Update gemini_handler.py to better handle NL+FC model output #617
+9
−5
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Gemini model is capable of outputting NL/text (for reasoning or verbosity) for the corresponding FC as different parts. Simply concatenation of text with FC will result in decode failures. So we should only extract FC parts for decoding and eval when it exists in the content.
See below example:
OUTPUT: ["Okay, I can help you with that. Let's calculate the future value for each investment option:\n\n\nBond:\n\n", {"calculate_future_value": "{"present_value": 5000, "periods": 10, "interest_rate": 0.05}"}, "\n\nMutual Fund:\n\n", {"calculate_future_value": "{"periods": 15, "interest_rate": 0.07, "present_value": 2000}"}, "\n\n\nStocks:\n\n", {"calculate_future_value": "{"periods": 20, "interest_rate": 0.1, "present_value": 1000}"}"]