mirror of
https://github.com/microsoft/autogen.git
synced 2026-02-12 06:14:57 -05:00
f7357499be
* Added initial code for TeamOne utils. * Fixed hatch errors. * Updated examples. * Fixed more hatch errors. * Improve readme --------- Co-authored-by: gagb <gagb@users.noreply.github.com>
39 lines
1.0 KiB
Markdown
39 lines
1.0 KiB
Markdown
# 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:
|
|
|
|
```json
|
|
{
|
|
"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:
|
|
|
|
```json
|
|
{
|
|
"api_key": "REPLACE_WITH_YOUR_API",
|
|
"model": "gpt-4o-2024-05-13"
|
|
}
|
|
```
|