J1147
/
CoW
보기 1
좋아요 0
포크 0
코드 이슈 0 풀 리퀘스트 0 릴리즈 0 위키 Activity
소스 검색

Merge Pull Request #774 into master

master
lanvent 1 년 전
부모
3a3affd3ec 45d72b8b9b
커밋
8c7d1d4010
9개의 변경된 파일과 396개의 추가작업 그리고 246개의 파일을 삭제
분할 보기
Diff Options
Show Stats Download Patch File Download Diff File
  1. +1
    -0
      .gitignore
  2. +1
    -1
      app.py
  3. +4
    -1
      channel/channel_factory.py
  4. +17
    -9
      channel/wechatmp/README.md
  5. +51
    -0
      channel/wechatmp/ServiceAccount.py
  6. +165
    -0
      channel/wechatmp/SubscribeAccount.py
  7. +63
    -0
      channel/wechatmp/common.py
  8. +89
    -232
      channel/wechatmp/wechatmp_channel.py
  9. +5
    -3
      config.py

+ 1
- 0
.gitignore 파일 보기

@@ -1,5 +1,6 @@
.DS_Store
.idea
.vscode
.wechaty/
__pycache__/
venv*


+ 1
- 1
app.py 파일 보기

@@ -36,7 +36,7 @@ def run():
# os.environ['WECHATY_PUPPET_SERVICE_ENDPOINT'] = '127.0.0.1:9001'

channel = channel_factory.create_channel(channel_name)
if channel_name in ['wx','wxy','wechatmp','terminal']:
if channel_name in ['wx','wxy','terminal','wechatmp','wechatmp_service']:
PluginManager().load_plugins()

# startup channel


+ 4
- 1
channel/channel_factory.py 파일 보기

@@ -19,5 +19,8 @@ def create_channel(channel_type):
return TerminalChannel()
elif channel_type == 'wechatmp':
from channel.wechatmp.wechatmp_channel import WechatMPChannel
return WechatMPChannel()
return WechatMPChannel(passive_reply = True)
elif channel_type == 'wechatmp_service':
from channel.wechatmp.wechatmp_channel import WechatMPChannel
return WechatMPChannel(passive_reply = False)
raise RuntimeError

+ 17
- 9
channel/wechatmp/README.md 파일 보기

@@ -1,10 +1,11 @@
# 个人微信公众号channel
# 微信公众号channel

鉴于个人微信号在服务器上通过itchat登录有封号风险，这里新增了个人微信公众号channel，提供无风险的服务。
但是由于个人微信公众号的众多接口限制，目前支持的功能有限，实现简陋，提供了一个最基本的文本对话服务，支持加载插件，优化了命令格式，支持私有api_key。暂未实现图片输入输出、语音输入输出等交互形式。
如有公众号是企业主体且可以通过微信认证，即可获得更多接口，解除大多数限制。欢迎大家提供更多的支持。
鉴于个人微信号在服务器上通过itchat登录有封号风险，这里新增了微信公众号channel，提供无风险的服务。
目前支持订阅号（个人）和服务号（企业）两种类型的公众号，它们的主要区别就是被动回复和主动回复。
个人微信订阅号有许多接口限制，目前仅支持最基本的文本对话和语音输入，支持加载插件，支持私有api_key。
暂未实现图片输入输出、语音输出等交互形式。

