Document Processing
Uploaded documents pass through text extraction and then structure extraction before they can be used to generate questions.
Accepted File Types
Section titled “Accepted File Types”| Type | Extensions | How text is obtained |
|---|---|---|
.pdf | Embedded text is read first; pages without usable text are read with optical character recognition | |
| Word | .docx | Text is read directly from the document |
| PowerPoint | .pptx | Text is read directly from the slides |
| Plain text | .txt | Read as-is |
| Image | .png, .jpg, .jpeg | Optical character recognition |
A PDF whose pages are scans of paper is handled by character recognition rather than by asking an AI model to read the images. Recognition is configured for Urdu, Arabic, and English by default; other languages depend on the language packs installed for your deployment.
Processing States
Section titled “Processing States”Text extraction and structure extraction are tracked separately, so a document can have finished one and not the other.
| Text extraction | Meaning |
|---|---|
none | Not started |
queued | Waiting for a worker |
processing | Being read now |
done | Text is available |
failed | Could not be read |
| Structure extraction | Meaning |
|---|---|
none | Not started |
queued | Waiting for a worker |
processing | Being analysed now |
ready | A structure tree is available |
failed | Could not be produced |
Large documents are routed to a separate, deliberately slower processing lane so that one long textbook cannot block every short document in the workspace.
Document Structure
Section titled “Document Structure”Structure extraction produces a tree of entries — chapters, sections, and topics — each with an optional summary and page range. You can edit any entry’s title, summary, and page range.
| Entry origin | Meaning |
|---|---|
| AI | Produced by structure extraction |
| Edited | Changed by a person after extraction |
Each regeneration snapshots the previous tree, so an earlier version can be restored.
Semantic Search
Section titled “Semantic Search”Once text extraction finishes, document text is split into chunks and indexed so the platform can find passages by meaning rather than by exact wording. This index is what grounds question generation and the AI assistant in your own material.