Files
autogen/python/teams/team-one
afourney 04d9709aec Agnext websurfer (#205)
* Initial work on multimodal websurfer

* A little more progress.

* Getting function calling to work.

* Some basic progress with navigation.

* Added ability to print multimodal messages to console.

* Fixed hatch error

* Nicely print multimodal messages to console.

* Got OCR working.

* Fixed the click action.

* Solved some hatch errors.

* Fixed some formatting errors.

* Fixed more type errors.

* Yet more fixes to types.

* Fixed many type errors.

* Fixed all type errors. Some needed to be ignored. See todos.

* Fixed all? hatch errors?

* Fixed multiline aria-names in prompts.
2024-07-11 10:52:29 -07:00
..
2024-07-11 10:52:29 -07:00
2024-07-11 10:52:29 -07:00
2024-06-24 10:36:10 -04:00
2024-07-11 10:52:29 -07:00
2024-07-09 17:46:55 +00:00

Environment Configuration for Chat Completion Client

This guide outlines how to configure your environment to use the create_completion_client_from_env function, which reads environment variables to return an appropriate ChatCompletionClient.

Azure with Active Directory

To configure for Azure with Active Directory, set the following environment variables:

  • CHAT_COMPLETION_PROVIDER='azure'
  • CHAT_COMPLETION_KWARGS_JSON with the following JSON structure:
{
  "api_version": "2024-02-15-preview",
  "azure_endpoint": "REPLACE_WITH_YOUR_ENDPOINT",
  "model_capabilities": {
    "function_calling": true,
    "json_output": true,
    "vision": true
  },
  "azure_ad_token_provider": "DEFAULT",
  "model": "gpt-4o-2024-05-13"
}

With OpenAI

To configure for OpenAI, set the following environment variables:

  • CHAT_COMPLETION_PROVIDER='openai'
  • CHAT_COMPLETION_KWARGS_JSON with the following JSON structure:
{
  "api_key": "REPLACE_WITH_YOUR_API",
  "model": "gpt-4o-2024-05-13"
}