JSON path prompt debug facilitation

[dylan1218]

Description

Update the JSON path base prompt to include an identifier that can be parsed from json_query.py. A parsing function was added to json_query.py to more accurately return the JSON path query string, and if not found an error clearly explaining the issues is returned to the user.

Fixes # #7587

Type of Change

[x] New feature (non-breaking change which adds functionality)
(1) Updates the default JSON path prompt to include an identifier that can be parsed with regex
(2) Adds a regex parsing function that finds the JSONPath prompt. If not found provides clearer error handling for trouble shooting

How Has This Been Tested?

[x] I stared at the code and made sure it makes sense
[x] Tested by initializing a JSONQueryEngine initialized with an Azure openAI LLM service context and making various queries to ensure that JSON path was being parsed correctlly from the LLM response.

Suggested Checklist:

• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added Google Colab support for the newly added notebooks.
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I ran make format; make lint to appease the lint gods

[logan-markewich]

@dylan1218 Looks like this change breaks some unit tests -- can you fix those up?

Also, run make lint to fix the linting CI