xinyin025/LangBot
1
0
Fork 0
mirror of https://github.com/langbot-app/LangBot.git synced 2026-06-08 14:56:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: rag engine (#1492)

Browse Source 
* feat: add embeddings model management (#1461)

* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add knowledge page

* feat: add api for uploading files

* kb

* delete ap

* feat: add functions

* fix: modify rag database

* feat: add embeddings model management (#1461)

* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add knowledge page

* feat: add api for uploading files

* feat: add sidebar for rag and related i18n

* feat: add knowledge base page

* feat: basic entities of kb

* feat: complete support_type for 302ai and compshare requester

* perf: format

* perf: ruff check --fix

* feat: basic definition

* feat: rag fe framework

* perf: en comments

* feat: modify the rag.py

* perf: definitions

* fix: success method bad params

* fix: bugs

* fix: bug

* feat: kb dialog action

* fix: create knwoledge base issue

* fix: kb get api format

* fix: kb get api not contains model uuid

* fix: api bug

* fix: the fucking logger

* feat(fe): component for available apis

* fix: embbeding and chunking

* fix: ensure File.status is set correctly after storing data to avoid null values

* fix: add functions for deleting files

* feat(fe): file uploading

* perf: adjust ui

* fix: file be deleted twice

* feat(fe): complete kb ui

* fix: ui bugs

* fix: no longer require Query for invoking embedding

* feat: add embedder

* fix: delete embedding models file

* chore: stash

* chore: stash

* feat(rag): make embedding and retrieving available

* feat(rag): all APIs ok

* fix: delete utils

* feat: rag pipeline backend

* feat: combine kb with pipeline

* fix: .md file parse failed

* perf: debug output

* feat: add functions for frontend of kb

* perf(rag): ui and related apis

* perf(rag): use badge show doc status

* perf: open kb detail dialog after creating

* fix: linter error

* deps: remove sentence-transformers

* perf: description of default pipeline

* feat: add html and epub

* chore: no longer supports epub

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: WangCham <651122857@qq.com>
This commit is contained in:
Junyan Qin (Chin)
2025-07-19 22:06:11 +08:00
committed by GitHub
parent c34d54a6cb 13f4ed8d2c
commit 277d1b0e30
120 changed files with 5224 additions and 643 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pkg/platform/logger.py
View File

@@ -119,7 +119,7 @@ class EventLogger:
async def _truncate_logs(self):
if len(self.logs) > MAX_LOG_COUNT:
for i in range(DELETE_COUNT_PER_TIME):
for image_key in self.logs[i].images:
for image_key in self.logs[i].images: # type: ignore
await self.ap.storage_mgr.storage_provider.delete(image_key)
self.logs = self.logs[DELETE_COUNT_PER_TIME:]

19
pkg/platform/sources/discord.py
View File

@@ -654,10 +654,10 @@ class DiscordMessageConverter(adapter.MessageConverter):
# 确保路径没有空字节
clean_path = ele.path.replace('\x00', '')
clean_path = os.path.abspath(clean_path)
if not os.path.exists(clean_path):
continue # 跳过不存在的文件
try:
with open(clean_path, 'rb') as f:
image_bytes = f.read()
@@ -677,12 +677,13 @@ class DiscordMessageConverter(adapter.MessageConverter):
filename = f'{uuid.uuid4()}.webp'
# 默认保持PNG
except Exception as e:
print(f"Error reading image file {clean_path}: {e}")
print(f'Error reading image file {clean_path}: {e}')
continue # 跳过读取失败的文件
if image_bytes:
# 使用BytesIO创建文件对象，避免路径问题
import io
image_files.append(discord.File(fp=io.BytesIO(image_bytes), filename=filename))
elif isinstance(ele, platform_message.Plain):
text_string += ele.text
@@ -1003,25 +1004,25 @@ class DiscordAdapter(adapter.MessagePlatformAdapter):
async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
msg_to_send, image_files = await self.message_converter.yiri2target(message)
try:
# 获取频道对象
channel = self.bot.get_channel(int(target_id))
if channel is None:
# 如果本地缓存中没有，尝试从API获取
channel = await self.bot.fetch_channel(int(target_id))
args = {
'content': msg_to_send,
}
if len(image_files) > 0:
args['files'] = image_files
await channel.send(**args)
except Exception as e:
await self.logger.error(f"Discord send_message failed: {e}")
await self.logger.error(f'Discord send_message failed: {e}')
raise e
async def reply_message(

8
pkg/platform/sources/lark.py
View File

@@ -378,15 +378,15 @@ class LarkAdapter(adapter.MessagePlatformAdapter):
if 'im.message.receive_v1' == type:
try:
event = await self.event_converter.target2yiri(p2v1, self.api_client)
except Exception as e:
await self.logger.error(f"Error in lark callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in lark callback: {traceback.format_exc()}')
if event.__class__ in self.listeners:
await self.listeners[event.__class__](event, self)
return {'code': 200, 'message': 'ok'}
except Exception as e:
await self.logger.error(f"Error in lark callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in lark callback: {traceback.format_exc()}')
return {'code': 500, 'message': 'error'}
async def on_message(event: lark_oapi.im.v1.P2ImMessageReceiveV1):