## 使用方法
## 使用方法（订阅号，服务号类似）

在开始部署前，你需要一个拥有公网IP的服务器，以提供微信服务器和我们自己服务器的连接。或者你需要进行内网穿透，否则微信服务器无法将消息发送给我们的服务器。

@@ -21,8 +22,10 @@ pip3 install web.py
相关的服务器验证代码已经写好，你不需要再添加任何代码。你只需要在本项目根目录的`config.json`中添加
```
"channel_type": "wechatmp",
"wechatmp_token": "your Token",
"wechatmp_port": 8080,
"wechatmp_token": "Token", # 微信公众平台的Token
"wechatmp_port": 8080, # 微信公众平台的端口,需要端口转发到80或443
"wechatmp_app_id": "", # 微信公众平台的appID，仅服务号需要
"wechatmp_app_secret": "", # 微信公众平台的appsecret，仅服务号需要
```
然后运行`python3 app.py`启动web服务器。这里会默认监听8080端口，但是微信公众号的服务器配置只支持80/443端口，有两种方法来解决这个问题。第一个是推荐的方法，使用端口转发命令将80端口转发到8080端口（443同理，注意需要支持SSL，也就是https的访问，在`wechatmp_channel.py`需要修改相应的证书路径）：
```
@@ -35,7 +38,7 @@ sudo iptables-save > /etc/iptables/rules.v4
随后在[微信公众平台](https://mp.weixin.qq.com)启用服务器，关闭手动填写规则的自动回复，即可实现ChatGPT的自动回复。

## 个人微信公众号的限制
由于目前测试的公众号不是企业主体，所以没有客服接口，因此公众号无法主动发出消息，只能被动回复。而微信官方对被动回复有5秒的时间限制，最多重试2次，因此最多只有15秒的自动回复时间窗口。因此如果问题比较复杂或者我们的服务器比较忙，ChatGPT的回答就没办法及时回复给用户。为了解决这个问题，这里做了回答缓存，它需要你在回复超时后，再次主动发送任意文字（例如1）来尝试拿到回答缓存。为了优化使用体验，目前设置了两分钟（120秒）的timeout，用户在至多两分钟后即可得到查询到回复或者错误原因。
由于人微信公众号不能通过微信认证，所以没有客服接口，因此公众号无法主动发出消息，只能被动回复。而微信官方对被动回复有5秒的时间限制，最多重试2次，因此最多只有15秒的自动回复时间窗口。因此如果问题比较复杂或者我们的服务器比较忙，ChatGPT的回答就没办法及时回复给用户。为了解决这个问题，这里做了回答缓存，它需要你在回复超时后，再次主动发送任意文字（例如1）来尝试拿到回答缓存。为了优化使用体验，目前设置了两分钟（120秒）的timeout，用户在至多两分钟后即可得到查询到回复或者错误原因。

另外，由于微信官方的限制，自动回复有长度限制。因此这里将ChatGPT的回答拆分，分成每段600字回复（限制大约在700字）。

@@ -43,4 +46,9 @@ sudo iptables-save > /etc/iptables/rules.v4
公共api有访问频率限制（免费账号每分钟最多20次ChatGPT的API调用），这在服务多人的时候会遇到问题。因此这里多加了一个设置私有api_key的功能。目前通过godcmd插件的命令来设置私有api_key。

## 测试范围
目前在`RoboStyle`这个公众号上进行了测试，感兴趣的可以关注并体验。开启了godcmd, Banwords, role, dungeon, finish这五个插件，其他的插件还没有测试。百度的接口暂未测试。语音对话没有测试。图片直接以链接形式回复（没有临时素材上传接口的权限）。
目前在`RoboStyle`这个公众号上进行了测试(基于[wechatmp-stable分支](https://github.com/JS00000/chatgpt-on-wechat/tree/wechatmp-stable),而[master分支](https://github.com/zhayujie/chatgpt-on-wechat)含有最新功能，但是稳定性有待测试)，感兴趣的可以关注并体验。开启了godcmd, Banwords, role, dungeon, finish这五个插件，其他的插件还没有测试。百度的接口暂未测试。语音对话没有测试。图片直接以链接形式回复（没有临时素材上传接口的权限）。

## TODO
* 服务号交互完善
* 服务号使用临时素材接口，提供图片回复能力
* 插件测试

+ 51
- 0
channel/wechatmp/ServiceAccount.py 파일 보기

@@ -0,0 +1,51 @@
import web
import time
import channel.wechatmp.reply as reply
import channel.wechatmp.receive as receive
from config import conf
from common.log import logger
from bridge.context import *
from channel.wechatmp.common import *
from channel.wechatmp.wechatmp_channel import WechatMPChannel

# This class is instantiated once per query
class Query():

def GET(self):
return verify_server(web.input())

def POST(self):
# Make sure to return the instance that first created, @singleton will do that.
channel_instance = WechatMPChannel()
try:
webData = web.data()
# logger.debug("[wechatmp] Receive request:\n" + webData.decode("utf-8"))
wechatmp_msg = receive.parse_xml(webData)
if wechatmp_msg.msg_type == 'text':
from_user = wechatmp_msg.from_user_id
message = wechatmp_msg.content.decode("utf-8")
message_id = wechatmp_msg.msg_id

logger.info("[wechatmp] {}:{} Receive post query {} {}: {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), from_user, message_id, message))
context = channel_instance._compose_context(ContextType.TEXT, message, isgroup=False, msg=wechatmp_msg)
if context:
# set private openai_api_key
# if from_user is not changed in itchat, this can be placed at chat_channel
user_data = conf().get_user_data(from_user)
context['openai_api_key'] = user_data.get('openai_api_key') # None or user openai_api_key
channel_instance.produce(context)
# The reply will be sent by channel_instance.send() in another thread
return "success"

elif wechatmp_msg.msg_type == 'event':
logger.info("[wechatmp] Event {} from {}".format(wechatmp_msg.Event, wechatmp_msg.from_user_id))
content = subscribe_msg()
replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
return replyMsg.send()
else:
logger.info("暂且不处理")
return "success"
