Your IP Vault provides enterprise-grade security. Your proprietary information stays isolated to your Digital Twin — even other Twins in the same account can’t see it unless you explicitly share it.
What You’ll See in Your IP Vault
Open the vault by clicking the Files button on the input bar. Each vault is a tab along the top:
Your Digital Twin answers from all of these vaults (except the Trash), even when you can only see the Personal tab. If that is the only tab you see, that’s by design: admins curate the shared vaults.
Find a file by its content
The vault grid filters by name and status. To find a file by what it says inside — a phrase, a clause number, a code snippet — use content search: the search bar at the top of the file panel has a mode toggle that switches it from file-name search to searching inside your files. See File Search for the full guide: scope (single vault vs all vaults), result ranking, snippet preview, and jumping straight to the matching segment in the file preview.Adding Files
You have three ways to add content to your vault, plus drag-and-drop and bulk paste once you’re in the file panel.The three upload methods
Device Upload
Browse and select files from your computer or phone. Best for documents, presentations, and media you already have locally.
- Click Device in the upload dialogue
- Pick one or more files (multi-select supported)
- Click Upload
URL Import
Paste any web page URL, YouTube link, or Google Docs / Sheets / Slides URL.
- YouTube — Pria auto-extracts the transcript with
[M:SS]timestamps, video title, channel name, and thumbnail. No captions? Check Skip Indexing to store metadata without embeddings. - Google Workspace — If you’ve connected Google under Your Profile › Google Cloud (Studio UI: Settings › Google Services), Pria can reach your private and shared docs. Otherwise only publicly shared docs work.
- Scrape site — Toggle on to follow links and pull in dependent pages.
Paste from Clipboard
Drop in any text snippet without saving it as a file first.
- Copy any text to your clipboard
- Open the Clipboard tab
- Paste, give it a title, save
Drag and drop
You can drag files from your desktop directly onto the vault panel to upload them. Drop a file onto a collection card to upload straight into that collection. (See Collections below.)Per-file options in the upload dialogue
Before you hit Upload, each staged file carries two toggles (with “for all” master switches when you’re uploading a batch):
The URL tab offers the same Skip Indexing option — handy for YouTube videos without captions, where you want the metadata and link saved but there’s nothing to transcribe.
Step-by-step upload flow
1
Open the vault
Click Files on the text input bar.
2
Click + Add
Bottom of the panel. Or drag files straight onto the panel to skip the dialogue.
3
Choose your method
4
Upload + monitor progress
A progress bar tracks each file through these stages:
- Uploading — Bytes streaming to the server
- Processing — Extracting text, generating segments, embedding, building the knowledge graph
- Included — Done; available for your Digital Twin to reference
- Failed — Something went wrong; check the file and try again
The counter updates in batches, not one chunk at a time, so on short files it may pause briefly before jumping. That’s normal — processing is still running.
5
Done — back to the vault
Supported file formats
Format notes:
- Legacy Word (
.doc, Word 97–2003) is fully supported — text is extracted directly from the original binary format. - Legacy PowerPoint (
.ppt) isn’t supported yet. You’ll get a clear message asking you to re-save the file as.pptx(or export it as PDF) and upload that instead. - Apple iWork files (
.pages,.key,.numbers) and EPUB e-books aren’t currently supported. Export them as PDF, Word, PowerPoint, or Excel from the source app and upload the export. - Files without an extension are identified automatically by inspecting their content — PDFs, HTML, images, Office documents, and ZIP archives are detected and processed normally.
- Executables, installers, and disk images (
.exe,.msi,.dmg,.iso, …) are always refused.
Large media — automatic chunking at 25 MB
Audio and video files larger than 25 MB are automatically split into smaller chunks before transcription. The transcripts are then stitched back together with continuous timestamps so your Digital Twin treats the file as one continuous transcript. You don’t have to split anything yourself — drop in a 2-hour lecture and Pria handles it.Audio & Video Processing: Speech is transcribed to text and indexed for RAG. Cue-point detection, speaker diarization, and timestamp-linked retrieval are in active development.
