pydantic-chatcompletion

here is code (with several examples) that takes it a couple steps further by validating the output json and pydantic model and providing feedback to the llm model when it gets either of those wrong: https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas...

Hey everyone, So, I stumbled upon this really cool idea of using Pydantic to deserialize and validate OpenAI's outputs over on this HN thread https://news.ycombinator.com/item?id=35821748. It got me thinking about how I'd like a slightly tweaked API to better fit my own needs. I also found some neat stuff in jiggy-ai's Pydantic implementation for chat completion https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas..., and picked up tips from various blog posts and comments on how to up the game with the quality of a model's output by providing examples. So, I cooked up this library - just about 100 lines of code, but it's got some nice features and it's fully tested. I hope some of you find it useful. I'd love to hear your thoughts and feedback. Cheers!

Nice project! I took some inspiration from this as well as https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas... to create the following: https://github.com/knowsuchagency/struct-gpt I tried to make the API as intuitive as possible and added the ability to provide examples to improve the reliability and quality of the LLM's output.

Here's 40 lines of python code that I've found to be unreasonably effective at accomplishing something similar: https://github.com/jiggy-ai/pydantic-chatcompletion/blob/mas...

pydantic_chatcompletion is a simple but powerful wrapper for OpenAI's ChatCompletion API that enables “one line of code” extraction of structured data from unstructured text using OpenAI and Pydantic. By providing a Pydantic model as an additional argument to an OpenAI ChatCompletion call, this package allows developers to easily obtain structured data that conforms to their Pydantic model definition. It works by inserting a tuned prompt that includes the Pydantic model’s json_schema. Post-completion it further validates the language model output and remediates errors by providing feedback to the model if errors are encountered during json parsing or during Pydantic model validation. Six examples are provided for different types of unstructured data, including nested data.