Compare commits

..

45 Commits
1.7.2 ... 1.7.4

Author SHA1 Message Date
Saboteur7
16324e7283 Merge pull request #2407 from ayasa520/fix_reloadp
fix(plugin): fix reloadp command not taking effect
2024-12-13 15:39:33 +08:00
Saboteur7
9f7e2e1572 Merge pull request #2413 from ayasa520/fix-scanp
fix: Memory leak caused by scanp command due to handler's reference of plugin instance
2024-12-13 14:57:22 +08:00
vision
857ce1d530 Merge pull request #2398 from stonyz/web-channel
增加web channel
2024-12-13 11:45:01 +08:00
vision
be0d72775d Merge pull request #2423 from 6vision/reedme_update_docker_deploy
update readme
2024-12-13 11:41:17 +08:00
vision
7832a2495b Merge pull request #2422 from printlndarling/master
add: add gemini-2.0-flash-exp model
2024-12-13 11:35:26 +08:00
6vision
0506b7f735 update readme 2024-12-13 11:25:36 +08:00
繁星_逐梦
4c0b7942f0 add: gemini-2.0-flash-exp model 2024-12-12 22:22:14 +08:00
繁星_逐梦
651c840c4a add: gemini-2.0-flash-exp model 2024-12-12 22:19:13 +08:00
rikka
2a351ca415 fix(reloadp): clear handlers when reloading plugin to avoid memory leaks 2024-12-05 00:33:00 +08:00
rikka
49b7106d71 fix: Memory leak caused by scanp command due to handler's reference to plugin instance.
close #2412
2024-12-03 22:39:56 +08:00
zhayujie
8bf633f539 Merge pull request #2408 from 6vision/fix-summary-image
图像识别逻辑优化
2024-12-02 21:53:52 +08:00
6vision
0f8efcb4b0 图像识别逻辑优化 2024-12-02 21:16:59 +08:00
Rikka
c567641c5c fix(plugin): fix reloadp command not taking effect
- Use write_plugin_config() instead of directly modifying plugin_config dict
- Add remove_plugin_config() to clear plugin config before reload
- Update plugins to use pconf() and write_plugin_config() for better config management
2024-12-02 16:38:21 +08:00
vision
bdc3820382 Merge pull request #2405 from 6vision/role-plugin-linkai
Linkai bot is compatible with the role plugin.
2024-12-02 12:16:30 +08:00
6vision
33a69a7907 Linkai bot is compatible with the role plugin. 2024-12-02 12:13:26 +08:00
vision
a4d0e9bbc3 Merge pull request #2401 from 6vision/plugins_source_update
插件列表更新
2024-11-29 11:09:27 +08:00
6vision
afc753e1d2 插件列表更新 2024-11-29 11:07:16 +08:00
zhayujie
e641a41224 Update README.md 2024-11-28 21:48:42 +08:00
vision
79305c0632 Merge pull request #2400 from 6vision/readme_update
readme update
2024-11-28 12:59:00 +08:00
6vision
ef2ce3f09d 说明文档更新 2024-11-28 12:41:00 +08:00
Stony
71c18c04fc 增加web channel 2024-11-27 08:53:13 +08:00
Saboteur7
cf84e57f81 fix: add exception handling 2024-11-15 11:58:10 +08:00
vision
9421d44579 Merge pull request #2373 from 6vision/summary_app_code
Buy using app code, supports custom summary prompt .
2024-11-07 20:16:53 +08:00
6vision
5cd2ae8cc8 Summary supports app_code 2024-11-06 21:45:03 +08:00
vision
22d67b3a59 Merge pull request #2364 from 6vision/1031
1.7.3 release readme
2024-10-31 14:44:55 +08:00
6vision
e102cbb8c4 1.7.3 release readme 2024-10-31 14:39:11 +08:00
vision
d90eeb7ee4 Merge pull request #2363 from 6vision/linkai_plugin
Summary and MJ  support can be configured through LinkAI platform app plugins
2024-10-31 11:50:53 +08:00
vision
1989d53031 Merge pull request #2361 from 6vision/claude_model_update
Claude model update
2024-10-31 11:50:11 +08:00
6vision
04ef0907b4 Summary and MJ support can be configured through LinkAI platform app plugins. 2024-10-31 11:15:44 +08:00
6vision
517b43561c Merge branch 'claude_model_update' of git@github.com:6vision/chatgpt-on-wechat.git into claude_model_update 2024-10-28 00:32:46 +08:00
6vision
ccb8c7227f Support setting base URL and proxy for Claude model. Also support reset command. 2024-10-28 00:32:05 +08:00
vision
9fbfeeb04f Merge branch 'zhayujie:master' into claude_model_update 2024-10-27 23:43:16 +08:00
6vision
8b753a5a1f Signed-off-by: 6vision <vision_wangpc@sina.com> 2024-10-27 21:44:06 +08:00
6vision
d25cab0627 Claude model supports system prompts. 2024-10-27 21:37:58 +08:00
6vision
84da0a8a35 feat:update claude-35-sonnet model 2024-10-24 20:57:03 +08:00
vision
6f665cffba Merge pull request #2354 from 6vision/group_patpat_note
fix: group patpat notes
2024-10-24 19:53:18 +08:00
6vision
aea8ac2e97 Signed-off-by: 6vision <vision_wangpc@sina.com> 2024-10-24 19:48:50 +08:00
vision
8418fa7b45 Merge pull request #2344 from 6vision/markdown_format_display
Optimize markdown format display
2024-10-21 10:27:03 +08:00
6vision
9cc4d0ee07 Optimize markdown format display 2024-10-21 10:23:39 +08:00
Saboteur7
da60831c44 fix: fixed the version of qrcode dependency 2024-10-19 16:14:49 +08:00
Saboteur7
0773174a20 Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat 2024-10-19 15:55:04 +08:00
Saboteur7
70e007d8ca fix: try to solve the unresponsiveness problem 2024-10-19 15:49:57 +08:00
vision
fcc4d02c2f Merge pull request #2339 from 6vision/master
Optimize Gemini model character statistics
2024-10-14 12:19:27 +08:00
vision
f4a5f00593 Merge branch 'zhayujie:master' into master 2024-10-14 12:18:33 +08:00
6vision
1170ed6566 Optimize Gemini model character statistics 2024-10-14 12:17:10 +08:00
28 changed files with 596 additions and 88 deletions

View File

@@ -40,11 +40,12 @@ DEMO视频https://cdn.link-ai.tech/doc/cow_demo.mp4