Files your Digital Twin builds
Not every file in your vault is one you uploaded. When a conversation builds something for you — a page, a report, a set of documents — those files land in Files too, and behave slightly differently from an upload. They open from their link. Pria gives you a link to what it built, and that link opens without asking anyone to sign in, as long as the file is public in Files. Built files are public unless you make them private, so you can paste the link into an email or a chat and it will work for the person who receives it. Make the file private in Files and the link stops opening for everyone else. They keep their project. A file built in one project doesn’t collide with a file of the same name built in another, so nothing gets overwritten or appears twice. Files shows you the plain file name; the project it belongs to is kept underneath. You can ask for them in the twin’s vault. By default the files land in your files. If you ask a build to save them in the vault of the Digital Twin you’re talking to — “save it in the twin’s vault” — and you’re allowed to edit that twin’s files, they land there instead, where every member of the twin can see them in Files. If you’re not allowed, they land in your own files and the answer tells you where they went and why.A file saved into a Digital Twin’s vault is listed by the twin straight away, but it isn’t part of the twin’s knowledge until it’s processed like any other upload. See Reprocessing if you want the twin to be able to search its contents.
Collections — Organizing Your Files
Collections are folders. They live inside a vault, can nest as deeply as you need, and exist purely for your own organization — your Digital Twin still searches all included files regardless of folder.
Creating a collection
Click the + New Collection button (or use the keyboard shortcut shown next to it). Give it a name and an optional color. The new collection card appears alongside your files. You can navigate into a collection by clicking its card, and use the breadcrumb at the top to climb back out.Drag and drop — files
- File into collection — Drag a file card onto a collection card to move it in.
- File out of collection — Drag the file from inside a collection up onto the breadcrumb to move it back to the parent (or to vault root).
- File between vaults (admin) — Drag a file onto your Digital Twin’s tab or your account’s tab to publish it to that shared vault, or onto Personal to bring it back. Dropping it on Trash deletes it.
Drag and drop — collections
- Collection into collection — Drop one collection onto another to make it a sub-collection. Nesting depth is unbounded.
- Collection between vaults (admin) — Drop a collection onto another vault’s tab to move the entire folder + all its files at once.
Collection highlighting
Collection cards that contain at least one Included file get a stronger blue border so you can spot active folders at a glance. Empty or excluded-only collections stay neutral.Download as a zip
- A whole collection — open the collection’s ⋮ menu and choose Download ZIP. The zip keeps the sub-collection folders.
- Several files — select them and choose Download in the selection toolbar. One file downloads as itself; several come as one zip.
- A personal collection downloads only for the person who owns it.
- In a Digital Twin or account collection, files that other people marked Confidential are left out of the zip, as they are of the file list.
- A refused download — a collection that isn’t yours, or an empty one — shows the reason instead of saving a zip.
- If you cancel, the download stops at once. If it fails part-way, your browser reports a failed download instead of saving a broken zip.
Reading the File Card — at a glance
Every file card surfaces its current state without you having to open it.Status dots
Two small dots in the corner of the card tell you the file’s role in RAG and whether it has a freshness issue:Access badges
- Public — anyone with the URL can view, including unauthenticated visitors.
- Private (default) — signed-in members of the Digital Twin only.
- Confidential — only the owner can open or download it; other members see ”🔒 CONFIDENTIAL” instead of its details.
Processing bar
While a file is being processed, the card shows a small progress bar with the current step (chunking, sanitizing, embedding, KAG…) and a percent counter. The card updates itself as the file works its way through.File Action Menu
Click the ⋮ on any file card to open the action menu.
In the Trash, a file offers only Restore from Trash and Delete Permanently.
File Preview
Clicking a thumbnail (or Preview in the action menu) opens the File Preview modal — your one-stop look at everything about a file.
- Body — renders the asset itself: image, PDF, video, audio, text, code with syntax highlighting.
- Right sidebar — the Asset Info panel, organized into collapsible sections.
