litestruct

Make structured output easy for different LLM providers with the help of litellm

This file will become your README and also the index of your documentation.

Developer Guide

If you are new to using nbdev here are some useful pointers to get you started.

Install litestruct in Development mode

# make sure litestruct package is installed in development mode
$ pip install -e .

# make changes under nbs/ directory
# ...

# compile to have changes apply to litestruct
$ nbdev_prepare

Usage

Installation

Install latest from the GitHub repository:

$ pip install git+https://github.com/gautam-e/litestruct.git

or from pypi

$ pip install litestruct

Documentation

Documentation can be found hosted on this GitHub repository’s pages. Additionally you can find package manager specific guidelines on conda and pypi respectively.

How to use

from litestruct import *
from pydantic import BaseModel

model="azure/gpt-4o-2024-08-06" # e.g. openai/gpt-4o-2024-08-06 would use the standard OpenAI
system_prompt = "Extract the event information."

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

user_prompt = "Alice and Bob are going to Carmen's birthday party on 22nd March 2025"

r = structured_output(model=model,
                      system_prompt=system_prompt,
                      response_format=CalendarEvent, #Note this is the class name (without the `()`)
                      user_prompt=user_prompt,
                 )

r.model_dump()

{'name': "Carmen's Birthday Party",
 'date': '2025-03-22',
 'participants': ['Alice', 'Bob']}