**企业服务和产品咨询** 可联系产品顾问:
<img width="160" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/github-product-consult.png">
<img width="160" src="https://cdn.link-ai.tech/consultant-s.jpg">
<br>
# 🏷 更新日志
>**2024.10.31** [1.7.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.3) 程序稳定性提升、数据库功能、Claude模型优化、linkai插件优化、离线通知
>**2024.09.26** [1.7.2版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.2) 和 [1.7.1版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.7.1) 文心讯飞等模型优化、o1 模型、快速安装和管理脚本
@@ -143,6 +144,7 @@ pip3 install -r requirements-optional.txt
{
"model": "gpt-3.5-turbo", # 模型名称, 支持 gpt-3.5-turbo, gpt-4, gpt-4-turbo, wenxin, xunfei, glm-4, claude-3-haiku, moonshot
"open_ai_api_key": "YOUR API KEY", # 如果使用openAI模型则填入上面创建的 OpenAI API KEY
"open_ai_api_base": "https://api.openai.com/v1", # OpenAI接口代理地址
"proxy": "", # 代理客户端的ip和端口国内环境开启代理的需要填写该项如 "127.0.0.1:7890"
"single_chat_prefix": ["bot", "@bot"], # 私聊时文本需要包含该前缀才能触发机器人回复
"single_chat_reply_prefix": "[bot] ", # 私聊时自动回复的前缀,用于区分真人
@@ -274,7 +276,7 @@ sudo docker logs -f chatgpt-on-wechat
volumes:
- ./config.json:/app/plugins/config.json
```
**注**采用docker方式部署的详细教程可以参考[docker部署CoW项目](https://www.wangpc.cc/ai/docker-deploy-cow/)
### 4. Railway部署
> Railway 每月提供5刀和最多500小时的免费额度。 (07.11更新: 目前大部分账号已无法免费部署)

2
app.py
View File

@@ -27,7 +27,7 @@ def sigterm_handler_wrap(_signo):
def start_channel(channel_name: str):
channel = channel_factory.create_channel(channel_name)
if channel_name in ["wx", "wxy", "terminal", "wechatmp", "wechatmp_service", "wechatcom_app", "wework",
if channel_name in ["wx", "wxy", "terminal", "wechatmp","web", "wechatmp_service", "wechatcom_app", "wework",
const.FEISHU, const.DINGTALK]:
PluginManager().load_plugins()

View File

@@ -57,7 +57,7 @@ class ChatGPTSession(Session):
def num_tokens_from_messages(messages, model):
"""Returns the number of tokens used by a list of messages."""
if model in ["wenxin", "xunfei", const.GEMINI]:
if model in ["wenxin", "xunfei"] or model.startswith(const.GEMINI):
return num_tokens_by_character(messages)
import tiktoken

View File

@@ -8,12 +8,12 @@ import anthropic
from bot.bot import Bot
from bot.openai.open_ai_image import OpenAIImage
from bot.chatgpt.chat_gpt_session import ChatGPTSession
from bot.gemini.google_gemini_bot import GoogleGeminiBot
from bot.baidu.baidu_wenxin_session import BaiduWenxinSession
from bot.session_manager import SessionManager
from bridge.context import ContextType
from bridge.reply import Reply, ReplyType
from common.log import logger
from common import const
from config import conf
user_session = dict()
@@ -23,17 +23,14 @@ user_session = dict()
class ClaudeAPIBot(Bot, OpenAIImage):
def __init__(self):
super().__init__()
proxy = conf().get("proxy", None)
base_url = conf().get("open_ai_api_base", None) # 复用"open_ai_api_base"参数作为base_url
self.claudeClient = anthropic.Anthropic(
api_key=conf().get("claude_api_key")
api_key=conf().get("claude_api_key"),
proxies=proxy if proxy else None,
base_url=base_url if base_url else None
)
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
self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "text-davinci-003")
self.sessions = SessionManager(BaiduWenxinSession, model=conf().get("model") or "text-davinci-003")
def reply(self, query, context=None):
# acquire reply content
@@ -76,14 +73,14 @@ class ClaudeAPIBot(Bot, OpenAIImage):
reply = Reply(ReplyType.ERROR, retstring)
return reply
def reply_text(self, session: ChatGPTSession, retry_count=0):
def reply_text(self, session: BaiduWenxinSession, retry_count=0):
try:
actual_model = self._model_mapping(conf().get("model"))
response = self.claudeClient.messages.create(
model=actual_model,
max_tokens=1024,
# system=conf().get("system"),
messages=GoogleGeminiBot.filter_messages(session.messages)
max_tokens=4096,
system=conf().get("character_desc", ""),
messages=session.messages
)
# response = openai.Completion.create(prompt=str(session), **self.args)
res_content = response.content[0].text.strip().replace("<|endoftext|>", "")
@@ -97,7 +94,7 @@ class ClaudeAPIBot(Bot, OpenAIImage):
}
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"}
result = {"total_tokens": 0, "completion_tokens": 0, "content": "我现在有点累了,等会再来吧"}
if isinstance(e, openai.error.RateLimitError):
logger.warn("[CLAUDE_API] RateLimitError: {}".format(e))
result["content"] = "提问太快啦,请休息一下再问我吧"
@@ -125,11 +122,11 @@ class ClaudeAPIBot(Bot, OpenAIImage):
def _model_mapping(self, model) -> str:
if model == "claude-3-opus":
return "claude-3-opus-20240229"
return const.CLAUDE_3_OPUS
elif model == "claude-3-sonnet":
return "claude-3-sonnet-20240229"
return const.CLAUDE_3_SONNET
elif model == "claude-3-haiku":
return "claude-3-haiku-20240307"
return const.CLAUDE_3_HAIKU
elif model == "claude-3.5-sonnet":
return "claude-3-5-sonnet-20240620"
return const.CLAUDE_35_SONNET
return model

View File

@@ -21,6 +21,9 @@ def create_channel(channel_type) -> Channel:
elif channel_type == "terminal":
from channel.terminal.terminal_channel import TerminalChannel
ch = TerminalChannel()
elif channel_type == 'web':
from channel.web.web_channel import WebChannel
