pip install docpick            # core (LLM extraction only)
pip install docpick[paddle]    # + PaddleOCR (recommended)
pip install docpick[easyocr]   # + EasyOCR (Korean-optimized)
pip install docpick[got]       # + GOT-OCR2.0 (GPU, vision-language)
pip install docpick[all]       # all OCR backends

from docpick import DocpickPipeline
from docpick.schemas import InvoiceSchema

pipeline = DocpickPipeline()
result = pipeline.extract("invoice.pdf", schema=InvoiceSchema)

print(result.data)           # Structured dict matching schema
print(result.validation)     # Validation errors/warnings
print(result.confidence)     # Per-field confidence scores

# Extract structured data
docpick extract invoice.pdf --schema invoice --output result.json

# OCR only (no LLM)
docpick ocr document.png --lang ko,en

# Validate extracted JSON
docpick validate result.json --schema invoice

# Batch process a directory
docpick batch ./documents/ --schema invoice --output ./results/ --concurrency 4

# List available schemas
docpick schemas list

# Show schema details
docpick schemas show invoice

from pydantic import BaseModel
from docpick import DocpickPipeline
from docpick.validation.rules import SumEqualsRule, RequiredFieldRule

class MyDocument(BaseModel):
    """Custom document schema."""
    company_name: str | None = None
    total_amount: float | None = None
    tax_amount: float | None = None
    net_amount: float | None = None
    items: list[dict] | None = None

    class ValidationRules:
        rules = [
            RequiredFieldRule("company_name"),
            SumEqualsRule(["net_amount", "tax_amount"], "total_amount"),
        ]

pipeline = DocpickPipeline()
result = pipeline.extract("my_document.pdf", schema=MyDocument)

docpick extract document.pdf --schema my_schema.json

from docpick.validation.cross_document import create_trade_document_validator

validator = create_trade_document_validator()
result = validator.validate({
    "invoice": invoice_data,
    "bl": bl_data,
    "packing_list": packing_list_data,
    "certificate": certificate_data,
})
print(result.is_valid)

docpick config set llm.provider ollama
docpick config set llm.base_url http://localhost:11434
docpick config set llm.model qwen3.5:7b

result = pipeline.extract("damaged.pdf", schema=InvoiceSchema)
if result.errors:
    print("Pipeline warnings:", result.errors)
if result.data:
    print("Partial extraction:", result.data)

from docpick.batch import BatchProcessor
from docpick.schemas import InvoiceSchema

processor = BatchProcessor(concurrency=4)
result = processor.process_directory(
    "./invoices/",
    schema=InvoiceSchema,
    recursive=True,
)

print(f"Processed {result.succeeded}/{result.total} files")
for path, extraction in result.results.items():
    print(f"{path}: {extraction.data.get('total_amount')}")

flowchart TD
    A["📄 Document\n(PDF / Image)"] --> B["DocumentLoader\n(pypdfium2)"]
    B --> C["Tier 1: OCR\n(PaddleOCR / EasyOCR)\nCPU"]
    C --> D{"Confidence\n≥ threshold?"}
    D -->|"yes"| F["LLM Extractor\n(vLLM / Ollama)\nSchema prompt"]
    D -->|"no"| E["Tier 2: VLM\n(GOT / VLM)\nGPU"]
    E --> F
    F --> G["Pydantic Validation"]
    G --> H["✅ ExtractionResult"]