except Exception as exc:
logger.exception(exc)
return exc


+ 165
- 0
channel/wechatmp/SubscribeAccount.py 파일 보기

@@ -0,0 +1,165 @@
import web
import time
import channel.wechatmp.reply as reply
import channel.wechatmp.receive as receive
from config import conf
from common.log import logger
from bridge.context import *
from channel.wechatmp.common import *
from channel.wechatmp.wechatmp_channel import WechatMPChannel

# This class is instantiated once per query
class Query():

def GET(self):
return verify_server(web.input())

def POST(self):
# Make sure to return the instance that first created, @singleton will do that.
channel = WechatMPChannel()
try:
query_time = time.time()
webData = web.data()
logger.debug("[wechatmp] Receive request:\n" + webData.decode("utf-8"))
wechatmp_msg = receive.parse_xml(webData)
if wechatmp_msg.msg_type == 'text':
from_user = wechatmp_msg.from_user_id
to_user = wechatmp_msg.to_user_id
message = wechatmp_msg.content.decode("utf-8")
message_id = wechatmp_msg.msg_id

logger.info("[wechatmp] {}:{} Receive post query {} {}: {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), from_user, message_id, message))
supported = True
if "【收到不支持的消息类型，暂无法显示】" in message:
supported = False # not supported, used to refresh
cache_key = from_user

reply_text = ""
# New request
if cache_key not in channel.cache_dict and cache_key not in channel.running:
# The first query begin, reset the cache
context = channel._compose_context(ContextType.TEXT, message, isgroup=False, msg=wechatmp_msg)
logger.debug("[wechatmp] context: {} {}".format(context, wechatmp_msg))
if message_id in channel.received_msgs: # received and finished
return
if supported and context:
# set private openai_api_key
# if from_user is not changed in itchat, this can be placed at chat_channel
user_data = conf().get_user_data(from_user)
context['openai_api_key'] = user_data.get('openai_api_key') # None or user openai_api_key
channel.received_msgs[message_id] = wechatmp_msg
channel.running.add(cache_key)
channel.produce(context)
else:
trigger_prefix = conf().get('single_chat_prefix',[''])[0]
if trigger_prefix or not supported:
if trigger_prefix:
content = textwrap.dedent(f"""\
请输入'{trigger_prefix}'接你想说的话跟我说话。
例如:
{trigger_prefix}你好，很高兴见到你。""")
else:
content = textwrap.dedent("""\
你好，很高兴见到你。
请跟我说话吧。""")
else:
logger.error(f"[wechatmp] unknown error")
content = textwrap.dedent("""\
未知错误，请稍后再试""")
replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
return replyMsg.send()
channel.query1[cache_key] = False
channel.query2[cache_key] = False
channel.query3[cache_key] = False
# Request again
elif cache_key in channel.running and channel.query1.get(cache_key) == True and channel.query2.get(cache_key) == True and channel.query3.get(cache_key) == True:
channel.query1[cache_key] = False #To improve waiting experience, this can be set to True.
channel.query2[cache_key] = False #To improve waiting experience, this can be set to True.
channel.query3[cache_key] = False
elif cache_key in channel.cache_dict:
# Skip the waiting phase
channel.query1[cache_key] = True
channel.query2[cache_key] = True
channel.query3[cache_key] = True

assert not (cache_key in channel.cache_dict and cache_key in channel.running)

if channel.query1.get(cache_key) == False:
# The first query from wechat official server
logger.debug("[wechatmp] query1 {}".format(cache_key))
channel.query1[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 45:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 45:
# waiting for timeout (the POST query will be closed by wechat official server)
time.sleep(1)
# and do nothing
return
else:
pass
elif channel.query2.get(cache_key) == False:
# The second query from wechat official server
logger.debug("[wechatmp] query2 {}".format(cache_key))
channel.query2[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 45:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 45:
