Refactor OpenAI exception handling from instruction parser #328
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
oh - what was the breaking change? Happy to take a look as well @neubig |
|
No worries @krrishdholakia , probably just a minor conflict: https://github.com/neulab/prompt2model/pull/328/conflicts |
|
ah yes, just a minor conflict, will update my PR |
|
Ok, sounds good. Thanks for the merge! |
neubig
approved these changes
Sep 7, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Description
Currently the
OpenAIInstructionParserhandles OpenAI exceptions from its own class. With this change, the exception is handled as required directly from theChatGPTAgent. Refactoring the exception handling is a step in the direction of converting theOpenAIInstructionParserto a more generalInstructionParserclass that can be passed any Generative Agent (OpenAI, cohere, local hf models, etc).Key Changes
handle_openai_errorreturns the handled error instead of the number of API callsOpenAIInstructionParserchecks for the response being an exception or an actual response and continues the same logic as previously specified. This pattern will be extendable to future models.prompt_parsertest modified to mock the exact function that would be throwing the error in use.