5
pkg/platform/sources/nakuru.py
View File

@@ -72,8 +72,9 @@ class NakuruProjectMessageConverter(adapter_model.MessageConverter):
content=content_list,
)
nakuru_forward_node_list.append(nakuru_forward_node)
except Exception as e:
except Exception:
import traceback
traceback.print_exc()
nakuru_msg_list.append(nakuru_forward_node_list)
@@ -276,7 +277,7 @@ class NakuruAdapter(adapter_model.MessagePlatformAdapter):
# 注册监听器
self.bot.receiver(source_cls.__name__)(listener_wrapper)
except Exception as e:
self.logger.error(f"Error in nakuru register_listener: {traceback.format_exc()}")
self.logger.error(f'Error in nakuru register_listener: {traceback.format_exc()}')
raise e
def unregister_listener(

4
pkg/platform/sources/officialaccount.py
View File

@@ -125,8 +125,8 @@ class OfficialAccountAdapter(adapter.MessagePlatformAdapter):
self.bot_account_id = event.receiver_id
try:
return await callback(await self.event_converter.target2yiri(event), self)
except Exception as e:
await self.logger.error(f"Error in officialaccount callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in officialaccount callback: {traceback.format_exc()}')
if event_type == platform_events.FriendMessage:
self.bot.on_message('text')(on_message)

9
pkg/platform/sources/qqofficial.py
View File

@@ -154,10 +154,7 @@ class QQOfficialAdapter(adapter.MessagePlatformAdapter):
raise ParamNotEnoughError('QQ官方机器人缺少相关配置项，请查看文档或联系管理员')
self.bot = QQOfficialClient(
app_id=config['appid'],
secret=config['secret'],
token=config['token'],
logger=self.logger
app_id=config['appid'], secret=config['secret'], token=config['token'], logger=self.logger
)
async def reply_message(
@@ -224,8 +221,8 @@ class QQOfficialAdapter(adapter.MessagePlatformAdapter):
self.bot_account_id = 'justbot'
try:
return await callback(await self.event_converter.target2yiri(event), self)
except Exception as e:
await self.logger.error(f"Error in qqofficial callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in qqofficial callback: {traceback.format_exc()}')
if event_type == platform_events.FriendMessage:
self.bot.on_message('DIRECT_MESSAGE_CREATE')(on_message)

8
pkg/platform/sources/slack.py
View File

@@ -104,7 +104,9 @@ class SlackAdapter(adapter.MessagePlatformAdapter):
if missing_keys:
raise ParamNotEnoughError('Slack机器人缺少相关配置项，请查看文档或联系管理员')
self.bot = SlackClient(bot_token=self.config['bot_token'], signing_secret=self.config['signing_secret'], logger=self.logger)
self.bot = SlackClient(
bot_token=self.config['bot_token'], signing_secret=self.config['signing_secret'], logger=self.logger
)
async def reply_message(
self,
@@ -139,8 +141,8 @@ class SlackAdapter(adapter.MessagePlatformAdapter):
self.bot_account_id = 'SlackBot'
try:
return await callback(await self.event_converter.target2yiri(event, self.bot), self)
except Exception as e:
await self.logger.error(f"Error in slack callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in slack callback: {traceback.format_exc()}')
if event_type == platform_events.FriendMessage:
self.bot.on_message('im')(on_message)

4
pkg/platform/sources/telegram.py
View File

@@ -160,8 +160,8 @@ class TelegramAdapter(adapter.MessagePlatformAdapter):
try:
lb_event = await self.event_converter.target2yiri(update, self.bot, self.bot_account_id)
await self.listeners[type(lb_event)](lb_event, self)
except Exception as e:
await self.logger.error(f"Error in telegram callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in telegram callback: {traceback.format_exc()}')
self.application = ApplicationBuilder().token(self.config['token']).build()
self.bot = self.application.bot

