introduce project self-translation
This commit is contained in:
40
predict.py
40
predict.py
@@ -25,7 +25,7 @@ def get_full_error(chunk, stream_response):
|
||||
break
|
||||
return chunk
|
||||
|
||||
def predict_no_ui(inputs, top_p, temperature, history=[]):
|
||||
def predict_no_ui(inputs, top_p, temperature, history=[], sys_prompt=""):
|
||||
"""
|
||||
发送至chatGPT,等待回复,一次性完成,不显示中间过程。
|
||||
predict函数的简化版。
|
||||
@@ -36,7 +36,7 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
|
||||
history 是之前的对话列表
|
||||
(注意无论是inputs还是history,内容太长了都会触发token数量溢出的错误,然后raise ConnectionAbortedError)
|
||||
"""
|
||||
headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt="", stream=False)
|
||||
headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt=sys_prompt, stream=False)
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
@@ -47,8 +47,8 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if MAX_RETRY!=0: print(f'请求超时,正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时,正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
try:
|
||||
result = json.loads(response.text)["choices"][0]["message"]["content"]
|
||||
@@ -58,6 +58,40 @@ def predict_no_ui(inputs, top_p, temperature, history=[]):
|
||||
raise ConnectionAbortedError("Json解析不合常规,可能是文本过长" + response.text)
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, top_p, temperature, history=[], sys_prompt=""):
|
||||
"""
|
||||
发送至chatGPT,等待回复,一次性完成,不显示中间过程。但内部用stream的方法避免有人中途掐网线。
|
||||
"""
|
||||
headers, payload = generate_payload(inputs, top_p, temperature, history, system_prompt=sys_prompt, stream=True)
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=False
|
||||
response = requests.post(API_URL, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
retry += 1
|
||||
traceback.print_exc()
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
if MAX_RETRY!=0: print(f'请求超时,正在重试 ({retry}/{MAX_RETRY}) ……')
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
result = ''
|
||||
while True:
|
||||
try: chunk = next(stream_response).decode()
|
||||
except StopIteration: break
|
||||
if len(chunk)==0: continue
|
||||
if not chunk.startswith('data:'):
|
||||
raise ConnectionAbortedError("OpenAI返回了错误:" + chunk)
|
||||
delta = json.loads(chunk.lstrip('data:'))['choices'][0]["delta"]
|
||||
if len(delta) == 0: break
|
||||
if "role" in delta: continue
|
||||
if "content" in delta: result += delta["content"]; print(delta["content"], end='')
|
||||
else: raise RuntimeError("意外Json结构:"+delta)
|
||||
return result
|
||||
|
||||
|
||||
def predict(inputs, top_p, temperature, chatbot=[], history=[], system_prompt='',
|
||||
stream = True, additional_fn=None):
|
||||
"""
|
||||
|
||||
Reference in New Issue
Block a user