ch = WebChannel()
elif channel_type == "wechatmp":
from channel.wechatmp.wechatmp_channel import WechatMPChannel
ch = WechatMPChannel(passive_reply=True)

View File

@@ -337,24 +337,27 @@ class ChatChannel(Channel):
while True:
with self.lock:
session_ids = list(self.sessions.keys())
for session_id in session_ids:
for session_id in session_ids:
with self.lock:
context_queue, semaphore = self.sessions[session_id]
if semaphore.acquire(blocking=False): # 等线程处理完毕才能删除
if not context_queue.empty():
context = context_queue.get()
logger.debug("[chat_channel] consume context: {}".format(context))
future: Future = handler_pool.submit(self._handle, context)
future.add_done_callback(self._thread_pool_callback(session_id, context=context))
if semaphore.acquire(blocking=False): # 等线程处理完毕才能删除
if not context_queue.empty():
context = context_queue.get()
logger.debug("[chat_channel] consume context: {}".format(context))
future: Future = handler_pool.submit(self._handle, context)
future.add_done_callback(self._thread_pool_callback(session_id, context=context))
with self.lock:
if session_id not in self.futures:
self.futures[session_id] = []
self.futures[session_id].append(future)
elif semaphore._initial_value == semaphore._value + 1: # 除了当前,没有任务再申请到信号量,说明所有任务都处理完毕
elif semaphore._initial_value == semaphore._value + 1: # 除了当前,没有任务再申请到信号量,说明所有任务都处理完毕
with self.lock:
self.futures[session_id] = [t for t in self.futures[session_id] if not t.done()]
assert len(self.futures[session_id]) == 0, "thread pool error"
del self.sessions[session_id]
else:
semaphore.release()
time.sleep(0.1)
else:
semaphore.release()
time.sleep(0.2)
# 取消session_id对应的所有任务只能取消排队的消息和已提交线程池但未执行的任务
def cancel_session(self, session_id):

7
channel/web/README.md Normal file
View File

@@ -0,0 +1,7 @@
# Web channel
使用SSEServer-Sent Events服务器推送事件实现提供了一个默认的网页。也可以自己实现加入api
#使用方法
- 在配置文件中channel_type填入web即可
- 访问地址 http://localhost:9899
- port可以在配置项 web_port中设置

165
channel/web/chat.html Normal file
View File

@@ -0,0 +1,165 @@
<!DOCTYPE html>
<html lang="zh">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Chat</title>
<style>
body {
font-family: Arial, sans-serif;
display: flex;
flex-direction: column;
height: 100vh; /* 占据所有高度 */
margin: 0;
/* background-color: #f8f9fa; */
}
#chat-container {
display: flex;
flex-direction: column;
width: 100%;
max-width: 500px;
margin: auto;
border: 1px solid #ccc;
border-radius: 5px;
overflow: hidden;
box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
flex: 1; /* 使聊天容器占据剩余空间 */
}
#messages {
flex-direction: column;
display: flex;
flex: 1;
overflow-y: auto;
padding: 10px;
overflow-y: auto;
border-bottom: 1px solid #ccc;
background-color: #ffffff;
}
.message {
margin: 5px 0; /* 间隔 */
padding: 10px 15px; /* 内边距 */
border-radius: 15px; /* 圆角 */
max-width: 80%; /* 限制最大宽度 */
min-width: 80px; /* 设置最小宽度 */
min-height: 40px; /* 设置最小高度 */
word-wrap: break-word; /* 自动换行 */
position: relative; /* 时间戳定位 */
display: inline-block; /* 内容自适应宽度 */
box-sizing: border-box; /* 包括内边距和边框 */
flex-shrink: 0; /* 禁止高度被压缩 */
word-wrap: break-word; /* 自动换行,防止单行过长 */
white-space: normal; /* 允许正常换行 */
overflow: hidden;
}
.bot {
background-color: #f1f1f1; /* 灰色背景 */
color: black; /* 黑色字体 */
align-self: flex-start; /* 左对齐 */
margin-right: auto; /* 确保消息靠左 */
text-align: left; /* 内容左对齐 */
}
.user {
background-color: #2bc840; /* 蓝色背景 */
align-self: flex-end; /* 右对齐 */
margin-left: auto; /* 确保消息靠右 */
text-align: left; /* 内容左对齐 */
}
.timestamp {
font-size: 0.8em; /* 时间戳字体大小 */
color: rgba(0, 0, 0, 0.5); /* 半透明黑色 */
margin-bottom: 5px; /* 时间戳下方间距 */
display: block; /* 时间戳独占一行 */
}
#input-container {
display: flex;
padding: 10px;
background-color: #ffffff;
border-top: 1px solid #ccc;
}
#input {
flex: 1;
padding: 10px;
border: 1px solid #ccc;
border-radius: 5px;
margin-right: 10px;
}
#send {
padding: 10px;
border: none;
background-color: #007bff;
color: white;
border-radius: 5px;
cursor: pointer;
}
#send:hover {
background-color: #0056b3;
}
</style>
</head>
<body>
<div id="chat-container">
<div id="messages"></div>
<div id="input-container">
<input type="text" id="input" placeholder="输入消息..." />
<button id="send">发送</button>
</div>
</div>
<script>
const messagesDiv = document.getElementById('messages');
const input = document.getElementById('input');
const sendButton = document.getElementById('send');
// 生成唯一的 user_id
const userId = 'user_' + Math.random().toString(36).substr(2, 9);
// 连接 SSE
const eventSource = new EventSource(`/sse/${userId}`);
eventSource.onmessage = function(event) {
const message = JSON.parse(event.data);
const messageDiv = document.createElement('div');
messageDiv.className = 'message bot';
const timestamp = new Date(message.timestamp).toLocaleTimeString(); // 假设消息中有时间戳
messageDiv.innerHTML = `<div class="timestamp">${timestamp}</div>${message.content}`; // 显示时间
messagesDiv.appendChild(messageDiv);
messagesDiv.scrollTop = messagesDiv.scrollHeight; // 滚动到底部
};
sendButton.onclick = function() {
sendMessage();
};
input.addEventListener('keypress', function(event) {
if (event.key === 'Enter') {
sendMessage();
event.preventDefault(); // 防止换行
}
});
function sendMessage() {
const userMessage = input.value;
if (userMessage) {
const timestamp = new Date().toISOString(); // 获取当前时间戳
fetch('/message', {
method: 'POST',
headers: {
'Content-Type': 'application/json'
},
body: JSON.stringify({ user_id: userId, message: userMessage, timestamp: timestamp }) // 发送时间戳
});
const messageDiv = document.createElement('div');
messageDiv.className = 'message user';
const userTimestamp = new Date().toLocaleTimeString(); // 获取当前时间
messageDiv.innerHTML = `<div class="timestamp">${userTimestamp}</div>${userMessage}`; // 显示时间
messagesDiv.appendChild(messageDiv);
messagesDiv.scrollTop = messagesDiv.scrollHeight; // 滚动到底部
input.value = ''; // 清空输入框
}
}
</script>
</body>
</html>

204
channel/web/web_channel.py Normal file
View File

@@ -0,0 +1,204 @@
import sys
import time
import web
import json
from queue import Queue
from bridge.context import *
from bridge.reply import Reply, ReplyType
from channel.chat_channel import ChatChannel, check_prefix
from channel.chat_message import ChatMessage
from common.log import logger
from common.singleton import singleton
from config import conf
import os
class WebMessage(ChatMessage):
def __init__(
self,
msg_id,
content,
ctype=ContextType.TEXT,
from_user_id="User",
to_user_id="Chatgpt",
other_user_id="Chatgpt",
):
self.msg_id = msg_id
self.ctype = ctype
self.content = content
self.from_user_id = from_user_id
self.to_user_id = to_user_id
self.other_user_id = other_user_id
@singleton
class WebChannel(ChatChannel):
NOT_SUPPORT_REPLYTYPE = [ReplyType.VOICE]
_instance = None
# def __new__(cls):
# if cls._instance is None:
# cls._instance = super(WebChannel, cls).__new__(cls)
# return cls._instance
def __init__(self):
super().__init__()
self.message_queues = {} # 为每个用户存储一个消息队列
self.msg_id_counter = 0 # 添加消息ID计数器
def _generate_msg_id(self):
"""生成唯一的消息ID"""
self.msg_id_counter += 1
return str(int(time.time())) + str(self.msg_id_counter)
def send(self, reply: Reply, context: Context):
try:
if reply.type == ReplyType.IMAGE:
from PIL import Image
image_storage = reply.content
image_storage.seek(0)
img = Image.open(image_storage)
print("<IMAGE>")
img.show()
elif reply.type == ReplyType.IMAGE_URL:
import io
import requests
from PIL import Image
img_url = reply.content
pic_res = requests.get(img_url, stream=True)
image_storage = io.BytesIO()
for block in pic_res.iter_content(1024):
image_storage.write(block)
image_storage.seek(0)
img = Image.open(image_storage)
print(img_url)
img.show()
else:
print(reply.content)
# 获取用户ID如果没有则使用默认值
# user_id = getattr(context.get("session", None), "session_id", "default_user")
user_id = context["receiver"]
# 确保用户有对应的消息队列
if user_id not in self.message_queues:
self.message_queues[user_id] = Queue()
# 将消息放入对应用户的队列
message_data = {
"type": str(reply.type),
"content": reply.content,
"timestamp": time.time()
}
self.message_queues[user_id].put(message_data)
logger.debug(f"Message queued for user {user_id}")
except Exception as e:
logger.error(f"Error in send method: {e}")
raise
def sse_handler(self, user_id):
"""
Handle Server-Sent Events (SSE) for real-time communication.
"""
web.header('Content-Type', 'text/event-stream')
web.header('Cache-Control', 'no-cache')
web.header('Connection', 'keep-alive')
# 确保用户有消息队列
if user_id not in self.message_queues:
self.message_queues[user_id] = Queue()
try:
while True:
try:
# 发送心跳
yield f": heartbeat\n\n"
# 非阻塞方式获取消息
if not self.message_queues[user_id].empty():
message = self.message_queues[user_id].get_nowait()
yield f"data: {json.dumps(message)}\n\n"
time.sleep(0.5)
except Exception as e:
logger.error(f"SSE Error: {e}")
break
finally:
# 清理资源
if user_id in self.message_queues:
# 只有当队列为空时才删除
if self.message_queues[user_id].empty():
del self.message_queues[user_id]
def post_message(self):
"""
Handle incoming messages from users via POST request.
"""
try:
data = web.data() # 获取原始POST数据
json_data = json.loads(data)
user_id = json_data.get('user_id', 'default_user')
prompt = json_data.get('message', '')
except json.JSONDecodeError:
return json.dumps({"status": "error", "message": "Invalid JSON"})
except Exception as e:
return json.dumps({"status": "error", "message": str(e)})
if not prompt:
return json.dumps({"status": "error", "message": "No message provided"})
try:
msg_id = self._generate_msg_id()
context = self._compose_context(ContextType.TEXT, prompt, msg=WebMessage(msg_id,
prompt,
from_user_id=user_id,
other_user_id = user_id
))
context["isgroup"] = False
# context["session"] = web.storage(session_id=user_id)
if not context:
return json.dumps({"status": "error", "message": "Failed to process message"})
self.produce(context)
return json.dumps({"status": "success", "message": "Message received"})
except Exception as e:
logger.error(f"Error processing message: {e}")
return json.dumps({"status": "error", "message": "Internal server error"})
def chat_page(self):
"""Serve the chat HTML page."""
file_path = os.path.join(os.path.dirname(__file__), 'chat.html') # 使用绝对路径
with open(file_path, 'r', encoding='utf-8') as f:
return f.read()
def startup(self):
logger.setLevel("WARN")
print("\nWeb Channel is running. Send POST requests to /message to send messages.")
urls = (
'/sse/(.+)', 'SSEHandler', # 修改路由以接收用户ID
'/message', 'MessageHandler',
'/chat', 'ChatHandler',
)
port = conf().get("web_port", 9899)
app = web.application(urls, globals(), autoreload=False)
web.httpserver.runsimple(app.wsgifunc(), ("0.0.0.0", port))
class SSEHandler:
def GET(self, user_id):
return WebChannel().sse_handler(user_id)
class MessageHandler:
def POST(self):
return WebChannel().post_message()
class ChatHandler:
def GET(self):
return WebChannel().chat_page()

View File

@@ -20,7 +20,7 @@ from common.expired_dict import ExpiredDict
from common.log import logger
from common.singleton import singleton
from common.time_check import time_checker
from common.utils import convert_webp_to_png
from common.utils import convert_webp_to_png, remove_markdown_symbol
from config import conf, get_appdata_dir
from lib import itchat
from lib.itchat.content import *
@@ -213,9 +213,11 @@ class WechatChannel(ChatChannel):
def send(self, reply: Reply, context: Context):
receiver = context["receiver"]
if reply.type == ReplyType.TEXT:
reply.content = remove_markdown_symbol(reply.content)
itchat.send(reply.content, toUserName=receiver)
logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
elif reply.type == ReplyType.ERROR or reply.type == ReplyType.INFO:
reply.content = remove_markdown_symbol(reply.content)
itchat.send(reply.content, toUserName=receiver)
logger.info("[WX] sendMsg={}, receiver={}".format(reply, receiver))
elif reply.type == ReplyType.VOICE:

View File

@@ -55,6 +55,16 @@ class WechatMessage(ChatMessage):
self.ctype = ContextType.EXIT_GROUP
self.content = itchat_msg["Content"]
self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
elif any(note_patpat in itchat_msg["Content"] for note_patpat in notes_patpat): # 若有任何在notes_patpat列表中的字符串出现在NOTE中:
self.ctype = ContextType.PATPAT
self.content = itchat_msg["Content"]
if "拍了拍我" in itchat_msg["Content"]: # 识别中文
self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
elif "tickled my" in itchat_msg["Content"] or "tickled me" in itchat_msg["Content"]:
self.actual_user_nickname = re.findall(r'^(.*?)(?:tickled my|tickled me)', itchat_msg["Content"])[0]
else:
raise NotImplementedError("Unsupported note message: " + itchat_msg["Content"])
elif "你已添加了" in itchat_msg["Content"]: #通过好友请求
self.ctype = ContextType.ACCEPT_FRIEND
@@ -62,11 +72,6 @@ class WechatMessage(ChatMessage):
elif any(note_patpat in itchat_msg["Content"] for note_patpat in notes_patpat): # 若有任何在notes_patpat列表中的字符串出现在NOTE中:
self.ctype = ContextType.PATPAT
self.content = itchat_msg["Content"]
if is_group:
if "拍了拍我" in itchat_msg["Content"]: # 识别中文
self.actual_user_nickname = re.findall(r"\"(.*?)\"", itchat_msg["Content"])[0]
elif ("tickled my" in itchat_msg["Content"] or "tickled me" in itchat_msg["Content"]):
self.actual_user_nickname = re.findall(r'^(.*?)(?:tickled my|tickled me)', itchat_msg["Content"])[0]
else:
raise NotImplementedError("Unsupported note message: " + itchat_msg["Content"])
elif itchat_msg["Type"] == ATTACHMENT:

View File

@@ -17,7 +17,7 @@ from channel.wechatcom.wechatcomapp_client import WechatComAppClient
from channel.wechatcom.wechatcomapp_message import WechatComAppMessage
from common.log import logger
from common.singleton import singleton
from common.utils import compress_imgfile, fsize, split_string_by_utf8_length, convert_webp_to_png
from common.utils import compress_imgfile, fsize, split_string_by_utf8_length, convert_webp_to_png, remove_markdown_symbol
from config import conf, subscribe_msg
from voice.audio_convert import any_to_amr, split_audio
@@ -52,7 +52,7 @@ class WechatComAppChannel(ChatChannel):
def send(self, reply: Reply, context: Context):
receiver = context["receiver"]
if reply.type in [ReplyType.TEXT, ReplyType.ERROR, ReplyType.INFO]:
reply_text = reply.content
reply_text = remove_markdown_symbol(reply.content)
texts = split_string_by_utf8_length(reply_text, MAX_UTF8_LEN)
if len(texts) > 1:
logger.info("[wechatcom] text too long, split into {} parts".format(len(texts)))

View File

@@ -19,7 +19,7 @@ from channel.wechatmp.common import *
from channel.wechatmp.wechatmp_client import WechatMPClient
from common.log import logger
from common.singleton import singleton
from common.utils import split_string_by_utf8_length
from common.utils import split_string_by_utf8_length, remove_markdown_symbol
from config import conf
from voice.audio_convert import any_to_mp3, split_audio
@@ -81,7 +81,7 @@ class WechatMPChannel(ChatChannel):
receiver = context["receiver"]
if self.passive_reply:
if reply.type == ReplyType.TEXT or reply.type == ReplyType.INFO or reply.type == ReplyType.ERROR:
reply_text = reply.content
reply_text = remove_markdown_symbol(reply.content)
logger.info("[wechatmp] text cached, receiver {}\n{}".format(receiver, reply_text))
self.cache_dict[receiver].append(("text", reply_text))
elif reply.type == ReplyType.VOICE:

View File

@@ -59,6 +59,8 @@ LINKAI_4o = "linkai-4o"
GEMINI_PRO = "gemini-1.0-pro"
GEMINI_15_flash = "gemini-1.5-flash"
GEMINI_15_PRO = "gemini-1.5-pro"
GEMINI_20_flash_exp = "gemini-2.0-flash-exp"
