Notebook

How to run a prompt plugins from file¶

Now that you're familiar with Kernel basics, let's see how the kernel allows you to run Prompt Plugins and Prompt Functions stored on disk.

A Prompt Plugin is a collection of Semantic Functions, where each function is defined with natural language that can be provided with a text file.

Refer to our glossary for an in-depth guide to the terms.

The repository includes some examples under the samples folder.

For instance, this is the Joke function part of the FunPlugin plugin:

WRITE EXACTLY ONE JOKE or HUMOROUS STORY ABOUT THE TOPIC BELOW.
JOKE MUST BE:
- G RATED
- WORKPLACE/FAMILY SAFE
NO SEXISM, RACISM OR OTHER BIAS/BIGOTRY.
BE CREATIVE AND FUNNY. I WANT TO LAUGH.
+++++
{{$input}}
+++++

Note the special {{$input}} token, which is a variable that is automatically passed when invoking the function, commonly referred to as a "function parameter".

We'll explore later how functions can accept multiple variables, as well as invoke other functions.

In the same folder you'll notice a second config.json file. The file is optional, and is used to set some parameters for large language models like Temperature, TopP, Stop Sequences, etc.

{
  "schema": 1,
  "description": "Generate a funny joke",
  "execution_settings": {
    "default": {
      "max_tokens": 1000,
      "temperature": 0.9,
      "top_p": 0.0,
      "presence_penalty": 0.0,
      "frequency_penalty": 0.0
    }
  },
  "input_variables": [
    {
      "name": "input",
      "description": "Joke subject",
      "default": ""
    },
    {
      "name": "style",
      "description": "Give a hint about the desired joke style",
      "default": ""
    }
  ]
}

Given a prompt function defined by these files, this is how to load and use a file based prompt function.

Load and configure the kernel, as usual, loading also the AI service settings defined in the Setup notebook:

In [ ]:

!python -m pip install semantic-kernel==1.0.3

In [ ]:

from services import Service

# Select a service to use for this notebook (available services: OpenAI, AzureOpenAI, HuggingFace)
selectedService = Service.OpenAI

In [ ]:

from semantic_kernel import Kernel

kernel = Kernel()

service_id = None
if selectedService == Service.OpenAI:
    from semantic_kernel.connectors.ai.open_ai import OpenAIChatCompletion

    service_id = "default"
    kernel.add_service(
        OpenAIChatCompletion(service_id=service_id, ai_model_id="gpt-3.5-turbo-1106"),
    )
elif selectedService == Service.AzureOpenAI:
    from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

    service_id = "default"
    kernel.add_service(
        AzureChatCompletion(service_id=service_id),
    )

Import the plugin and all its functions:

In [ ]:

# note: using plugins from the samples folder
plugins_directory = "../../../prompt_template_samples/"

funFunctions = kernel.add_plugin(parent_directory=plugins_directory, plugin_name="FunPlugin")

jokeFunction = funFunctions["Joke"]

How to use the plugin functions, e.g. generate a joke about "time travel to dinosaur age":

In [ ]:

result = await kernel.invoke(jokeFunction, input="travel to dinosaur age", style="silly")
print(result)

Great, now that you know how to load a plugin from disk, let's show how you can create and run a prompt function inline.