Skip to main content

​
Overview

itellicoAI supports three types of knowledge items, each designed for different content sources and use cases. Understanding how each type works and how they’re processed will help you choose the right format for your information.

​
Content Type Overview

Text Items

Direct content entry using the built-in editor

File Uploads

Upload PDF, DOC, DOCX, TXT, and other document formats up to 10MB

URL Scraping

Pull content from web pages

​
Text Items

​
What Are Text Items?

Text items are content you enter directly into the itellicoAI knowledge base editor. They’re the most straightforward and reliable content type.

​
When to Use Text Items

Create question-and-answer pairs directly in the system.Example:
Title: How do I reset my password?

Content:
To reset your password:

1. Go to the login page
2. Click "Forgot Password"
3. Enter your email address
4. Check your email for a reset link
5. Click the link and create a new password

Password requirements:
- Minimum 8 characters
- At least one uppercase letter
- At least one number
- At least one special character

If you don't receive the email within 5 minutes, check your spam
folder or contact support@company.com.
Write clear, concise policy statements.Example:
Title: Return Policy - Digital Products

Content:
Digital products can be refunded within 30 days of purchase if:

Eligible for refund:
- Product has a technical defect preventing usage
- Product description was materially inaccurate
- Customer has not accessed or downloaded the product

Not eligible for refund:
- Change of mind after accessing the product
- Compatibility issues disclosed in product description
- User error or misunderstanding of features

To request a refund:
Email support@company.com with your order number and reason
for the refund request.

Processing time: 5-7 business days
Refund method: Original payment method
Step-by-step instructions for processes.Example:
Title: Order Modification Process

Content:
Customers can modify orders within 24 hours of placement.

What can be modified:
- Shipping address
- Delivery speed
- Item quantities (if inventory available)

What cannot be modified:
- Payment method (must cancel and reorder)
- Items after processing has begun
- Orders placed more than 24 hours ago

Modification process:
1. Customer contacts support via phone or email
2. Agent verifies order is within modification window
3. Agent checks inventory for requested changes
4. Agent updates order in system
5. Customer receives confirmation email

If order has already shipped, customer must use return process instead.
Brief, frequently referenced information.Example:
Title: Business Hours & Contact Information

Content:
Customer Support:
- Phone: 1-800-555-0123
- Email: support@company.com
- Hours: Monday-Friday, 9 AM - 6 PM EST
- After-hours: emergency@company.com (urgent issues only)

Sales:
- Phone: 1-800-555-0124
- Email: sales@company.com
- Hours: Monday-Friday, 8 AM - 8 PM EST

Billing:
- Phone: 1-800-555-0125
- Email: billing@company.com
- Hours: Monday-Friday, 9 AM - 5 PM EST

​
Creating Text Items

1

Navigate to folder

Open the folder where you want to add the item.
2

Click 'Add Knowledge Item'

Click the button to create a new item.
3

Select 'TEXT' category

Choose TEXT from the content type options.
4

Enter title

Give your item a clear, descriptive title.
5

Write content

Enter your content in the editor. Use formatting for clarity:
  • Headings for sections
  • Bullet points for lists
  • Numbers for steps
  • Bold for emphasis
6

Click 'Create'

Save your text item. Status will immediately show as COMPLETED.

​
Text Item JSON Example

{
  "category": "TEXT",
  "title": "Product Pricing Information",
  "content": "Our pricing tiers include Basic ($29/month), Pro ($99/month), and Enterprise (custom pricing).",
  "status": "COMPLETED"
}

​
Advantages of Text Items

Instant Processing

Text items are immediately available - no processing delay

Full Control

Complete control over formatting and content structure

Easy Updates

Quick to edit and update when information changes

Reliable

No processing errors or extraction issues
Text items are the most reliable content type. When possible, enter content as text rather than uploading files.

​
File Upload Items

​
What Are File Upload Items?

File upload items allow you to upload existing documents in various formats. The system extracts the text content and makes it available to your agents.

