phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(fix) litellm.acompletion with type hints

Browse source
This commit is contained in:
ishaan-jaff 2024-01-11 10:47:12 +05:30
parent 2433d6c613
commit cf86af46a8
2 changed files with 40 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

11
litellm/main.py
View file

@ -230,17 +230,19 @@ async def acompletion(
"api_version": api_version,
"api_key": api_key,
"model_list": model_list,
"acompletion": True # assuming this is a required parameter
"acompletion": True, # assuming this is a required parameter
}
try:
# Use a partial function to pass your keyword arguments
func = partial(completion, *args, **kwargs)
func = partial(completion, **completion_kwargs)
# Add the context to the function
ctx = contextvars.copy_context()
func_with_context = partial(ctx.run, func)
_, custom_llm_provider, _, _ = get_llm_provider(model=model, api_base=completion_kwargs.get("base_url", None))
_, custom_llm_provider, _, _ = get_llm_provider(
model=model, api_base=completion_kwargs.get("base_url", None)
)
if (
custom_llm_provider == "openai"
@ -284,7 +286,7 @@ async def acompletion(
model=model,
custom_llm_provider=custom_llm_provider,
original_exception=e,
completion_kwargs=args,
completion_kwargs=completion_kwargs,
)
@ -3260,7 +3262,6 @@ def stream_chunk_builder(chunks: list, messages: Optional[list] = None):
if isinstance(
chunks[0]["choices"][0], litellm.utils.TextChoices
): # route to the text completion logic
return stream_chunk_builder_text_completion(chunks=chunks, messages=messages)
role = chunks[0]["choices"][0]["delta"]["role"]
finish_reason = chunks[-1]["choices"][0]["finish_reason"]

18
litellm/tests/test_async_fn.py
View file

@ -15,22 +15,6 @@ from litellm import completion, acompletion, acreate
litellm.num_retries = 3
def test_sync_response():
litellm.set_verbose = False
user_message = "Hello, how are you?"
messages = [{"content": user_message, "role": "user"}]
try:
response = completion(model="gpt-3.5-turbo", messages=messages, timeout=5)
print(f"response: {response}")
except litellm.Timeout as e:
pass
except Exception as e:
pytest.fail(f"An exception occurred: {e}")
# test_sync_response()
def test_sync_response_anyscale():
litellm.set_verbose = False
user_message = "Hello, how are you?"
@ -197,6 +181,7 @@ def test_get_cloudflare_response_streaming():
asyncio.run(test_async_call())
@pytest.mark.asyncio
async def test_hf_completion_tgi():
# litellm.set_verbose=True
@ -212,6 +197,7 @@ async def test_hf_completion_tgi():
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_get_cloudflare_response_streaming()