文档不是文本，而是版面。

pip install z-parser-sdk

import zparser as zp

# 1. Know the cost before spending it — local, no API call, free.
est = zp.estimate("catalogue.pdf")
print(est)              # ~$0.7000 (175 page(s), ocr:mistral-ocr-latest)

# 2. Parse with business context: accuracy comes from vocabulary.
doc = zp.parse(
    "balance-sheet.pdf",
    domain="finance",
    context="Algerian balance sheet, amounts in DZD, SCF chart of accounts.",
)

print(doc.text)         # Markdown: tables, chart data recovered, LaTeX
print(doc.cost)         # 0.0533 — real cost, every unit included
print(doc.usage)        # breakdown of billed units
print(doc.cost_unpriced)  # flags any model with an unknown price

npm install z-parser

import { parse } from 'z-parser';

const doc = await parse('prescription.jpg', {
  domain: 'medical',        // primes drug names, dosages, reference ranges
  visionProvider: 'mistral',
});

console.log(doc.text);
console.log(doc.cost);

// Zero dependencies, TypeScript types shipped, CLI included.

# Fully offline: no data leaves the machine.
# Text, HTML, XML, CSV, Office, Excel, images, EPUB, email AND PDF.

doc = zp.parse(
    "patient_file.pdf",
    doc_vision=True,
    vision_base_url="http://internal-gpu:8000/v1",   # vLLM, Qwen2.5-VL
)

print(doc.cost)   # 0.0 — local engine, nothing billed

# Security contract: a URL you choose never receives the
# server's keys. With no key supplied, the key sent is empty.

docker run -d -p 4056:4056 -e MISTRAL_API_KEY=xxx yatchiyax/z-parser

# file -> {status, kind, parser, num_chars, usage, text}
curl -F file=@invoice.pdf http://localhost:4056/v1/parse

# Office -> displayable PDF (page N = slide N)
curl -F file=@deck.pptx http://localhost:4056/v1/render -o deck.pdf

# PDF -> extracted figures (artwork / page / embedded)
curl -F file=@report.pdf http://localhost:4056/v1/images

# monitoring
curl http://localhost:4056/healthz
curl http://localhost:4056/metrics    # Prometheus metrics