(WIP) Add support for early stopping in agent executor #268
+684
−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Outdated suggestions cannot be applied.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.
Following #265, here we add support for early stopping (e.g., via
max_iterations
ormax_execution_time
) as in AgentExecutor.WIP: looking for feedback on the general strategy for incorporating AgentExecutor's attributes, eventually including
return_intermediate_steps
max_iterations
max_execution_time
early_stopping_method
handle_parsing_errors
trim_intermediate_steps
Here I've added some to
AgentState
, but it's unclear to me how to set defaults when they are not passed in by the caller on invoke, stream, etc. For example, even if I setiteration_count: int = 0
in AgentState, it gets set to 0 if not included in the input. Looking for suggestions on other ways to do this!