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.
I've been working on a solution that involves using Amazon Lex in Amazon Connect to get customer input and the process it and get an answer back from an agent in Amazon Bedrock.
The part where I'm...
0
answers
0
votes
11
views
asked an hour agolg...
I have deployed a pytorch model as sagemaker endpoint which I am triggering using API gateway. I have created a POST method to trigger sagemaker endpoint as AWS Service. Below I have attached some...
0
answers
0
votes
23
views
asked 4 hours agolg...
Hi,
I would like to achieve the following. The customer visiting the webpage initiating the live chat. They should be able to ask the questions and the bot (Lex) should be able to answer them...
1
answers
0
votes
31
views
asked 6 hours agolg...
Hi,
I am working on AWS lex v2 console. My Lambda is in JavaScript. I can retrieve user input with following command:
` let userInput = event.inputTranscript;`
I want to know how do I get slot...
1
answers
0
votes
30
views
asked 7 hours agolg...
Hello,
I have setup a VPC in the following manner:
1) one public subnet with a public route-table connected to internet gateway
2) two private subnets with a private route-table connected to NAT...
0
answers
0
votes
90
views
asked 19 hours agolg...
My question is ultimately a generic one about how "best" to allow SageMaker resources (such as Studio instances) access to private services running in our AWS VPCs.
Specifically, I have a dataset...
0
answers
0
votes
53
views
asked a day agolg...
Exception: com.amazonaws.http.AmazonHttpClient$RequestExecutor.handleErrorResponse(AmazonHttpClient.java:1880),...
0
answers
0
votes
95
views
asked a day agolg...
Hi, I am currently doing the Industry Quest - Healthcare. In order to finish "Build a Medical Image Analysis Solution," I need to deploy the model to a serverless endpoint. In the AWS Management...
0
answers
0
votes
88
views
asked 2 days agolg...
The model boasts handling 200k tokens, I would like more than 4k output tokens, doesn't even work when using the API.
1
answers
0
votes
142
views
asked 2 days agolg...
I have several SageMaker Instances that will not start because they are using an old platform version (notebook-al1-v1). I would like to backup / access the files stored on these instances - is there...
1
answers
0
votes
79
views
asked 4 days agolg...
New to SageMaker evalutating ML models. I have 2 domains each created with quick and custom setup.
Each domain connects to 2 different VPCs, the quick setup is under staging-vpc and the custom domain...
1
answers
0
votes
134
views
asked 4 days agolg...
Hi, I could not find information about the precision of models such as Mistral and Llama, which are accessible on Amazon Bedrock. Could you please provide information about their precision?
1
answers
0
votes
206
views
asked 4 days agolg...