Get document loading right.
Quickstart
Section titled “Quickstart”uv tool install complydocOCR and name detection are optional extras. complydoc doctor reports which are
installed and what their absence leaves out of a run.
import complydoc as cd
with cd.observe("contracts-ingest"): documents = PyMuPDF4LLMLoader("contract.pdf").load() chunks = splitter.split_documents(documents) vector_store.add_documents(chunks)Each loader, splitter, embedding call and vector store becomes a step of a trace,
written to .complydoc, with each document followed through them and warnings for the
failures that raise no error. Open it with complydoc ui.
complydoc audit ~/contractscomplydoc uiCost, extraction readiness, identifiers and hidden text, document by document.
complydoc demoA full report on the documents bundled with complydoc, opened in the viewer.
What you can do
Section titled “What you can do”The viewer and the report
Section titled “The viewer and the report”complydoc ui opens every report and pipeline run in a folder in your browser, served
from your machine. A trace shows the calls in a tree with each one’s input and output;
a document shows every page with the chunks drawn over its text and each finding in
place; two readers of a document show as a diff. See The report viewer.
The report itself is JSON, carrying schema_version, currently 27. Identifiers are
masked everywhere in it, including the page text, unless the run used --reveal;
--page-images adds a picture of each page, which shows them, kept in a .parts
folder beside the report rather than inside it.
Network access
Section titled “Network access”The process makes no outbound connections of its own. Before any file is opened,
socket.socket.connect, connect_ex, socket.create_connection and
socket.getaddrinfo are replaced with functions that raise. AF_UNIX sockets
are permitted. Each report records whether the guard was active. Model prices
are vendored as data files.
A pipeline observed with cd.observe may need the network, for an embedding API
say: inside the block, its connections go through and each is recorded against the
step that made it. Two things a caller can ask for send data out themselves. An
instruction classifier backed by a hosted service sends the passages it judges; the
report names the hosts in run.content_sent_to, states it as an important
limitation, and expect(report).no_network() fails.
complydoc assist sends a finished report to a hosted chat
model. Both need allow_network=True and neither runs as part of an audit. See
Network isolation.
Limits
Section titled “Limits”- Masking is best effort. Categories with a checksum are confirmed; names and organisations come from a statistical model and are missed at some rate.
- Unmeasured signals are reported as unmeasured and excluded from scores.
- Table fidelity describes the extractor that ran. Only an extractor that reads table structure detects a table at all, so the measurement is of that reader’s own text.
- Hidden-content checks cover PDF text layers and the markup of Word, Excel, PowerPoint, HTML, Markdown and email files, not text inside images.
A hosted companion for teams, complydoc Cloud, is planned. Say if your team would use it.