Skip to content

Document Ingestion

Upload and manage documents in your knowledge repositories to power RAG-enabled AI agents.


Overview

The Knowledge Repository system allows you to upload various document types that your AI agents can use to answer questions and provide information. Documents are processed, indexed, and made searchable for intelligent retrieval.


Accessing Knowledge Repositories

Step 1: Navigate to Knowledge

  1. Click on KNOWLEDGE in the top navigation menu
  2. You will see a list of configured repositories

Knowledge Navigation Knowledge section with list of configured repositories


Viewing Repository Documents

Step 1: Access Repository

  1. Locate your repository in the list (e.g., "Product Documentation Repository")
  2. Click on the Documents link to view all documents in that repository

Document List View

The documents list displays:

  • Document ID: Unique identifier for the document
  • Document Type: File type (PDF, DOCX, CSV, TXT, etc.)
  • Document Name: Name of the uploaded file
  • Modified Date: Last modification timestamp
  • Status: Processing status (Ready, Processing, Failed)

Repository Documents List of documents within a knowledge repository


Adding New Documents

Step 1: Access Upload Options

  1. Click the Add Document(s) button in the top-left corner of the documents page
  2. A modal dialog will appear with different upload options

Add Documents Button Add Document(s) button in the documents view


Step 2: Select Upload Method

The platform offers several upload methods:

Upload Options

Method Description Use When
Folder (Auto OCR) Automatically detects need for OCR Uploading scanned PDFs or mixed content
Folder (No OCR) Upload without OCR processing All documents are digital/searchable
Folder (Force OCR) Forces OCR on all documents All documents need OCR
Plain Text Upload raw text data Uploading text-only content

Crawl Options

Method Description Use When
Confluence Crawl Confluence data Syncing from Confluence
Website Crawl and extract website content Importing web pages
SharePoint/OneDrive Crawl Microsoft document libraries Syncing from Microsoft 365
Human Assisted Crawl with browser plugin Sites requiring authentication

API Option

Method Description Use When
API Add documents via API Programmatic integration

Choose Folder (Auto OCR) from the Upload section. This option:

  • ✅ Automatically detects the need for OCR
  • ✅ Supports multiple file formats (.pdf, .docx, .csv, .txt)
  • ✅ Can handle up to 1000 files per upload
  • ✅ Intelligent processing based on document type

Upload Method Selection Select Folder (Auto OCR) for intelligent document processing


Step 3: Upload Files

You can upload files in two ways:

Option 1: Drag and Drop

  • Drag file(s) directly into the upload area
  • Visual feedback when files are over the drop zone
  • Supports multiple files at once

Option 2: Browse

  • Click in the upload area to open a file browser
  • Select one or more files
  • Click "Open" to add them to the upload queue

File Upload Interface Drag and drop or browse to select files

Supported formats: - .pdf - PDF documents - .docx - Microsoft Word documents - .csv - Comma-separated values - .txt - Plain text files


Step 4: Configure Document Locks (Optional)

Document Locks allow you to restrict document visibility based on user roles.

How It Works

  • Enter keywords in the "Document Locks" field
  • Press Enter to add multiple keywords
  • Only users with roles matching these keywords can see results from this document in search/retrieval

Use Cases

  • Confidential Documents: Lock to "executive", "finance"
  • Department-Specific: Lock to "sales", "marketing"
  • Role-Based Access: Lock to specific role names

Document Locks Configuration Configure document locks for role-based access control


Step 5: Save Documents

  1. Review your file selections
  2. Click the Save button to complete the upload
  3. Documents will be processed and added to the repository
  4. The status will show as "Ready" once processing is complete

Processing Statuses

Status Types

Status Description What It Means
Processing Document is being ingested Wait for processing to complete
Ready Document is indexed and searchable Available for agent retrieval
Failed Processing encountered an error Check document format or size

Processing Time

  • Small files (< 1 MB): Usually under 1 minute
  • Medium files (1-10 MB): 1-5 minutes
  • Large files (10-50 MB): 5-15 minutes
  • Bulk uploads: Processed in parallel, monitor status

Important Notes

OCR Processing

  • Auto OCR automatically detects whether OCR is needed for uploaded files
  • Files containing both OCR and non-OCR data may result in data loss
  • Use "Force OCR" only if all documents require OCR

Upload Limits

  • Maximum upload limit: 1000 files per upload
  • Supported formats: .pdf, .docx, .csv, .txt files
  • File size limit: 50 MB per file (varies by plan)

Best Practices

  1. Organize Before Uploading: Group related documents
  2. Use Consistent Naming: Makes documents easier to find
  3. Clean Content: Remove unnecessary pages or sections
  4. Test with Sample: Upload a few files first to verify processing
  5. Monitor Status: Check processing status for errors

Crawl Options

Confluence

Integrate with Confluence to automatically sync spaces and pages.

Requirements: - Confluence URL - API token or credentials - Appropriate permissions

What Gets Crawled: - Pages and sub-pages - Attachments - Comments (optional)


Website Crawling

Crawl public websites to extract content.

Configuration: - Starting URL - Crawl depth - Include/exclude patterns

Use Cases: - Competitor documentation - Public knowledge bases - Blog content

Learn more about Web Crawling


SharePoint/OneDrive

Sync document libraries from Microsoft 365.

Requirements: - Microsoft Graph API credentials - Library/folder URLs - Proper permissions

Supported Content: - Documents - Folders - Metadata


Managing Documents

Viewing Document Details

  1. Click on a document name in the list
  2. View metadata, processing status, and content preview

Editing Documents

  1. Click the Edit icon next to a document
  2. Update document locks or metadata
  3. Save changes

Deleting Documents

  1. Click the Delete icon next to a document
  2. Confirm deletion
  3. Document is removed from the repository and search index

Deletion is Permanent

Deleted documents cannot be recovered and will no longer be available for agent retrieval.


Troubleshooting

Document Status Stuck on "Processing"

Issue: Document remains in "Processing" status for extended time

Solution: - Wait at least 15 minutes for large files - Refresh the page to check for status update - If stuck for over 30 minutes, delete and re-upload - Contact support if issue persists


Upload Failed Error

Issue: File upload returns an error

Solution: - Check file size (must be under 50 MB) - Verify file format is supported (.pdf, .docx, .csv, .txt) - Ensure file is not corrupted - Try uploading files individually instead of in bulk


Documents Not Appearing in Agent Responses

Issue: Uploaded documents are not being used by agents

Solution: - Verify document status is "Ready" - Check that agent has the repository configured in Tools section - Ensure document locks don't restrict access - Test agent with specific questions related to document content