microsoft-teams-ai 2.0.0a78

package to handle interacting with ai or llms

Microsoft Teams SDK

[!WARNING] Deprecated — This package was originally in preview, but we have decided to stop maintaining it before General Availability. We recommend using the Agent Framework instead, which provides better long-term support for building AI-powered Teams applications.

AI-powered conversational experiences for Microsoft Teams applications. Provides prompt management, action planning, and model integration for building intelligent Teams bots.

📖 Documentation

Installation

pip install microsoft-teams-ai

Or if using uv:

uv add microsoft-teams-ai

Usage

ChatPrompt

from microsoft_teams.ai import ChatPrompt, Function
from microsoft_teams.openai import OpenAICompletionsAIModel
from pydantic import BaseModel

model = OpenAICompletionsAIModel(api_key="your-api-key", model="gpt-4")

# Create a ChatPrompt
prompt = ChatPrompt(model)

result = await prompt.send(
    input="Hello!",
    instructions="You are a helpful assistant."
)

Function Calling

class GetWeatherParams(BaseModel):
    location: str

async def get_weather(params: GetWeatherParams) -> str:
    return f"The weather in {params.location} is sunny"

weather_function = Function(
    name="get_weather",
    description="Get weather for a location",
    parameter_schema=GetWeatherParams,
    handler=get_weather
)

prompt = ChatPrompt(model, functions=[weather_function])