aws-samples / aws-genai-llm-chatbot

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
https://aws-samples.github.io/aws-genai-llm-chatbot/
MIT No Attribution
1.1k stars 332 forks source link

bug: Exclude internal calls from WAF rate limiter #591

Closed charles-marion closed 1 month ago

charles-marion commented 1 month ago

Issue #, if available:

Description of changes: The internal calls sending chunks (LLM Response Streaming) to the end user were reaching the WAF throttling limit added in #581.

To prevent this, the change excludes the VPC IPs from the throttling limit.

Testing Check WAF Metrics + requested large output from the model with streaming.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.