Ramiro Salas
Ramiro Salas
I reported a [somewhat related issue](https://github.com/stanfordnlp/dspy/issues/749) with `ChainOfThoughtWithHint()`, but I *do* get the proper output with `ChainOfThough('question -> answer', n=3)` using `lm = dspy.OllamaLocal(model="openhermes:7b-mistral-v2.5-fp16", max_tokens=4000, timeout_s=240) dspy.settings.configure(lm=lm)`
I recommend you re-test with the latest version of Ollama. The issue I opened initially is now closed. Please see this: https://github.com/stanfordnlp/dspy/issues/749#issuecomment-2094875038
It would be great to support this. I've moved to [Drift](https://akhater.github.io/drift/) (a TiddlyWiki custom distribution) exclusively for my personal and professional information management, but for very large amounts of text,...
Thanks a lot! I'll make a note whenever I can't parse a site, to attempt this mechanism. Wondering if we should keep this open basically to ensure it gets in...