​
When to Use File Uploads

You already have content in document format.Examples:
  • User manuals
  • Product specifications
  • Legal documents
  • Training materials
Documents with specific layouts that are easier to maintain as files.Examples:
  • Technical diagrams
  • Tables and charts
  • Multi-column layouts
  • Branded templates
Documentation you receive from vendors or partners.Examples:
  • Supplier catalogs
  • Compliance documents
  • Certification materials

​
File Requirements

File specifications:
  • Formats: PDF, DOC, DOCX, TXT, and other document formats
  • Size limit: 10MB maximum
  • Content: Text-based documents and scanned images (advanced parsing handles most scans)
  • Protection: No password protection
The system uses advanced document parsing to extract text from scanned images and PDFs. Most scanned documents will process correctly, though very poor quality scans may require manual text entry.

​
Creating File Items

1

Navigate to folder

Open the folder where you want to add the file.
2

Click 'Add Knowledge Item'

Click the button to create a new item.
3

Select 'FILE' category

Choose FILE from the content type options.
4

Enter title

Give your file a descriptive title (this is separate from the filename).
5

Upload file

Click Upload and select your document from your computer.
6

Click 'Create'

The system will upload and begin processing your file.Status progression:
  • PENDING → File uploaded, queued for processing
  • PROCESSING → Extracting text content
  • COMPLETED → Ready for use
  • FAILED → Processing error occurred

​
File Item JSON Example

{
  "category": "FILE",
  "title": "User Manual - Product X",
  "file": "/uploads/knowledge/user-manual-product-x.pdf",
  "status": "COMPLETED"
}

​
Processing Time

File processing time varies based on:
  • File size: Larger files take longer
  • Page count: More pages = longer processing
  • Complexity: Tables, images, and complex layouts slow processing
  • Text quality: Clean, simple text extracts faster
Typical processing times:
  • Small files (< 1MB, 10 pages): 10-30 seconds
  • Medium files (1-5MB, 10-50 pages): 30-90 seconds
  • Large files (5-10MB, 50+ pages): 2-5 minutes

​
Common File Issues

Causes:
  • File exceeds 10MB
  • File is password-protected
  • File is corrupted
  • Very poor quality scanned images
Solutions:
  • Compress file or split into smaller files
  • Remove password protection
  • Re-export file from source
  • For very poor quality scans, copy content into text item instead
Causes:
  • Complex layouts (multi-column, tables)
  • Very poor quality scanned images
  • Special fonts or encoding
  • Form fields and interactive elements
Solutions:
  • Check extracted content in edit mode
  • Re-create as text item with proper formatting
  • Simplify document layout before uploading
  • Export as plain text document
What to do:
  • Wait 5-10 minutes before assuming failure
  • Check file size and page count
  • For large files, consider splitting into multiple files
  • Convert to text and upload as TEXT items instead

​
File Upload Best Practices

Optimize before upload

  • Compress large files
  • Remove unnecessary images
  • Use text-based documents
  • Keep under 5MB when possible

Test extraction

  • Review extracted content after processing
  • Check for formatting issues
  • Verify critical information is accurate
  • Re-upload if extraction is poor

​
URL Items

​
What Are URL Items?

URL items scrape content from web pages and store it in your knowledge base. This is useful for referencing online documentation, help centers, or blog posts.

​
When to Use URL Items

Reference external documentation you don’t maintain.Examples:
  • API documentation (your own or third-party)
  • Public knowledge bases
  • Help center articles
  • Product pages
Content that changes regularly and you want to keep current by re-scraping.Examples:
  • Pricing pages
  • Product availability
  • Current promotions
  • Status pages
Educational content or announcements.Examples:
  • How-to guides
  • Best practices articles
  • Product announcements
  • Feature tutorials

​
Creating URL Items

1

Navigate to folder

Open the folder where you want to add the URL.
2

Click 'Add Knowledge Item'

