export GEMINI_API_KEY="your-api-key-here"

cd .claude/skills/gemini-document-processing
echo "GEMINI_API_KEY=your-api-key-here" > .env

echo "GEMINI_API_KEY=your-api-key-here" > .env

pip install google-genai python-dotenv

# Use the provided script
python .claude/skills/gemini-document-processing/scripts/process-document.py \
  --file invoice.pdf \
  --prompt "Extract invoice details as JSON" \
  --format json

# Process and summarize
python .claude/skills/gemini-document-processing/scripts/process-document.py \
  --file report.pdf \
  --prompt "Provide a concise executive summary"

# Q&A on document content
python .claude/skills/gemini-document-processing/scripts/process-document.py \
  --file contract.pdf \
  --prompt "What are the key terms and conditions?"

from google import genai

client = genai.Client()

# Read PDF
with open('document.pdf', 'rb') as f:
    pdf_data = f.read()

# Process document
response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=[
        'Extract key information from this document',
        genai.types.Part.from_bytes(
            data=pdf_data,
            mime_type='application/pdf'
        )
    ]
)

print(response.text)

from google import genai
from pydantic import BaseModel

class InvoiceData(BaseModel):
    invoice_number: str
    date: str
    total: float
    vendor: str

client = genai.Client()

response = client.models.generate_content(
    model='gemini-2.5-flash',
    contents=[
        'Extract invoice details',
        genai.types.Part.from_bytes(
            data=open('invoice.pdf', 'rb').read(),
            mime_type='application/pdf'
        )
    ],
    config=genai.types.GenerateContentConfig(
        response_mime_type='application/json',
        response_schema=InvoiceData
    )
)

invoice_data = InvoiceData.model_validate_json(response.text)

PDF < 20MB?
├─ Yes → Use inline base64 encoding
└─ No  → Use File API

Need structured JSON output?
├─ Yes → Define response_schema with Pydantic
└─ No  → Get text response

Multiple queries on same PDF?
├─ Yes → Use File API + Context Caching
└─ No  → Inline encoding is sufficient

# Basic usage
python scripts/process-document.py --file document.pdf --prompt "Your prompt"

# With JSON output
python scripts/process-document.py --file document.pdf --prompt "Extract data" --format json

# With File API (for large files)
python scripts/process-document.py --file large-document.pdf --prompt "Summarize" --use-file-api

# Multiple prompts
python scripts/process-document.py --file document.pdf --prompt "Question 1" --prompt "Question 2"

# Check API key is set
./scripts/check-api-key.sh