Paula Ceccon

I'm just doing: ``` teacher_model = dspy.OpenAI( model=config.COMPLETION_CONFIG["model_teacher"], max_tokens=config.COMPLETION_CONFIG["max_tokens"], ) ``` While my config is: ``` COMPLETION_CONFIG: dict[str, any] = { "max_tokens": 250, "temperature": 0.0, "model_teacher": "gpt-4", "model_student": "gpt-3.5-turbo", "presence_penalty":...

As I said, I don't get anything that gives me more clues about the error, but it only happens when threads > 1. Once it happens, it doesn't recover. ```...

I'm doing something similar, using GPT-4, and using `dspy` vs "raw" call to OpenAi is extremely slow. With 10k points, I get a result with OpenAI in 30 minutes. With...

Same issue , any updates?

Following as I'm having the same issue, using gpt-4o-mini. ``` ValueError: Expected dict_keys(['advice', 'categories']) but got dict_keys(['advice']) Average Metric: 66.34999999999998 / 184 (36.1): 62%|██████▏ | 184/299 [00:19

As per another [example](https://github.com/stanfordnlp/dspy/issues/1717) provided by @okhat, adding type hints seems to have solved the issue for me. It might be worth updating docs (such as [this](https://dspy-docs.vercel.app/building-blocks/5-metrics/?h=trace#advanced-accessing-the-trace)) to make clear...