GLM_4 = "glm-4"
GLM_4_PLUS = "glm-4-plus"
@@ -69,6 +71,17 @@ GLM_4_0520 = "glm-4-0520"
GLM_4_AIR = "glm-4-air"
GLM_4_AIRX = "glm-4-airx"
CLAUDE_3_OPUS = "claude-3-opus-latest"
CLAUDE_3_OPUS_0229 = "claude-3-opus-20240229"
CLAUDE_35_SONNET = "claude-3-5-sonnet-latest" # 带 latest 标签的模型名称,会不断更新指向最新发布的模型
CLAUDE_35_SONNET_1022 = "claude-3-5-sonnet-20241022" # 带具体日期的模型名称,会固定为该日期发布的模型
CLAUDE_35_SONNET_0620 = "claude-3-5-sonnet-20240620"
CLAUDE_3_SONNET = "claude-3-sonnet-20240229"
CLAUDE_3_HAIKU = "claude-3-haiku-20240307"
MODEL_LIST = [
GPT35, GPT35_0125, GPT35_1106, "gpt-3.5-turbo-16k",
O1, O1_MINI, GPT_4o, GPT_4O_0806, GPT_4o_MINI, GPT4_TURBO, GPT4_TURBO_PREVIEW, GPT4_TURBO_01_25, GPT4_TURBO_11_06, GPT4, GPT4_32k, GPT4_06_13, GPT4_32k_06_13,
@@ -76,8 +89,8 @@ MODEL_LIST = [
XUNFEI,
ZHIPU_AI, GLM_4, GLM_4_PLUS, GLM_4_flash, GLM_4_LONG, GLM_4_ALLTOOLS, GLM_4_0520, GLM_4_AIR, GLM_4_AIRX,
MOONSHOT, MiniMax,
GEMINI, GEMINI_PRO, GEMINI_15_flash, GEMINI_15_PRO,
"claude", "claude-3-haiku", "claude-3-sonnet", "claude-3-opus", "claude-3-opus-20240229", "claude-3.5-sonnet",
GEMINI, GEMINI_PRO, GEMINI_15_flash, GEMINI_15_PRO,GEMINI_20_flash_exp,
CLAUDE_3_OPUS, CLAUDE_3_OPUS_0229, CLAUDE_35_SONNET, CLAUDE_35_SONNET_1022, CLAUDE_35_SONNET_0620, CLAUDE_3_SONNET, CLAUDE_3_HAIKU, "claude", "claude-3-haiku", "claude-3-sonnet", "claude-3-opus", "claude-3.5-sonnet",
"moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k",
QWEN, QWEN_TURBO, QWEN_PLUS, QWEN_MAX,
LINKAI_35, LINKAI_4_TURBO, LINKAI_4o

View File

@@ -2,7 +2,7 @@ from bridge.context import Context, ContextType
from bridge.reply import Reply, ReplyType
from common.log import logger
from linkai import LinkAIClient, PushMsg
from config import conf, pconf, plugin_config, available_setting
from config import conf, pconf, plugin_config, available_setting, write_plugin_config
from plugins import PluginManager
import time
@@ -51,10 +51,10 @@ class ChatClient(LinkAIClient):
local_config["voice_reply_voice"] = False
if config.get("admin_password"):
if not plugin_config.get("Godcmd"):
plugin_config["Godcmd"] = {"password": config.get("admin_password"), "admin_users": []}
if not pconf("Godcmd"):
write_plugin_config({"Godcmd": {"password": config.get("admin_password"), "admin_users": []} })
else:
plugin_config["Godcmd"]["password"] = config.get("admin_password")
pconf("Godcmd")["password"] = config.get("admin_password")
PluginManager().instances["GODCMD"].reload()
if config.get("group_app_map") and pconf("linkai"):

View File

@@ -1,5 +1,6 @@
import io
import os
import re
from urllib.parse import urlparse
from PIL import Image
from common.log import logger
@@ -68,3 +69,10 @@ def convert_webp_to_png(webp_image):
except Exception as e:
logger.error(f"Failed to convert WEBP to PNG: {e}")
raise
def remove_markdown_symbol(text: str):
# 移除markdown格式目前先移除**
if not text:
return text
return re.sub(r'\*\*(.*?)\*\*', r'\1', text)

View File

@@ -179,6 +179,7 @@ available_setting = {
"Minimax_api_key": "",
"Minimax_group_id": "",
"Minimax_base_url": "",
"web_port": 9899,
}
@@ -341,6 +342,14 @@ def write_plugin_config(pconf: dict):
for k in pconf:
plugin_config[k.lower()] = pconf[k]
def remove_plugin_config(name: str):
"""
移除待重新加载的插件全局配置
:param name: 待重载的插件名
"""
global plugin_config
plugin_config.pop(name.lower(), None)
def pconf(plugin_name: str) -> dict:
"""

View File

@@ -313,7 +313,7 @@ class Godcmd(Plugin):
except Exception as e:
ok, result = False, "你没有设置私有GPT模型"
elif cmd == "reset":
if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI]:
if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI, const.CLAUDEAPI]:
bot.sessions.clear_session(session_id)
if Bridge().chat_bots.get(bottype):
Bridge().chat_bots.get(bottype).sessions.clear_session(session_id)
@@ -477,7 +477,7 @@ class Godcmd(Plugin):
return model
def reload(self):
gconf = plugin_config[self.name]
gconf = pconf(self.name)
if gconf:
if gconf.get("password"):
self.password = gconf["password"]

View File

@@ -98,6 +98,8 @@
如果不想创建 `plugins/linkai/config.json` 配置,可以直接通过 `$linkai sum open` 指令开启该功能。
也可以通过私聊(全局 `config.json` 中的 `linkai_app_code`)或者群聊绑定(通过`group_app_map`参数配置)的应用来开启该功能在LinkAI平台 [应用配置](https://link-ai.tech/console/factory) 里添加并开启**内容总结**插件。
#### 使用
功能开启后,向机器人发送 **文件****分享链接卡片**、**图片** 即可生成摘要,进一步可以与文件或链接的内容进行多轮对话。如果需要关闭某种类型的内容总结,设置 `summary`配置中的type字段即可。

View File

@@ -9,7 +9,7 @@ from common.expired_dict import ExpiredDict
from common import const
import os
from .utils import Util
from config import plugin_config
from config import plugin_config, conf
@plugins.register(
@@ -28,7 +28,7 @@ class LinkAI(Plugin):
# 未加载到配置,使用模板中的配置
self.config = self._load_config_template()
if self.config:
self.mj_bot = MJBot(self.config.get("midjourney"))
self.mj_bot = MJBot(self.config.get("midjourney"), self._fetch_group_app_code)
self.sum_config = {}
if self.config:
self.sum_config = self.config.get("summary")
@@ -56,7 +56,8 @@ class LinkAI(Plugin):
return
if context.type != ContextType.IMAGE:
_send_info(e_context, "正在为你加速生成摘要,请稍后")
res = LinkSummary().summary_file(file_path)