Click the button to create a new item.
3

Select 'URL' category

Choose URL from the content type options.
4

Enter title

Give the content a descriptive title.
5

Enter source URL

Paste the complete URL including https://Example:
https://docs.company.com/api/authentication
6

Click 'Create'

The system will fetch and process the web page.Status progression:
  • PENDING → URL queued for scraping
  • PROCESSING → Fetching and extracting content
  • COMPLETED → Content available
  • FAILED → Scraping error occurred

​
URL Item JSON Example

{
  "category": "URL",
  "title": "API Authentication Documentation",
  "source_url": "https://docs.company.com/api/authentication",
  "status": "COMPLETED"
}

​
URL Requirements

Working URLs:
  • Publicly accessible (no login required)
  • Simple HTML content pages
  • Documentation sites
  • Blog posts and articles
  • Static content pages
Problematic URLs:
  • Pages requiring authentication
  • JavaScript-heavy applications (SPAs)
  • Paywalled content
  • Dynamically loaded content
  • Interactive applications
URL scraping works best with simple, text-based web pages. Complex web applications may not scrape successfully.

​
Common URL Issues

Causes:
  • Page requires login/authentication
  • URL is incorrect or broken
  • Content loads via JavaScript
  • Website blocks scraping (robots.txt)
  • Page doesn’t exist (404)
Solutions:
  • Verify URL is publicly accessible
  • Test URL in incognito browser window
  • Check URL is complete and correct
  • Copy content manually into text item
  • Use PDF export of page instead
Causes:
  • JavaScript-rendered content not captured
  • Dynamic content loading
  • Multiple tabs/sections on page
  • Comments or sidebar scraped instead of main content
Solutions:
  • Inspect scraped content in edit mode
  • Use direct URL to specific content
  • Copy desired content into text item
  • Export page as PDF and upload instead
Solution: URL content is scraped once at creation time. To update:
  • Delete and re-create the URL item
  • Or copy current content into a text item for manual updates
For frequently changing content, consider:
  • Manual text items you update regularly
  • PDF exports you refresh periodically

​
URL Best Practices

Test accessibility

  • Open URL in incognito window
  • Verify no login required
  • Check content is visible
  • Ensure page loads quickly

Review scraped content

  • Check content after scraping
  • Verify correct content was captured
  • Look for formatting issues
  • Confirm no extra content (ads, sidebars)

​
Processing Status Flow

Knowledge items go through two separate processing pipelines:
  1. Content Processing - Extracting text from files/URLs
  2. Vector Indexing - Preparing content for RAG (semantic search)

​
Content Processing Status

This tracks the extraction of text content from your source.
1

PENDING

Meaning: Item created, queued for content extractionWhat’s happening:
  • Item has been saved to database
  • Waiting for processing worker to pick it up
  • Usually very brief (seconds)
Action needed: None - wait for processing to begin
2

PROCESSING

Meaning: Item content is being extracted right nowWhat’s happening:
  • For FILES: Extracting text from PDF, Word, etc.
  • For URLs: Fetching and scraping the specific web page
  • For TEXT: N/A (skips directly to COMPLETED)
Action needed: Wait for processing to complete
3

COMPLETED

Meaning: Content extraction finished successfullyWhat’s happening:
  • Content has been extracted and stored
  • Vector indexing will begin automatically
  • Item will be available once indexing completes
Action needed: None - wait for vector indexing
4

FAILED

Meaning: Content extraction encountered an errorWhat’s happening:
  • File extraction failed (corrupted PDF, unsupported format)
  • URL scraping failed (page not found, blocked, requires auth)
  • Content is not available to agents
Action needed: Check error message and fix the issue
Content Processing Flow: CREATED → PENDING → PROCESSING → COMPLETED or FAILED

​
Vector Indexing Status

After content is extracted, it must be indexed for RAG (semantic search). This allows agents to find relevant knowledge based on meaning, not just keywords.
1

PENDING

Meaning: Waiting for vector indexing to startWhat’s happening:
  • Content processing completed successfully
  • Queued for embedding generation
  • Usually brief (seconds to minutes)
Action needed: None
2

