microsoft / sample-app-aoai-chatGPT

Sample code for a simple web chat experience through Azure OpenAI, including Azure OpenAI On Your Data.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Internal Server Error

DMF194 opened this issue · comments

Describe the bug
After I git clone into my own private branch and running all the instructions from the READ.ME, I got the internal server error

To Reproduce
I am following the instructions for local machine deployment

  1. Fill the details for my .env file as follows
  • AZURE_OPENAI_RESOURCE
  • AZURE_OPENAI_MODEL
  • AZURE_OPENAI_KEY
  1. Fill the details for my .env file as follows
  • AZURE_SEARCH_SERVICE
  • AZURE_SEARCH_INDEX
  • AZURE_SEARCH_KEY
  1. Made sure that my startup command is as follows:
    python -m gunicorn app:app under web service configuration tab

Screenshots
image

Note that I am doing this using company proxy and not using chat history.

Just an update to this case, I tried to enter the cosmos details and restarted the application.

The following screenshot is shown
image

Hi @DMF194 , could you please share the full stack trace from the backend when you receive this error?

Hi @abhahn, when I tried restarting the application by running the start.cmd command this morning.

I no longer run into the internal server issue.

This is what it looks like today

IMG_20240524_091001

But comparing both the debug log from previous runs and today, I noticed the httpx python package is not throwing errors.

Previously, when I tested the conversation API by clicking on the send button, 500 error code kept appearing. My assumption is that the httpx python package used had some issues.

Thanks for sharing this info. I'm glad to see you are no longer facing the issue. :) I'll close this for now, but if you run into the same issue later on feel free to reopen to share more details and we can investigate.