Uploading Resources

Resources are the files you upload to give your companion deep expertise. The companion processes these files, learns from them, and uses that knowledge to answer user questions accurately.

Upload FlowCopy Anchor Link

Supported File TypesCopy Anchor Link

Resources come in three categories - Documents, Videos, and Images. There is no separate audio type; if you need to give your companion spoken content, upload it as a video.

DocumentsCopy Anchor Link

All office formats (Word, Excel, PowerPoint, OpenDocument) are automatically converted and parsed. CSV, TSV, Markdown, and plain text files are parsed natively.

VideosCopy Anchor Link

Videos are automatically transcribed - the companion extracts the spoken content and learns from it.

ImagesCopy Anchor Link

Images are automatically analyzed when uploaded. Aura's AI examines each image using vision analysis to generate a descriptive caption, and optionally runs OCR to extract any text in the image. The companion uses this understanding to answer questions about the image content. Images can also be displayed in conversations (via the Rich Media skill) and in the Featured Photos gallery.

OCR LanguagesCopy Anchor Link

If you enable OCR on a document or image, you can choose from 48 supported languages, including:

The default language is English. Choose the language that matches the text in your document or image for best results.

Processing StatusCopy Anchor Link

After uploading, each resource goes through a series of stages:

Every resource in the list also shows a small ingestion-status dot so you can see readiness at a glance: amber (pending), blue and pulsing (queued or processing), emerald (ready), or rose (failed).

Processing StagesCopy Anchor Link

During processing, each document goes through these stages (visible in the progress tracker):

• Preparing - downloading and setting up the file for processing
• Converting - converting office formats for parsing (Word, PowerPoint, Excel, OpenDocument formats only)
• Scanning - extracting text content with optional OCR
• Learning - embedding the content and indexing it for AI retrieval
• Finalising - updating the resource status and completing the job

Image ProcessingCopy Anchor Link

When an image is processed, two things happen:

1. AI Vision Analysis - The image is analyzed by an AI vision model that generates a detailed caption describing the image content, objects, text, and context.
2. OCR (if enabled) - Optical Character Recognition extracts any readable text from the image.

The generated caption and extracted text become part of the companion's knowledge, allowing it to answer questions about the image intelligently.

The Progress TrackerCopy Anchor Link

While files are uploading or processing, a floating, draggable progress tracker panel appears (bottom-right by default - drag it anywhere on screen). It stays open across page reloads and keeps tracking your uploads even if you navigate elsewhere in the profile, so you never lose sight of what's still in flight.

Each row in the tracker shows the filename, a live percentage, its current phase (Queued, Uploading, Processing, Complete, Already exists, or Failed), and a progress bar. Depending on the file's state, you get contextual actions right there:

• Retry upload or Retry processing if something failed
• Cancel an upload that's still in progress, or a processing job that hasn't finished
• Dismiss a completed or failed row
• View to jump straight to the finished resource

A small Activity button on the Resources header shows a colored, breathing status dot summarizing what's happening (connecting, active, completed, or error) with a count badge, so you can tell at a glance whether anything needs your attention without opening the full tracker.

Reprocessing ResourcesCopy Anchor Link

If a resource failed to process, or you want to reprocess it (for example, with different OCR settings), select it and choose Process - this opens the reprocess dialog. You can queue multiple resources at once, remove individual files from the batch before confirming, and adjust OCR (enable/disable, change language) per file for documents and images. Reprocessing clears the previous results and re-queues the file; for images, it also regenerates the AI caption.

Browsing Your ResourcesCopy Anchor Link

The Resources sub-tab is a single, unified list backed by server-side pagination (50 resources per page by default, adjustable up to 250), so it stays fast even with a large library. To find what you need:

• Search - a debounced search box filters resources by name as you type
• Type filter pills - narrow the list to All, Documents, Videos, or Images (collapses into a dropdown on narrower screens)
• AI Ready filter - show only resources that are ready, or only ones that aren't
• Sort - by name, size, or created/updated date, ascending or descending; in list view you can also click a column header to sort by it
• Grid / list toggle - switch between a visual grid and a detailed list layout

Selecting and Bulk ActionsCopy Anchor Link

Select resources by ticking their checkboxes, or click and drag across the list to draw a selection box (hold Shift, Cmd, or Ctrl to add to an existing selection). Once you have a selection, a toolbar lets you Select All, Process the selected resources in bulk, or Delete them. Pressing Delete or Backspace with a selection active also opens the bulk-delete confirmation.

The Per-Resource MenuCopy Anchor Link

Every resource - in both grid and list view - has a ⋮ menu with actions for that one file. As the owner, you get:

• Open - opens the resource in the viewer panel
• Open in New Tab - opens the resource at its own URL in a new browser tab
• Rename - opens the Rename dialog
• Process (or Reprocess if it's already been analyzed) - same action as the bulk Process button, scoped to this one file
• Delete - deletes the resource (with a confirmation step)
• About - opens the Resource Details dialog
• Download - downloads the original file

If someone else is viewing your companion's resources from a public or shared link, they see a shorter menu: Open, Open in New Tab, and Download - no Rename, Process, Delete, or About.

Renaming a resourceCopy Anchor Link

Choosing Rename opens a small dialog with a single Title field, pre-filled with the resource's current name (without its file extension - the extension is preserved automatically and reappended when you save). Type a new name and click Save; click Discard to reset the field back to the original name without closing the dialog, or the × in the corner to close without saving. The title can't be empty - leaving it blank shows an inline error and disables Save. There's no separate character limit beyond that.

Resource DetailsCopy Anchor Link

Choosing About opens a read-only details panel for the file: Name, whether it's AI Ready, Size, Type, Extension, Created and Last Modified dates (in your account's time zone). For documents, it also shows format-specific counts where they apply - slide count for presentations, sheet count for spreadsheets, row and column counts for CSV/TSV files. For images, it shows the AI-generated caption underneath the standard details.

Image ViewerCopy Anchor Link

Click any processed image to open the Image Viewer. The viewer shows:

• The full-size image
• The AI-generated caption describing the image content
• Controls to edit, regenerate, or delete the caption
• OCR status and language settings
• Processing status indicator

You can regenerate captions with different OCR settings if the initial result was not satisfactory.

See the Limits & Quotas reference for every file-size and count limit on this page in one place, alongside every other limit in Aura, and the Actions & Menus reference for every menu on this page, including the per-resource ⋮ menu's mode-dependent entries.