aws-genai-llm-chatbot
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
Bumps [langchain](https://github.com/langchain-ai/langchain) from 0.1.5 to 0.1.11. Release notes Sourced from langchain's releases. v0.1.11 What's Changed more query analysis docs by @hwchase17 in langchain-ai/langchain#18358 docs: anthropic qa quickstart by @baskaryan in...
When sending a request to the chatbot, I received the following message as reply: ``` :An error occurred (throttlingException) when calling the InvokeModelWithResponseStream operation: Too many requests, please wait before...
Currently workspace is not private for a user account. Its public and visible across all users. Workspace should be private and option to make it public.
Currently cross encoder models are used to rank the search results but the models available need to be hosted on Sagemaker which increases cost significantly. Having an option to disable...
I have really non-informative error message in the WebUI - 'Something went wrong' Am I alone ? Has anyone tested WebUI functionality before releasing the code ?
Hi there, congrats for good project and good progress speed. I just wanted to suggest implementing Llamaindex as another alternative for Langchain. Best regards,
I was wondering if it would be possible to use this demo to query a SQL DB directly like you can do [here](https://demos.aiml.aws.dev/intro.html?demo=chat-sql-rag) using text-to-sql, but also having the option...
To reduce the number of API calls that is being made to Bedrock/Sagemaker, a caching layer would help. Basically, when a user asks the same question several times then we...
User should be able to download the documents from documents tab. This way, they can cross check the content and later on delete the outdated content. This feature would be...