complydoc 0.3.1

Document analysis for LLM pipelines, fully offline.

complydoc inspects documents, and the output of document loaders, before they are sent to an LLM. It measures what processing them will cost, how reliably text can be read off each page, which personal and financial identifiers they contain, and whether anything hidden in a file is addressed to a model.

[!TIP] Run complydoc demo to produce a full report on the sample documents bundled with the package.

Quickstart

uv tool install complydoc
complydoc audit ./documents

import complydoc as cd

report = cd.full_audit("./documents")
print(report.overall.score)
cd.write_html(report, "report.html")

Output from a LangChain or LlamaIndex loader:

from langchain_community.document_loaders import PyPDFLoader

report = cd.inspect_documents(PyPDFLoader("contract.pdf"))

OCR and name detection are optional extras. complydoc doctor shows what is installed.

What it reports

• Token cost: text and vision tokens per document, priced across models and three extraction paths (text layer, OCR, vision).
• Extraction readiness: measured per-page signals such as text layer coverage, tables, columns, rotation, scan resolution and garbled characters.
• Identifiers: personal and financial identifiers in UK, US and EU formats, checksum-validated where a checksum exists, masked in every output.
• Hidden content and prompt injection: text a reader does not see and a model does (white or invisible text, hidden formatting, Unicode tag characters), and passages that read as instructions to a model.
• Loader inspection and comparison: what a loader extracted, the metadata it attached, the network connections it attempted, and where several loaders disagree.
• Masked text: the documents' text with identifiers covered, chunked and counted in tokens.

How it works

• Offline: outbound sockets and DNS lookups are blocked for the whole run, and each report records that the guard was armed.
• Measured, not inferred: a signal that cannot be measured is reported as not measured and left out of scores.
• Evidence tiers: every finding states how it was established, whether by checksum, corroboration, pattern or model.
• Configurable: prices, signal weights and detection patterns are YAML files.
• One report: a self-contained HTML file and a JSON file with a versioned schema.

Resources

• Documentation: guides and design notes
• Command line reference
• Python API reference
• Report JSON
• Changelog
• Contributing

License

MIT