Asset Info sidebar — sections
The sidebar lists four collapsible sections. They share the available height — open one and it fills the panel; open several and they split equally. Each section’s body scrolls internally, so long Properties text or a large segment list can never push other section headers off-screen.Both Knowledge sections show a “Currently processing” placeholder while the file is mid-ingestion — segments and graph stats only materialize once the pipeline reaches
done.Progress bar consistency: the progress bar only ever moves forward. If you leave a file while it’s still processing and come back, the bar picks up where it really is instead of jumping around — even when parts of the work finish out of order.
Custom thumbnail
The thumbnail next to the file is clickable in Edit mode. Pick a new picture from your camera, file picker, or by cropping an existing one — the same picker used for profile pictures. The new thumbnail saves immediately and refreshes everywhere the file is displayed.Inline renderers — what shows in the preview body
The preview body renders the asset directly in-browser so you don’t have to download it first:Viewing OCR-extracted text
For image-only PDFs and photos of documents, Pria runs OCR during ingestion. To inspect the extracted text:- Open the file preview.
- Expand the Knowledge — RAG segments section in the right sidebar.
- Each segment shows the text Pria indexed; for OCR’d content, this is the OCR output.
Editing Files in the Preview
Click Edit segments in the preview’s toolbar to flip into edit mode (Edit Content edits a text file as a whole instead). The body switches to an inline form alongside the segments editor.Editable fields
A single Update button at the top-right of the File Properties section saves all the inline fields in one round-trip. A green ✓ confirmation appears briefly when the save lands.
Inline RAG segments editing
Below the properties, every RAG segment is editable inline. Each segment has:- Update — save your changes to this one segment (text and embeddings are regenerated).
- Sanitize (sparkle icon) — let the AI clean up noise (navigation menus, broken formatting, OCR junk) while preserving the substantive content. Each sanitize is independently undoable.
- Delete — remove the segment from RAG (the source file is untouched).
Unsaved-changes protection
If you try to close the preview or switch back to view mode with unsaved edits, a confirmation dialog asks Keep Editing or Discard & Close — no accidental loss of work.Reprocessing — RAG and KAG
Two distinct pipelines run on every file. You can re-run either independently.Why reprocess?
- Your Digital Twin’s embedding model changed and you want existing files re-indexed.
- A web page you imported by URL has been updated.
- The preview shows the file has no indexed segments, or its knowledge-graph counts look wrong.
- KAG Fusion was turned on after the file was added.
Pick what to rebuild
Reprocess Content in the file action menu (or Reprocess in the selection toolbar) opens a dialog:
Reprocessing keeps the file’s identity: its links, collection, and Public / Private / Confidential setting stay the same.
What happens during processing
The file card shows a progress bar with the live step. Until it finishes, the preview’s Knowledge sections say “Currently processing”.When a file fails
Pria already retries on its own when the AI service is briefly unavailable. If a file still ends in an error, open it and read the reason under Processing in the preview, then:- A passing problem (network, busy service) — Reprocess Content and tick both options.
- A bad or damaged source file — replace it with Swap Asset (see Re-uploading).
- Only the knowledge graph failed — Reprocess Content → Rebuild knowledge graph (KAG).
Deleting Files
Delete a file from the action menu (⋮ → Delete), from the selection toolbar, or by dragging it onto the Trash tab. Deleting a collection moves the files inside it, and inside its sub-collections, to the Trash too; the confirmation says how many.The Trash — a 30-day safety net
Deleting a file moves it to the Trash — it isn’t destroyed right away:- Pria stops using the file at once, and any processing still running on it stops.
- The Trash tab appears next to your vaults while it holds anything, with a count. It gathers deleted files from every vault in one place.
- The file’s card counts down the days left. After 30 days in the Trash the file is deleted for good, with everything Pria learned from it.
- While your personal Trash holds files, a short notice above the [+] menu says how many and when the oldest will be deleted; one click opens the Trash. Dismiss it and it stays quiet until something changes.
Restoring and permanent deletion
In the Trash tab, a file offers two actions:- Restore from Trash — returns the file to its previous vault, collection and state.
- Delete Permanently — deletes it now instead of after 30 days, after a confirmation.
