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
Dear all, During the deployment via 'npx cdk deploy' in Cloud9 environment I get the following warning messages: current credentials could not be used to assume 'arn:aws:iam::XXXXXXXXXXXX:role/cdk-hnb659fds-lookup-role-XXXXXXXXXXXX-YYYYYYYYY', but are for...
Consumable APIs would ensure that the chatbot functionality can be accessed by other products via APIs. It would make the integration with other products easy.
While cross encoders have shown better performance than using cosine similarity scores on sentence embeddings, there are no multilingual cross encoders, making this solution only viable for English. Experiments show...
This PR is for work on Issue #99 - Please see issue for detailed documentation of changes to user interface By submitting this pull request, I confirm that you can...
Dear all, I have created a Workspace with all default settings and tried to upload a pdf file of ~54 MB (https://docs.aws.amazon.com/AmazonRDS/latest/UserGuide/rds-ug.pdf) The uploading task is not finished since then...
The chatbot currently supports only [exact keyword search](https://github.com/aws-samples/aws-genai-llm-chatbot/blob/f8189bad7e5fc0281c350c8d450527ebfdcd9f18/lib/shared/layers/python-sdk/python/genai_core/opensearch/query.py#L204) when using hybrid search configuration for the workspace. While this setting works fine for some type of documents, it might not be...
Currently, there is no indication about the cost related to the call of an LLM. It would be interesting to understand how much the message affects the cost of invoking...
### Enable Metadata Filter Queries for OpenSearch: Implement Approximate KNN Search with Metadata Filtering in Amazon OpenSearch **Goal** - Implement self-querying or metadata filtering for approximate KNN search in Amazon...
While testing a new chatbot it is important to be able to gather information about the quality of the answers. Since quality might mean different things for different use cases,...
I tried deploying today with minimal input (with a private website only accessible in a VPC) during the config process, but the deployed CFN had an empty string for the...