sii_web_fetch - Web Content Fetching

Overview

The sii_web_fetch tool processes content from URLs using SII backend service, including local and private network addresses (e.g., localhost). Include up to 20 URLs and instructions (e.g., summarize, extract specific data) directly in the 'prompt' parameter.

Tool Name

• Internal Name: sii_web_fetch
• Display Name: SII Web Fetch
• Icon: Download

Prerequisites

1. SII Account: Valid SII account required
2. Environment Variables:
   • SII_USERNAME: SII username
   • SII_PASSWORD: SII password
   • SII_BASE_URL: SII backend URL (optional, defaults to https://www.opensii.ai/backend)

Parameters

Required Parameters

Parameter	Type	Description
prompt	string	A comprehensive prompt that includes the URL(s) (up to 20) to fetch and specific instructions on how to process their content (e.g., "Summarize https://example.com/article and extract key points from https://another.com/data"). Must contain at least one URL starting with http:// or https://.

Features

1. Multi-URL Support: Process up to 20 URLs at once
2. Content Processing: Automatic content fetching and intelligent extraction
3. Flexible Instructions: Summarize, extract, compare, or custom processing
4. Local Network Support: Supports localhost and private IP addresses

Usage Examples

Summarize Single Page

{
  "prompt": "Summarize the main content of this article: https://example.com/article"
}

Extract Specific Information

{
  "prompt": "Extract all product names and prices from https://example.com/products"
}

Process Multiple URLs

{
  "prompt": "Compare the viewpoints from these three articles: https://site1.com/article1, https://site2.com/article2, https://site3.com/article3"
}

Local Development Server

{
  "prompt": "Analyze the homepage content at http://localhost:3000 and list all navigation links"
}

Return Value

The tool returns an object containing:

• llmContent: Processed content
• returnDisplay: User-friendly display information
• summary: Operation summary
• sources: List of processed URLs

Best Practices

1. Clear Instructions: Be specific about what you want extracted or processed
2. Reasonable URL Count: Keep to 5-10 URLs per task for optimal performance
3. Specific Extraction Requirements: Clearly specify the type of information needed
4. Error Handling: Check return messages and verify URL accessibility

Related Tools

• sii_web_search: Search for web pages
• sii_hybrid_search: Combined web and cognition search
• sii_cognition_extract_upload: Extract and upload cognitions
• read_file: Read local files