Michael Pearson

Predictions are not as accurate as they could be

2

Hey, not sure if I'm doing something wrong here or everyone gets this. With mnistSimple, every prediction after 4 is wrong just using the keyboard. 5 -> 3; 6 ->...

Improvements to ConvoOutputParser and MessageHistory

7

* Updated ConvoOutputParser to more robustly handle poorly formatted response scenarios from an LLM like GPT-3.5-Turbo. * Added a ActionBasedChatMessageHistory as an alternative to ChatMessageHistory to avoid prompt contamination caused...

Fix for early_stopping_method "generate" raising an exception when used by ConversationalChatAgent

2

early_stopping_method was not using _construct_scratchpad function and not appending BaseMessage in the case where a scratchpad was expected by the agent to use a list of BaseMessages.