app_code = self._fetch_app_code(context)
res = LinkSummary().summary_file(file_path, app_code)
if not res:
if context.type != ContextType.IMAGE:
_set_reply_text("因为神秘力量无法获取内容,请稍后再试吧", e_context, level=ReplyType.TEXT)
@@ -74,7 +75,8 @@ class LinkAI(Plugin):
if not LinkSummary().check_url(context.content):
return
_send_info(e_context, "正在为你加速生成摘要,请稍后")
res = LinkSummary().summary_url(context.content)
app_code = self._fetch_app_code(context)
res = LinkSummary().summary_url(context.content, app_code)
if not res:
_set_reply_text("因为神秘力量无法获取文章内容,请稍后再试吧~", e_context, level=ReplyType.TEXT)
return
@@ -169,7 +171,7 @@ class LinkAI(Plugin):
return
if len(cmd) == 3 and cmd[1] == "sum" and (cmd[2] == "open" or cmd[2] == "close"):
# 知识库开关指令
# 总结对话开关指令
if not Util.is_admin(e_context):
_set_reply_text("需要管理员权限执行", e_context, level=ReplyType.ERROR)
return
@@ -192,14 +194,36 @@ class LinkAI(Plugin):
return
def _is_summary_open(self, context) -> bool:
if not self.sum_config or not self.sum_config.get("enabled"):
return False
if context.kwargs.get("isgroup") and not self.sum_config.get("group_enabled"):
return False
support_type = self.sum_config.get("type") or ["FILE", "SHARING"]
if context.type.name not in support_type and context.type.name != "TEXT":
return False
return True
# 获取远程应用插件状态
remote_enabled = False
if context.kwargs.get("isgroup"):
# 群聊场景只查询群对应的app_code
group_name = context.get("msg").from_user_nickname
app_code = self._fetch_group_app_code(group_name)
if app_code:
if context.type.name in ["FILE", "SHARING"]:
remote_enabled = Util.fetch_app_plugin(app_code, "内容总结")
else:
# 非群聊场景使用全局app_code
app_code = conf().get("linkai_app_code")
if app_code:
if context.type.name in ["FILE", "SHARING"]:
remote_enabled = Util.fetch_app_plugin(app_code, "内容总结")
# 基础条件:总开关开启且消息类型符合要求
base_enabled = (
self.sum_config
and self.sum_config.get("enabled")
and (context.type.name in (
self.sum_config.get("type") or ["FILE", "SHARING"]) or context.type.name == "TEXT")
)
# 群聊:需要满足(总开关和群开关)或远程插件开启
if context.kwargs.get("isgroup"):
return (base_enabled and self.sum_config.get("group_enabled")) or remote_enabled
# 非群聊:只需要满足总开关或远程插件开启
return base_enabled or remote_enabled
# LinkAI 对话任务处理
def _is_chat_task(self, e_context: EventContext):
@@ -230,6 +254,19 @@ class LinkAI(Plugin):
app_code = group_mapping.get(group_name) or group_mapping.get("ALL_GROUP")
return app_code
def _fetch_app_code(self, context) -> str:
"""
根据主配置或者群聊名称获取对应的应用code,优先获取群聊配置的应用code
:param context: 上下文
:return: 应用code
"""
app_code = conf().get("linkai_app_code")
if context.kwargs.get("isgroup"):
# 群聊场景只查询群对应的app_code
group_name = context.get("msg").from_user_nickname
app_code = self._fetch_group_app_code(group_name)
return app_code
def get_help_text(self, verbose=False, **kwargs):
trigger_prefix = _get_trigger_prefix()
help_text = "用于集成 LinkAI 提供的知识库、Midjourney绘画、文档总结、联网搜索等能力。\n\n"
@@ -254,7 +291,7 @@ class LinkAI(Plugin):
plugin_conf = json.load(f)
plugin_conf["midjourney"]["enabled"] = False
plugin_conf["summary"]["enabled"] = False
plugin_config["linkai"] = plugin_conf
write_plugin_config({"linkai": plugin_conf})
return plugin_conf
except Exception as e:
logger.exception(e)

View File

@@ -10,6 +10,7 @@ from bridge.context import ContextType
from plugins import EventContext, EventAction
from .utils import Util
INVALID_REQUEST = 410
NOT_FOUND_ORIGIN_IMAGE = 461
NOT_FOUND_TASK = 462
@@ -67,10 +68,11 @@ class MJTask:
# midjourney bot
class MJBot:
def __init__(self, config):
def __init__(self, config, fetch_group_app_code):
self.base_url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/img/midjourney"
self.headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
self.config = config
self.fetch_group_app_code = fetch_group_app_code
self.tasks = {}
self.temp_dict = {}
self.tasks_lock = threading.Lock()
@@ -98,7 +100,7 @@ class MJBot:
return TaskType.VARIATION
elif cmd_list[0].lower() == f"{trigger_prefix}mjr":
return TaskType.RESET
elif context.type == ContextType.IMAGE_CREATE and self.config.get("use_image_create_prefix") and self.config.get("enabled"):
elif context.type == ContextType.IMAGE_CREATE and self.config.get("use_image_create_prefix") and self._is_mj_open(context):
return TaskType.GENERATE
def process_mj_task(self, mj_type: TaskType, e_context: EventContext):
@@ -129,8 +131,8 @@ class MJBot:
self._set_reply_text(f"Midjourney绘画已{tips_text}", e_context, level=ReplyType.INFO)
return
if not self.config.get("enabled"):
logger.warn("Midjourney绘画未开启请查看 plugins/linkai/config.json 中的配置")
if not self._is_mj_open(context):
logger.warn("Midjourney绘画未开启请查看 plugins/linkai/config.json 中的配置或者在LinkAI平台 应用中添加/打开”MJ“插件")
self._set_reply_text(f"Midjourney绘画未开启", e_context, level=ReplyType.INFO)
return
@@ -409,6 +411,25 @@ class MJBot:
result.append(task)
return result
def _is_mj_open(self, context) -> bool:
# 获取远程应用插件状态
remote_enabled = False
if context.kwargs.get("isgroup"):
# 群聊场景只查询群对应的app_code
group_name = context.get("msg").from_user_nickname
app_code = self.fetch_group_app_code(group_name)
if app_code:
