Questions in Machine Learning & AI
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.
Hi,
Is there any way to monitor the cost of Bedrock invocations per invocation resource?
I.e. if I have several Lambdas that call Bedrock, I want to know how much Bedrock costs for each one of...
3
answers
0
votes
163
views
asked 4 days agolg...
I am currently looking to create a system to recommend items in a certain game.
To briefly explain this game, there are rounds, and for each round, the player selects and purchases a number of items...
2
answers
0
votes
54
views
asked 4 days agolg...
All,
In my use case I am planning to use the agent with couple of function calls and one knowledgebase search.
While testing I found out that my knowledgebase search needs metadata-based filtering to...
2
answers
0
votes
322
views
asked 5 days agolg...
I am curious to understand why is Llama 3 70B restricted to only 2048 output token length?
Is there a way to increase the limit for me? Also, I do get an exception of number of calls I make...
1
answers
0
votes
173
views
asked 6 days agolg...
Hi,
When using the Amazon Kendra Box Connector, is it possible to specify folders/files to be searched in the Box from Kendra?
I would like to specify only some folders/files to be searched and not...
Accepted AnswerAmazon Kendra
1
answers
0
votes
98
views
asked 6 days agolg...
I planned to develop a AWS-Powered pet lost and found system that implement the aws rekognition to find potential matches by comparing pet image uploaded. Is it possible to develop this system using...
1
answers
0
votes
76
views
asked 6 days agolg...
Bedrock LLMs cachelg...
Does Bedrock API's for LLMs have a cache to answer the same input?
Im using claude-instant-v1 model with 0 temperature and I see that sometimes for the same input the response is the same and other...
2
answers
0
votes
265
views
asked 7 days agolg...
Is there any way to configure an Amazon Lex Bot intent where everything that the user says as input is recognized as this intent?
I imagine something like a wildcard utterance? For example could be...
0
answers
0
votes
93
views
asked 7 days agolg...
AWS Textract issuelg...
Hi AWS, we are working on a project that requires real-time document processing and we are encountering latency issues with AWS Textract for multipage, large PDF files. Despite using the asynchronous...
1
answers
0
votes
64
views
asked 7 days agolg...
Hi everyone, I was trying to create a knowledge base with amazon recommended option "Quick create a new opensearch vector". Anyway, it seems that the pricing is not really clear.
I found somewhere...
1
answers
0
votes
328
views
asked 7 days agolg...
Hello, I need help deleting a knowledge base.
Here is the setup. I have a knowledge base with a Data source pointing to Amazon S3 and the Vector database in Amazon OpenSearch Serverless. My mistake...
1
answers
0
votes
287
views
asked 7 days agolg...
Can I answer the AWS re:Post question with the generate AI?
Are users asking questions to this community looking for answers created by the generated AI?
At least I'm not looking for an answer...
2
answers
0
votes
71
views
asked 7 days agolg...