Update OpenAI api - add costs

This commit is contained in:
Martin Kask 2023-11-07 12:55:27 +02:00
parent 331c21e395
commit 0b4c9dde7b
3 changed files with 13 additions and 8 deletions

View File

@ -63,24 +63,27 @@ class OpenAIModel(ModelBackend):
"gpt-4": 8192,
"gpt-4-0613": 8192,
"gpt-4-32k": 32768,
"gpt-4-1106-preview": 128000,
"gpt-4-1106-preview": 4096,
}
num_max_token = num_max_token_map[self.model_type.value]
num_max_completion_tokens = num_max_token - num_prompt_tokens
self.model_config_dict['max_tokens'] = num_max_completion_tokens
response = openai.ChatCompletion.create(*args, **kwargs,
print("using model: {}".format(self.model_type.value))
response = openai.chat.completions.create(*args, **kwargs,
model=self.model_type.value,
**self.model_config_dict)
cost = prompt_cost(
self.model_type.value,
num_prompt_tokens=response["usage"]["prompt_tokens"],
num_completion_tokens=response["usage"]["completion_tokens"]
num_prompt_tokens=response.usage.prompt_tokens,
num_completion_tokens=response.usage.completion_tokens
)
log_and_print_online(
"**[OpenAI_Usage_Info Receive]**\nprompt_tokens: {}\ncompletion_tokens: {}\ntotal_tokens: {}\ncost: ${:.6f}\n".format(
response["usage"]["prompt_tokens"], response["usage"]["completion_tokens"],
response["usage"]["total_tokens"], cost))
response.usage.prompt_tokens, response.usage.completion_tokens,
response.usage.total_tokens, cost
)
)
if not isinstance(response, Dict):
raise RuntimeError("Unexpected return from OpenAI API")
return response

View File

@ -12,6 +12,7 @@ def prompt_cost(model_type: str, num_prompt_tokens: float, num_completion_tokens
"gpt-4": 0.03,
"gpt-4-0613": 0.03,
"gpt-4-32k": 0.06,
"gpt-4-1106-preview": 0.01,
}
output_cost_map = {
@ -22,6 +23,7 @@ def prompt_cost(model_type: str, num_prompt_tokens: float, num_completion_tokens
"gpt-4": 0.06,
"gpt-4-0613": 0.06,
"gpt-4-32k": 0.12,
"gpt-4-1106-preview": 0.03,
}
if model_type not in input_cost_map or model_type not in output_cost_map:

View File

@ -3,7 +3,7 @@ Flask==2.3.2
Flask-SocketIO==5.3.4
importlib-metadata==6.8.0
numpy==1.24.3
openai==0.27.8
openai==1.1.1
regex==2023.6.3
requests==2.31.0
tenacity==8.2.2