Introduction to Instructor

The Instructor project is a powerful library designed for data extraction, leveraging the capabilities of OpenAI models. With a robust codebase of over 110,000 lines and 750 files, it provides a comprehensive framework for developers looking to enhance their data extraction workflows.

Main Features of Instructor

• Evaluation Tests: Monitor the quality of OpenAI models and the Instructor library.
• Flexible Integration: Support for various LLM providers through optional dependencies.
• Utility Scripts: Maintain code quality and documentation with integrated scripts.
• Community Contributions: Open for collaboration, allowing developers to report issues and submit pull requests.

Technical Architecture and Implementation

Instructor is built using Python and follows a modular architecture, allowing for easy integration of new features and providers. The project utilizes pytest for testing, ensuring that all components function as expected.

To understand the structure, you can explore the test_extract_users.py file, which demonstrates how to create parameterized tests for various data extraction scenarios.

Setup and Installation Process

Setting up the Instructor library is straightforward. You can choose between UV or Poetry for dependency management. Here’s how to get started:

Using UV

# macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows PowerShell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Clone the repository
git clone https://github.com/YOUR-USERNAME/instructor.git
cd instructor

# Install with development dependencies
uv pip install -e ".[dev,docs]"

Using Poetry

# Install Poetry
curl -sSL https://install.python-poetry.org | python3 -

# Clone the repository
cd instructor

# Install with development dependencies
poetry install --with dev,docs

Usage Examples and API Overview

Once installed, you can start using the Instructor library to extract data. Here’s a simple example:

import instructor
from openai import OpenAI
from pydantic import BaseModel

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

client = instructor.from_openai(OpenAI())

person = client.chat.completions.create(
    model="gpt-3.5-turbo",
    response_model=Person,
    messages=[
        {"role": "user", "content": "Extract: John Doe is 25 years old"}
    ]
)

print(person.name)  # "John Doe"
print(person.age)   # 25

Community and Contribution Aspects

The Instructor project thrives on community contributions. Here’s how you can get involved:

• Evaluation Tests: Create new tests to evaluate specific capabilities.
• Reporting Issues: If you find a bug, file an issue on GitHub with detailed information.
• Contributing Code: Submit pull requests for small changes or discuss larger changes through issues.

For more details, refer to the Contributing Guidelines.

License and Legal Considerations

The Instructor library is licensed under the MIT License, allowing for free use, modification, and distribution. Ensure to include the copyright notice in all copies or substantial portions of the software.

Conclusion

Instructor is a powerful tool for developers looking to enhance their data extraction capabilities. By contributing to the project, you can help improve its functionality and performance. Join the community today and start making a difference!

For more information, visit the Instructor GitHub Repository.

FAQ

Have questions? Check out our FAQ section below!