401
pkg/platform/sources/wechatpad.py
View File

@@ -1,5 +1,4 @@
import requests
import websockets
import websocket
import json
import time
@@ -10,32 +9,25 @@ from libs.wechatpad_api.client import WeChatPadClient
import typing
import asyncio
import traceback
import time
import re
import base64
import uuid
import json
import os
import copy
import datetime
import threading
import quart
import aiohttp
from .. import adapter
from ...pipeline.longtext.strategies import forward
from ...core import app
from ..types import message as platform_message
from ..types import events as platform_events
from ..types import entities as platform_entities
from ...utils import image
from ..logger import EventLogger
import xml.etree.ElementTree as ET
from typing import Optional, List, Tuple
from typing import Optional, Tuple
from functools import partial
import logging
class WeChatPadMessageConverter(adapter.MessageConverter):
def __init__(self, config: dict, logger: logging.Logger):
@@ -44,19 +36,14 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
self.logger = logger
@staticmethod
async def yiri2target(
message_chain: platform_message.MessageChain
) -> list[dict]:
async def yiri2target(message_chain: platform_message.MessageChain) -> list[dict]:
content_list = []
current_file_path = os.path.abspath(__file__)
for component in message_chain:
if isinstance(component, platform_message.At):
content_list.append({"type": "at", "target": component.target})
content_list.append({'type': 'at', 'target': component.target})
elif isinstance(component, platform_message.Plain):
content_list.append({"type": "text", "content": component.text})
content_list.append({'type': 'text', 'content': component.text})
elif isinstance(component, platform_message.Image):
if component.url:
async with httpx.AsyncClient() as client:
@@ -68,15 +55,16 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
else:
raise Exception('获取文件失败')
# pass
content_list.append({"type": "image", "image": base64_str})
content_list.append({'type': 'image', 'image': base64_str})
elif component.base64:
content_list.append({"type": "image", "image": component.base64})
content_list.append({'type': 'image', 'image': component.base64})
elif isinstance(component, platform_message.WeChatEmoji):
content_list.append(
{'type': 'WeChatEmoji', 'emoji_md5': component.emoji_md5, 'emoji_size': component.emoji_size})
{'type': 'WeChatEmoji', 'emoji_md5': component.emoji_md5, 'emoji_size': component.emoji_size}
)
elif isinstance(component, platform_message.Voice):
content_list.append({"type": "voice", "data": component.url, "duration": component.length, "forma": 0})
content_list.append({'type': 'voice', 'data': component.url, 'duration': component.length, 'forma': 0})
elif isinstance(component, platform_message.WeChatAppMsg):
content_list.append({'type': 'WeChatAppMsg', 'app_msg': component.app_msg})
elif isinstance(component, platform_message.Forward):
@@ -86,7 +74,6 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
return content_list
async def target2yiri(
self,
message: dict,
@@ -97,11 +84,12 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
message_list = []
bot_wxid = self.config['wxid']
ats_bot = False # 是否被@
content = message["content"]["str"]
content = message['content']['str']
content_no_preifx = content # 群消息则去掉前缀
is_group_message = self._is_group_message(message)
if is_group_message:
ats_bot = self._ats_bot(message, bot_account_id)
self.logger.info(f"ats_bot: {ats_bot}; bot_account_id: {bot_account_id}; bot_wxid: {bot_wxid}")
if "@所有人" in content:
message_list.append(platform_message.AtAll())
@@ -116,7 +104,7 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
content_no_preifx, _ = self._extract_content_and_sender(content)
msg_type = message["msg_type"]
msg_type = message['msg_type']
# 映射消息类型到处理器方法
handler_map = {
@@ -138,11 +126,7 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
return platform_message.MessageChain(message_list)
async def _handler_text(
self,
message: Optional[dict],
content_no_preifx: str
) -> platform_message.MessageChain:
async def _handler_text(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
"""处理文本消息 (msg_type=1)"""
if message and self._is_group_message(message):
pattern = r'@\S{1,20}'
@@ -150,16 +134,12 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
return platform_message.MessageChain([platform_message.Plain(content_no_preifx)])
async def _handler_image(
self,
message: Optional[dict],
content_no_preifx: str
) -> platform_message.MessageChain:
async def _handler_image(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
"""处理图像消息 (msg_type=3)"""
try:
image_xml = content_no_preifx
if not image_xml:
return platform_message.MessageChain([platform_message.Unknown("[图片内容为空]")])
return platform_message.MessageChain([platform_message.Unknown('[图片内容为空]')])
root = ET.fromstring(image_xml)
# 提取img标签的属性
@@ -169,28 +149,22 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
cdnthumburl = img_tag.get('cdnthumburl')
# cdnmidimgurl = img_tag.get('cdnmidimgurl')
image_data = self.bot.cdn_download(aeskey=aeskey, file_type=1, file_url=cdnthumburl)
if image_data["Data"]['FileData'] == '':
if image_data['Data']['FileData'] == '':
image_data = self.bot.cdn_download(aeskey=aeskey, file_type=2, file_url=cdnthumburl)
base64_str = image_data["Data"]['FileData']
base64_str = image_data['Data']['FileData']
# self.logger.info(f"data:image/png;base64,{base64_str}")
elements = [
platform_message.Image(base64=f"data:image/png;base64,{base64_str}"),
platform_message.Image(base64=f'data:image/png;base64,{base64_str}'),
# platform_message.WeChatForwardImage(xml_data=image_xml) # 微信消息转发
]
return platform_message.MessageChain(elements)
except Exception as e:
self.logger.error(f"处理图片失败: {str(e)}")
return platform_message.MessageChain([platform_message.Unknown("[图片处理失败]")])
self.logger.error(f'处理图片失败: {str(e)}')
return platform_message.MessageChain([platform_message.Unknown('[图片处理失败]')])
async def _handler_voice(
self,
message: Optional[dict],
content_no_preifx: str
) -> platform_message.MessageChain:
async def _handler_voice(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
"""处理语音消息 (msg_type=34)"""
message_List = []
try:
@@ -206,39 +180,33 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
bufid = voicemsg.get('bufid')
length = voicemsg.get('voicelength')
voice_data = self.bot.get_msg_voice(buf_id=str(bufid), length=int(length), msgid=str(new_msg_id))
audio_base64 = voice_data["Data"]['Base64']
audio_base64 = voice_data['Data']['Base64']
# 验证语音数据有效性
if not audio_base64:
message_List.append(platform_message.Unknown(text="[语音内容为空]"))
message_List.append(platform_message.Unknown(text='[语音内容为空]'))
return platform_message.MessageChain(message_List)
# 转换为平台支持的语音格式（如 Silk 格式）
voice_element = platform_message.Voice(
base64=f"data:audio/silk;base64,{audio_base64}"
)
voice_element = platform_message.Voice(base64=f'data:audio/silk;base64,{audio_base64}')
message_List.append(voice_element)
except KeyError as e:
self.logger.error(f"语音数据字段缺失: {str(e)}")
message_List.append(platform_message.Unknown(text="[语音数据解析失败]"))
self.logger.error(f'语音数据字段缺失: {str(e)}')
message_List.append(platform_message.Unknown(text='[语音数据解析失败]'))
except Exception as e:
self.logger.error(f"处理语音消息异常: {str(e)}")
message_List.append(platform_message.Unknown(text="[语音处理失败]"))
self.logger.error(f'处理语音消息异常: {str(e)}')
message_List.append(platform_message.Unknown(text='[语音处理失败]'))
return platform_message.MessageChain(message_List)
async def _handler_compound(
self,
message: Optional[dict],
content_no_preifx: str
) -> platform_message.MessageChain:
async def _handler_compound(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
"""处理复合消息 (msg_type=49)，根据子类型分派"""
try:
xml_data = ET.fromstring(content_no_preifx)
appmsg_data = xml_data.find('.//appmsg')
if appmsg_data:
data_type = appmsg_data.findtext('.//type', "")
data_type = appmsg_data.findtext('.//type', '')
# 二次分派处理器
sub_handler_map = {
'57': self._handler_compound_quote,
@@ -247,9 +215,9 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
'74': self._handler_compound_file,
'33': self._handler_compound_mini_program,
'36': self._handler_compound_mini_program,
'2000': partial(self._handler_compound_unsupported, text="[转账消息]"),
'2001': partial(self._handler_compound_unsupported, text="[红包消息]"),
'51': partial(self._handler_compound_unsupported, text="[视频号消息]"),
'2000': partial(self._handler_compound_unsupported, text='[转账消息]'),
'2001': partial(self._handler_compound_unsupported, text='[红包消息]'),
'51': partial(self._handler_compound_unsupported, text='[视频号消息]'),
}
handler = sub_handler_map.get(data_type, self._handler_compound_unsupported)
@@ -260,56 +228,54 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
else:
return platform_message.MessageChain([platform_message.Unknown(text=content_no_preifx)])
except Exception as e:
self.logger.error(f"解析复合消息失败: {str(e)}")
self.logger.error(f'解析复合消息失败: {str(e)}')
return platform_message.MessageChain([platform_message.Unknown(text=content_no_preifx)])
async def _handler_compound_quote(
self,
message: Optional[dict],
xml_data: ET.Element
self, message: Optional[dict], xml_data: ET.Element
) -> platform_message.MessageChain:
"""处理引用消息 (data_type=57)"""
message_list = []
# self.logger.info("_handler_compound_quote", ET.tostring(xml_data, encoding='unicode'))
# self.logger.info("_handler_compound_quote", ET.tostring(xml_data, encoding='unicode'))
appmsg_data = xml_data.find('.//appmsg')
quote_data = "" # 引用原文
quote_data = '' # 引用原文
quote_id = None # 引用消息的原发送者
tousername = None # 接收方: 所属微信的wxid
user_data = "" # 用户消息
user_data = '' # 用户消息
sender_id = xml_data.findtext('.//fromusername') # 发送方：单聊用户/群member
# 引用消息转发
if appmsg_data:
user_data = appmsg_data.findtext('.//title') or ""
user_data = appmsg_data.findtext('.//title') or ''
quote_data = appmsg_data.find('.//refermsg').findtext('.//content')
quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr')
message_list.append(
platform_message.WeChatAppMsg(
app_msg=ET.tostring(appmsg_data, encoding='unicode'))
)
message_list.append(platform_message.WeChatAppMsg(app_msg=ET.tostring(appmsg_data, encoding='unicode')))
if message:
tousername = message['to_user_name']["str"]
tousername = message['to_user_name']['str']
_ = quote_id
_ = tousername
if quote_data:
quote_data_message_list = platform_message.MessageChain()
# 文本消息
try:
if "<msg>" not in quote_data:
if '<msg>' not in quote_data:
quote_data_message_list.append(platform_message.Plain(quote_data))
else:
# 引用消息展开
quote_data_xml = ET.fromstring(quote_data)
if quote_data_xml.find("img"):
if quote_data_xml.find('img'):
quote_data_message_list.extend(await self._handler_image(None, quote_data))
elif quote_data_xml.find("voicemsg"):
elif quote_data_xml.find('voicemsg'):
quote_data_message_list.extend(await self._handler_voice(None, quote_data))
elif quote_data_xml.find("videomsg"):
elif quote_data_xml.find('videomsg'):
quote_data_message_list.extend(await self._handler_default(None, quote_data)) # 先不处理
else:
# appmsg
quote_data_message_list.extend(await self._handler_compound(None, quote_data))
except Exception as e:
self.logger.error(f"处理引用消息异常 expcetion:{e}")
self.logger.error(f'处理引用消息异常 expcetion:{e}')
quote_data_message_list.append(platform_message.Plain(quote_data))
message_list.append(
