phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 10:44:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(test_parallel_request_limiter.py): use mock responses for streaming

Browse source
This commit is contained in:
Krrish Dholakia 2024-02-08 21:45:24 -08:00
parent 1ef7ad3416
commit b9393fb769
5 changed files with 35 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/utils.py
View file

@ -1576,7 +1576,7 @@ class Logging:
# only add to cache once we have a complete streaming response
litellm.cache.add_cache(result, **kwargs)
if isinstance(callback, CustomLogger): # custom logger class
print_verbose(f"Async success callbacks: CustomLogger")
print_verbose(f"Async success callbacks: {callback}")
if self.stream:
if "complete_streaming_response" in self.model_call_details:
await callback.async_log_success_event(
@ -8819,6 +8819,14 @@ def mock_completion_streaming_obj(model_response, mock_response, model):
yield model_response
async def async_mock_completion_streaming_obj(model_response, mock_response, model):
for i in range(0, len(mock_response), 3):
completion_obj = Delta(role="assistant", content=mock_response)
model_response.choices[0].delta = completion_obj
model_response.choices[0].finish_reason = "stop"
yield model_response
########## Reading Config File ############################
def read_config_args(config_path) -> dict:
try: