dspy

dspy copied to clipboard

sfc-gh-alherrera

Deprecation warnings point to non-existing `dspy.set_log_level`

2

There are deprecation warnings ([here ](https://github.com/stanfordnlp/dspy/blob/afa654f805d0b93eb56035ecdfa2e6eb5c477d66/dspy/evaluate/evaluate.py#L56 )and [here](https://github.com/stanfordnlp/dspy/blob/afa654f805d0b93eb56035ecdfa2e6eb5c477d66/dspy/teleprompt/copro_optimizer.py#L78)) saying that the user should use `dspy,set_log_level`, which does not exist.

Xargonus

AvaTaR agent: 'Action' object has no attribute 'strip'

2

(dspy-ai 2.5.0) Hi dspy-team, I am getting the following error after upgrading dspy-ai to 2.5.0 when using the AvatarOptimizer. Starting the task... Processing examples: 14%|█▍ | 1/7 [00:01

tikoehle

Use of LiteLLM Router for load balancing and fallbacks

14

As DSPy is using LiteLLM internally, I wonder how to use the LiteLLM router. In particular, I would like to add load balancing and fallbacks via LiteLLM. Another example. LiteLLM...

denisergashbaev

Empty context causes 4o models to return "N/A"

2

if dspy.Prediction is called with context = [] this causes in chat_adapter.py ``` def format_fields(fields): output = [] for k, v in fields.items(): v = _format_field_value(v) output.append(f"[[ ## {k} ##...

excubo-jg

Prompt changed based on when `dspy.settings.configure(lm=lm)` is executed.

20

If you configure the LM (`dspy.settings.configure(lm=lm)`) before initializing your modules you get a different prompt to if you configure your LM after initializing your modules. ```python dspy.settings.configure(lm=lm) pot = ChainOfThought(BasicQA)...

mikeedjones

support TEI

2

support TEI(Text Embeddings Inference), For detailed information, visit: [https://github.com/huggingface/text-embeddings-inference](https://github.com/huggingface/text-embeddings-inference).

xiayouran

resolve #1045 Change summary: - Add a `dump_state`/`load_state` pair to Signature class for better modularization. - Remove the `save_verbose` option, as it doesn't make sense to change input fields to...

chenmoneygithub

Improve the observability and readability of BootstrapFewShot optimizer

2

The PR has two parts: 1. Better progbar, currently the progbar is quite confusing because it never finishes. Instead of setting the length of progbar as the training set size,...

chenmoneygithub

[Insights & Questions] About MIPROV2

1

Firstly, thanks for the amazing package! I've done a sharing session with senior tech managers in my company, and they were quite convinced. I have some interesting insights to share...

SauceCat