Dhar Rawal

@arnavsinghvi11 - I did what you suggested and used loops to load/save the candidate programs. But I noticed that the json for candidate program at index 0 actually had ALL...

@arnavsinghvi11 - I have submitted PR #843 for this issue. Ready for review I have punted on the "json for candidate program at index 0 actually had ALL the other...

@arnavsinghvi11 PR #795 does not implement any special code for exponential backoff so it would be welcome. @aazizisoufiane can implement once PR #795 is merged. just noticed there is a...

@okhat @arnavsinghvi11 - This PR now also includes a fix for issue #824. The fix is in teleprompt/random_search.py

@okhat - any progress on this review? I am continuing to work on intelligent ensemble routing and don't want to muddy this PR with commits related to that work btw,...

> This is so cool.... I need to check the parallelization, it's a bit tricky in DSPy due to dspy.settings. > > In dspy.evaluate.Evaluate we do things in a bit...

Fixed #894 in dsp/modules/aws_models.py, in class AWSMeta(AWSModel) by moving below functionality from __init__ function: ``` max_tokens = query_args.pop("max_tokens", None) if max_tokens: query_args["max_gen_len"] = max_tokens ``` to the __create_body__ function and...

@okhat - I have reverted the parallelization in EnsembledProgram.forward() based on your review and feedback. The remaining fixes/improvements are targeted and should not have side-effects

Perhaps the code should have a key error check like this? ``` if i in example_sets[id(predictor)]: new_instruct = dspy.Predict( BasicGenerateInstructionWithExamplesAndDataObservations, n=1, temperature=self.init_temperature, )( basic_instruction=basic_instruction, observations=self.observations, examples=example_sets[id(predictor)][i], ) ```

Reviewed. I fixed this comprehensively in https://github.com/stanfordnlp/dspy/pull/843. You caught the dict copy issue but there's another check that's also needed. You can review the aws_models.py in my PR