# waiting for timeout (the POST query will be closed by wechat official server)
time.sleep(1)
# and do nothing
return
else:
pass
elif channel.query3.get(cache_key) == False:
# The third query from wechat official server
logger.debug("[wechatmp] query3 {}".format(cache_key))
channel.query3[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 40:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 40:
# Have waiting for 3x5 seconds
# return timeout message
reply_text = "【正在思考中，回复任意文字尝试获取回复】"
logger.info("[wechatmp] Three queries has finished For {}: {}".format(from_user, message_id))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost
else:
pass

if float(time.time()) - float(query_time) > 4.8:
reply_text = "【正在思考中，回复任意文字尝试获取回复】"
logger.info("[wechatmp] Timeout for {} {}, return".format(from_user, message_id))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost
if cache_key in channel.cache_dict:
content = channel.cache_dict[cache_key]
if len(content.encode('utf8'))<=MAX_UTF8_LEN:
reply_text = channel.cache_dict[cache_key]
channel.cache_dict.pop(cache_key)
else:
continue_text = "\n【未完待续，回复任意文字以继续】"
splits = split_string_by_utf8_length(content, MAX_UTF8_LEN - len(continue_text.encode('utf-8')), max_split= 1)
reply_text = splits[0] + continue_text
channel.cache_dict[cache_key] = splits[1]
logger.info("[wechatmp] {}:{} Do send {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), reply_text))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost

elif wechatmp_msg.msg_type == 'event':
logger.info("[wechatmp] Event {} from {}".format(wechatmp_msg.content, wechatmp_msg.from_user_id))
content = subscribe_msg()
replyMsg = reply.TextMsg(wechatmp_msg.from_user_id, wechatmp_msg.to_user_id, content)
return replyMsg.send()
else:
logger.info("暂且不处理")
return "success"
except Exception as exc:
logger.exception(exc)
return exc

+ 63
- 0
channel/wechatmp/common.py 파일 보기

@@ -0,0 +1,63 @@
from config import conf
import hashlib
import textwrap

MAX_UTF8_LEN = 2048

class WeChatAPIException(Exception):
pass


def verify_server(data):
try:
if len(data) == 0:
return "None"
signature = data.signature
timestamp = data.timestamp
nonce = data.nonce
echostr = data.echostr
token = conf().get('wechatmp_token') #请按照公众平台官网\基本配置中信息填写

data_list = [token, timestamp, nonce]
data_list.sort()
sha1 = hashlib.sha1()
# map(sha1.update, data_list) #python2
sha1.update("".join(data_list).encode('utf-8'))
hashcode = sha1.hexdigest()
print("handle/GET func: hashcode, signature: ", hashcode, signature)
if hashcode == signature:
return echostr
else:
return ""
except Exception as Argument:
return Argument

def subscribe_msg():
trigger_prefix = conf().get('single_chat_prefix',[''])[0]
msg = textwrap.dedent(f"""\
感谢您的关注！
这里是ChatGPT，可以自由对话。
资源有限，回复较慢，请勿着急。
支持通用表情输入。
暂时不支持图片输入。
支持图片输出，画字开头的问题将回复图片链接。
支持角色扮演和文字冒险两种定制模式对话。
输入'{trigger_prefix}#帮助' 查看详细指令。""")
return msg


def split_string_by_utf8_length(string, max_length, max_split=0):
encoded = string.encode('utf-8')
start, end = 0, 0
result = []
while end < len(encoded):
if max_split > 0 and len(result) >= max_split:
result.append(encoded[start:].decode('utf-8'))
break
end = start + max_length
# 如果当前字节不是 UTF-8 编码的开始字节，则向前查找直到找到开始字节为止
while end < len(encoded) and (encoded[end] & 0b11000000) == 0b10000000:
end -= 1
result.append(encoded[start:end].decode('utf-8'))
start = end
return result

+ 89
- 232
channel/wechatmp/wechatmp_channel.py 파일 보기

@@ -1,20 +1,17 @@
# -*- coding: utf-8 -*-
import web
import time
import math
import hashlib
import textwrap
from channel.chat_channel import ChatChannel
import channel.wechatmp.reply as reply
import channel.wechatmp.receive as receive
from common.expired_dict import ExpiredDict
import json
import requests
import threading
from common.singleton import singleton
from common.log import logger
from common.expired_dict import ExpiredDict
