Notebook

Streaming Results¶

Here is an example pattern if you want to stream your multiple results. Note that this is not supported for Hugging Face text completions at this time.

Import Semantic Kernel SDK from pypi.org

In [ ]:

# Note: if using a virtual environment, do not run this cell
%pip install -U semantic-kernel
from semantic_kernel import __version__

__version__

Initial configuration for the notebook to run properly.

In [ ]:

# Make sure paths are correct for the imports

import os
import sys

notebook_dir = os.path.abspath("")
parent_dir = os.path.dirname(notebook_dir)
grandparent_dir = os.path.dirname(parent_dir)


sys.path.append(grandparent_dir)

Configuring the Kernel¶

Let's get started with the necessary configuration to run Semantic Kernel. For Notebooks, we require a .env file with the proper settings for the model you use. Create a new file named .env and place it in this directory. Copy the contents of the .env.example file from this directory and paste it into the .env file that you just created.

NOTE: Please make sure to include GLOBAL_LLM_SERVICE set to either OpenAI, AzureOpenAI, or HuggingFace in your .env file. If this setting is not included, the Service will default to AzureOpenAI.

Option 1: using OpenAI¶

Add your OpenAI Key key to your .env file (org Id only if you have multiple orgs):

GLOBAL_LLM_SERVICE="OpenAI"
OPENAI_API_KEY="sk-..."
OPENAI_ORG_ID=""
OPENAI_CHAT_MODEL_ID=""
OPENAI_TEXT_MODEL_ID=""
OPENAI_EMBEDDING_MODEL_ID=""

The names should match the names used in the .env file, as shown above.

Option 2: using Azure OpenAI¶

Add your Azure Open AI Service key settings to the .env file in the same folder:

GLOBAL_LLM_SERVICE="AzureOpenAI"
AZURE_OPENAI_API_KEY="..."
AZURE_OPENAI_ENDPOINT="https://..."
AZURE_OPENAI_CHAT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_TEXT_DEPLOYMENT_NAME="..."
AZURE_OPENAI_EMBEDDING_DEPLOYMENT_NAME="..."
AZURE_OPENAI_API_VERSION="..."

The names should match the names used in the .env file, as shown above.

For more advanced configuration, please follow the steps outlined in the setup guide.

We will load our settings and get the LLM service to use for the notebook.

In [ ]:

from services import Service

from samples.service_settings import ServiceSettings

service_settings = ServiceSettings.create()

# Select a service to use for this notebook (available services: OpenAI, AzureOpenAI, HuggingFace)
selectedService = (
    Service.AzureOpenAI
    if service_settings.global_llm_service is None
    else Service(service_settings.global_llm_service.lower())
)
print(f"Using service type: {selectedService}")

First, we will set up the text and chat services we will be submitting prompts to.

In [ ]:

from semantic_kernel import Kernel
from semantic_kernel.connectors.ai.open_ai import (
    AzureChatCompletion,
    AzureChatPromptExecutionSettings,  # noqa: F401
    AzureTextCompletion,
    OpenAIChatCompletion,
    OpenAIChatPromptExecutionSettings,  # noqa: F401
    OpenAITextCompletion,
    OpenAITextPromptExecutionSettings,  # noqa: F401
)
from semantic_kernel.contents import ChatHistory  # noqa: F401

kernel = Kernel()

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

    service_id = "default"
    oai_chat_service = OpenAIChatCompletion(
        service_id="oai_chat",
    )
    oai_text_service = OpenAITextCompletion(
        service_id="oai_text",
    )
elif selectedService == Service.AzureOpenAI:
    from semantic_kernel.connectors.ai.open_ai import AzureChatCompletion

    service_id = "default"
    aoai_chat_service = AzureChatCompletion(
        service_id="aoai_chat",
    )
    aoai_text_service = AzureTextCompletion(
        service_id="aoai_text",
    )

# Configure Hugging Face service
if selectedService == Service.HuggingFace:
    from semantic_kernel.connectors.ai.hugging_face import (
        HuggingFacePromptExecutionSettings,  # noqa: F401
        HuggingFaceTextCompletion,
    )

    hf_text_service = HuggingFaceTextCompletion(ai_model_id="distilgpt2", task="text-generation")

Next, we'll set up the completion request settings for text completion services.

In [ ]:

oai_prompt_execution_settings = OpenAITextPromptExecutionSettings(
    service_id="oai_text",
    max_tokens=150,
    temperature=0.7,
    top_p=1,
    frequency_penalty=0.5,
    presence_penalty=0.5,
)

Streaming Open AI Text Completion¶

In [ ]:

if selectedService == Service.OpenAI:
    prompt = "What is the purpose of a rubber duck?"
    stream = oai_text_service.get_streaming_text_contents(prompt=prompt, settings=oai_prompt_execution_settings)
    async for message in stream:
        print(str(message[0]), end="")  # end = "" to avoid newlines

Streaming Azure Open AI Text Completion¶

In [ ]:

if selectedService == Service.AzureOpenAI:
    prompt = "provide me a list of possible meanings for the acronym 'ORLD'"
    stream = aoai_text_service.get_streaming_text_contents(prompt=prompt, settings=oai_prompt_execution_settings)
    async for message in stream:
        print(str(message[0]), end="")

Streaming Hugging Face Text Completion¶

In [ ]:

if selectedService == Service.HuggingFace:
    hf_prompt_execution_settings = HuggingFacePromptExecutionSettings(
        service_id="hf_text",
        extension_data={
            "max_new_tokens": 80,
            "top_p": 1,
            "eos_token_id": 11,
            "pad_token_id": 0,
        },
    )

In [ ]:

if selectedService == Service.HuggingFace:
    prompt = "The purpose of a rubber duck is"
    stream = hf_text_service.get_streaming_text_contents(
        prompt=prompt, prompt_execution_settings=hf_prompt_execution_settings
    )
    async for text in stream:
        print(str(text[0]), end="")  # end = "" to avoid newlines

Here, we're setting up the settings for Chat completions.

In [ ]:

oai_chat_prompt_execution_settings = OpenAIChatPromptExecutionSettings(
    service_id="oai_chat",
    max_tokens=150,
    temperature=0.7,
    top_p=1,
    frequency_penalty=0.5,
    presence_penalty=0.5,
)

Streaming OpenAI Chat Completion¶

In [ ]:

if selectedService == Service.OpenAI:
    content = "You are an AI assistant that helps people find information."
    chat = ChatHistory()
    chat.add_system_message(content)
    stream = oai_chat_service.get_streaming_chat_message_contents(
        chat_history=chat, settings=oai_chat_prompt_execution_settings
    )
    async for text in stream:
        print(str(text[0]), end="")  # end = "" to avoid newlines

Streaming Azure OpenAI Chat Completion¶

In [ ]:

az_oai_chat_prompt_execution_settings = AzureChatPromptExecutionSettings(
    service_id="aoai_chat",
    max_tokens=150,
    temperature=0.7,
    top_p=1,
    frequency_penalty=0.5,
    presence_penalty=0.5,
)

In [ ]:

if selectedService == Service.AzureOpenAI:
    content = "You are an AI assistant that helps people find information."
    chat = ChatHistory()
    chat.add_system_message(content)
    chat.add_user_message("What is the purpose of a rubber duck?")
    stream = aoai_chat_service.get_streaming_chat_message_contents(
        chat_history=chat, settings=az_oai_chat_prompt_execution_settings
    )
    async for text in stream:
        print(str(text[0]), end="")  # end = "" to avoid newlines