platform_message.Quote(
@@ -324,15 +290,11 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
return platform_message.MessageChain(message_list)
async def _handler_compound_file(
self,
message: dict,
xml_data: ET.Element
) -> platform_message.MessageChain:
async def _handler_compound_file(self, message: dict, xml_data: ET.Element) -> platform_message.MessageChain:
"""处理文件消息 (data_type=6)"""
file_data = xml_data.find('.//appmsg')
if file_data.findtext('.//type', "") == "74":
if file_data.findtext('.//type', '') == '74':
return None
else:
@@ -355,22 +317,21 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
file_data = self.bot.cdn_download(aeskey=aeskey, file_type=5, file_url=cdnthumburl)
file_base64 = file_data["Data"]['FileData']
file_base64 = file_data['Data']['FileData']
# print(file_data)
file_size = file_data["Data"]['TotalSize']
file_size = file_data['Data']['TotalSize']
# print(file_base64)
return platform_message.MessageChain([
platform_message.WeChatFile(file_id=file_id, file_name=file_name, file_size=file_size,
file_base64=file_base64),
platform_message.WeChatForwardFile(xml_data=xml_data_str)
])
return platform_message.MessageChain(
[
platform_message.WeChatFile(
file_id=file_id, file_name=file_name, file_size=file_size, file_base64=file_base64
),
platform_message.WeChatForwardFile(xml_data=xml_data_str),
]
)
async def _handler_compound_link(
self,
message: dict,
xml_data: ET.Element
) -> platform_message.MessageChain:
async def _handler_compound_link(self, message: dict, xml_data: ET.Element) -> platform_message.MessageChain:
"""处理链接消息（如公众号文章、外部网页）"""
message_list = []
try:
@@ -383,56 +344,38 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
link_title=appmsg.findtext('title', ''),
link_desc=appmsg.findtext('des', ''),
link_url=appmsg.findtext('url', ''),
link_thumb_url=appmsg.findtext("thumburl", '') # 这个字段拿不到
link_thumb_url=appmsg.findtext('thumburl', ''), # 这个字段拿不到
)
)
# 还没有发链接的接口, 暂时还需要自己构造appmsg, 先用WeChatAppMsg。
message_list.append(
platform_message.WeChatAppMsg(
app_msg=ET.tostring(appmsg, encoding='unicode')
)
)
message_list.append(platform_message.WeChatAppMsg(app_msg=ET.tostring(appmsg, encoding='unicode')))
except Exception as e:
self.logger.error(f"解析链接消息失败: {str(e)}")
self.logger.error(f'解析链接消息失败: {str(e)}')
return platform_message.MessageChain(message_list)
async def _handler_compound_mini_program(
self,
message: dict,
xml_data: ET.Element
self, message: dict, xml_data: ET.Element
) -> platform_message.MessageChain:
"""处理小程序消息（如小程序卡片、服务通知）"""
xml_data_str = ET.tostring(xml_data, encoding='unicode')
return platform_message.MessageChain([
platform_message.WeChatForwardMiniPrograms(xml_data=xml_data_str)
])
return platform_message.MessageChain([platform_message.WeChatForwardMiniPrograms(xml_data=xml_data_str)])
async def _handler_default(
self,
message: Optional[dict],
content_no_preifx: str
) -> platform_message.MessageChain:
async def _handler_default(self, message: Optional[dict], content_no_preifx: str) -> platform_message.MessageChain:
"""处理未知消息类型"""
if message:
msg_type = message["msg_type"]
msg_type = message['msg_type']
else:
msg_type = ""
return platform_message.MessageChain([
platform_message.Unknown(text=f"[未知消息类型 msg_type:{msg_type}]")
])
msg_type = ''
return platform_message.MessageChain([platform_message.Unknown(text=f'[未知消息类型 msg_type:{msg_type}]')])
def _handler_compound_unsupported(
self,
message: dict,
xml_data: str,
text: Optional[str] = None
self, message: dict, xml_data: str, text: Optional[str] = None
) -> platform_message.MessageChain:
"""处理未支持复合消息类型(msg_type=49)子类型"""
if not text:
text = f"[xml_data={xml_data}]"
text = f'[xml_data={xml_data}]'
content_list = []
content_list.append(
platform_message.Unknown(text=f"[处理未支持复合消息类型[msg_type=49]|{text}"))
content_list.append(platform_message.Unknown(text=f'[处理未支持复合消息类型[msg_type=49]|{text}'))
return platform_message.MessageChain(content_list)
@@ -441,7 +384,7 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
ats_bot = False
try:
to_user_name = message['to_user_name']['str'] # 接收方: 所属微信的wxid
raw_content = message["content"]["str"] # 原始消息内容
raw_content = message['content']['str'] # 原始消息内容
content_no_prefix, _ = self._extract_content_and_sender(raw_content)
# 直接艾特机器人（这个有bug，当被引用的消息里面有@bot,会套娃
# ats_bot = ats_bot or (f"@{bot_account_id}" in content_no_prefix)
@@ -452,7 +395,7 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
msg_source = message.get('msg_source', '') or ''
if len(msg_source) > 0:
msg_source_data = ET.fromstring(msg_source)
at_user_list = msg_source_data.findtext("atuserlist") or ""
at_user_list = msg_source_data.findtext('atuserlist') or ''
ats_bot = ats_bot or (to_user_name in at_user_list)
# 引用bot
if message.get('msg_type', 0) == 49:
@@ -463,7 +406,7 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
quote_id = appmsg_data.find('.//refermsg').findtext('.//chatusr') # 引用消息的原发送者
ats_bot = ats_bot or (quote_id == tousername)
except Exception as e:
self.logger.error(f"_ats_bot got except: {e}")
self.logger.error(f'_ats_bot got except: {e}')
finally:
return ats_bot
@@ -489,21 +432,21 @@ class WeChatPadMessageConverter(adapter.MessageConverter):
try:
# 检查消息开头，如果有 wxid_sbitaz0mt65n22:\n 则删掉
# add: 有些用户的wxid不是上述格式。换成user_name:
regex = re.compile(r"^[a-zA-Z0-9_\-]{5,20}:")
line_split = raw_content.split("\n")
regex = re.compile(r'^[a-zA-Z0-9_\-]{5,20}:')
line_split = raw_content.split('\n')
if len(line_split) > 0 and regex.match(line_split[0]):
raw_content = "\n".join(line_split[1:])
sender_id = line_split[0].strip(":")
raw_content = '\n'.join(line_split[1:])
sender_id = line_split[0].strip(':')
return raw_content, sender_id
except Exception as e:
self.logger.error(f"_extract_content_and_sender got except: {e}")
self.logger.error(f'_extract_content_and_sender got except: {e}')
finally:
return raw_content, None
# 是否是群消息
def _is_group_message(self, message: dict) -> bool:
from_user_name = message['from_user_name']['str']
return from_user_name.endswith("@chatroom")
return from_user_name.endswith('@chatroom')
class WeChatPadEventConverter(adapter.EventConverter):
@@ -514,9 +457,7 @@ class WeChatPadEventConverter(adapter.EventConverter):
self.logger = logger
@staticmethod
async def yiri2target(
event: platform_events.MessageEvent
) -> dict:
async def yiri2target(event: platform_events.MessageEvent) -> dict:
pass
async def target2yiri(
@@ -526,10 +467,12 @@ class WeChatPadEventConverter(adapter.EventConverter):
) -> platform_events.MessageEvent:
# 排除公众号以及微信团队消息
if event['from_user_name']['str'].startswith('gh_') \
or event['from_user_name']['str']=='weixin'\
or event['from_user_name']['str'] == "newsapp"\
or event['from_user_name']['str'] == self.config["wxid"]:
if (
event['from_user_name']['str'].startswith('gh_')
or event['from_user_name']['str'] == 'weixin'
or event['from_user_name']['str'] == 'newsapp'
or event['from_user_name']['str'] == self.config['wxid']
):
return None
message_chain = await self.message_converter.target2yiri(copy.deepcopy(event), bot_account_id)
@@ -538,7 +481,7 @@ class WeChatPadEventConverter(adapter.EventConverter):
if '@chatroom' in event['from_user_name']['str']:
# 找出开头的 wxid_ 字符串，以:结尾
sender_wxid = event['content']['str'].split(":")[0]
sender_wxid = event['content']['str'].split(':')[0]
return platform_events.GroupMessage(
sender=platform_entities.GroupMember(
@@ -550,13 +493,13 @@ class WeChatPadEventConverter(adapter.EventConverter):
name=event['from_user_name']['str'],
permission=platform_entities.Permission.Member,
),
special_title="",
special_title='',
join_timestamp=0,
last_speak_timestamp=0,
mute_time_remaining=0,
),
message_chain=message_chain,
time=event["create_time"],
time=event['create_time'],
source_platform_object=event,
)
else:
@@ -567,13 +510,13 @@ class WeChatPadEventConverter(adapter.EventConverter):
remark='',
),
message_chain=message_chain,
time=event["create_time"],
time=event['create_time'],
source_platform_object=event,
)
class WeChatPadAdapter(adapter.MessagePlatformAdapter):
name: str = "WeChatPad" # 定义适配器名称
name: str = 'WeChatPad' # 定义适配器名称
bot: WeChatPadClient
quart_app: quart.Quart
@@ -606,27 +549,21 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
# self.ap.logger.debug(f"Gewechat callback event: {data}")
# print(data)
try:
event = await self.event_converter.target2yiri(data.copy(), self.bot_account_id)
except Exception as e:
await self.logger.error(f"Error in wechatpad callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in wechatpad callback: {traceback.format_exc()}')
if event.__class__ in self.listeners:
await self.listeners[event.__class__](event, self)
return 'ok'
async def _handle_message(
self,
message: platform_message.MessageChain,
target_id: str
):
async def _handle_message(self, message: platform_message.MessageChain, target_id: str):
"""统一消息处理核心逻辑"""
content_list = await self.message_converter.yiri2target(message)
# print(content_list)
at_targets = [item["target"] for item in content_list if item["type"] == "at"]
at_targets = [item['target'] for item in content_list if item['type'] == 'at']
# print(at_targets)
# 处理@逻辑
at_targets = at_targets or []
@@ -634,7 +571,7 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
if at_targets:
member_info = self.bot.get_chatroom_member_detail(
target_id,
)["Data"]["member_data"]["chatroom_member_list"]
)['Data']['member_data']['chatroom_member_list']
# 处理消息组件
for msg in content_list:
@@ -642,63 +579,51 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
if msg['type'] == 'text' and at_targets:
at_nick_name_list = []
for member in member_info:
if member["user_name"] in at_targets:
if member['user_name'] in at_targets:
at_nick_name_list.append(f'@{member["nick_name"]}')
msg['content'] = f'{" ".join(at_nick_name_list)} {msg["content"]}'
# 统一消息派发
handler_map = {
'text': lambda msg: self.bot.send_text_message(
to_wxid=target_id,
message=msg['content'],
ats=at_targets
to_wxid=target_id, message=msg['content'], ats=at_targets
),
'image': lambda msg: self.bot.send_image_message(
to_wxid=target_id,
img_url=msg["image"],
ats = at_targets
to_wxid=target_id, img_url=msg['image'], ats=at_targets
),
'WeChatEmoji': lambda msg: self.bot.send_emoji_message(
to_wxid=target_id,
emoji_md5=msg['emoji_md5'],
emoji_size=msg['emoji_size']
to_wxid=target_id, emoji_md5=msg['emoji_md5'], emoji_size=msg['emoji_size']
),
'voice': lambda msg: self.bot.send_voice_message(
to_wxid=target_id,
voice_data=msg['data'],
voice_duration=msg["duration"],
voice_forma=msg["forma"],
voice_duration=msg['duration'],
voice_forma=msg['forma'],
),
'WeChatAppMsg': lambda msg: self.bot.send_app_message(
to_wxid=target_id,
app_message=msg['app_msg'],
type=0,
),
'at': lambda msg: None
'at': lambda msg: None,
}
if handler := handler_map.get(msg['type']):
handler(msg)
# self.ap.logger.warning(f"未处理的消息类型: {ret}")
else:
self.ap.logger.warning(f"未处理的消息类型: {msg['type']}")
self.ap.logger.warning(f'未处理的消息类型: {msg["type"]}')
continue
async def send_message(
self,
target_type: str,
target_id: str,
message: platform_message.MessageChain
):
async def send_message(self, target_type: str, target_id: str, message: platform_message.MessageChain):
"""主动发送消息"""
return await self._handle_message(message, target_id)
async def reply_message(
self,
message_source: platform_events.MessageEvent,
message: platform_message.MessageChain,
