Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.omnifact.ai/llms.txt

Use this file to discover all available pages before exploring further.

A Space’s Uploaded Files are a collection of documents that provides specialized knowledge to your . By managing these documents effectively, you can create a powerful, context-aware AI assistant that understands your organization’s specific information.
Looking to connect cloud storage instead of uploading files manually? See Connected Sources to automatically index and search files from Google Drive, OneDrive, or SharePoint.

​
Accessing Uploaded Files

To access your Space’s uploaded files, navigate to the Space Settings (via the “Cog” icon in the Space header or the “Space Settings” button in the sidebar). Next, navigate to the “Uploaded Files” tab. This will take you to the complete document management interface where you can add, remove, and organize your files.
Knowledge tab in Space Settings
You need admin permissions in a Space to manage its uploaded files. If your organization has enabled the KnowledgeBaseManagerRole feature, you must also be assigned the organization-level Knowledge Base Manager role in addition to being a Space Admin to manage document content.

​
Adding Documents

Adding documents to your Space is a straightforward process:
1

Open upload interface

In the Knowledge tab, you’ll see a prominent upload area with “Drag & Drop” functionality.
Uploaded Files upload interface
2

Choose files

Either drag files directly into the upload area or click “Browse” to select files from your computer or cloud storage (Google Drive, OneDrive, SharePoint). To use cloud storage, connect your accounts first in Account Settings > Connections.
For ongoing access to cloud storage files that change frequently, consider using Connected Sources instead of manual uploads. Connected Sources automatically keeps content synced and up to date.
Supported formats include PDFs, common office document types (Word, PowerPoint, OpenDocument text/presentation formats), plain text files (TXT, JSON, Markdown, CSV, SVG), and images (PNG, JPEG, WebP, HEIC/HEIF, AVIF, BMP, GIF, ICO, SVG, and TIFF). Images are automatically optimized for efficient processing while maintaining quality.
3

Monitor upload progress

A progress bar will show the upload and processing status for each document.
Uploaded Files upload progress
You can continue using Omnifact while documents are being processed. The AI will be able to use them once processing is complete.

​
Document Processing Pipeline

After you upload a document, it goes through several steps before it’s ready for the AI to use:
  1. Content Extraction: Text and structure are extracted from the file. For scanned PDFs or images, Optical Character Recognition (OCR) powered by Apache Tika is used to read the text.
  2. Validation & Chunking: The extracted text is validated and broken down into smaller, searchable pieces (chunks).
  3. Embedding: These chunks are converted into vector representations so the AI can perform semantic searches.
  4. Summarization: An LLM-powered process generates a summary of the document for quick reference.
Status Indicators:
  • Processing: The document is actively going through the pipeline. This can take some time depending on the file size and complexity.
  • Ready: The document is fully processed and available for the AI to retrieve.
  • Failed/Error: The document could not be processed. This might happen if you exceed your document quota or if the file content cannot be extracted.

​
Document Source References

When the AI assistant uses information from your uploaded files, it will automatically its sources in the . This helps you:
  • Track which documents contain specific information
  • Verify the accuracy of AI responses
  • Understand which documents are most frequently referenced
  • Build trust in the AI’s answers
Example of Uploaded Files citation in AI response
For more details about how the AI references and uses uploaded files in its responses, see Knowledge Base Retrieval.

​
Managing Existing Documents

Once documents are uploaded, you have several management options:

Renaming Documents

  1. Click the “Options” icon next to the document
  2. Select “Rename Document”
  3. Enter the new name in the popup dialog
  4. Confirm the change
Renaming an uploaded file
Use clear, descriptive names to help team members understand document contents at a glance.
  1. Click the “Options” icon next to the document
  2. Select “Delete Document”
  3. Confirm deletion in the prompt
Deleting an uploaded file
Document deletion is permanent and cannot be undone. Make sure you have a backup if needed.

​
Best Practices

Follow these guidelines to maintain your uploaded files effectively:

Keep it Relevant

Only include documents directly related to the Space’s purpose. This helps the AI provide more accurate and focused responses.

Update Regularly

Replace outdated documents with current versions to ensure your AI assistant always works with the latest information.

Organize Thoughtfully

Use clear naming conventions and remove duplicate or redundant documents to maintain a clean, efficient collection of files.

Monitor Size

Be mindful of document size limits. Large files may take longer to process and could impact performance.

​
Tips for Success

Document Quality Matters

  • Use high-quality, well-formatted documents
  • Ensure text is clear and readable
  • Check for proper text formatting and layout
  • Verify document accuracy before uploading
  • Prioritize authoritative sources
  • Add documents that directly support the Space’s objectives
  • Remove outdated or superseded documents
  • Coordinate with other Space admins
  • Communicate document updates to team members
  • Establish clear document management guidelines
  • Regular review and cleanup of the uploaded files

​
Common Questions

The Uploaded Files feature supports PDFs, common office formats (Word, PowerPoint, OpenDocument text/presentation formats), plain text files (TXT, JSON, Markdown, CSV, SVG), and images (PNG, JPEG, WebP, HEIC/HEIF, AVIF, BMP, GIF, ICO, SVG, and TIFF).
No, there are no size limits on individual files or the total size of your uploaded files. However, larger documents will require more processing time when being analyzed by the AI assistant.
All members of the Space can see the names of the uploaded files. Only upload documents to a Space that you want all members to have access to.

​
Next Steps

Now that you understand how to manage your uploaded files, you might want to explore: