Start with Azure OpenAI#

CAUTION Tested with Chat Completion endpoint only. Pending testing with v1/ end points.

If you have Ollama running, create a file enkaidu.yaml and copy in the following configuration, then run enkaidu from the commandline in the same folder as the config file.

session:
  model: gpt4o
auto_load:
  toolsets:
    - DateAndTime
llms:
  azure:
    provider: azure_openai
    env:
      AZURE_OPENAI_ENDPOINT: $AZURE_OPENAI_ENDPOINT
    models:
      - name: gpt4o
        model: ${AZURE_OPENAI_MODEL:-gpt-4o}

Environment variables#

To use Azure Open AI for your models, you will need to set the following environment variables before running Enkaidu.

Env. variable Description
AZURE_OPENAI_API_VER For example, 2024-08-01-preview. Use the one suitable for your model.
AZURE_OPENAI_MODEL Defaults to gpt-4o if not specified.
AZURE_OPENAI_ENDPOINT For example, https://X.openai.azure.com for your deployment X. Just the bare endpoint please!
AZURE_OPENAI_API_KEY The API key for your deployment