Library limits: file size, ceilings, and retention

Use this page to size a file, a corpus, a batch, or a storage plan. It groups the Library limits that affect those decisions by the question that sends you looking for them.

Some limits are part of the versioned API contract. Changing them breaks clients. Other limits are settings that a release can change.

What one file can be

One file can be 500 MiB at most, and its file type must be one Duale AI reads. Split a larger source and upload each part as its own document.

The supported formats cover documents, spreadsheets, presentations, images, videos, email, subtitles, data, and code. From a video, Duale AI reads text visible in the frames, not speech. Upload a recording as a transcript or subtitle file when its spoken content must be searchable.

In the Dashboard, the upload file picker offers the supported file types and names their categories. The list changes only with a release.

What a Library can hold

Two values bound a Library: its path length and its tags size. Nothing caps the documents in a Library or the Libraries in a tenant, so size a Library around its reader group, not around a count.

What one call returns

Document listings and the four Library Tools limit the results returned by one request.

The model’s Library Tools run under ceilings that your code does not pass:

Your own code passes none of those numbers. The model chooses a Tool during a Task, and Duale AI applies the ceiling. Library retrieval explains what each Tool matches, the name each one has in a trace, and how to read an answer that stopped early.

The SDK exposes two listing operations:

• list_documents(request) takes a limit of 1 to 500 and returns that many documents in one response, with a cursor for the next response. Pass each cursor back until next_cursor is None.
• list() returns all active Libraries covered by the caller’s read access, without pagination. When that access comes from more than 5,000 separate allows, or combines broad allows with refusals on particular Library paths, the call fails with an error instead of returning a partial list. Use get() with known Library IDs; each request checks that Library’s permissions.

SDK reference states both signatures and the exception type, and Access and isolation states who grants the actions that a caller resolves.

How long each window lasts

Four windows govern incomplete uploads and deletion. Act before each one ends.

Nothing removes a document permanently inside its 30-day window unless you delete its Library. Deleting that Library also deletes the document, even while it is in Recently deleted. Security and data handling owns the delete and restore lifecycle.

How long processing takes

The SDK’s polling helper stops after 360 seconds by default, before the processing allowance of Duale AI can end. A client timeout does not prove that processing failed. Pass a longer timeout= for a large file, then read the returned status instead of uploading the file a second time.

Manage libraries shows the polling call and client-timeout recovery.

Duale AI publishes no total time for a batch, and documents can finish in any order. Test a representative batch under your production conditions, then wait for every document the task needs to reach ready.

How stored document volume is measured

Duale AI records stored document volume from the document lifecycle described below.

A document counts from when Duale AI stores it until Duale AI deletes it permanently. A deleted document stays in the 30-day Recently deleted window and still counts during that window. Delete it as soon as your retention policy allows. Include the 30-day window when you estimate stored document volume.

Nothing expires a Library that a task created for its attachments, so its documents remain recorded until you delete them. Attach documents covers the files that one task carries. Pricing and access states whether the applicable commercial terms bill recorded volume separately.

What a nightly refresh records

A nightly refresh that uploads every file and deletes the prior documents still holds about thirty superseded copies of every file, plus the current one. A change-only refresh keeps that extra volume to the files that changed.

This happens because uploading a file again creates a new document instead of replacing the old one, and a document you delete keeps counting for its 30-day window.

Best practices gives the habit that keeps a changing set of documents to roughly its own size.