7 Comments
User's avatar
Yiming's avatar

I noticed that your article was improperly forwarded by CSDN and paid for reading: https://blog.csdn.net/llm_way/article/details/147583065

Expand full comment
Zachary Huang's avatar

Thank you! Not much I can do though 😔

Expand full comment
Jim's avatar

It resolved a question by me.

Why are there so many people I saw using YAML to get their LLM answers.

Expand full comment
tam's avatar

In your experience, is generated yaml more likely to be 'correct' than generated json (guided by a json schema, then run through a json repair library like https://github.com/mangiucugna/json_repair)? I ask because I have reasonably good results with json schema+repair, but if I can truly get yet better results with yaml that would be quite valuable.

Expand full comment
Zachary Huang's avatar

If the json repair is for parsing issues, yaml is definitely better

Expand full comment
patcap's avatar

Whats the advantage of YAML + Prompt based vs something like instructor library? Most of the large LLM providers already support some form of structured output/tool calling which instructor seems to use.

Expand full comment
Zachary Huang's avatar

This post is about how structured output can be implemented. Instructor provides one specific implementation that is suboptimal. For example, it uses JSON: https://github.com/instructor-ai/instructor/blob/4779f25a28227e6975d77904f30173a7800ff963/instructor/process_response.py#L310, which causes a lot of troubles.

So this post is like telling you how the vehicle engine works. Instructor provides a built car, but not a perfect one.

Expand full comment