Instructor is a Python library that makes it a breeze to work with structured outputs from large language models (LLMs). Built on top of Pydantic, it provides a simple, transparent, and user-friendly API to manage validation, retries, and streaming responses. Get ready to supercharge your LLM workflows!
- 🎭 Response Models: Specify Pydantic models to define the structure of your LLM outputs
- 🔄 Retry Management: Easily configure the number of retry attempts for your requests
- ✅ Validation: Ensure LLM responses conform to your expectations with Pydantic validation
- 🌊 Streaming Support: Work with Lists and Partial responses effortlessly
- 🔌 Flexible Backends: Seamlessly integrate with various LLM providers beyond OpenAI
Install Instructor with a single command:
pip install -U instructorNow, let's see Instructor in action with a simple example:
frompydanticimportBaseModelfrominstructorimportpatchfromopenaiimportOpenAI# Define your desired output structureclassUserInfo(BaseModel):
name: strage: int# Patch the OpenAI clientclient=patch(OpenAI())
# Extract structured data from natural languageuser_info=client.chat.completions.create(
model="gpt-3.5-turbo",
response_model=UserInfo, messages=[
{"role": "user", "content": "John Doe is 30 years old."}
]
)
print(user_info.name) # "John Doe"print(user_info.age) # 30Instructor leverages Pydantic to make validating LLM outputs a breeze. Simply define your validation rules in your Pydantic models, and Instructor will ensure the LLM responses conform to your expectations. No more manual checking or parsing!
frompydanticimportBaseModel, ValidationError, BeforeValidatorfromtyping_extensionsimportAnnotatedfrominstructorimportllm_validatorclassQuestionAnswer(BaseModel):
question: stranswer: 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",
)
exceptValidationErrorase:
print(e)Dive deeper into Instructor's concepts and features:
Have questions? Want to share your Instructor projects? Join our vibrant community on Discord! We're here to help you get the most out of Instructor and celebrate your successes.
Instructor is your friendly companion on the exciting journey of working with LLMs. Install it now and unlock the full potential of structured outputs in your projects. Happy building! 🚀
We can't wait to see the amazing things you create with Instructor. If you have any questions, ideas, or just want to say hello, don't hesitate to reach out on Twitter or Discord. Let's build the future together! 🌟
Install dependencies with
poetry install -E anthropicUsage:
importinstructorfromanthropicimportAnthropicclassUser(BaseModel):
name: strage: intcreate=instructor.patch(create=anthropic.Anthropic().messages.create, mode=instructor.Mode.ANTHROPIC_TOOLS)
resp=create(
model="claude-3-opus-20240229",
max_tokens=1024,
max_retries=0,
messages=[
{
"role": "user",
"content": "Extract Jason is 25 years old.",
}
],
response_model=User,
)
assertisinstance(resp, User)
assertresp.name=="Jason"assertresp.age==25We invite you to contribute to evals in pytest as a way to monitor the quality of the OpenAI models and the instructor library. To get started check out the jxnl/instructor/tests/evals and contribute your own evals in the form of pytest tests. These evals will be run once a week and the results will be posted.
If you want to help, checkout some of the issues marked as good-first-issue or help-wanted found here. They could be anything from code improvements, a guest blog post, or a new cookbook.
We also provide some added CLI functionality for easy convinience:
instructor jobs: This helps with the creation of fine-tuning jobs with OpenAI. Simple useinstructor jobs create-from-file --helpto get started creating your first fine-tuned GPT3.5 modelinstructor files: Manage your uploaded files with ease. You'll be able to create, delete and upload files all from the command lineinstructor usage: Instead of heading to the OpenAI site each time, you can monitor your usage from the cli and filter by date and time period. Note that usage often takes ~5-10 minutes to update from OpenAI's side
This project is licensed under the terms of the MIT License.