From the course: LangGraph.js: Building Agents with Javascript

Unlock this course with a free trial

Join today to access over 25,500 courses taught by industry experts.

Creating a tool that searches the web

Creating a tool that searches the web

From the course: LangGraph.js: Building Agents with Javascript

Start my 1-month free trial Buy for my team

Creating a tool that searches the web

“

In this video, we'll be building and using a tool that searches the web to power the final AI feature in our application, the Smart Search feature. So far, our agent can only work with data inside our application. But with the Smart Search tool, users will be able to browse notes from around the World Wide Web. How awesome is that? To implement this, we'll be employing a search API tool called Tavili. As you can see the website on the screen. Tavili is specifically built for LLMs to search the web for information. This is because it returns actual content and not just links. It is also optimized for AI use cases and it offers a generous free tier for us to test things out. To use Tavili, first you need to visit the website at tavili.com. Then sign up for a free account. This takes you to your dashboard where you can copy your API key. With this key in hand, we can now authenticate with and use the Tavili API. To do this, we need to add the key we just copied to our environment file…

Contents