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 24,900 courses taught by industry experts.
Integrating chain-of-thought reasoning into your app - ChatGPT Tutorial
From the course: Building Apps with AI Tools: ChatGPT, Semantic Kernel, and Langchain
Integrating chain-of-thought reasoning into your app
- [Instructor] As developers, one of the best way to debug is to explain the problem to someone else, whether a real person or a rubber duck. Similarly, large language models perform better when they explain their thinking. This is a technique called Chain of Thought Reasoning. By explaining and thinking step-by-step, models can perform better on certain tasks. Now, let's jump back into our code. I'm on Branch: 03_03 since we'll be using just one code base for this video. Now, let's improve on our e-commerce example. We're loading in our order here, but this time I have a file called order_big which has 35 examples in here rather than just 10. Now, I've included an example in here for chain of thought reasoning, but let's see what happens when we don't include it. I'm going to delete prompt_examples here, going to save, and I'm going to hit Run. Now, this might take a little bit of time since we're going through a bigger…
Contents
-
-
-
-
-
(Locked)
A simple summarizer with Semantic Kernel4m 40s
-
(Locked)
Formatting your data with few-shot learning4m 47s
-
(Locked)
Integrating chain-of-thought reasoning into your app4m 5s
-
(Locked)
Learning to use Whisper for text to speech2m 27s
-
(Locked)
Challenge: Creating a "thinking out loud" librarian41s
-
(Locked)
Solution: Creating a "thinking out loud" librarian2m 32s
-
(Locked)
-
-
-