You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: lessons/04-structured-output/README.md
+3-3
Original file line number
Diff line number
Diff line change
@@ -12,7 +12,7 @@ If you haven't already, set up your development environment. Here's how you can
12
12
13
13
## Related resources
14
14
15
-
It's worth rewatching the video of prompt engineering is it lays the foundations of what you're about to learn in this chapter, that is how to have the AI deliver more structured outputs.
15
+
It's worth rewatching the video on prompt engineering as it lays the foundations of what you're about to learn in this chapter, that is how to have the AI deliver more structured outputs.
16
16
17
17
[](https://www.youtube.com/watch?v=gQ6TlyxBmWs&list=PLlrxD0HtieHi5ZpsHULPLxm839IrhmeDk&index=3)
Figure out which skill to use based on a users prompt and extract the necessary parameters, respond with the extracted data in JSON format with columns skill, parameters, extracted_data
486
+
Figure out which skill to use based on a user's prompt and extract the necessary parameters, respond with the extracted data in JSON format with columns skill, parameters, extracted_data
487
487
488
488
{user_input}
489
489
```
@@ -522,7 +522,7 @@ Assuming that {user_input} contains the previous skills, let's try out the follo
522
522
}
523
523
```
524
524
525
-
This combination of presenting skills and parameters and extracting data from prompts is also known as _tool calling_ or _function calling_. A response like this from your model makes it easy for you as developer to understand what the user wants and how to call a corresponding function to fulfill the user's request.
525
+
This combination of presenting skills and parameters and extracting data from prompts is also known as _tool calling_ or _function calling_. A response like this from your model makes it easy for you as a developer to understand what the user wants and how to call a corresponding function to fulfill the user's request.
526
526
527
527
**You:** Well that lasted for a full 20 seconds. Actually, what you said there, George, that was pretty good.
0 commit comments