mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
Litellm dev 01 06 2025 p1 (#7594)
* fix(custom_logger.py): expose new 'async_get_chat_completion_prompt' event hook * fix(custom_logger.py): langfuse_prompt_management.py remove 'headers' from custom logger 'async_get_chat_completion_prompt' and 'get_chat_completion_prompt' event hooks * feat(router.py): expose new function for prompt management based routing * feat(router.py): partial working router prompt factory logic allows load balanced model to be used for model name w/ langfuse prompt management call * feat(router.py): fix prompt management with load balanced model group * feat(langfuse_prompt_management.py): support reading in openai params from langfuse enables user to define optional params on langfuse vs. client code * test(test_Router.py): add unit test for router based langfuse prompt management * fix: fix linting errors
This commit is contained in:
parent
7133cf5b74
commit
fef7839e8a
9 changed files with 214 additions and 90 deletions
|
@ -2700,3 +2700,40 @@ def test_router_completion_with_model_id():
|
|||
) as mock_pre_call_checks:
|
||||
router.completion(model="123", messages=[{"role": "user", "content": "hi"}])
|
||||
mock_pre_call_checks.assert_not_called()
|
||||
|
||||
|
||||
def test_router_prompt_management_factory():
|
||||
router = Router(
|
||||
model_list=[
|
||||
{
|
||||
"model_name": "gpt-3.5-turbo",
|
||||
"litellm_params": {"model": "gpt-3.5-turbo"},
|
||||
},
|
||||
{
|
||||
"model_name": "chatbot_actions",
|
||||
"litellm_params": {
|
||||
"model": "langfuse/openai-gpt-3.5-turbo",
|
||||
"tpm": 1000000,
|
||||
"prompt_id": "jokes",
|
||||
},
|
||||
},
|
||||
{
|
||||
"model_name": "openai-gpt-3.5-turbo",
|
||||
"litellm_params": {
|
||||
"model": "openai/gpt-3.5-turbo",
|
||||
"api_key": os.getenv("OPENAI_API_KEY"),
|
||||
},
|
||||
},
|
||||
]
|
||||
)
|
||||
|
||||
assert router._is_prompt_management_model("chatbot_actions") is True
|
||||
assert router._is_prompt_management_model("openai-gpt-3.5-turbo") is False
|
||||
|
||||
response = router._prompt_management_factory(
|
||||
model="chatbot_actions",
|
||||
messages=[{"role": "user", "content": "Hello world!"}],
|
||||
kwargs={},
|
||||
)
|
||||
|
||||
print(response)
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue