from gaia.vision import VisionSDK, ExtractionSchema

vision = VisionSDK()

# Medical forms → structured data
result = vision.extract("form.pdf", schema=medical_schema)

# Legal logs → text + tables + visuals
result = vision.extract("logs.pdf", extract_tables=True, extract_visuals=True)

# Technical manuals → RAG indexing
result = vision.extract("manual.pdf", pages="all")

from gaia.vision import VisionSDK, ExtractionSchema

schema = ExtractionSchema.from_dict({
    "required": ["first_name", "last_name"],
    "fields": {
        "date_of_birth": {"type": "date"},
        "allergies": {"type": "string", "critical": True},
    },
    "allow_additional": True,
})

vision = VisionSDK()
result = vision.extract("intake_form.pdf", schema=schema)

vision = VisionSDK()

result = vision.extract(
    "driver_logs.pdf",
    pages="all",  # 1,200 pages
    extract_tables=True,
    extract_visuals=True,
    on_progress=callback,
)

# Access timeline charts
for page in result.pages:
    for visual in page.visuals:
        if visual.type == "timeline":
            print(visual.data)

from gaia.vision import VisionSDK
from gaia.rag import RAGSDK

# Extract with tables
vision = VisionSDK()
doc = vision.extract("manual.pdf", pages="all", extract_tables=True)

# Index with RAG
rag = RAGSDK()
rag.add_document(doc.to_markdown())

# Query
answer = rag.query("What are the safety procedures?")

vision = VisionSDK()

# Batch process receipts
results = vision.extract_batch(
    files=["receipt1.jpg", "receipt2.jpg", ...],
    schema=receipt_schema,
)

# Export as expense report
results.to_excel("expenses.xlsx")

# Or single image with multiple receipts
result = vision.extract(
    "three_receipts.jpg",
    detect_multiple=True,  # Detect 3 receipts in one image
    schema=receipt_schema,
)

vision = VisionSDK()

result = vision.extract("business_card.jpg", schema=contact_schema)

# Export to VCF/CSV
result.to_vcard("contact.vcf")
# Fields: name, title, company, email, phone, linkedin

vision = VisionSDK()

result = vision.extract(
    "drivers_license.jpg",
    schema=id_card_schema,
    detect_face=True,  # Face detection
)

# Validate
age = calculate_age(result.data["date_of_birth"])
is_valid = result.data["expiration_date"] > today()

vision = VisionSDK()

result = vision.extract(
    "bank_statement.pdf",
    pages="all",
    extract_tables=True,
)

# Transaction table
transactions = result.tables[0].to_dataframe()
transactions.to_csv("transactions.csv")

vision = VisionSDK()

# Handwritten meeting notes
result = vision.extract(
    "meeting_notes.jpg",
    handwriting_mode=True,  # Optimized for handwriting
)

# Filled forms (mixed print + handwriting)
result = vision.extract(
    "filled_application.pdf",
    schema=application_schema,
    handwriting_mode=True,
)

src/gaia/vision/
├── sdk.py               # Main VisionSDK class
├── document.py          # Document/Page models
├── schema.py            # ExtractionSchema, ValidationRule
├── preprocessor.py      # Image optimization
├── loaders.py           # PDF/image loading
├── extractors/
│   ├── text.py          # OCR extraction
│   ├── table.py         # Table extraction
│   ├── visual.py        # Visual element extraction
│   └── structured.py    # Schema-based extraction
└── mixin.py             # Agent integration