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

Merge pull request #3537 from BerriAI/litellm_support_stream_options_param

Browse source 
[Feat] support `stream_options` param for OpenAI
This commit is contained in:
Ishaan Jaff 2024-05-09 08:34:08 -07:00 • committed by GitHub
commit 0b1885ca99
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 101 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

8
litellm/main.py
View file

@ -187,6 +187,7 @@ async def acompletion(
top_p: Optional[float] = None,
n: Optional[int] = None,
stream: Optional[bool] = None,
stream_options: Optional[dict] = None,
stop=None,
max_tokens: Optional[int] = None,
presence_penalty: Optional[float] = None,
@ -206,6 +207,7 @@ async def acompletion(
api_version: Optional[str] = None,
api_key: Optional[str] = None,
model_list: Optional[list] = None, # pass in a list of api_base,keys, etc.
extra_headers: Optional[dict] = None,
# Optional liteLLM function params
**kwargs,
):
@ -223,6 +225,7 @@ async def acompletion(
top_p (float, optional): The top-p parameter for nucleus sampling (default is 1.0).
n (int, optional): The number of completions to generate (default is 1).
stream (bool, optional): If True, return a streaming response (default is False).
stream_options (dict, optional): A dictionary containing options for the streaming response. Only use this if stream is True.
stop(string/list, optional): - Up to 4 sequences where the LLM API will stop generating further tokens.
max_tokens (integer, optional): The maximum number of tokens in the generated completion (default is infinity).
presence_penalty (float, optional): It is used to penalize new tokens based on their existence in the text so far.
@ -260,6 +263,7 @@ async def acompletion(
"top_p": top_p,
"n": n,
"stream": stream,
"stream_options": stream_options,
"stop": stop,
"max_tokens": max_tokens,
"presence_penalty": presence_penalty,
@ -457,6 +461,7 @@ def completion(
top_p: Optional[float] = None,
n: Optional[int] = None,
stream: Optional[bool] = None,
stream_options: Optional[dict] = None,
stop=None,
max_tokens: Optional[int] = None,
presence_penalty: Optional[float] = None,
@ -496,6 +501,7 @@ def completion(
top_p (float, optional): The top-p parameter for nucleus sampling (default is 1.0).
n (int, optional): The number of completions to generate (default is 1).
stream (bool, optional): If True, return a streaming response (default is False).
stream_options (dict, optional): A dictionary containing options for the streaming response. Only set this when you set stream: true.
stop(string/list, optional): - Up to 4 sequences where the LLM API will stop generating further tokens.
max_tokens (integer, optional): The maximum number of tokens in the generated completion (default is infinity).
presence_penalty (float, optional): It is used to penalize new tokens based on their existence in the text so far.
@ -573,6 +579,7 @@ def completion(
"top_p",
"n",
"stream",
"stream_options",
"stop",
"max_tokens",
"presence_penalty",
@ -785,6 +792,7 @@ def completion(
top_p=top_p,
n=n,
stream=stream,
stream_options=stream_options,
stop=stop,
max_tokens=max_tokens,
presence_penalty=presence_penalty,