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 code

Browse Source
This commit is contained in:
lanvent
2023-04-17 01:00:08 +08:00
parent 3b8972ce1f
commit 8f72e8c3e6
92 changed files with 1850 additions and 1188 deletions
Download Patch File Download Diff File Expand all files Collapse all files

120
bot/chatgpt/chat_gpt_bot.py
View File

@@ -1,42 +1,53 @@
# encoding:utf-8
import time
import openai
import openai.error
from bot.bot import Bot
from bot.chatgpt.chat_gpt_session import ChatGPTSession
from bot.openai.open_ai_image import OpenAIImage
from bot.session_manager import SessionManager
from bridge.context import ContextType
from bridge.reply import Reply, ReplyType
from config import conf, load_config
from common.log import logger
from common.token_bucket import TokenBucket
import openai
import openai.error
import time
from config import conf, load_config
# OpenAI对话模型API (可用)
class ChatGPTBot(Bot,OpenAIImage):
class ChatGPTBot(Bot, OpenAIImage):
def __init__(self):
super().__init__()
# set the default api_key
openai.api_key = conf().get('open_ai_api_key')
if conf().get('open_ai_api_base'):
openai.api_base = conf().get('open_ai_api_base')
proxy = conf().get('proxy')
openai.api_key = conf().get("open_ai_api_key")
if conf().get("open_ai_api_base"):
openai.api_base = conf().get("open_ai_api_base")
proxy = conf().get("proxy")
if proxy:
openai.proxy = proxy
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.args ={
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.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
"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
"timeout": conf().get('request_timeout', None), #重试超时时间，在这个时间内，将会自动重试
"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
"timeout": conf().get("request_timeout", None), # 重试超时时间，在这个时间内，将会自动重试
}
def reply(self, query, context=None):
@@ -44,39 +55,50 @@ class ChatGPTBot(Bot,OpenAIImage):
if context.type == ContextType.TEXT:
logger.info("[CHATGPT] query={}".format(query))
session_id = context['session_id']
session_id = context["session_id"]
reply = None
clear_memory_commands = conf().get('clear_memory_commands', ['#清除记忆'])
clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
if query in clear_memory_commands:
self.sessions.clear_session(session_id)
reply = Reply(ReplyType.INFO, '记忆已清除')
elif query == '#清除所有':
reply = Reply(ReplyType.INFO, "记忆已清除")
elif query == "#清除所有":
self.sessions.clear_all_session()
reply = Reply(ReplyType.INFO, '所有人记忆已清除')
elif query == '#更新配置':
reply = Reply(ReplyType.INFO, "所有人记忆已清除")
elif query == "#更新配置":
load_config()
reply = Reply(ReplyType.INFO, '配置已更新')
reply = Reply(ReplyType.INFO, "配置已更新")
if reply:
return reply
session = self.sessions.session_query(query, session_id)
logger.debug("[CHATGPT] session query={}".format(session.messages))
api_key = context.get('openai_api_key')
api_key = context.get("openai_api_key")
# if context.get('stream'):
# # reply in stream
# return self.reply_text_stream(query, new_query, session_id)
reply_content = self.reply_text(session, api_key)
logger.debug("[CHATGPT] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(session.messages, session_id, reply_content["content"], reply_content["completion_tokens"]))
if reply_content['completion_tokens'] == 0 and len(reply_content['content']) > 0:
reply = Reply(ReplyType.ERROR, reply_content['content'])
logger.debug(
"[CHATGPT] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
session.messages,
session_id,
reply_content["content"],
reply_content["completion_tokens"],
)
)
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'])
reply = Reply(ReplyType.ERROR, reply_content["content"])
logger.debug("[CHATGPT] reply {} used 0 tokens.".format(reply_content))
return reply
@@ -89,53 +111,55 @@ class ChatGPTBot(Bot,OpenAIImage):
reply = Reply(ReplyType.ERROR, retstring)
