# Web Search The Web Search tool enables the chatbot to retrieve live, real-time information from the internet before generating a response — grounding answers in current data rather than the model's training cutoff. *** #### What It Does When Web Search is enabled, the model actively searches the web based on your prompt and incorporates retrieved information into its response. All tool-enabled LLMs in Qolaba have built-in web search — meaning you stay on your selected model and get live results without being switched to a different provider. This is particularly useful for: * News and current events * Market trends and competitor research * Live product comparisons and pricing * Regulatory updates and policy changes * Any query where up-to-date accuracy matters *** #### How to Enable It Toggle **Web Search** on in the Toolkit panel before sending your prompt. The model will retrieve relevant web results and use them as context when generating its response. {% hint style="info" %} Use Web Search alongside a Knowledge Base for tasks that need both your internal documents and live external data — for example, comparing your internal strategy against current market conditions. {% endhint %} --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.qolaba.ai/chatbot/toolkit/web-search.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.