working a lot with langchain4j and also AWS Bedrock, I was wondering how can I generate charts from the data I already have stored in my vector DB using natural language. I though about...
2
answers
0
votes
132
views
asked a month ago
Getting the issue both on playground and via API. My request for the model has been approved and getting this error on the first request. Does that mean that rate limit has been set to 0? How to chang...
1
answers
0
votes
502
views
asked a month ago
A few weeks ago I used the "On-demand InvokeModel requests per minute for Stability.ai Stable Image Core" service no problem, but now my account-level quota has been set to 0 despite the AWS default b...
1
answers
0
votes
123
views
asked a month ago
AWS Bedrock requests has been down since past few hours and I do not see any outages information anywhere though few people have been reporting. What could be the cause of the issue and when can we ex...
1
answers
1
votes
106
views
asked a month ago
Hello, I've imported an LLM to bedrock. It's a fine-tuned llama 3 8B model, but when I try to test it in the playground, I get '*User input fails validation*'. This does not happen with FMs, and it d...
1
answers
0
votes
60
views
asked a month ago
When attempting to generate a set of images, via text prompt, using the default Titan Image Generator G1 V2 model; the results from the image generator frequently do not match the `numberOfImages` par...
1
answers
0
votes
56
views
asked 2 months ago