Skip to content

Latest commit

 

History

History
38 lines (29 loc) · 1.82 KB

File metadata and controls

38 lines (29 loc) · 1.82 KB

OpenAIChatCompletionsRequest

Properties

Name Type Description Notes
messages List[PromptMessage] A list of messages to be sent to the model
tools List[OpenAITool] [optional]
stream bool [optional]
stream_options OpenAIStreamOptions [optional]
max_tokens int The maximum number of tokens to generate [optional] [default to 512]
model str The name of the model used for generating the completion
temperature float The temperature of the generated text [optional] [default to 0.7]
top_p float The top-p value for nucleus sampling [optional] [default to 0.9]
stop Stop1 [optional]
response_format OpenAIResponseFormat [optional]

Example

from cms_client.models.open_ai_chat_completions_request import OpenAIChatCompletionsRequest

# TODO update the JSON string below
json = "{}"
# create an instance of OpenAIChatCompletionsRequest from a JSON string
open_ai_chat_completions_request_instance = OpenAIChatCompletionsRequest.from_json(json)
# print the JSON string representation of the object
print(OpenAIChatCompletionsRequest.to_json())

# convert the object into a dict
open_ai_chat_completions_request_dict = open_ai_chat_completions_request_instance.to_dict()
# create an instance of OpenAIChatCompletionsRequest from a dict
open_ai_chat_completions_request_from_dict = OpenAIChatCompletionsRequest.from_dict(open_ai_chat_completions_request_dict)

[Back to Model list] [Back to API list] [Back to README]