> ## 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.

# Web Search and Browsing

> How Omnifact finds real-time information on the internet to give you up-to-date answers

export const Glossary = ({children, term}) => {
  const glossaryDefinitions = {
    'ai': 'Artificial Intelligence - computer systems that can perform tasks typically requiring human intelligence',
    'artificial-intelligence-ai': 'Computer systems that can perform tasks typically requiring human intelligence',
    'ai-assistant': 'An AI system designed to help users with tasks through conversation',
    'space': 'A dedicated environment with a specialized AI assistant and optional Knowledge Base',
    'knowledge': 'The sub-menu in Space settings where you manage Uploaded Files and Connected Sources',
    'knowledge-base': 'The collection of documents in a Space (from Uploaded Files and Connected Sources) that the AI assistant can retrieve',
    'uploaded-files': 'Documents manually uploaded to a Space under the Knowledge tab',
    'prompt': 'Instructions or questions you give to an AI assistant',
    'response': 'The AI assistant\'s answer to your prompt or question',
    'query': 'A question or request for information',
    'context': 'Background information that helps the AI understand your request',
    'llm': 'Large Language Model - an AI system trained on vast amounts of text data to understand and generate human language',
    'large-language-model-llm': 'An AI system trained on vast amounts of text data to understand and generate human language',
    'privacy-filter': 'A system that automatically detects and masks sensitive information before it reaches AI models, and restricts images from being sent to non-EU hosted models for compliance',
    'chat-instructions': 'Custom guidelines that define how an AI assistant behaves and responds in a Space',
    'pattern-matching': 'The process by which AI recognizes and uses patterns in data to provide responses',
    'patterns': 'Recognizable structures or trends in data that AI systems can identify and use',
    'training-data': 'The text and information used to teach an AI system how to understand and respond to requests',
    'natural-language': 'Everyday human language that people use to communicate, as opposed to computer code or formal syntax',
    'hallucination': 'When an AI generates information that sounds plausible but is actually incorrect or fabricated',
    'filtering': 'The process of automatically detecting and temporarily replacing sensitive information to protect it during AI processing',
    'masking': 'Temporarily replacing sensitive information with generic labels to protect it from being seen by external AI models',
    're-insertion': 'The automatic process of putting original sensitive information back into AI responses after they\'ve been generated with filtered data',
    'retrieval': 'The process of finding and accessing relevant documents from Uploaded Files to answer questions',
    'hosting': 'Where an AI model is deployed and made available for use - either by third-party providers, on your organization\'s own servers, or in private cloud environments',
    'cite': 'To reference or mention the source of information, helping you know where an AI\'s answer came from',
    'sidebar': 'A panel that appears on the side of the screen showing additional information and options',
    'toggle': 'A button or control that switches something on or off, like opening and closing a sidebar',
    'navigation': 'The system of menus and buttons that help you move between different parts of Omnifact',
    'favoriting': 'Marking a Space as a favorite to pin it to the main navigation for quick access',
    'pinning': 'Attaching a Space to the main navigation bar so it\'s always visible and easily accessible'
  };
  const definition = glossaryDefinitions[term];
  return <Tooltip tip={definition}>{children}</Tooltip>;
};

Omnifact isn't limited to just the knowledge it was trained on. With **Web Search and Browsing**, your AI assistant can access the live internet to find up-to-date information, fact-check details, and research topics in real-time.

<Card title="Mastering Web Search" icon="graduation-cap" href="/en/guides/mastering-chat/skills/using-web-search-research">
  Want to learn how to use Web Search effectively for professional research? Check out our **in-depth guide on using Web Search for Research**.
</Card>

## How It Works

Web Search is integrated directly into the chat experience within the [**Auto** response mode](/en/platform/core-features/chats/response-modes#auto-mode-default).

1. **Automatic Detection:** Omnifact intelligently detects when a question requires outside information (e.g., "current stock prices," "today's news") and triggers a search automatically.
2. **Explicit Requests:** You can also force a search by starting your prompt with instructions like "Search for..." or "Find the latest on...".
3. **Transparency:** You will see status indicators ("Searching...", "Reading...") as the AI works, followed by **numbered citations** in the final response that link back to the original sources.

<Note>
  Web Search is **disabled** in **Quick Response** and **Simple Lookup** modes to ensure speed or strictly internal answers.
</Note>

## Privacy and Security

Your privacy remains a top priority. The [Privacy Filter](/en/platform/core-features/privacy-security/how-privacy-filter-works) actively protects your search queries:

* **Scanning:** Before any query is sent to a search provider, it is scanned for sensitive information.
* **Blocking:** If your query contains masked sensitive data (like names or account numbers), the search is **blocked** to prevent data leakage.
* **Notification:** You will be notified if a search is blocked, allowing you to rephrase without the sensitive details.

## Capabilities & Limitations

* **Live Data:** Access news, market data, and events that happened after the AI's training cutoff.
* **Page Reading:** The AI can visit and read the text content of specific URLs you provide (up to 2MB).
* **No Paywalls:** It cannot access content behind paywalls, login screens, or captchas.
* **Media:** It processes text (HTML), not videos or interactive charts.