Build a smart AI voice assistant (connect to the Internet)
Let's learn how to build a smart AI assistant using OpenAI API assistant and function calling so we can expand its knowledge with real-time data.
Let's learn how to build a smart AI voice assistant! Previously, we built a simple AI voice assistant using the OpenAI API. Feel free to follow the tutorial here.
This time, we want to eliminate the knowledge limitation of the OpenAI model (which is cut off in a certain year) by adding the ability to Google for an answer. If we can Google the answer, we can get real-time data!
"LLMs can reason about wide-ranging topics, but their knowledge is limited to the public data up to a specific point in time that they were trained on. If you want to build AI applications that can reason about private data or data introduced after a model’s cutoff date, you need to augment the knowledge of the model with the specific information it needs. The process of bringing the appropriate information and inserting it into the model prompt is known as Retrieval Augmented Generation (RAG)." - What is RAG - LangChain.
OpenAI has a separate API called function calling , which enables the AI assistant to call external APIs. Luckily, SerpApi offers an API to access Google Search results. So, we'll call the SerpApi Google Search API via function calling inside our app whenever the assistant needs real-time data.