remote_enabled = Util.fetch_app_plugin(app_code, "Midjourney")
else:
# 非群聊场景使用全局app_code
app_code = conf().get("linkai_app_code")
if app_code:
remote_enabled = Util.fetch_app_plugin(app_code, "Midjourney")
# 本地配置
base_enabled = self.config.get("enabled")
return base_enabled or remote_enabled
def _send(channel, reply: Reply, context, retry_cnt=0):
try:

View File

@@ -9,20 +9,26 @@ class LinkSummary:
def __init__(self):
pass
def summary_file(self, file_path: str):
def summary_file(self, file_path: str, app_code: str):
file_body = {
"file": open(file_path, "rb"),
"name": file_path.split("/")[-1],
"name": file_path.split("/")[-1]
}
body = {
"app_code": app_code
}
url = self.base_url() + "/v1/summary/file"
res = requests.post(url, headers=self.headers(), files=file_body, timeout=(5, 300))
logger.info(f"[LinkSum] file summary, app_code={app_code}")
res = requests.post(url, headers=self.headers(), files=file_body, data=body, timeout=(5, 300))
return self._parse_summary_res(res)
def summary_url(self, url: str):
def summary_url(self, url: str, app_code: str):
url = html.unescape(url)
body = {
"url": url
"url": url,
"app_code": app_code
}
logger.info(f"[LinkSum] url summary, app_code={app_code}")
res = requests.post(url=self.base_url() + "/v1/summary/url", headers=self.headers(), json=body, timeout=(5, 180))
return self._parse_summary_res(res)
@@ -48,7 +54,7 @@ class LinkSummary:
def _parse_summary_res(self, res):
if res.status_code == 200:
res = res.json()
logger.debug(f"[LinkSum] url summary, res={res}")
logger.debug(f"[LinkSum] summary result, res={res}")
if res.get("code") == 200:
data = res.get("data")
return {

View File

@@ -1,7 +1,9 @@
import requests
from common.log import logger
from config import global_config
from bridge.reply import Reply, ReplyType
from plugins.event import EventContext, EventAction
from config import conf
class Util:
@staticmethod
@@ -26,3 +28,23 @@ class Util:
reply = Reply(level, content)
e_context["reply"] = reply
e_context.action = EventAction.BREAK_PASS
@staticmethod
def fetch_app_plugin(app_code: str, plugin_name: str) -> bool:
try:
headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
# do http request
base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
params = {"app_code": app_code}
res = requests.get(url=base_url + "/v1/app/info", params=params, headers=headers, timeout=(5, 10))
if res.status_code == 200:
plugins = res.json().get("data").get("plugins")
for plugin in plugins:
if plugin.get("name") and plugin.get("name") == plugin_name:
return True
return False
else:
logger.warning(f"[LinkAI] find app info exception, res={res}")
return False
except Exception as e:
return False

View File

@@ -1,6 +1,6 @@
import os
import json
from config import pconf, plugin_config, conf
from config import pconf, plugin_config, conf, write_plugin_config
from common.log import logger
@@ -24,13 +24,13 @@ class Plugin:
plugin_conf = json.load(f)
# 写入全局配置内存
plugin_config[self.name] = plugin_conf
write_plugin_config({self.name: plugin_conf})
logger.debug(f"loading plugin config, plugin_name={self.name}, conf={plugin_conf}")
return plugin_conf
def save_config(self, config: dict):
try:
plugin_config[self.name] = config
write_plugin_config({self.name: config})
# 写入全局配置
global_config_path = "./plugins/config.json"
if os.path.exists(global_config_path):

View File

@@ -9,7 +9,7 @@ import sys
from common.log import logger
from common.singleton import singleton
from common.sorted_dict import SortedDict
from config import conf, write_plugin_config
from config import conf, remove_plugin_config, write_plugin_config
from .event import *
@@ -151,6 +151,8 @@ class PluginManager:
self.disable_plugin(name)
failed_plugins.append(name)
continue
if name in self.instances:
self.instances[name].handlers.clear()
self.instances[name] = instance
for event in instance.handlers:
if event not in self.listening_plugins:
@@ -161,10 +163,13 @@ class PluginManager:
def reload_plugin(self, name: str):
name = name.upper()
remove_plugin_config(name)
if name in self.instances:
for event in self.listening_plugins:
if name in self.listening_plugins[event]:
self.listening_plugins[event].remove(name)
if name in self.instances:
self.instances[name].handlers.clear()
del self.instances[name]
self.activate_plugins()
return True

View File

@@ -180,6 +180,7 @@ class Role(Plugin):
e_context["reply"] = reply
e_context.action = EventAction.BREAK_PASS
else:
e_context["context"]["generate_breaked_by"] = EventAction.BREAK
prompt = self.roleplays[sessionid].action(content)
e_context["context"].type = ContextType.TEXT
e_context["context"].content = prompt

View File

@@ -12,10 +12,6 @@
"url": "https://github.com/lanvent/plugin_summary.git",
"desc": "总结聊天记录的插件"
},
"timetask": {
"url": "https://github.com/haikerapples/timetask.git",
"desc": "一款定时任务系统的插件"
},
"Apilot": {
"url": "https://github.com/6vision/Apilot.git",
"desc": "通过api直接查询早报、热榜、快递、天气等实用信息的插件"

View File

@@ -1,7 +1,7 @@
openai==0.27.8
HTMLParser>=0.0.2
PyQRCode>=1.2.1
qrcode>=7.4.2
PyQRCode==1.2.1
qrcode==7.4.2
requests>=2.28.2
chardet>=5.1.0
Pillow