openextract
Structured extraction for PythonPython 3.12+ · MIT

Any file.
Structured data.

Turn documents, images, audio, and video into validated Pydantic models.

pip install 'openextract[all]'
See how it works

Define it. Extract it.

Set your provider’s API key, then pass a schema and a file.

Your code
from pydantic import BaseModel
from openextract import extract

class Invoice(BaseModel):
    vendor: str
    total: float
    currency: str

invoice = extract(
    Invoice,
    "openai:gpt-5",
    source="./invoice.pdf",
)
Validated result
vendor
Halvorsen Print Co.
total
1240.0
currency
EUR

A few details.

What do I pass in?
extract(schema, model, source, instructions=None, *, media_type=None)
schema
The Pydantic model you want back.
model
A pydantic-ai model string like "anthropic:claude-sonnet-5", or a configured Model.
source
Where the file is: a path like "./invoice.pdf", a pathlib.Path, or an https:// URL. Or the file's raw bytes. A string is never read as the document's text.
instructions
Optional guidance, like "Amounts are in EUR."
media_type
Only needed to override what openextract infers.
How does it know the file type?

It takes the first answer it finds: the media_type you passed, the file extension, the URL's Content-Type header, then the file's leading bytes.

Recognized by content
PDF, PNG, JPEG, GIF, WebP, MP3, WAV, FLAC, OGG, MP4, and UTF-8 text.
What happens when it fails?

Every error subclasses ExtractionError and keeps the original exception as its cause.

ModelError
The provider returns an error.
SchemaValidationError
The output doesn't match your schema.
ProviderNotInstalledError
The provider's SDK isn't installed.
ExtractionError
A URL can't be fetched.
Which models can I use?

Any model pydantic-ai supports. Install the matching extra and set its API key.

pip install 'openextract[anthropic]'   # openai, google, bedrock, groq, mistral,
                                       # cohere, huggingface, openrouter, xai, all
Can I use decision models?

Yes. Use OpenAI Decisions with OPENAI_API_KEY, or Jev with OPENROUTER_API_KEY. Both read text and images into bool, Literal, or Enum fields. No provider extra is needed.

triage = extract(
    Triage, "openai-decisions:gpt-6-luna",
    source="./receipt.png",
)
Fields
bool, Literal, or Enum. Any other type raises a TypeError.
Questions
Each field becomes one question, phrased by its description.
bool
True when the probability of yes is at least 0.5.
OpenAI
Use openai-decisions: for Decisions; openai: keeps general extraction. Supports 1–400 fields.
Sources
Text and images only.
Is there an async version?

Yes. It takes the same arguments. Await it.

invoice = await extract_async(Invoice, "openai:gpt-5", source="./invoice.pdf")