Re-uploading — replacing an existing file
If you have an updated version of a file already in the vault:- Swap the file in place — choose Swap Asset in the file’s action menu (or the swap button in the preview’s toolbar). Upload the new version (or point at a URL) and Pria replaces the stored bytes while keeping the file’s identity — shareable links, collection membership, access level, and custom thumbnail all stay intact. Swap replaces only the stored file; run Reprocess Content afterwards if you want the AI search index rebuilt from the new content.
- URL-imported file — Use ⋮ → Reprocess Content → Re-ingest from URL to fetch the latest content from the original page. The file’s identity and link stay the same.
- Major reorganisation — Delete the old one (it stays restorable in the Trash for 30 days) and upload the new file fresh; expect new citations to look slightly different.
How long files are kept
Each file has a Keep if unused period. A file that goes that long without being used moves to the Trash, where you can still restore it for 30 days.- Each use starts the period again. A use is Pria answering with the file, a download, a shared link, or the file shown in a conversation. Opening the preview in Files does not count.
- Only Forever keeps a file for good. 0 days means Forever.
- The countdown runs only while the file is included in AI search. An excluded file has no countdown; including it starts one.
- Where you see it: the file card shows the days left (amber, then red, in the last week; Removing soon once the date has passed), and the preview’s Keep if unused row shows the date and lets you pick 7, 14, 30 or 90 days, or Forever. To give several files more time, select them and use Extend… (+7, +30 or +90 days, or Keep forever).
- No countdown? The preview says why: Forever, the period only starts when the file is included in search, or No end date for some files kept under the earlier rule.
Bulk Operations
Check the boxes on several file cards (or Select All) to show the selection toolbar. Which buttons appear depends on the vault and your rights.
To change Public / Private for many files at once, use a collection’s ⋮ → Make All Public / Make All Private. In the Trash tab the toolbar offers Restore and Delete Permanently instead.
Display filter — narrowing the file grid
The sidebar’s Display segmented control narrows the file grid to a single state. The active filter is also pinned next to the Files (N) header and the Collections (N) header as a colored chip with an × to clear.Processing and Error are “attention” filters — they surface every file in scope that needs your eye, including files nested inside a collection or sub-collection. The other three modes (All / Included / Excluded) keep the standard drive-style view where collection-bound files only show up when you navigate into their folder.
Vault Health
The vault header shows an A–F letter grade plus a tooltip breakdown. The grade is computed server-side from your file inventory and reflects how usable your Digital Twin’s knowledge base is.What the grade measures
Each category’s penalty is (weight × count) ÷ total files. A vault with no files returns
N/A.
Files with issues — the panel
Below the health pills, the Files with issues panel lists every problematic file in scope. The list and the counts are worked out the same way, so they always agree — if the pills say “5 errors”, the list shows 5. Scope follows your browsing context:- At the vault root, the panel covers the whole vault (incl. files nested in collections).
- Inside a collection, the panel narrows to that collection’s subtree. The heading reads
Files with issues in Collection › Sub-collection:and a “All collections in this vault” checkbox lets you expand the scope back to vault-wide. - With the All Vaults Health toggle on, the panel covers your personal, Digital Twin and account vaults, and each row starts with a colored vault pill (blue = personal, emerald = Digital Twin, purple = account).
Reading a row
Each row reads:- The vault pill is only present in All Vaults mode — it tells you which vault the file lives in.
- The collection breadcrumb uses the same colored folder icons as the rest of the product (per-collection accent color when set; default outline icon otherwise).
- The issue chip at the right summarizes the problem (
error,needs reprocess,missing,invalid URL,unoptimized,stale,never used,needs delete).
Improving your grade
The grade is recomputed every time you open the vault. Health-only filters in the header let you narrow the grid to just one category for fast cleanup.
