Pamela Fox

I'm closing this issue since the original M1 compatibility issue is resolved, but please open new issues if needed.

@RobertCraigie Where does telemetry_transport come from in that code? I'm testing this out in our samples, as I'm not seeing good traces for the OpenAI calls currently.

Have you gone through the steps here about debugging answer quality? https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/customization.md#improving-answer-quality It sounds like you're seeing that it's not doing a good job searching. See https://github.com/Azure-Samples/azure-search-openai-demo/blob/main/docs/customization.md#improving-azure-ai-search-results and let us...

Glad those helped! You could check out the evaluation tool: https://github.com/Azure-Samples/ai-rag-chat-evaluator To find the answers for users, I believe you should be able to use logging.info() and see those logs...

This sample now uses ChatCompletion API everywhere, and I've added an FAQ about using GPT-4 (it's a one-line change): https://github.com/Azure-Samples/azure-search-openai-demo#faq

Thanks for the report! I've proposed a fix at https://github.com/pallets-eco/flask-sqlalchemy/pull/1296/files

@hydra-zim Is this ready for review? I notice you haven't completed the tasks on the checklist, like updating the changelog. Please go through those.

CI checks passing now, ready for review.

Very interesting, I hadn't seen that before, and there's a lot of interest in observability. I think we'd want to get Langfuse deployed on Azure to make sure it was...

Thanks @marcklingen , I started experimenting with langfuse yesterday, it's a very helpful UI. From my experiment, the changes to this repo are pretty minimal - just setting the env...