Avoid rate-limiting, improve --changed

Azure-Samples / ai-rag-chat-evaluator

Tools for evaluation of RAG Chat Apps using Azure AI Evaluate SDK and OpenAI

MIT License

209 stars 75 forks source link

Closed pamelafox closed 4 months ago

pamelafox commented 4 months ago

This PR changes evaluations to run serially, as the current approach with threadpool is too liable to run into rate-limit errors.

This PR also fixes an issue with --changed so that 5 and 5.00 are not considered changed.