Mr Ruben

I have been waiting for this fix since March-2024. I am with @ssonal Who wants a useless url in the error message? (+noise, +tokens, no benefit) I bet you will...

If this is not what you are after, could you show us some code? ``` class Output(BaseModel): name: str age: int ``` Let's imagine we just have the object. ```...

> Could you help me understand what might be the reason for this? Without Instructor: Call == Text With Instructor: Call == Text + Output_Schema More work to be done,...

That web nailed it! Really good analysis. https://www.boundaryml.com/blog/type-definition-prompting-baml It has been my experience since the beginning. I documented it briefly here https://github.com/jxnl/instructor/discussions/497#discussioncomment-8979998 I do by hand what that web describes...

I'll respond myself Q: Can the schema be modified to not include **title**s? A: Yes Example: ```python from pydantic import BaseModel class Output(BaseModel): type_of_atomic_element: str name_of_the_compound: str date_it_was_first_discovered: str @classmethod...

Regarding 'removing titles' and other optimizations to the 'schema sent' https://community.openai.com/t/advanced-structured-output-use-case-accident-research/663005/9

> That being said, it's an interesting paper, I wonder if we can get best of both worlds by allowing more freeform reasoning followed by highly structured output or by...

> We released a blog post on this : https://python.useinstructor.com/blog/2024/09/26/bad-schemas-could-break-your-llm-structured-outputs/ Nice study. It would have been very nice to include "plain-text output" as part of the experiments, although I understand...

Additionally ... I have noticed Burr has good 'early errors detection' like "you are doing ... but you haven't done ..." You may consider adding 2 more: - If State...

In -> https://github.com/apache/burr/tree/main/examples/talks But only if it wasn't meant to be where it is presently (there may be a reason, which is still unclear / unanswered).