from config import conf
from bridge.reply import *
from bridge.context import *
from plugins import *
import traceback
from channel.chat_channel import ChatChannel
from channel.wechatmp.common import *

# If using SSL, uncomment the following lines, and modify the certificate path.
# from cheroot.server import HTTPServer
@@ -23,37 +20,101 @@ import traceback
# certificate='/ssl/cert.pem',
# private_key='/ssl/cert.key')


# from concurrent.futures import ThreadPoolExecutor
# thread_pool = ThreadPoolExecutor(max_workers=8)

MAX_UTF8_LEN = 2048
@singleton
class WechatMPChannel(ChatChannel):
NOT_SUPPORT_REPLYTYPE = [ReplyType.IMAGE, ReplyType.VOICE]
def __init__(self):
def __init__(self, passive_reply = True):
super().__init__()
self.cache_dict = dict()
self.passive_reply = passive_reply
self.running = set()
self.query1 = dict()
self.query2 = dict()
self.query3 = dict()
self.received_msgs = ExpiredDict(60*60*24)
self.received_msgs = ExpiredDict(60*60*24)
if self.passive_reply:
self.NOT_SUPPORT_REPLYTYPE = [ReplyType.IMAGE, ReplyType.VOICE]
self.cache_dict = dict()
self.query1 = dict()
self.query2 = dict()
self.query3 = dict()
else:
# TODO support image
self.NOT_SUPPORT_REPLYTYPE = [ReplyType.IMAGE, ReplyType.VOICE]
self.app_id = conf().get('wechatmp_app_id')
self.app_secret = conf().get('wechatmp_app_secret')
self.access_token = None
self.access_token_expires_time = 0
self.access_token_lock = threading.Lock()
self.get_access_token()

def startup(self):
urls = (
'/wx', 'SubsribeAccountQuery',
)
if self.passive_reply:
urls = ('/wx', 'channel.wechatmp.SubscribeAccount.Query')
else:
urls = ('/wx', 'channel.wechatmp.ServiceAccount.Query')
app = web.application(urls, globals(), autoreload=False)
port = conf().get('wechatmp_port', 8080)
web.httpserver.runsimple(app.wsgifunc(), ('0.0.0.0', port))


def wechatmp_request(self, method, url, **kwargs):
r = requests.request(method=method, url=url, **kwargs)
r.raise_for_status()
r.encoding = "utf-8"
ret = r.json()
if "errcode" in ret and ret["errcode"] != 0:
raise WeChatAPIException("{}".format(ret))
return ret

def get_access_token(self):

# return the access_token
if self.access_token:
if self.access_token_expires_time - time.time() > 60:
return self.access_token

# Get new access_token
# Do not request access_token in parallel! Only the last obtained is valid.
if self.access_token_lock.acquire(blocking=False):
# Wait for other threads that have previously obtained access_token to complete the request
# This happens every 2 hours, so it doesn't affect the experience very much
time.sleep(1)
self.access_token = None
url="https://api.weixin.qq.com/cgi-bin/token"
params={
"grant_type": "client_credential",
"appid": self.app_id,
"secret": self.app_secret
}
data = self.wechatmp_request(method='get', url=url, params=params)
self.access_token = data['access_token']
self.access_token_expires_time = int(time.time()) + data['expires_in']
logger.info("[wechatmp] access_token: {}".format(self.access_token))
self.access_token_lock.release()
else:
# Wait for token update
while self.access_token_lock.locked():
time.sleep(0.1)
return self.access_token

def send(self, reply: Reply, context: Context):
receiver = context["receiver"]
self.cache_dict[receiver] = reply.content
self.running.remove(receiver)
logger.debug("[send] reply to {} saved to cache: {}".format(receiver, reply))
if self.passive_reply:
receiver = context["receiver"]
self.cache_dict[receiver] = reply.content
self.running.remove(receiver)
logger.debug("[send] reply to {} saved to cache: {}".format(receiver, reply))
else:
receiver = context["receiver"]
reply_text = reply.content
url="https://api.weixin.qq.com/cgi-bin/message/custom/send"
params = {
"access_token": self.get_access_token()
}
json_data = {
"touser": receiver,
"msgtype": "text",
"text": {"content": reply_text}
}
