Json correction

[velocitatem]

Hi! Love the project! I observed that when dealing with larger inputs, the integration often struggles to properly parse the JSON data, usually due to trailing commas. To address this, I've implemented a function that automatically corrects the JSON formatting for those cases :)

Summary by CodeRabbit

Release Notes

• Bug Fix: Implemented a new function correct_json() to ensure the JSON response from OpenAI is valid. This prevents potential errors during further processing.
• Refactor: Updated get_response_data() function to use correct_json(), enhancing the reliability of data extraction.
• Refactor: Modified get_response_data() to return a tuple (response_data, 200), improving the clarity of response status handling.

[yoheinakajima]

Hey I love this! I'm reviewing from mobile which makes why merge conflicts hard to manage, but if you're able to fix happy to pull this in!

[coderabbitai]

Walkthrough

The changes primarily focus on enhancing the handling of OpenAI's JSON response. A new function correct_json() is introduced to ensure the validity of the JSON data. The get_response_data() function now utilizes this correction mechanism and returns a tuple for better error handling.

Changes

File	Summary
main.py	Introduced correct_json() to validate and correct JSON responses from OpenAI. Updated get_response_data() to use this function and return a tuple (response_data, 200). Minor formatting updates and comments added for clarity.

🐇💻

In the land of code, where the brackets lie,

A rabbit hopped in, with an eagle's eye.

Fixed some JSON, made it shine,

Now the data flows, oh so fine!

With tuples returned, and errors caught,

A better script, the rabbit has wrought! 🎉

---

Tips

Chat with CodeRabbit Bot (@coderabbitai)

• Mention @coderabbitai in any review comment for bot assistance.
• Note: Review comments are made on code diffs or files, not on the PR overview.

Pause Incremental Reviews

• Insert @coderabbitai: ignore in the PR description to halt the bot's ongoing reviews. Remove the line to resume.

[coderabbitai]

Review Status

Actionable comments generated: 2

Commits

Files that changed from the base of the PR and between bd9cc5a and 5b13698 commits.

Files selected for processing (1)

• main.py (5 hunks)

Additional comments (Suppressed): 3

main.py (3)

• 3-3: The re module has been imported to handle and correct JSON formatting issues in the new function correct_json().

• 47-55: A new function correct_json() has been introduced to correct JSON formatting issues, specifically trailing commas. This function uses regular expressions to replace invalid JSON patterns with valid ones.

+ def correct_json(response_data):
+     """
+     Corrects the JSON response from OpenAI to be valid JSON
+     """
+     response_data = re.sub(
+         r',\s*}', '}',
+         re.sub(r',\s*]', ']',
+                re.sub(r'(\w+)\s*:', r'"\1":', response_data)))
+     return response_data

• 172-172: The return type of get_response_data() has been modified to return a tuple (response_data, 200). Ensure that all calls to this function throughout the codebase have been updated to handle the new return type.

[coderabbitai]

The get_response_data() function now calls the new correct_json() function to ensure that all response data is corrected for JSON formatting before further processing.

  response_data = completion.choices[0]["message"]["function_call"]["arguments"]
+ response_data = correct_json(response_data)

[coderabbitai]

Error messages are not being formatted correctly due to missing arguments in the format method. This will result in error messages that simply say "{}".

- return jsonify({"error": "".format(e)}), 400
+ return jsonify({"error": str(e)}), 400

- return jsonify({"error": "".format(jde)}), 500
+ return jsonify({"error": str(jde)}), 500