In this lecture, I want to give you a quick preview of Google BART as a large language model and show you how powerful of a tool Google BART can be when it comes to extracting information using conversational AI, specifically in the use case of working with the internet and live data which is not essentially available in charge GPT in the base model.
I’ll start with a very simple prompt and ask BART to help me plan a trip. My prompt is, ‘Let’s plan a trip to Smoky Mountains National Park near Atlanta. Can you write me a three-day plan which focuses on outdoor activities?’ BART came back with a plan that includes links to different information and photos. The plan suggests starting the day with a hike to Clingmans Dome, visiting Kate’s Cove in the afternoon, and exploring other places on day two and day three.
Next, I asked BART about the longest hikes in Smoky Mountain. BART provided information about the third highest peak in the Smokies, the Kephart Prong Trail, and Klingman’s Dome.
Then, I asked BART about the best town to book an Airbnb close to Smoky Mountains. BART suggested Gatlinburg, Pigeon Forge, Silverwell, Cherokee, and Bryson City as options.
I also asked BART about the price range for a one-bedroom Airbnb in September. BART provided approximate prices for different locations and advised to book early and be flexible.
I then asked BART about the weather in September, and it gave me the weather conditions for Smoky Mountains.
To summarize the three-day trip, I asked BART to provide the plan in tabular format, including a very long hike on day two. BART generated the data in the desired format.
This was just a brief introduction to the power of Google BART as a conversational AI tool for extracting personalized information from the internet. In the next video, I’ll show you how the same concept can be applied to programming, where BART can write code and extract data from different sources to generate graphs without us writing a single line of code. Stay tuned!