return reply
else:
reply = Reply(ReplyType.ERROR, 'Bot不支持处理{}类型的消息'.format(context.type))
reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
return reply
def reply_text(self, session:ChatGPTSession, api_key=None, retry_count=0) -> dict:
'''
def reply_text(self, session: ChatGPTSession, api_key=None, retry_count=0) -> dict:
"""
call openai's ChatCompletion to get the answer
:param session: a conversation session
:param session_id: session id
:param retry_count: retry count
:return: {}
'''
"""
try:
if conf().get('rate_limit_chatgpt') and not self.tb4chatgpt.get_token():
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
)
# logger.info("[ChatGPT] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
return {"total_tokens": response["usage"]["total_tokens"],
"completion_tokens": response["usage"]["completion_tokens"],
"content": response.choices[0]['message']['content']}
return {
"total_tokens": response["usage"]["total_tokens"],
"completion_tokens": response["usage"]["completion_tokens"],
"content": response.choices[0]["message"]["content"],
}
except Exception as e:
need_retry = retry_count < 2
result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
if isinstance(e, openai.error.RateLimitError):
logger.warn("[CHATGPT] RateLimitError: {}".format(e))
result['content'] = "提问太快啦，请休息一下再问我吧"
result["content"] = "提问太快啦，请休息一下再问我吧"
if need_retry:
time.sleep(5)
elif isinstance(e, openai.error.Timeout):
logger.warn("[CHATGPT] Timeout: {}".format(e))
result['content'] = "我没有收到你的消息"
result["content"] = "我没有收到你的消息"
if need_retry:
time.sleep(5)
elif isinstance(e, openai.error.APIConnectionError):
logger.warn("[CHATGPT] APIConnectionError: {}".format(e))
need_retry = False
result['content'] = "我连接不到你的网络"
result["content"] = "我连接不到你的网络"
else:
logger.warn("[CHATGPT] Exception: {}".format(e))
need_retry = False
self.sessions.clear_session(session.session_id)
if need_retry:
logger.warn("[CHATGPT] 第{}次重试".format(retry_count+1))
return self.reply_text(session, api_key, retry_count+1)
logger.warn("[CHATGPT] 第{}次重试".format(retry_count + 1))
return self.reply_text(session, api_key, retry_count + 1)
else:
return result
@@ -145,4 +169,4 @@ class AzureChatGPTBot(ChatGPTBot):
super().__init__()
openai.api_type = "azure"
openai.api_version = "2023-03-15-preview"
self.args["deployment_id"] = conf().get("azure_deployment_id")
self.args["deployment_id"] = conf().get("azure_deployment_id")

40
bot/chatgpt/chat_gpt_session.py
View File

@@ -1,20 +1,23 @@
from bot.session_manager import Session
from common.log import logger
'''
"""
e.g. [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Who won the world series in 2020?"},
{"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
{"role": "user", "content": "Where was it played?"}
]
'''
"""
class ChatGPTSession(Session):
def __init__(self, session_id, system_prompt=None, model= "gpt-3.5-turbo"):
def __init__(self, session_id, system_prompt=None, model="gpt-3.5-turbo"):
super().__init__(session_id, system_prompt)
self.model = model
self.reset()
def discard_exceeding(self, max_tokens, cur_tokens= None):
def discard_exceeding(self, max_tokens, cur_tokens=None):
precise = True
try:
cur_tokens = self.calc_tokens()
@@ -22,7 +25,9 @@ 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)
@@ -34,25 +39,32 @@ 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()
else:
cur_tokens = cur_tokens - max_tokens
return cur_tokens
def calc_tokens(self):
return num_tokens_from_messages(self.messages, self.model)
# refer to https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb
def num_tokens_from_messages(messages, model):
"""Returns the number of tokens used by a list of messages."""
import tiktoken
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
@@ -63,13 +75,17 @@ 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: