Extract File

from pulse import Pulse

client = Pulse(api_key="YOUR_API_KEY")

# The SDK handles large document responses automatically
response = client.extract(
    file_url="https://www.impact-bank.com/user/file/dummy_statement.pdf"
)

# If the response contains is_url, fetch from S3
if hasattr(response, 'is_url') and response.is_url:
    import requests
    full_result = requests.get(response.url).json()
    print(full_result["markdown"])
else:
    print(response.markdown)

from pulse import Pulse
from pulse.types import (
    ExtractRequestFigureProcessing,
    ExtractRequestExtensions,
    ExtractRequestExtensionsAltOutputs,
)

client = Pulse(api_key="YOUR_API_KEY")

# Extract from URL with figure processing and HTML output
response = client.extract(
    file_url="https://www.impact-bank.com/user/file/dummy_statement.pdf",
    figure_processing=ExtractRequestFigureProcessing(
        description=True,
    ),
    extensions=ExtractRequestExtensions(
        alt_outputs=ExtractRequestExtensionsAltOutputs(
            return_html=True,
        ),
    ),
)

print(f"Markdown: {response.markdown}")
print(f"HTML: {response.extensions.alt_outputs.html}")
print(f"Extraction ID: {response.extraction_id}")

from pulse.types import ExtractRequestFigureProcessing

# Upload and extract a local file
with open("document.pdf", "rb") as f:
    response = client.extract(
        file=f,
    figure_processing=ExtractRequestFigureProcessing(
        description=True,
    ),
    )

# Step 1: Extract the document
response = client.extract(
    file_url="https://www.impact-bank.com/user/file/dummy_statement.pdf"
)

extraction_id = response.extraction_id

# Step 2: Apply schema separately
schema_result = client.schema(
    extraction_id=extraction_id,
    schema_config={
        "input_schema": {
            "type": "object",
            "properties": {
                "total": {"type": "number"},
                "vendor": {"type": "string"}
            }
        },
        "schema_prompt": "Extract invoice total and vendor"
    }
)

print(schema_result.schema_output)

from pulse.types import (
    ExtractRequestExtensions,
    ExtractRequestExtensionsChunking,
)

response = client.extract(
    file_url="https://www.impact-bank.com/user/file/dummy_statement.pdf",
    pages="1-5,10",  # 1-indexed
    extensions=ExtractRequestExtensions(
        chunking=ExtractRequestExtensionsChunking(
            chunk_types=["semantic", "page"],
            chunk_size=1000,
        ),
    ),
)

# Chunk data is in extensions.chunking
print(response.extensions.chunking.semantic)
print(response.extensions.chunking.page)

from pulse.types import ExtractRequestExtensions

response = client.extract(
    file_url="https://example.com/research-paper.pdf",
    extensions=ExtractRequestExtensions(
        footnote_references=True,
    ),
)

# Footnote links are in extensions.footnote_references
for ref in response.extensions.footnote_references:
    print(f"Marker: {ref.symbol}")
    print(f"  Footnote: {ref.footnote_text_id}")
    print(f"  Referenced by: {ref.reference_text_ids}")

response = client.extract(
    file_url="https://www.impact-bank.com/user/file/dummy_statement.pdf",
    storage={"enabled": False}
)