mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
5202456b4c
* update api * update generation_kwargs impl * update api * refactor --------- Co-authored-by: Leymore <zfz-960727@163.com>
142 lines
4.5 KiB
Python
142 lines
4.5 KiB
Python
import time
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
from typing import Dict, List, Optional, Union
|
|
|
|
import requests
|
|
|
|
from opencompass.utils.prompt import PromptList
|
|
|
|
from .base_api import BaseAPIModel
|
|
|
|
PromptType = Union[PromptList, str]
|
|
|
|
|
|
class SenseTime(BaseAPIModel):
|
|
"""Model wrapper around SenseTime.
|
|
|
|
Args:
|
|
path (str): The name of SenseTime model.
|
|
e.g. `nova-ptc-xl-v1`
|
|
key (str): Authorization key.
|
|
query_per_second (int): The maximum queries allowed per second
|
|
between two consecutive calls of the API. Defaults to 1.
|
|
max_seq_len (int): Unused here.
|
|
meta_template (Dict, optional): The model's meta prompt
|
|
template if needed, in case the requirement of injecting or
|
|
wrapping of any meta instructions.
|
|
retry (int): Number of retires if the API call fails. Defaults to 2.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
path: str,
|
|
key: str,
|
|
url: str,
|
|
query_per_second: int = 2,
|
|
max_seq_len: int = 2048,
|
|
meta_template: Optional[Dict] = None,
|
|
retry: int = 2,
|
|
):
|
|
super().__init__(path=path,
|
|
max_seq_len=max_seq_len,
|
|
query_per_second=query_per_second,
|
|
meta_template=meta_template,
|
|
retry=retry)
|
|
self.headers = {
|
|
'Content-Type': 'application/json',
|
|
'Authorization': f'Bearer {key}'
|
|
}
|
|
self.url = url
|
|
self.model = path
|
|
|
|
def generate(
|
|
self,
|
|
inputs: List[str or PromptList],
|
|
max_out_len: int = 512,
|
|
) -> List[str]:
|
|
"""Generate results given a list of inputs.
|
|
|
|
Args:
|
|
inputs (List[str or PromptList]): A list of strings or PromptDicts.
|
|
The PromptDict should be organized in OpenCompass'
|
|
API format.
|
|
max_out_len (int): The maximum length of the output.
|
|
|
|
Returns:
|
|
List[str]: A list of generated strings.
|
|
"""
|
|
with ThreadPoolExecutor() as executor:
|
|
results = list(
|
|
executor.map(self._generate, inputs,
|
|
[max_out_len] * len(inputs)))
|
|
self.flush()
|
|
return results
|
|
|
|
def _generate(
|
|
self,
|
|
input: str or PromptList,
|
|
max_out_len: int = 512,
|
|
) -> str:
|
|
"""Generate results given an input.
|
|
|
|
Args:
|
|
inputs (str or PromptList): A string or PromptDict.
|
|
The PromptDict should be organized in OpenCompass'
|
|
API format.
|
|
max_out_len (int): The maximum length of the output.
|
|
|
|
Returns:
|
|
str: The generated string.
|
|
"""
|
|
assert isinstance(input, (str, PromptList))
|
|
|
|
if isinstance(input, str):
|
|
messages = [{'role': 'user', 'content': input}]
|
|
else:
|
|
messages = []
|
|
for item in input:
|
|
msg = {'content': item['prompt']}
|
|
if item['role'] == 'HUMAN':
|
|
msg['role'] = 'user'
|
|
elif item['role'] == 'BOT':
|
|
msg['role'] = 'assistant'
|
|
|
|
messages.append(msg)
|
|
|
|
data = {'messages': messages, 'model': self.model}
|
|
|
|
max_num_retries = 0
|
|
while max_num_retries < self.retry:
|
|
self.acquire()
|
|
raw_response = requests.request('POST',
|
|
url=self.url,
|
|
headers=self.headers,
|
|
json=data)
|
|
response = raw_response.json()
|
|
self.release()
|
|
|
|
if response is None:
|
|
print('Connection error, reconnect.')
|
|
# if connect error, frequent requests will casuse
|
|
# continuous unstable network, therefore wait here
|
|
# to slow down the request
|
|
self.wait()
|
|
continue
|
|
if raw_response.status_code == 200:
|
|
msg = response['data']['choices'][0]['message']
|
|
return msg
|
|
|
|
if (raw_response.status_code != 200):
|
|
if response['error']['code'] == 18:
|
|
# security issue
|
|
return 'error:unsafe'
|
|
else:
|
|
print(raw_response.text)
|
|
time.sleep(1)
|
|
continue
|
|
|
|
print(response)
|
|
max_num_retries += 1
|
|
|
|
raise RuntimeError(raw_response.text)
|