quote_origin: bool = False
self,
message_source: platform_events.MessageEvent,
message: platform_message.MessageChain,
quote_origin: bool = False,
):
"""回复消息"""
if message_source.source_platform_object:
@@ -709,58 +634,49 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
pass
def register_listener(
self,
event_type: typing.Type[platform_events.Event],
callback: typing.Callable[[platform_events.Event, adapter.MessagePlatformAdapter], None]
self,
event_type: typing.Type[platform_events.Event],
callback: typing.Callable[[platform_events.Event, adapter.MessagePlatformAdapter], None],
):
self.listeners[event_type] = callback
def unregister_listener(
self,
event_type: typing.Type[platform_events.Event],
callback: typing.Callable[[platform_events.Event, adapter.MessagePlatformAdapter], None]
self,
event_type: typing.Type[platform_events.Event],
callback: typing.Callable[[platform_events.Event, adapter.MessagePlatformAdapter], None],
):
pass
async def run_async(self):
if not self.config["admin_key"] and not self.config["token"]:
raise RuntimeError("无wechatpad管理密匙，请填入配置文件后重启")
if not self.config['admin_key'] and not self.config['token']:
raise RuntimeError('无wechatpad管理密匙，请填入配置文件后重启')
else:
if self.config["token"]:
self.bot = WeChatPadClient(
self.config['wechatpad_url'],
self.config["token"]
)
if self.config['token']:
self.bot = WeChatPadClient(self.config['wechatpad_url'], self.config['token'])
data = self.bot.get_login_status()
self.ap.logger.info(data)
if data["Code"] == 300 and data["Text"] == "你已退出微信":
if data['Code'] == 300 and data['Text'] == '你已退出微信':
response = requests.post(
f"{self.config['wechatpad_url']}/admin/GenAuthKey1?key={self.config['admin_key']}",
json={"Count": 1, "Days": 365}
f'{self.config["wechatpad_url"]}/admin/GenAuthKey1?key={self.config["admin_key"]}',
json={'Count': 1, 'Days': 365},
)
if response.status_code != 200:
raise Exception(f"获取token失败: {response.text}")
self.config["token"] = response.json()["Data"][0]
raise Exception(f'获取token失败: {response.text}')
self.config['token'] = response.json()['Data'][0]
elif not self.config["token"]:
elif not self.config['token']:
response = requests.post(
f"{self.config['wechatpad_url']}/admin/GenAuthKey1?key={self.config['admin_key']}",
json={"Count": 1, "Days": 365}
f'{self.config["wechatpad_url"]}/admin/GenAuthKey1?key={self.config["admin_key"]}',
json={'Count': 1, 'Days': 365},
)
if response.status_code != 200:
raise Exception(f"获取token失败: {response.text}")
self.config["token"] = response.json()["Data"][0]
raise Exception(f'获取token失败: {response.text}')
self.config['token'] = response.json()['Data'][0]
self.bot = WeChatPadClient(
self.config['wechatpad_url'],
self.config["token"],
logger=self.logger
)
self.ap.logger.info(self.config["token"])
self.bot = WeChatPadClient(self.config['wechatpad_url'], self.config['token'], logger=self.logger)
self.ap.logger.info(self.config['token'])
thread_1 = threading.Event()
def wechat_login_process():
# 不登录，这些先注释掉，避免登陆态尝试拉qrcode。
# login_data =self.bot.get_login_qr()
@@ -768,67 +684,54 @@ class WeChatPadAdapter(adapter.MessagePlatformAdapter):
# url = login_data['Data']["QrCodeUrl"]
# self.ap.logger.info(login_data)
profile =self.bot.get_profile()
profile = self.bot.get_profile()
self.ap.logger.info(profile)
self.bot_account_id = profile["Data"]["userInfo"]["nickName"]["str"]
self.config["wxid"] = profile["Data"]["userInfo"]["userName"]["str"]
self.bot_account_id = profile['Data']['userInfo']['nickName']['str']
self.config['wxid'] = profile['Data']['userInfo']['userName']['str']
thread_1.set()
# asyncio.create_task(wechat_login_process)
threading.Thread(target=wechat_login_process).start()
def connect_websocket_sync() -> None:
thread_1.wait()
uri = f"{self.config['wechatpad_ws']}/GetSyncMsg?key={self.config['token']}"
self.ap.logger.info(f"Connecting to WebSocket: {uri}")
uri = f'{self.config["wechatpad_ws"]}/GetSyncMsg?key={self.config["token"]}'
self.ap.logger.info(f'Connecting to WebSocket: {uri}')
def on_message(ws, message):
try:
data = json.loads(message)
self.ap.logger.debug(f"Received message: {data}")
self.ap.logger.debug(f'Received message: {data}')
# 这里需要确保ws_message是同步的，或者使用asyncio.run调用异步方法
asyncio.run(self.ws_message(data))
except json.JSONDecodeError:
self.ap.logger.error(f"Non-JSON message: {message[:100]}...")
self.ap.logger.error(f'Non-JSON message: {message[:100]}...')
def on_error(ws, error):
self.ap.logger.error(f"WebSocket error: {str(error)[:200]}")
self.ap.logger.error(f'WebSocket error: {str(error)[:200]}')
def on_close(ws, close_status_code, close_msg):
self.ap.logger.info("WebSocket closed, reconnecting...")
self.ap.logger.info('WebSocket closed, reconnecting...')
time.sleep(5)
connect_websocket_sync() # 自动重连
def on_open(ws):
self.ap.logger.info("WebSocket connected successfully!")
self.ap.logger.info('WebSocket connected successfully!')
ws = websocket.WebSocketApp(
uri,
on_message=on_message,
on_error=on_error,
on_close=on_close,
on_open=on_open
)
ws.run_forever(
ping_interval=60,
ping_timeout=20
uri, on_message=on_message, on_error=on_error, on_close=on_close, on_open=on_open
)
ws.run_forever(ping_interval=60, ping_timeout=20)
# 直接调用同步版本（会阻塞）
# connect_websocket_sync()
# 这行代码会在WebSocket连接断开后才会执行
# self.ap.logger.info("WebSocket client thread started")
thread = threading.Thread(
target=connect_websocket_sync,
name="WebSocketClientThread",
daemon=True
)
thread = threading.Thread(target=connect_websocket_sync, name='WebSocketClientThread', daemon=True)
thread.start()
self.ap.logger.info("WebSocket client thread started")
self.ap.logger.info('WebSocket client thread started')
async def kill(self) -> bool:
pass