INDEXING

Meaning: Creating vector embeddings for RAGWhat’s happening:
  • Content is being split into chunks
  • AI embeddings being generated for each chunk
  • Vectors being stored in the knowledge base
Action needed: Wait - this can take several minutes for large documents
3

INDEXED

Meaning: Item is fully ready for RAG retrievalWhat’s happening:
  • Vector embeddings stored successfully
  • Item can be retrieved via semantic search
  • Agents can now use this knowledge
Action needed: None - item is fully ready
4

FAILED

Meaning: Vector indexing failedWhat’s happening:
  • Embedding generation encountered an error
  • Item won’t appear in RAG results
  • May be available for context injection only
Action needed: Try re-indexing or contact support
5

REMOVED

Meaning: Vectors were deletedWhat’s happening:
  • Item was deleted or explicitly removed from index
  • No longer available for RAG
Action needed: Re-index if needed
Vector Indexing Flow: PENDING → INDEXING → INDEXED or FAILED
Both statuses must succeed for full functionality:
  • Content Status: COMPLETED
  • Vector Status: INDEXED
Only then can the item be used in both context injection and RAG retrieval.

​
Error Handling

​
When Items Fail

If a knowledge item shows FAILED status:
1

Check the error message

Click on the failed item to see error details.
2

Identify the cause

Common causes:
  • Files: File too large, corrupted, password-protected, scanned image
  • URL: Authentication required, broken link, content not accessible
3

Try solutions

  • For Files: Compress, remove protection, add text layer, or convert to text
  • For URLs: Verify accessibility, try different URL, or copy content to text item
4

Recreate or convert

  • Delete failed item
  • Create new item with fixes applied
  • Or convert to text item by copying content manually

​
Preventing Errors

File Prevention

  • Keep files under 5MB
  • Use text-based documents or quality scans
  • Remove passwords
  • Test with small file first

URL Prevention

  • Test URL in incognito mode
  • Use simple HTML pages
  • Avoid authenticated content
  • Check robots.txt compatibility

​
Monitoring Processing

​
Dashboard Indicators

In your knowledge base dashboard, you can see processing status at a glance for each item in your folders: Status indicators:
  • Green checkmark = COMPLETED
  • Hourglass = PROCESSING
  • Pause symbol = PENDING
  • Red X = FAILED
Example folder view:
  • User Manual.pdf - COMPLETED
  • Quick Start Guide.pdf - PROCESSING
  • API Documentation - PENDING
  • Legacy Manual.pdf - FAILED

​
Bulk Processing

When uploading multiple items:
  1. Items process sequentially or in parallel (system-dependent)
  2. Check back after 5-10 minutes for large batches
  3. Review status of each item
  4. Fix any failures individually
Upload a test item first to verify format and processing before bulk uploading.

​
Choosing the Right Content Type

Use this decision tree to select the best content type: Do you have existing content?
  • No → Use TEXT (write directly)
  • Yes, it’s a document →
    • Under 10MB → Use FILE
    • Over 10MB → Extract text, use TEXT
  • Yes, it’s a web page →
    • Publicly accessible → Use URL (if scraping fails, copy to TEXT)
    • Not accessible → Copy content to TEXT

​
Quick Recommendations

Your SituationBest Content Type
Writing FAQs from scratchTEXT
Have existing Word/PDF docsUpload as FILE
Have documents under 10MBFILE
Have documents over 10MBSplit into smaller files or extract to TEXT
Public web documentationURL (with TEXT as backup)
Private/authenticated contentCopy to TEXT
Need immediate availabilityTEXT (no processing delay)
Complex formatting mattersFILE

​
Next Steps

Context vs RAG

Learn how agents access your knowledge content

Create Knowledge Bases

Step-by-step creation guide

Architecture Overview

Understand knowledge base structure

Variables & Dynamic Content

Reference knowledge in agent instructions