Questions tagged with Generative AI on AWS
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 trying to run this lab in Cloud Quest, but get stuck right after the step where you have to enter
```
# create a vpc with IpAddresses 10.10.0.0/16, a NAT gateway, a public subnet,...
asked 3 days ago
We have enabled the memory retention feature for our Amazon Bedrock Agent to retain session information.
Our guided chat flow takes the user through a 10-step journey. We want the Agent to resume the...
Hey, I have encountered an issue with Confluence Connector; The Connector is not correctly crawling the specified pages. Despite setting various filters to target specific pages and spaces (to avoid...
I have been trying to get Bedrock Knowledge Bases to fetch documents that contain "log" or "logging" from a Confluence space called "Observability" (or "OSRE" in the URL path) using different...
I have created a bedrock agent with Claude 3 Sonnet model and associate it with a customer service FAQs knowledge base. I can't seem to get general responses from the agent if I prompted a simple...
asked 24 days ago
I am using Llama 3 70B through AWS Bedrock SDK. I observe that 90%+ responses are not in JSON, as mentioned in the prompt. Instead, I'm getting blank responses or string responses. Can anyone help me...
Is there any limit on context length of imported custom model in Bedrock?
Trying to import a model from the Llama-3 family with a long context length.
Context lengths beyond 32K don't seem to be...
Hi,
I need to create a mongodb vector store through AWS Bedrock's default chunking.
I am successful in creating that, yet when I am using metadata filters throught the API's "Retrieve_and_generate"...
I have a lambda which query dynamo Db table for an available times once the the date is entered by the user and then the lambda will add those available time to the session attribute and will elicit...
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...
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...
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?