self.wechatmp_request(method='post', url=url, params=params, data=json.dumps(json_data, ensure_ascii=False).encode('utf8'))
logger.info("[send] Do send to {}: {}".format(receiver, reply_text))
return


def _fail_callback(self, session_id, exception, context, **kwargs):
logger.exception("[wechatmp] Fail to generation message to user, msgId={}, exception={}".format(context['msg'].msg_id, exception))
@@ -61,208 +122,4 @@ class WechatMPChannel(ChatChannel):
self.running.remove(session_id)


def verify_server():
try:
data = web.input()
if len(data) == 0:
return "None"
signature = data.signature
timestamp = data.timestamp
nonce = data.nonce
echostr = data.echostr
token = conf().get('wechatmp_token') #请按照公众平台官网\基本配置中信息填写

data_list = [token, timestamp, nonce]
data_list.sort()
sha1 = hashlib.sha1()
# map(sha1.update, data_list) #python2
sha1.update("".join(data_list).encode('utf-8'))
hashcode = sha1.hexdigest()
print("handle/GET func: hashcode, signature: ", hashcode, signature)
if hashcode == signature:
return echostr
else:
return ""
except Exception as Argument:
return Argument


# This class is instantiated once per query
class SubsribeAccountQuery():

def GET(self):
return verify_server()

def POST(self):
channel = WechatMPChannel()
try:
query_time = time.time()
webData = web.data()
logger.debug("[wechatmp] Receive request:\n" + webData.decode("utf-8"))
wechat_msg = receive.parse_xml(webData)
if wechat_msg.msg_type == 'text':
from_user = wechat_msg.from_user_id
to_user = wechat_msg.to_user_id
message = wechat_msg.content.decode("utf-8")
message_id = wechat_msg.msg_id

logger.info("[wechatmp] {}:{} Receive post query {} {}: {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), from_user, message_id, message))
supported = True
if "【收到不支持的消息类型，暂无法显示】" in message:
supported = False # not supported, used to refresh
cache_key = from_user

reply_text = ""
# New request
if cache_key not in channel.cache_dict and cache_key not in channel.running:
# The first query begin, reset the cache
context = channel._compose_context(ContextType.TEXT, message, isgroup=False, msg=wechat_msg)
logger.debug("[wechatmp] context: {} {}".format(context, wechat_msg))
if message_id in channel.received_msgs: # received and finished
return
if supported and context:
# set private openai_api_key
# if from_user is not changed in itchat, this can be placed at chat_channel
user_data = conf().get_user_data(from_user)
context['openai_api_key'] = user_data.get('openai_api_key') # None or user openai_api_key
channel.received_msgs[message_id] = wechat_msg
channel.running.add(cache_key)
channel.produce(context)
else:
trigger_prefix = conf().get('single_chat_prefix',[''])[0]
if trigger_prefix or not supported:
if trigger_prefix:
content = textwrap.dedent(f"""\
请输入'{trigger_prefix}'接你想说的话跟我说话。
例如:
{trigger_prefix}你好，很高兴见到你。""")
else:
content = textwrap.dedent("""\
你好，很高兴见到你。
请跟我说话吧。""")
else:
logger.error(f"[wechatmp] unknown error")
content = textwrap.dedent("""\
未知错误，请稍后再试""")
replyMsg = reply.TextMsg(wechat_msg.from_user_id, wechat_msg.to_user_id, content)
return replyMsg.send()
channel.query1[cache_key] = False
channel.query2[cache_key] = False
channel.query3[cache_key] = False
# Request again
elif cache_key in channel.running and channel.query1.get(cache_key) == True and channel.query2.get(cache_key) == True and channel.query3.get(cache_key) == True:
channel.query1[cache_key] = False #To improve waiting experience, this can be set to True.
channel.query2[cache_key] = False #To improve waiting experience, this can be set to True.
channel.query3[cache_key] = False
elif cache_key in channel.cache_dict:
# Skip the waiting phase
channel.query1[cache_key] = True
channel.query2[cache_key] = True
channel.query3[cache_key] = True

assert not (cache_key in channel.cache_dict and cache_key in channel.running)

if channel.query1.get(cache_key) == False:
