dspy

dspy copied to clipboard

Add `wandb` logging to `BootstrapFewShot`'s `metric_val`

1

Weights & Biases (wandb) are one of the industry leaders in experiment tracking software for Machine Learning. I think `runs` and `sweeps` both offer significant value to monitoring DSPy optimization...

CShorten

Adds ensemble to the teleprompt imports. Solves #533

isaacbmiller

Error when running Evaluate: 'str' object has no attribute '_store'

4

I am trying out DSPy 2.3.6 with a simple transcript summarization example: ```python class Summarizer(dspy.Module): def __init__(self): super().__init__() self.summarizer = dspy.Predict('transcript -> summary') def forward(self, transcript): return dspy.Prediction(summary=self.summarizer(transcript=transcript)) ``` I...

gramster

DSPy Only Predict

1

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,...

KCaverly

Fix return_all_scores in evaluate

4

Addresses https://github.com/stanfordnlp/dspy/issues/477

quajak

ci(dspy): Fix failing tests coming from forks

1

This PR does two main things: 1. It fixes an issue where the code would try to checkout code from a repo it did not have access to. The way...

isaacbmiller

add 'k' as argument to FaissRM.forward()

4

add 'k' as argument to FaissRM.forward()

software-artisan

Adds native support for Claude models

2

Adds native support for claude wrapper

skucherlapati

Fix applymap deprecation warning

4

Fixes #492

quajak

Fix `long_text` key problem with RMs

2

Draft, started with changing `dsp.retrieveEnsemble` to `dsp.settings.rm` in calls to dspy.Retrieve === TODO == I now need to remove the long_text key from all the RMs === RELATED PROJECT TODO...

CShorten