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'm currently leveraging a custom HuggingFace model, stored in an S3 bucket, for my serverless inference endpoint. The model size is approximately 750MB. However, I'm encountering significant cold...
0
answers
0
votes
111
views
asked 6 days agolg...
As per the documentation only 250 unique labels are supported in a manifest https://docs.aws.amazon.com/rekognition/latest/customlabels-dg/limits.html.
I have a use case to train more than 3000 unique...
0
answers
0
votes
41
views
asked 6 days agolg...
Testing the new Titan Text Premier model and have been getting this error:
> An error occurred (ValidationException) when calling the InvokeModel operation: Invalid inference input
Anyone else...
Accepted AnswerAmazon Bedrock
2
answers
0
votes
325
views
asked 6 days agolg...
All,
OpenAi provides feature known as “function calling”. In simple words, you describe a function, parameters, and conditions for model to call the function.
Does anybody know if Bedrock has similar...
2
answers
0
votes
87
views
asked 6 days agolg...
Hi,
I'm writing a simple Python script to send a question to a Bedrock agent and then print the response.
My code is as follows:
```
import boto3
agent_id = agent_id
region_name =...
Accepted AnswerAmazon Bedrock
1
answers
0
votes
314
views
asked 6 days agolg...
Hello,
I know that Cohere (through Bedrock) has a limit of 512 tokens (also known as 2048 characters) in the Bedrock API.
But when I try to create embeddings I got this error:
Input is too long...
0
answers
0
votes
289
views
asked 6 days agolg...
I used Amazon Transcribe real time transcription service, recording audio live. When I downloaded the transcript, it saved as a JSON file comprised of 13,000 pages of text. Does anyone know how I can ...
1
answers
0
votes
91
views
asked 7 days agolg...
I want to understand the following benchmarks for LLama 3 8B on AWS Bedrock:
1. Max concurrency for a single user/API
2. Latency
3. Tokens per second
4. Rate limits, if any (number of requests per...
1
answers
0
votes
333
views
asked 7 days agolg...
Hi AWS, I am creating a SageMaker Studio domain for a single user and facing the issue attached in the screenshot below
![SageMaker Studio...
2
answers
0
votes
69
views
asked 7 days agolg...
I can only use once a minute(60s).
Bedrock Claude Error: An error occurred (ThrottlingException) when calling the InvokeModel operation (reached max retries: 4): Too many requests, please wait before...
1
answers
0
votes
335
views
asked 7 days agolg...
This question should be in Textract category, but system places it in ML for some unknown reason.
I am interfacing with the Textract API using the AWS PHP SDK. I'd like to use the new Textract...
1
answers
0
votes
47
views
asked 7 days agolg...
Hello everyone,
We have CloudTrail capturing all event logs from `qbusiness` and sending the logs to an S3 bucket, yet there is no recording of user conversations in any of the logs. Does anyone...
0
answers
0
votes
47
views
asked 7 days agolg...