From the course: Building Apps with AI Tools: ChatGPT, Semantic Kernel, and Langchain

Unlock this course with a free trial

Join today to access over 24,800 courses taught by industry experts.

Answering questions with a vector DB

Answering questions with a vector DB - ChatGPT Tutorial

From the course: Building Apps with AI Tools: ChatGPT, Semantic Kernel, and Langchain

Start my 1-month free trial Buy for my team

Answering questions with a vector DB

“

- [Instructor] Imagine being able to build a conversational chatbot on the topic of your choice. I'd be interested in building one about tea. Let's use LangChain's built-in functionality to help us do that. I'm on branch 0402B and let's install some more requirements. I'm going to head over to my requirements dot txt. And now we're going to install three requirements. The first one is called Beautiful Soup. Beautiful Soup is a website some of you might have used to scrape web pages. We're going to do that since we want to load data from Wikipedia. So let's install Beautiful Soup 4 equals 4.12.2. Okay. The next requirement we're going to install is called FAISS. This is a vector database we'll use to store our information. So let's type in FAISS is equal to CPU equal, equal, 1.7.4. Okay, great. Now the final one is a tokenizer called tiktoken. We don't have to worry too much about it. Tiktoken equals 0.4.0.…

Contents