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

(fix) completion: max_retries using OpenAI client

Browse source
This commit is contained in:
ishaan-jaff 2023-11-20 16:53:18 -08:00
parent 2bd934e56c
commit 11ec2710c6
4 changed files with 19 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

9
litellm/main.py
View file

@ -331,8 +331,8 @@ def completion(
eos_token = kwargs.get("eos_token", None)
acompletion = kwargs.get("acompletion", False)
######## end of unpacking kwargs ###########
openai_params = ["functions", "function_call", "temperature", "temperature", "top_p", "n", "stream", "stop", "max_tokens", "presence_penalty", "frequency_penalty", "logit_bias", "user", "request_timeout", "api_base", "api_version", "api_key", "deployment_id", "organization", "base_url", "default_headers", "timeout", "response_format", "seed", "tools", "tool_choice"]
litellm_params = ["metadata", "acompletion", "caching", "return_async", "mock_response", "api_key", "api_version", "api_base", "force_timeout", "logger_fn", "verbose", "custom_llm_provider", "litellm_logging_obj", "litellm_call_id", "use_client", "id", "fallbacks", "azure", "headers", "model_list", "num_retries", "context_window_fallback_dict", "roles", "final_prompt_value", "bos_token", "eos_token", "request_timeout", "complete_response", "self", "max_retries"]
openai_params = ["functions", "function_call", "temperature", "temperature", "top_p", "n", "stream", "stop", "max_tokens", "presence_penalty", "frequency_penalty", "logit_bias", "user", "request_timeout", "api_base", "api_version", "api_key", "deployment_id", "organization", "base_url", "default_headers", "timeout", "response_format", "seed", "tools", "tool_choice", "max_retries"]
litellm_params = ["metadata", "acompletion", "caching", "return_async", "mock_response", "api_key", "api_version", "api_base", "force_timeout", "logger_fn", "verbose", "custom_llm_provider", "litellm_logging_obj", "litellm_call_id", "use_client", "id", "fallbacks", "azure", "headers", "model_list", "num_retries", "context_window_fallback_dict", "roles", "final_prompt_value", "bos_token", "eos_token", "request_timeout", "complete_response", "self"]
default_params = openai_params + litellm_params
non_default_params = {k: v for k,v in kwargs.items() if k not in default_params} # model-specific params - pass them straight to the model/provider
@ -342,9 +342,9 @@ def completion(
timeout = 600 # set timeout for 10 minutes by default
timeout = float(timeout)
try:
if base_url:
if base_url is not None:
api_base = base_url
if max_retries:
if max_retries is not None: # openai allows openai.OpenAI(max_retries=3)
num_retries = max_retries
logging = litellm_logging_obj
fallbacks = (
@ -410,6 +410,7 @@ def completion(
seed=seed,
tools=tools,
tool_choice=tool_choice,
max_retries=max_retries,
**non_default_params
)