From the course: Introduction to Azure AI Foundry: Exploring Services and Capabilities
Unlock this course with a free trial
Join today to access over 24,900 courses taught by industry experts.
The Python template code
From the course: Introduction to Azure AI Foundry: Exploring Services and Capabilities
The Python template code
- [Instructor] This is a simple chat prompt flow, but it'll give us an opportunity to look at how we can set up tokens in our Python template and so on. Let's go down and look at our large language model. A couple things I want to point out here is you will have to at some point connect to your service, so choose that from this list. Otherwise, when you try to run the chat here, you'll get an error. This is also where you can set different parameters for your large language model. I'll leave them at the defaults. And then here's our system instructions. And then below that is some Python template code. This is from the jinja template. And these items that you're seeing here, like items.inputs.question, those are tokens and those are defined in several places. So up here you can see in my Inputs, there's two values defined, chat_history and question. So chat_history is a collection that will be populated by the previous prompts. This is the placeholder for the incoming or the new…
Contents
-
-
-
-
-
-
-
(Locked)
What is a prompt flow?3m 42s
-
(Locked)
Load and edit system instructions5m 25s
-
(Locked)
Create a simple prompt flow3m 19s
-
(Locked)
Explore the prompt flow editor2m 52s
-
(Locked)
The Python template code4m 40s
-
(Locked)
Use a standard prompt flow3m 37s
-
(Locked)
Use search engine results with Serp API4m 34s
-
(Locked)
Deploy a prompt flow or playground1m 39s
-
(Locked)
-