mirror of
https://github.com/microsoft/autogen.git
synced 2025-12-29 16:09:07 +00:00
af5dcc7fdf
- Updated HumanEval template to use AgentChat - Update templates to use config.yaml for model and other configuration - Read environment from ENV.yaml (ENV.json still supported but deprecated) - Temporarily removed WebArena and AssistantBench. Neither had viable Templates after `autogen_magentic_one` was removed. Templates need to be update to AgentChat (in a future PR, but this PR is getting big enough already)
31 lines
971 B
YAML
31 lines
971 B
YAML
# ENV.yaml
|
|
#
|
|
# This file specifies environment variables to be passed to the Docker task
|
|
# instances or virtual environments. These values are ephemeral, and are
|
|
# discarded when the task concludes. This is useful for passing API keys, etc.
|
|
# since they will not be saved in logs or to any task output.
|
|
#
|
|
# String values can reference environment variable on the host machine.
|
|
# For example:
|
|
#
|
|
# OPENAI_API_KEY: ${OPENAI_API_KEY}
|
|
#
|
|
# Will copy the host's OPENAI_API_KEY environment variable to the corresponding
|
|
# variable in the task environment.
|
|
#
|
|
# Complex values will be converte to JSON, and then passed as a string to the
|
|
# task environment. For example:
|
|
#
|
|
# MODEL_CONFIG:
|
|
# provider: autogen_ext.models.openai.OpenAIChatCompletionClient
|
|
# config:
|
|
# model: gpt-4o
|
|
#
|
|
# Will be converted to:
|
|
#
|
|
# MODEL_CONFIG: >-
|
|
# {"provider": "autogen_ext.models.openai.OpenAIChatCompletionClient", "config": {"model": "gpt-4o"}}
|
|
#
|
|
|
|
OPENAI_API_KEY: ${OPENAI_API_KEY}
|