intuned-files 0.1.0.dev0

Intuned SDK for file operations (to markdown, extract tables)

intuned-files

Intuned SDK for file operations. Provides helpers for converting files to markdown and extracting tables from files, backed by the Intuned file APIs.

Installation

pip install intuned-files
# intuned-runtime is required at runtime (provided by the Intuned runtime).
# intuned-browser is optional, only needed for the `download` file source.

Usage

from intuned_files import to_markdown, extract_tables, PdfFile

# Convert a file to markdown
markdown = await to_markdown(PdfFile(url="https://example.com/report.pdf"))

# Extract tables from a file
tables = await extract_tables(PdfFile(url="https://example.com/report.pdf"))

Both functions also accept a plain dict (typed via the *Dict TypedDicts):

from intuned_files import to_markdown

await to_markdown({"type": "pdf", "url": "https://example.com/report.pdf"})

Extract structured data

extract_structured_data converts the file to markdown and then extracts data against a schema. It requires the optional intuned-browser dependency (the other operations do not); it raises a clear error at call time if it is missing.

from intuned_files import extract_structured_data

data = await extract_structured_data(
    {"type": "pdf", "url": "https://example.com/invoice.pdf"},
    data_schema={
        "type": "object",
        "properties": {
            "invoice_number": {"type": "string"},
            "total": {"type": "number"},
        },
        "required": ["invoice_number", "total"],
    },
)

data_schema accepts a JSON Schema dict or a Pydantic model class.

File sources

Provide exactly one source key on the file object: url, base64, buffer (raw bytes), or download. The download source accepts the result of download_file from intuned-browser, awaited or not:

from intuned_files import to_markdown
from intuned_browser import download_file

await to_markdown({"type": "pdf", "download": download_file(page, trigger)})

Supported file types

PdfFile, ImageFile, SpreadsheetFile (.xlsx), and DocumentFile (.docx).

Development

uv sync
uv run ruff format --check .
uv run ruff check .
uv run pyright
uv run pytest -m "not e2e"