openextract 0.3.0

Extract structured data from documents, images, audio, and video using LLMs

openextract

Extract structured data from documents, images, audio, and video using LLMs.

Installation

uv add openextract

Usage

from pydantic import BaseModel
from openextract import extract

class PdfInfo(BaseModel):
    summary: str
    language: str

result = extract(
    schema=PdfInfo,
    model="openai-responses:gpt-5.2",
    url="https://example.com/document.pdf",
    instructions="return a 2 sentence summary and the primary language of the document",
)
print(result)

Logging

To enable logfire instrumentation for tracing:

from openextract import configure_logging

configure_logging()

Error Handling

from openextract import (
    extract,
    ExtractionError,
    ModelError,
    SchemaValidationError,
    UrlFetchError,
)

try:
    result = extract(...)
except UrlFetchError as e:
    print(f"Failed to fetch URL: {e}")
except SchemaValidationError as e:
    print(f"Output didn't match schema: {e}")
except ModelError as e:
    print(f"Model API error: {e}")
except ExtractionError as e:
    print(f"Extraction failed: {e}")

Supported Media Types

Type	Extensions
Documents	.pdf, .doc, .docx, .txt, .html, .csv, .xls, .xlsx
Images	.jpg, .jpeg, .png, .gif, .webp, .bmp, .svg
Audio	.mp3, .wav, .ogg, .flac, .aac, .m4a
Video	.mp4, .mov, .avi, .mkv, .webm, .wmv

Changelog

See CHANGELOG.md for release history.

Contributing

See CONTRIBUTING.md for development setup and guidelines.