OE
on main | sessions, styles, and typed results

Structured Extraction

Typed output from any media.

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

Read the guide View Source
Terminal install 
$ uv add openextract
$ openextract report.pdf \
    --schema mypkg:Invoice \
    --model xai:grok-4.3
{ "total": 1240.00, "currency": "USD", ... }
Pydantic Any LLM

Zero Config

One function call, or a reusable session. Bring a schema, media, and a model string.

Multi-Media

Documents, images, audio, and video with smart routing.

Any LLM

OpenAI, Anthropic, Google, Bedrock, xAI, Groq, Mistral, OpenRouter, Ollama, and more via pydantic-ai.

Type Safe

Pydantic schemas ensure validated, typed output every time.

How it works

Schema in, typed data out

Define a BaseModel, call extract(), get validated output.

1

Define a schema

Describe the shape you want with a Pydantic model.

2

Point at any media

Documents, images, audio, or video via path, URL, bytes, or a session.

3

Get typed output

Validated against your schema. No parsing, no regex.

Terminal extract.py 
from pydantic import BaseModel
from openextract import extract

class Report(BaseModel):
    title: str
    findings: list[str]
    severity: int

result = extract(
    schema=Report,
    model="xai:grok-4.3",
    input_file="https://example.com/report.pdf",
    instructions="Extract findings",
)

What’s new

In v0.11.0

The latest PyPI release: v0.11.0.

Full changelog
Swarms

Swarms and agents

extract_swarm runs several agents over one input and reduces their outputs; define_agent packages a specialist you can import, compose, or serve over HTTP.

extract_swarm define_agent
Styles

Direct, search, or code

Send media in one shot, grep a text document with file tools, or let the model write Python against it.

direct search code
CLI

Batch-ready CLI

Incremental --output jsonl, --manifest per-input media types, progress on stderr, and --swarm / --agent from the shell.

jsonl manifest swarm

Also in v0.11.0: reusable Extractor sessions, typed input/result contracts, 50 MiB input caps, ExtractBench for any model. v0.10.0 shipped non-blocking async I/O and transient-only retries.

Documentation

Guides and contracts

Start with the guide. Coding agents should use the agent contract or llms.txt.

Guide

Install, inputs, styles, sessions, batch, errors, and CLI — the how-to.

For agents

Which API to generate, input pitfalls, exceptions, and TestModel fixtures.

API reference

Public functions, sessions, input/result contracts, and common arguments.

CLI contracts

Stdout, stderr, exit codes, retries, styles, and batch partial failures.

Providers

Capability matrix, extras, credentials, and verified vs expected media support.

Troubleshooting

Missing extras, URL fetch, schema failures, retries, and batch API choice.

Works with any media

Documents Images Audio Video

PDF, DOCX, PNG, JPG, MP3, MP4, and 20+ formats