afourney e5ebdb66bf Remove GPT-4 as the default model. (#1072) ...

* Remove GPT-4 as the default model.

* Updated test_compressible_agent to work around a bug that would otherwise default to gpt-4. Revist after #1073 is addressed.

* Worked around another bug in test_compressible_agent. It seems the config_list was always empty!

* Reverted changes to compressible agent.

* Noted that GPT-4 is the preferred model in the OAI_CONFIG_LIST_sample and README.

* Fixed failing tests after #1110

* Update OAI_CONFIG_LIST_sample

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

---------

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

2024-01-05 14:27:48 +00:00

..

agentchat

Remove GPT-4 as the default model. (#1072)

2024-01-05 14:27:48 +00:00

oai

Let run tests directly via python test_xyz.py, fix for conftest import via sys.path.append (#1144)

2024-01-05 14:24:49 +00:00

test_files

Adding first version of AgentEval -- a framework for assessing task utility for LLM-powered applications (#681)

2023-11-21 04:07:33 +00:00

conftest.py

Skip tests that depend on OpenAI via --skip-openai (#1097)

2023-12-31 19:37:21 +00:00

test_code.py

Message "content" now supports both str and List in Agents (#713)

2023-12-03 01:40:50 +00:00

test_function_utils.py

Add decorator for function calling (#1018)

2023-12-25 16:07:20 +00:00

test_notebook.py

Skip tests that depend on OpenAI via --skip-openai (#1097)

2023-12-31 19:37:21 +00:00

test_pydantic.py

Add decorator for function calling (#1018)

2023-12-25 16:07:20 +00:00

test_retrieve_utils.py

Skip tests that depend on OpenAI via --skip-openai (#1097)

2023-12-31 19:37:21 +00:00

test_token_count.py

Fix/typo (#1034)

2023-12-22 16:00:46 +00:00

twoagent.py

make retry_time configurable, add doc (#53)

2023-09-30 16:21:07 +00:00