Enabling Web Browsing for an Assistant
To enable web tools for your elvex assistant, follow these steps:
Open your assistant's configuration settings
Navigate to the Tools section
Locate the Web Browsing option and toggle it on
Save your assistant configuration by clicking Save & Publish
Note that while web tools are available to all users, they need to be enabled individually for each assistant.
When do Assistants use Web Browsing?
Once web tools are enabled, your assistant can decide when to perform web searches or read specific URLs based on its internal logic and user interactions. Users can also explicitly ask the assistant to search or read a URL if the assistant supports that functionality.
To guide your assistant's web searching behavior more consistently, you can set up assistant rules in the assistant's configuration settings. These rules help define when and how the assistant should utilize web tools.
The Web Browsing tool will work in conversations using the elvex user interface, Slack integration, or API.
When an assistant uses the Web Browsing tool, you'll see confirmation in the assistant's response.
Web Content Retrieval Options
elvex's web browsing tools offer two ways to retrieve content from web pages:
Standard Text Extraction (Default)
By default, when an assistant accesses a webpage, elvex extracts the text content and removes all HTML tags, providing clean, readable text. This approach:
Removes formatting, scripts, and styling elements
Focuses on the main textual content
Is ideal for most information retrieval tasks
Works well for reading articles, blog posts, and documentation
Raw HTML Retrieval
When specifically requested, assistants can also retrieve the complete raw HTML content of a webpage, including all tags, scripts, and formatting elements. This option:
Preserves the complete HTML structure
Includes all tags, attributes, and embedded content
Is useful for web development tasks, HTML analysis, or when page structure is important
Provides access to metadata, styling information, and embedded scripts
To request raw HTML content, you can ask your assistant to "get the raw HTML" or "retrieve the HTML source" of a specific webpage.
Best practices and usage guidelines
When leveraging web searching in your elvex assistants, consider the following best practices and guidelines:
Searching the web allows your assistant to find up to date information that is outside of the training data in the underlying model or information that is outside of the data in the Datasources that may be connected to that assistant.
Provide clear instructions in your assistant to explain when and how it should perform web searches or read specific pages.
You may include specific URLs or sites that you want your assistant to reference.
Conclusion
Integrating web searching and webpage reading capabilities into your elvex assistants opens up a world of possibilities for enhanced functionality and information access. By leveraging web tools, you can create assistants that provide users with up-to-date, relevant, and comprehensive information.
As you explore web browsing with your assistants, remember to follow best practices and provide rules to guide behavior. If you have any further questions or need assistance, don't hesitate to reach out to the elvex support or consult the documentation.
Happy building!
FAQ
Q: Does Web Browsing work with any AI provider and model?
A: Yes, elvex has designed "tools", like Web Browsing, to work across any AI provider and model your assistant is connected with. Tools like Data Analysis are elvex features that we make work on top of the model your assistant is connected to. That being said, Web Browsing will work best with more advanced models like ChatGPT-4, ChatGPT-4 Turbo, Claude 3 Opus, Claude 3 Sonnet, and other similarly powerful models.
Q: Can the Web Browsing tool access information on web pages that are private or behind a login screen?
A: No, the Web Browsing tool can only access information on web pages that are not gated.