instructor

I've been using the instructor[1] library recently and have found the abstractions simple and extremely helpful for getting great structured outputs from LLMs with pydantic. 1 https://github.com/jxnl/instructor/tree/main

One of the most powerful ways to integrate LLMs with existing systems is constrained generation. Libraries such as outlines[1] and instructor[2] allow structural specification of the expected outputs as regex patterns, simple types, jsonschema or pydantic models. Llama.cpp supports bnf grammars. These outputs often consume significantly fewer tokens than chat or text completions. [1] https://github.com/outlines-dev/outlines [2] https://github.com/jxnl/instructor

The best GPT-wrapper you’ll see today? ...but this one hasn't raised oodles of cash. Mike (creator) here, excited to hear what HN-folks think. Anything to add/improve? Had fun building, extra s/out to Railway, NextJS, and https://github.com/jxnl/instructor Check it out: https://www.unboundedbooks.com/ email: mike@unboundedbooks.com

There was another post today about using Pydantic for function enabled completions: https://github.com/jxnl/openai_function_call I whipped up an example doing something similar last Friday using a decorator, inspect, ast and __doc__ usage: https://gist.github.com/kordless/7d306b0646bf0b56c44ebca2b8e.... The example pulls top results from Algoia's HN search and then chains them into another prompt for GPT-X. The blog post is here: https://www.featurebase.com/blog/function-integration-in-ope... Currently integrating this approach into PythonGPT[1], which will build a function on the fly, extract the method info, then call the code in exec(). I would label it "very dangerous"... [1] https://github.com/FeatureBaseDB/PythonGPT

I mostly wrote this to be as minimally invasive as possible and no require installation (just copy paste the code) The blog and code is here: https://github.com/jxnl/openai_function_call based on a thread of notes i took yesterday: https://twitter.com/jxnlco/status/1668819081187983360 I plan to add some examples in the future on how to be creative with pydantic and also how to get better performance out.