aws-genai-llm-chatbot icon indicating copy to clipboard operation
aws-genai-llm-chatbot copied to clipboard

A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon Bedrock, Anthropic, HuggingFace, OpenAI, Meta, AI21, Cohere, Mistral) using AWS CDK on AWS

Results 168 aws-genai-llm-chatbot issues
Sort by recently updated
recently updated
newest added

Kendra supports web crawling - we should enable this for Kendra in the application, so that it creates a webcrawling datasource in kendra, enabling functionality similar to other RAGs already...

stale

To help users understand differences between RAG vs fine tuning we could offer a method to fine tune a model example mistral with documents from the users workspace, then host...

stale

to limit hallucinations add an option to provide a null response in case RAG returns 0 documents, otherwise models may use their internal trained corpus to answer.

stale

Currently the chatbot allows to start new conversation by opening the right side panel and clicking on "New Session". This is fine, but having a mechanism (like a button) in...

enhancement

We are using tools drawer of `AppLayout` for displaying user session history. The icon for tools drawer is Info icon which does not represent history, so end user might find...

user interface

Does the app support federated sign using Google, Facebook etc? I can see that there is some code in `app-configured.tsx` file which is related to federated sign in but there...

documentation

Ref: https://docs.amplify.aws/react/build-a-backend/troubleshooting/migrate-from-javascript-v5-to-v6/ _Originally posted by @bigadsoleiman in https://github.com/aws-samples/aws-genai-llm-chatbot/issues/237#issuecomment-1892535943_

help wanted
dependencies
user interface

Hi All, Can we update this use case to work with PODMAN also instead of DOCKER only? Docker is licensed now and not free anymore. Please let me know your...

This feature would help customers to evaluate different models using use case specific data and prompts and rate the answers. This new functionality should also allow the user to setup...

enhancement

Hello, i've tried two idefics multimodal models and although they work out of the box previously now I am getting this message when I try to upload an image: Anybody...