Connor Shorten

Hey team, some notes so far: 1. Backend refactor sounds great! 2. Indeed, this is an interesting one. 3. Can’t comment on how this is currently configured. 4. Awesome, certain...

@S1M0N38 you would still need the thin wrapper though to pass in optional arguments with `kwargs`.

@S1M0N38 I think the way multiple generations are sampled -- for example Cohere has `num_generations` but the google.generativeai API has no such option. Probably little nuances like this, but the...

Interesting question, I suspect digging into how `dspy.ReAct` implements the `dspy.Retrieve` tool could be a good start to understanding how to interface all tools @CyrusOfEden. Maybe this is the argument...

**[Tool vs. Retrieve]** Ah, I think a very interesting distinction could be made between `dspy.Retrieve` and `dspy.Tool`. Can you please catch me up on how the Python Interpreter is interfaced?...

Would love this!

Hey @arnavsinghvi11! No I don't believe so, it looks like the PR is removing default arguments from the hybrid search -- which I'm not 100% sure the utility of, cc...

Hey @betimd! Thank you so much for telling us more about this problem, really happy to hear about use cases with DSPy, LlamaIndex, and Weaviate! I have reviewed the PR...

Really powerful stuff, will have a massive impact on how we interface LLM Fine-Tuning APIs as well, e.g. https://docs.endpoints.anyscale.com/fine_tune/e2e_finetune_and_serve_example#using-the-fine-tuned-model. 👍

Hey @BoxiYu! It does not look like DSPy is working towards supporting black-box tool APIs. Please see this example of how the `dspy.ReAct` module interfaces tools in DSPy: https://github.com/stanfordnlp/dspy/blob/main/examples/agents/multi_agent.ipynb. Please...