Skip to content

Azure

Before starting this guide, ensure you have completed the Installation Guide and installed all required dependencies.

Run LiteLLM as a Docker Container#

To connect LiteLLM with an Azure model, configure your litellm_config.yaml as follows:

model_list:
  - model_name: azure-gpt-4o-mini
    litellm_params:
      model: azure/gpt-4o-mini
      api_base: os.environ/AZURE_API_BASE
      api_key: os.environ/AZURE_API_KEY
      api_version: os.environ/AZURE_API_VERSION

Before starting the container, ensure you have correctly set the following environment variables: - AZURE_API_KEY - AZURE_API_BASE - AZURE_API_VERSION

Run the container using: 

docker run -v $(pwd)/litellm_config.yaml:/app/config.yaml  \
-e AZURE_API_KEY="your_api_key" -e AZURE_API_BASE="your_api_base_url" -e AZURE_API_VERSION="your_api_version"\
-p 4000:4000 ghcr.io/berriai/litellm:main-latest --config /app/config.yaml --detailed_debug

Once running, LiteLLM will be accessible at: http://0.0.0.0:4000

To confirm that config.yaml is correctly mounted, check the logs:

...
13:49:43 - LiteLLM Proxy:DEBUG: proxy_server.py:1507 - loaded config={
    "model_list": [
        {
            "model_name": "azure-gpt-4o-mini",
            "litellm_params": {
                "model": "azure/gpt-4o-mini",
                "api_base": "os.environ/AZURE_API_BASE",
                "api_key": "os.environ/AZURE_API_KEY",
                "api_version": "os.environ/AZURE_API_VERSION"
            }
        }
    ]
}
...

Initiate Chat#

To communicate with LiteLLM, configure the model in config_list and initiate a chat session.

from autogen import AssistantAgent, UserProxyAgent

config_list = [
    {
        "model": "azure-gpt-4o-mini",
        "base_url": "http://0.0.0.0:4000",
    }
]

user_proxy = UserProxyAgent(
    name="user_proxy",
    human_input_mode="NEVER",
)
assistant = AssistantAgent(
    name="assistant",
    llm_config={"config_list": config_list},
)


user_proxy.initiate_chat(
    recipient=assistant,
    message="Solve the following equation: 2x + 3 = 7",
    max_turns=3,
)