6
pkg/platform/sources/wecom.py
View File

@@ -157,7 +157,7 @@ class WecomAdapter(adapter.MessagePlatformAdapter):
token=config['token'],
EncodingAESKey=config['EncodingAESKey'],
contacts_secret=config['contacts_secret'],
logger=self.logger
logger=self.logger,
)
async def reply_message(
@@ -201,8 +201,8 @@ class WecomAdapter(adapter.MessagePlatformAdapter):
self.bot_account_id = event.receiver_id
try:
return await callback(await self.event_converter.target2yiri(event), self)
except Exception as e:
await self.logger.error(f"Error in wecom callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in wecom callback: {traceback.format_exc()}')
if event_type == platform_events.FriendMessage:
self.bot.on_message('text')(on_message)

6
pkg/platform/sources/wecomcs.py
View File

@@ -145,7 +145,7 @@ class WecomCSAdapter(adapter.MessagePlatformAdapter):
secret=config['secret'],
token=config['token'],
EncodingAESKey=config['EncodingAESKey'],
logger=self.logger
logger=self.logger,
)
async def reply_message(
@@ -178,8 +178,8 @@ class WecomCSAdapter(adapter.MessagePlatformAdapter):
self.bot_account_id = event.receiver_id
try:
return await callback(await self.event_converter.target2yiri(event), self)
except Exception as e:
await self.logger.error(f"Error in wecomcs callback: {traceback.format_exc()}")
except Exception:
await self.logger.error(f'Error in wecomcs callback: {traceback.format_exc()}')
if event_type == platform_events.FriendMessage:
self.bot.on_message('text')(on_message)