Your Access table
For the Digital Twin and account vaults, the Vault Health panel includes a small Your Access table at the bottom showing whether you can List / Add / Edit / Delete files in that vault — a quick reminder of what entitlements gate your actions there. The table is hidden in the Personal vault (you always have full control over your own files).File Access Control — Public / Private / Confidential
Every file is one of three access levels, settable per-file or in bulk:
Change from the file action menu, or in bulk via the selection toolbar. To switch every file in a collection at once, use the collection’s ⋮ → Make All Public / Private.
Files accessed without the required permissions show a sign-in / access-denied page:
What Confidential really means
Confidential applies to files in shared vaults (the Digital Twin and account vaults) — personal files are only yours to begin with. Marking a shared file Confidential keeps it — and its knowledge — to you:- Only you can open it. Other members — including admins — can’t preview, download, or read the file. Where its name would appear with a title and summary, they see a ”🔒 CONFIDENTIAL” marker instead, with no download link or file details.
- Its knowledge stays with you too. The file is still processed and searchable in your own conversations, but other members’ questions never draw on it: the Digital Twin’s search, its knowledge graph and its file tools all leave another person’s confidential file out.
- You keep full access. In your own conversations the file behaves normally — full citations, full preview, full retrieval.
- You can change your mind. Confidential is a toggle, not a one-way door: use Make Public in the action menu (or edit the Rights field in the preview) to lift the protection at any time. Toggling works before or after upload.
Import Course Packages (IMSCC)
Pria imports IMS Common Cartridge (.imscc) packages — the standard export format from Canvas, Blackboard, Moodle, and D2L.
What you get:
- Upload a
.imsccfile - Pria extracts:
- Syllabus + course overview pages
- HTML content from lessons, assignments, modules
- Images and embedded media (vision-described)
- Discussion topics + announcements
- Extracted content is organized into a Collection and indexed for retrieval
Image-heavy courses take longer — Pria uses vision models to caption embedded images for retrieval.
Sorting & View Options
Click an active sort button again to flip its direction.
Tree of Knowledge — browse your vault as a graph
The sidebar’s Display selector can switch the whole panel from Files to Tree of Knowledge — a hierarchical view of the knowledge graph Pria has extracted from your documents. Instead of file cards you browse pillars (top-level themes) down into entities (people, organizations, concepts), the relationships between them, and finally the source files each piece of knowledge came from. Clicking a node opens a detail panel describing it.- A vault filter narrows the tree to your personal, Digital Twin or account knowledge.
- A Knowledge Layer badge shows how ready the graph is — it fills in as files finish knowledge-graph extraction.
- The tree grows over time: “Your Tree of Knowledge will grow as files are indexed.” New uploads add branches automatically once their graph extraction completes.
Best Practices
Organize with Collections
Use Collections to mirror how you think about the content — by topic, course, project, or release. Sub-collections nest as deeply as you need.
Mind the dots
An orange dot means something to fix; a green dot means the file is pulling its weight. Skim the grid before a big conversation to spot anything that needs attention.
Sanitize noisy sources
Web scrapes, OCR’d PDFs, and email exports often contain navigation and boilerplate. Run Sanitize All in the RAG Segments editor to strip noise — retrieval quality jumps measurably.
Watch the vault grade
Aim for an A or B. The breakdown tells you exactly which files are dragging the score down so you can focus cleanup where it matters.
Use Edit mode to refine metadata
The AI-generated Title and Description are starting points. Tighten them so your Digital Twin retrieves the file when you’d expect — wording in the Title affects RAG ranking.
Reprocess when models change
After your Digital Twin’s embedding model changes, run Reprocess Content → Rebuild search index (RAG) on important files so they’re indexed with the new model.
Your Digital Twin gets sharper with every file you add — but only if those files are findable. The vault health grade, RAG Segments editor, and KAG section are all there to make sure what you upload actually gets used.
Related
- IP Vault — Vault concepts: scope, access tiers, RAG/KAG.
- Collections — Folders, nesting, drag-drop, multi-select.
- File Search — Content search across vaults.
- File Processing — Ingestion pipeline phases and what each step does.
- Citations — How Pria cites files in conversation.
- Audio Notes — Voice-only uploads.
- Knowledge Modes — Retrieval mode selector (RAG, KAG Fusion, Search Only).