kaiyuan/chatgpt-on-wechat
1
0
Fork 0
mirror of https://github.com/zhayujie/chatgpt-on-wechat.git synced 2026-07-20 21:57:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

formatting: run precommit on all files

Browse Source
This commit is contained in:
lanvent
2023-04-22 12:01:29 +08:00
parent eaf4e9174f
commit 618c94edb8
40 changed files with 229 additions and 647 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
bot/chatgpt/chat_gpt_bot.py
View File

@@ -30,23 +30,15 @@ class ChatGPTBot(Bot, OpenAIImage):
if conf().get("rate_limit_chatgpt"):
self.tb4chatgpt = TokenBucket(conf().get("rate_limit_chatgpt", 20))
self.sessions = SessionManager(
ChatGPTSession, model=conf().get("model") or "gpt-3.5-turbo"
)
self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "gpt-3.5-turbo")
self.args = {
"model": conf().get("model") or "gpt-3.5-turbo", # 对话模型的名称
"temperature": conf().get("temperature", 0.9), # 值在[0,1]之间，越大表示回复越具有不确定性
# "max_tokens":4096, # 回复最大的字符数
"top_p": 1,
"frequency_penalty": conf().get(
"frequency_penalty", 0.0
), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"presence_penalty": conf().get(
"presence_penalty", 0.0
), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"request_timeout": conf().get(
"request_timeout", None
), # 请求超时时间，openai接口默认设置为600，对于难问题一般需要较长时间
"frequency_penalty": conf().get("frequency_penalty", 0.0), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"presence_penalty": conf().get("presence_penalty", 0.0), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"request_timeout": conf().get("request_timeout", None), # 请求超时时间，openai接口默认设置为600，对于难问题一般需要较长时间
"timeout": conf().get("request_timeout", None), # 重试超时时间，在这个时间内，将会自动重试
}
@@ -87,15 +79,10 @@ class ChatGPTBot(Bot, OpenAIImage):
reply_content["completion_tokens"],
)
)
if (
reply_content["completion_tokens"] == 0
and len(reply_content["content"]) > 0
):
if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
reply = Reply(ReplyType.ERROR, reply_content["content"])
elif reply_content["completion_tokens"] > 0:
self.sessions.session_reply(
reply_content["content"], session_id, reply_content["total_tokens"]
)
self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
reply = Reply(ReplyType.TEXT, reply_content["content"])
else:
reply = Reply(ReplyType.ERROR, reply_content["content"])
@@ -126,9 +113,7 @@ class ChatGPTBot(Bot, OpenAIImage):
if conf().get("rate_limit_chatgpt") and not self.tb4chatgpt.get_token():
raise openai.error.RateLimitError("RateLimitError: rate limit exceeded")
# if api_key == None, the default openai.api_key will be used
response = openai.ChatCompletion.create(
api_key=api_key, messages=session.messages, **self.args
)
response = openai.ChatCompletion.create(api_key=api_key, messages=session.messages, **self.args)
# logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
return {
"total_tokens": response["usage"]["total_tokens"],

22
bot/chatgpt/chat_gpt_session.py
View File

@@ -25,9 +25,7 @@ class ChatGPTSession(Session):
precise = False
if cur_tokens is None:
raise e
logger.debug(
"Exception when counting tokens precisely for query: {}".format(e)
)
logger.debug("Exception when counting tokens precisely for query: {}".format(e))
while cur_tokens > max_tokens:
if len(self.messages) > 2:
self.messages.pop(1)
@@ -39,16 +37,10 @@ class ChatGPTSession(Session):
cur_tokens = cur_tokens - max_tokens
break
elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
logger.warn(
"user message exceed max_tokens. total_tokens={}".format(cur_tokens)
)
logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
break
else:
logger.debug(
"max_tokens={}, total_tokens={}, len(messages)={}".format(
max_tokens, cur_tokens, len(self.messages)
)
)
logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens, len(self.messages)))
break
if precise:
cur_tokens = self.calc_tokens()
@@ -75,17 +67,13 @@ def num_tokens_from_messages(messages, model):
elif model == "gpt-4":
return num_tokens_from_messages(messages, model="gpt-4-0314")
elif model == "gpt-3.5-turbo-0301":
tokens_per_message = (
4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
)
tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
tokens_per_name = -1 # if there's a name, the role is omitted
elif model == "gpt-4-0314":
tokens_per_message = 3
tokens_per_name = 1
else:
logger.warn(
f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo-0301."
)
logger.warn(f"num_tokens_from_messages() is not implemented for model {model}. Returning num tokens assuming gpt-3.5-turbo-0301.")
return num_tokens_from_messages(messages, model="gpt-3.5-turbo-0301")
num_tokens = 0
for message in messages: