Files
agent-framework/python/packages/copilotstudio
T
Eduard van Valkenburg 6138487888 Python: Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference (#4207)
* Phase 2: Embedding clients for Ollama, Bedrock, and Azure AI Inference

Add embedding client implementations to existing provider packages:

- OllamaEmbeddingClient: Text embeddings via Ollama's embed API
- BedrockEmbeddingClient: Text embeddings via Amazon Titan on Bedrock
- AzureAIInferenceEmbeddingClient: Text and image embeddings via Azure AI
  Inference, supporting Content | str input with separate model IDs for
  text (AZURE_AI_INFERENCE_EMBEDDING_MODEL_ID) and image
  (AZURE_AI_INFERENCE_IMAGE_EMBEDDING_MODEL_ID) endpoints

Additional changes:
- Rename EmbeddingCoT -> EmbeddingT, EmbeddingOptionsCoT -> EmbeddingOptionsT
- Add otel_provider_name passthrough to all embedding clients
- Register integration pytest marker in all packages
- Add lazy-loading namespace exports for Ollama and Bedrock embeddings
- Add image embedding sample using Cohere-embed-v3-english
- Add azure-ai-inference dependency to azure-ai package

Part of #1188

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* Fix mypy duplicate name and ruff lint issues

- Rename second 'vector' variable to 'img_vector' in image embedding loop
- Combine nested with statements in tests
- Remove unused result assignments in tests

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

* updates from feedback

* Fix CI failures in embedding usage handling

- Fix Azure AI embedding mypy issues by normalizing vectors to list[float],
  safely accumulating optional usage token fields, and filtering None entries
  before constructing GeneratedEmbeddings
- Avoid Bandit false positive by initializing usage details as an empty dict
- Update OpenAI embedding tests to assert canonical usage keys
  (input_token_count/total_token_count)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
6138487888 ยท 2026-02-25 17:45:08 +00:00
History
..

Get Started with Microsoft Agent Framework Copilot Studio

Please install this package via pip:

pip install agent-framework-copilotstudio --pre

Copilot Studio Agent

The Copilot Studio agent enables integration with Microsoft Copilot Studio, allowing you to interact with published copilots through the Agent Framework.

Prerequisites

Before using the Copilot Studio agent, you need:

  1. Copilot Studio Environment: Access to a Microsoft Copilot Studio environment with a published copilot
  2. App Registration: An Azure AD App Registration with appropriate permissions for Power Platform API
  3. Environment Configuration: Set the required environment variables or pass them as parameters

Environment Variables

The following environment variables are used for configuration:

  • COPILOTSTUDIOAGENT__ENVIRONMENTID - Your Copilot Studio environment ID
  • COPILOTSTUDIOAGENT__SCHEMANAME - Your copilot's agent identifier/schema name
  • COPILOTSTUDIOAGENT__AGENTAPPID - Your App Registration client ID
  • COPILOTSTUDIOAGENT__TENANTID - Your Azure AD tenant ID

Basic Usage Example

import asyncio
from agent_framework.microsoft import CopilotStudioAgent

async def main():
    # Create agent using environment variables
    agent = CopilotStudioAgent()

    # Run a simple query
    result = await agent.run("What is the capital of France?")
    print(result)

asyncio.run(main())

Explicit Configuration Example

import asyncio
import os
from agent_framework.microsoft import CopilotStudioAgent, acquire_token
from microsoft_agents.copilotstudio.client import ConnectionSettings, CopilotClient, PowerPlatformCloud, AgentType

async def main():
    # Acquire authentication token
    token = acquire_token(
        client_id=os.environ["COPILOTSTUDIOAGENT__AGENTAPPID"],
        tenant_id=os.environ["COPILOTSTUDIOAGENT__TENANTID"]
    )

    # Create connection settings
    settings = ConnectionSettings(
        environment_id=os.environ["COPILOTSTUDIOAGENT__ENVIRONMENTID"],
        agent_identifier=os.environ["COPILOTSTUDIOAGENT__SCHEMANAME"],
        cloud=PowerPlatformCloud.PROD,
        copilot_agent_type=AgentType.PUBLISHED,
        custom_power_platform_cloud=None
    )

    # Create client and agent
    client = CopilotClient(settings=settings, token=token)
    agent = CopilotStudioAgent(client=client)

    # Run a query
    result = await agent.run("What is the capital of Italy?")
    print(result)

asyncio.run(main())

Authentication

The package uses MSAL (Microsoft Authentication Library) for authentication with interactive flows when needed. Ensure your App Registration has:

  • API Permissions: Power Platform API permissions (https://api.powerplatform.com/.default)
  • Redirect URIs: Configured appropriately for your authentication method
  • Public Client Flows: Enabled if using interactive authentication

Examples

For more comprehensive examples, see the Copilot Studio examples which demonstrate:

  • Basic non-streaming and streaming execution
  • Explicit settings and manual token acquisition
  • Different authentication patterns
  • Error handling and troubleshooting