# The first query from wechat official server
logger.debug("[wechatmp] query1 {}".format(cache_key))
channel.query1[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 45:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 45:
# waiting for timeout (the POST query will be closed by wechat official server)
time.sleep(1)
# and do nothing
return
else:
pass
elif channel.query2.get(cache_key) == False:
# The second query from wechat official server
logger.debug("[wechatmp] query2 {}".format(cache_key))
channel.query2[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 45:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 45:
# waiting for timeout (the POST query will be closed by wechat official server)
time.sleep(1)
# and do nothing
return
else:
pass
elif channel.query3.get(cache_key) == False:
# The third query from wechat official server
logger.debug("[wechatmp] query3 {}".format(cache_key))
channel.query3[cache_key] = True
cnt = 0
while cache_key not in channel.cache_dict and cnt < 40:
cnt = cnt + 1
time.sleep(0.1)
if cnt == 40:
# Have waiting for 3x5 seconds
# return timeout message
reply_text = "【正在思考中，回复任意文字尝试获取回复】"
logger.info("[wechatmp] Three queries has finished For {}: {}".format(from_user, message_id))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost
else:
pass

if float(time.time()) - float(query_time) > 4.8:
reply_text = "【正在思考中，回复任意文字尝试获取回复】"
logger.info("[wechatmp] Timeout for {} {}, return".format(from_user, message_id))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost
if cache_key in channel.cache_dict:
content = channel.cache_dict[cache_key]
if len(content.encode('utf8'))<=MAX_UTF8_LEN:
reply_text = channel.cache_dict[cache_key]
channel.cache_dict.pop(cache_key)
else:
continue_text = "\n【未完待续，回复任意文字以继续】"
splits = split_string_by_utf8_length(content, MAX_UTF8_LEN - len(continue_text.encode('utf-8')), max_split= 1)
reply_text = splits[0] + continue_text
channel.cache_dict[cache_key] = splits[1]
logger.info("[wechatmp] {}:{} Do send {}".format(web.ctx.env.get('REMOTE_ADDR'), web.ctx.env.get('REMOTE_PORT'), reply_text))
replyPost = reply.TextMsg(from_user, to_user, reply_text).send()
return replyPost

elif wechat_msg.msg_type == 'event':
logger.info("[wechatmp] Event {} from {}".format(wechat_msg.content, wechat_msg.from_user_id))
trigger_prefix = conf().get('single_chat_prefix',[''])[0]
content = textwrap.dedent(f"""\
感谢您的关注！
这里是ChatGPT，可以自由对话。
资源有限，回复较慢，请勿着急。
支持通用表情输入。
暂时不支持图片输入。
支持图片输出，画字开头的问题将回复图片链接。
支持角色扮演和文字冒险两种定制模式对话。
输入'{trigger_prefix}#帮助' 查看详细指令。""")
replyMsg = reply.TextMsg(wechat_msg.from_user_id, wechat_msg.to_user_id, content)
return replyMsg.send()
else:
logger.info("暂且不处理")
return "success"
except Exception as exc:
logger.exception(exc)
return exc

def split_string_by_utf8_length(string, max_length, max_split=0):
encoded = string.encode('utf-8')
start, end = 0, 0
result = []
while end < len(encoded):
if max_split > 0 and len(result) >= max_split:
result.append(encoded[start:].decode('utf-8'))
break
end = start + max_length
# 如果当前字节不是 UTF-8 编码的开始字节，则向前查找直到找到开始字节为止
while end < len(encoded) and (encoded[end] & 0b11000000) == 0b10000000:
end -= 1
result.append(encoded[start:end].decode('utf-8'))
start = end
return result

+ 5
- 3
config.py 파일 보기

@@ -79,14 +79,16 @@ available_setting = {
"wechaty_puppet_service_token": "", # wechaty的token

# wechatmp的配置
"wechatmp_token": "", # 微信公众平台的Token
"wechatmp_port": 8080, # 微信公众平台的端口,需要端口转发到80或443
"wechatmp_token": "", # 微信公众平台的Token
"wechatmp_port": 8080, # 微信公众平台的端口,需要端口转发到80或443
"wechatmp_app_id": "", # 微信公众平台的appID，仅服务号需要
"wechatmp_app_secret": "", # 微信公众平台的appsecret，仅服务号需要

# chatgpt指令自定义触发词
"clear_memory_commands": ['#清除记忆'], # 重置会话指令，必须以#开头

# channel配置
"channel_type": "wx", # 通道类型，支持：{wx,wxy,terminal,wechatmp}
"channel_type": "wx", # 通道类型，支持：{wx,wxy,terminal,wechatmp,wechatmp_service}

"debug": False, # 是否开启debug模式，开启后会打印更多日志



Write Preview
Loading…
취소
저장