/instructor

openai function calls for humans

Primary LanguagePythonMIT LicenseMIT

Instructor (openai_function_call)

GitHub stars GitHub forks GitHub issues GitHub license Documentation Buy Me a Coffee Twitter Follow

Structured extraction in Python, powered by OpenAI's function calling api, designed for simplicity, transparency, and control.

This library is built to interact with openai's function call api from python code, with python structs / objects. It's designed to be intuitive, easy to use, but give great visibily in how we call openai.

Requirements

This library depends on Pydantic and OpenAI that's all.

Installation

To get started with OpenAI Function Call, you need to install it using pip. Run the following command in your terminal:

$ pip install instructor

Quick Start with Patching ChatCompletion

To simplify your work with OpenAI models and streamline the extraction of Pydantic objects from prompts, we offer a patching mechanism for the `ChatCompletion`` class. Here's a step-by-step guide:

Step 1: Import and Patch the Module

First, import the required libraries and apply the patch function to the OpenAI module. This exposes new functionality with the response_model parameter.

import openai
import instructor
from pydantic import BaseModel

instructor.patch()

Step 2: Define the Pydantic Model

Create a Pydantic model to define the structure of the data you want to extract. This model will map directly to the information in the prompt.

class UserDetail(BaseModel):
    name: str
    age: int

Step 3: Extract Data with ChatCompletion

Use the openai.ChatCompletion.create method to send a prompt and extract the data into the Pydantic object. The response_model parameter specifies the Pydantic model to use for extraction.

user: UserDetail = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    response_model=UserDetail,
    messages=[
        {"role": "user", "content": "Extract Jason is 25 years old"},
    ]
)

Step 4: Validate the Extracted Data

You can then validate the extracted data by asserting the expected values. By adding the type things you also get a bunch of nice benefits with your IDE like spell check and auto complete!

assert user.name == "Jason"
assert user.age == 25

LLM-Based Validation

LLM-based validation can also be plugged into the same Pydantic model. Here, if the answer attribute contains content that violates the rule "don't say objectionable things," Pydantic will raise a validation error.

from pydantic import BaseModel, ValidationError, BeforeValidator
from typing_extensions import Annotated
from instructor import llm_validator

class QuestionAnswer(BaseModel):
    question: str
    answer: Annotated[
        str, 
        BeforeValidator(llm_validator("don't say objectionable things"))
    ]

try:
    qa = QuestionAnswer(
        question="What is the meaning of life?",
        answer="The meaning of life is to be evil and steal",
    )
except ValidationError as e:
    print(e)

Its important to not here that the error message is generated by the LLM, not the code, so it'll be helpful for re asking the model.

1 validation error for QuestionAnswer
answer
   Assertion failed, The statement is objectionable. (type=assertion_error)

Using the Client with Retries

Here, the UserDetails model is passed as the response_model, and max_retries is set to 2.

import instructor
from pydantic import BaseModel, field_validator

# Apply the patch to the OpenAI client
instructor.patch()

class UserDetails(BaseModel):
    name: str
    age: int

    @field_validator("name")
    @classmethod
    def validate_name(cls, v):
        if v.upper() != v:
            raise ValueError("Name must be in uppercase.")
        return v

model = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    response_model=UserDetails,
    max_retries=2,
    messages=[
        {"role": "user", "content": "Extract jason is 25 years old"},
    ],
)

assert model.name == "JASON"

IDE Support

Everything is designed for you to get the best developer experience possible, with the best editor support.

Including autocompletion:

autocomplete

And even inline errors

errors

To see more examples of how we can create interesting models check out some examples.

License

This project is licensed under the terms of the MIT License.