feat: support generate as an early stopping method for OpenAIFunctionsAgent
#7229
Conversation
This file contains hidden or 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
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
hwchase17
reviewed
Jul 5, 2023
Contributor
hwchase17
left a comment
hwchase17
left a comment
There was a problem hiding this comment.
this is great! can we add some documentation of this either on the class or in a notebook?
Contributor
Author
|
@hwchase17 for sure, will request a review once added |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
This PR proposes an implementation to support
generateas anearly_stopping_methodfor the newOpenAIFunctionsAgentclass.The motivation behind is to facilitate the user to set a maximum number of actions the agent can take with
max_iterationsand force a final response with this new agent (as with theAgentclass).The following changes were made:
OpenAIFunctionsAgent.return_stopped_responsemethod was overwritten to supportgenerateas anearly_stopping_methodwith_functionsparameter was added to theOpenAIFunctionsAgent.planmethodThis way the
OpenAIFunctionsAgent.return_stopped_responsemethod can call theOpenAIFunctionsAgent.planmethod withwith_function=Falsewhen theearly_stopping_methodis set togenerate, making a call to the LLM with no functions and forcing a final response from the"assistant".