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

o1 - add image param handling (#7312)

Browse source 
* fix(openai.py): fix returning o1 non-streaming requests

fixes issue where fake stream always true for o1

* build(model_prices_and_context_window.json): add 'supports_vision' for o1 models

* fix: add internal server error exception mapping

* fix(base_llm_unit_tests.py): drop temperature from test

* test: mark prompt caching as a flaky test
This commit is contained in:
Krish Dholakia 2024-12-19 11:22:25 -08:00 • committed by GitHub
parent a101c1fff4
commit 62b00cf28d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 68 additions and 79 deletions
Download patch file Download diff file Expand all files Collapse all files

15
litellm/llms/openai/openai.py
View file

@ -453,18 +453,18 @@ class OpenAIChatCompletion(BaseLLM):
super().completion()
try:
fake_stream: bool = False
if custom_llm_provider is not None and model is not None:
provider_config = ProviderConfigManager.get_provider_chat_config(
model=model, provider=LlmProviders(custom_llm_provider)
)
fake_stream = provider_config.should_fake_stream(
model=model, custom_llm_provider=custom_llm_provider
)
inference_params = optional_params.copy()
stream_options: Optional[dict] = inference_params.pop(
"stream_options", None
)
stream: Optional[bool] = inference_params.pop("stream", False)
if custom_llm_provider is not None and model is not None:
provider_config = ProviderConfigManager.get_provider_chat_config(
model=model, provider=LlmProviders(custom_llm_provider)
)
fake_stream = provider_config.should_fake_stream(
model=model, custom_llm_provider=custom_llm_provider, stream=stream
)
if headers:
inference_params["extra_headers"] = headers
if model is None or messages is None:
@ -502,7 +502,6 @@ class OpenAIChatCompletion(BaseLLM):
litellm_params=litellm_params,
headers=headers or {},
)
try:
max_retries = data.pop("max_retries", 2)
if acompletion is True: