kcaverly
kcaverly
Migrated OpenAI GPT3 LM client to v1's OpenAI/AzureOpenAI clients. The previous version, had kwarg inconsistencies with Azure calls. Fixes #377
Currently, the new Google LM class, does not have consistent imports with the remainder of the LMs. ie. dspy.Cohere works, but dspy.Google does not. This PR makes small import changes...
I took a look into how we can integrate global joblib Memory caching into the `BaseLM` class. It takes a little bit of misdirection, but the below `BaseLM` class will...
Merging main with backend-refactor to accomodate for new tests integrations and signatures.
Thanks for your work on ybc. Im looking to implement onkeydown events for an input, as it looks like only oninput callbacks are currently supported, would you be interested in...
This PR is intended to get a "DSPy Only Predict" running, ie. No `dsp` code running. This is ultimately the point at which the Backend refactor becomes breaking, ## TODOs,...
In an effort to harden the Evaluate function, I have moved all metrics from dsp to dspy, added type hints and made Evaluate Pydantic validated. This should not affect any...
Hi Team, In an effort to increase transparency and type safety, the below PR does the following: 1. Make Dataloader/Dataset objects Pydantic & Type Safe 2. Make Dataloader/Dataset consistent. Some...
Running the example works fine if you both generate, dump then load the index. However, if you generate and dump the index, you cannot reload the index in a new...
In a few different places, the transformers logger is used in log warnings. However, throughout the remainder of the `save.py` code print statements are provided to show the user additional...