Bug: fix generate title function

[ianlcassidy]

Motivation and Context

The generate_title function in app.py has a few bugs in it.

Description

• remove use_data kwarg since init_openai_client() no long accepts it
• remove prompt instructions around outputting the title in JSON format
  • this seems unnecessarily complex and can lead to JSON decode errors
  • just output the title as plain text
• add exception logging in the function to capture when something fails
• also added DATASOURCE_TYPE to .env.sample since that controls what data source the tool should use
  • should this default to AzureCognitiveSearch either in .env.sample or backend.settings?

Contribution Checklist

• I have built and tested the code locally and in a deployed app
• For frontend changes, I have pulled the latest code from main, built the frontend, and committed all static files.
• This is a change for all users of this app. No code or asset is specific to my use case or my organization.
• I didn't break any existing functionality 😄

[ianlcassidy]

@microsoft-github-policy-service agree

[sarah-widder]

Looks great. Thank you for the contribution!

[ianlcassidy]

@sarah-widder feel free to merge when you want, i don't have the ability to.