Document Extraction Guide

from rotavision import Rotavision

client = Rotavision()

# Extract from Aadhaar card
result = client.dastavez.extract(
    document_type="aadhaar",
    file_url="https://storage.example.com/aadhaar-scan.pdf"
)

print(f"Name: {result.fields['name']}")
print(f"Name (English): {result.fields['name_english']}")
print(f"DOB: {result.fields['dob']}")
print(f"Confidence: {result.confidence}")

result = client.dastavez.extract(
    document_type="pan",
    file_url="https://storage.example.com/pan-card.jpg"
)

with open("document.pdf", "rb") as f:
    result = client.dastavez.extract(
        document_type="gst_invoice",
        file=f
    )

import base64

with open("document.pdf", "rb") as f:
    base64_content = base64.b64encode(f.read()).decode()

result = client.dastavez.extract(
    document_type="bank_statement",
    file_base64=base64_content
)

result = client.dastavez.extract(
    document_type="aadhaar",
    file_url="...",
    options={
        "mask_number": True,  # Returns XXXX-XXXX-1234
        "extract_photo": True
    }
)

# Fields extracted:
# - name (in original script)
# - name_english
# - dob
# - gender
# - aadhaar_number (masked if option set)
# - address (full, line1, line2, city, state, pincode)
# - photo (if extract_photo=True)

result = client.dastavez.extract(
    document_type="gst_invoice",
    file_url="..."
)

# Fields extracted:
# - invoice_number
# - invoice_date
# - seller (name, gstin, address)
# - buyer (name, gstin, address)
# - items[] (description, hsn_code, quantity, unit_price, total)
# - subtotal, cgst, sgst, igst, total
# - amount_in_words

result = client.dastavez.extract(
    document_type="bank_statement",
    file_url="...",
    options={
        "mask_account": True
    }
)

# Fields extracted:
# - bank_name
# - account_number (masked)
# - account_holder
# - statement_period (from, to)
# - opening_balance
# - closing_balance
# - transactions[] (date, description, debit, credit, balance)

result = client.dastavez.extract(
    document_type="bank_statement",
    file_url="...",
    options={
        "pages": "all"  # or "1-5" or [1, 3, 5]
    }
)

# Transactions are aggregated across all pages
print(f"Total transactions: {len(result.fields['transactions'])}")

result = client.dastavez.extract(
    document_type="aadhaar",
    file_url="..."
)

if result.confidence < 0.9:
    print("Warning: Low confidence extraction")
    print(f"Confidence: {result.confidence}")

# Per-field confidence
for field, value in result.fields.items():
    if hasattr(value, 'confidence'):
        print(f"{field}: {value.value} (confidence: {value.confidence})")

# Built-in validation for Indian documents
if result.validation['checksum_valid']:
    print("Document checksum verified")
else:
    print("Warning: Checksum validation failed")

# Aadhaar Verhoeff check
if result.validation.get('verhoeff_check') == 'pass':
    print("Aadhaar number is valid")

result = client.dastavez.extract(
    document_type="aadhaar",
    file_url="...",
    options={
        "language_hint": "hi"  # Hindi
        # Supported: hi, ta, te, bn, mr, gu, kn, ml, pa, or, as, en
    }
)

# Names and addresses are returned in both original script and transliterated
print(f"Name (original): {result.fields['name']}")
print(f"Name (English): {result.fields['name_english']}")

from rotavision.exceptions import (
    ValidationError,
    DocumentProcessingError
)

try:
    result = client.dastavez.extract(
        document_type="aadhaar",
        file_url="..."
    )
except ValidationError as e:
    print(f"Invalid input: {e.message}")
except DocumentProcessingError as e:
    if e.code == "unreadable_document":
        print("Document image is too blurry or damaged")
    elif e.code == "wrong_document_type":
        print("Document doesn't match specified type")
    else:
        print(f"Processing error: {e.message}")