J1147
/
CoW
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
Browse Source

Merge branch 'master' of https://github.com/whw23/chatgpt-on-wechat

master
unknown 7 months ago
parent
22c7f8fe9e 3d47be1f49
commit
dd95f849d4
24 changed files with 293 additions and 57 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +13
    -18
      README.md
  2. +4
    -1
      bot/bot_factory.py
  3. +3
    -2
      bot/chatgpt/chat_gpt_session.py
  4. +133
    -0
      bot/claudeapi/claude_api_bot.py
  5. +6
    -2
      bot/gemini/google_gemini_bot.py
  6. +11
    -4
      bot/linkai/link_ai_bot.py
  7. +2
    -1
      bot/xunfei/xunfei_spark_bot.py
  8. +5
    -2
      bridge/bridge.py
  9. +1
    -1
      bridge/reply.py
  10. +5
    -3
      channel/chat_channel.py
  11. +0
    -1
      channel/wechat/wechat_channel.py
  12. +5
    -2
      common/const.py
  13. +1
    -0
      config-template.json
  14. +3
    -1
      config.py
  15. +13
    -0
      docs/version/old-version.md
  16. +2
    -2
      plugins/godcmd/godcmd.py
  17. +16
    -14
      plugins/plugin_manager.py
  18. +8
    -0
      plugins/source.json
  19. +3
    -0
      requirements-optional.txt
  20. +1
    -1
      requirements.txt
  21. +3
    -1
      voice/audio_convert.py
  22. +1
    -1
      voice/baidu/baidu_voice.py
  23. +50
    -0
      voice/edge/edge_voice.py
  24. +4
    -0
      voice/factory.py

+ 13
- 18
README.md View File

@@ -1,11 +1,11 @@
# 简介

> 本项目是基于大模型的智能对话机器人，支持微信、企业微信、公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/LinkAI/ZhipuAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。
> 本项目是基于大模型的智能对话机器人，支持企业微信、微信公众号、飞书、钉钉接入，可选择GPT3.5/GPT4.0/Claude/文心一言/讯飞星火/通义千问/Gemini/LinkAI/ZhipuAI，能处理文本、语音和图片，通过插件访问操作系统和互联网等外部资源，支持基于自有知识库定制企业AI应用。

最新版本支持的功能如下：

- [x] **多端部署：** 有多种部署方式可选择且功能完备，目前已支持个人微信、微信公众号和、企业微信、飞书、钉钉等部署方式
- [x] **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, claude, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM
- [x] **多端部署：** 有多种部署方式可选择且功能完备，目前已支持微信生态下公众号、企业微信应用、飞书、钉钉等部署方式
- [x] **基础对话：** 私聊及群聊的消息智能回复，支持多轮会话上下文记忆，支持 GPT-3.5, GPT-4, Claude-3, Gemini, 文心一言, 讯飞星火, 通义千问，ChatGLM-4
- [x] **语音能力：** 可识别语音消息，通过文字或语音回复，支持 azure, baidu, google, openai(whisper/tts) 等多种语音模型
- [x] **图像能力：** 支持图片生成、图片识别、图生图（如照片修复），可选择 Dall-E-3, stable diffusion, replicate, midjourney, CogView-3, vision模型
- [x] **丰富插件：** 支持个性化插件扩展，已实现多角色切换、文字冒险、敏感词过滤、聊天记录总结、文档总结和对话、联网搜索等插件
@@ -35,7 +35,11 @@ SaaS服务、私有化部署、稳定托管接入 等多种模式。

# 更新日志

>**2023.11.11：** [1.5.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.3) 和 [1.5.4版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.4)，新增Google Gemini、通义千问模型
>**2024.03.26：** [1.5.8版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.8) 和 [1.5.7版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.7)，新增 GLM-4、Claude-3 模型，edge-tts 语音支持

>**2024.01.26：** [1.5.6版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.6) 和 [1.5.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.5)，钉钉接入，tool插件升级，4-turbo模型更新

>**2023.11.11：** [1.5.3版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.3) 和 [1.5.4版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.4)，新增通义千问模型、Google Gemini

>**2023.11.10：** [1.5.2版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.5.2)，新增飞书通道、图像识别对话、黑名单配置

@@ -47,19 +51,9 @@ SaaS服务、私有化部署、稳定托管接入 等多种模式。

>**2023.08.08：** 接入百度文心一言模型，通过 [插件](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins/linkai) 支持 Midjourney 绘图

>**2023.06.12：** 接入 [LinkAI](https://link-ai.tech/console) 平台，可在线创建领域知识库，并接入微信、公众号及企业微信中，打造专属客服机器人。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。

>**2023.04.26：** 支持企业微信应用号部署，兼容插件，并支持语音图片交互，私人助理理想选择，[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatcom/README.md)。(contributed by [@lanvent](https://github.com/lanvent) in [#944](https://github.com/zhayujie/chatgpt-on-wechat/pull/944))

>**2023.04.05：** 支持微信公众号部署，兼容插件，并支持语音图片交互，[使用文档](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/wechatmp/README.md)。(contributed by [@JS00000](https://github.com/JS00000) in [#686](https://github.com/zhayujie/chatgpt-on-wechat/pull/686))

>**2023.04.05：** 增加能让ChatGPT使用工具的`tool`插件，[使用文档](https://github.com/goldfishh/chatgpt-on-wechat/blob/master/plugins/tool/README.md)。工具相关issue可反馈至[chatgpt-tool-hub](https://github.com/goldfishh/chatgpt-tool-hub)。(contributed by [@goldfishh](https://github.com/goldfishh) in [#663](https://github.com/zhayujie/chatgpt-on-wechat/pull/663))

>**2023.03.25：** 支持插件化开发，目前已实现 多角色切换、文字冒险游戏、管理员指令、Stable Diffusion等插件，使用参考 [#578](https://github.com/zhayujie/chatgpt-on-wechat/issues/578)。(contributed by [@lanvent](https://github.com/lanvent) in [#565](https://github.com/zhayujie/chatgpt-on-wechat/pull/565))

>**2023.03.09：** 基于 `whisper API`(后续已接入更多的语音`API`服务) 实现对微信语音消息的解析和回复，添加配置项 `"speech_recognition":true` 即可启用，使用参考 [#415](https://github.com/zhayujie/chatgpt-on-wechat/issues/415)。(contributed by [wanggang1987](https://github.com/wanggang1987) in [#385](https://github.com/zhayujie/chatgpt-on-wechat/pull/385))
>**2023.06.12：** 接入 [LinkAI](https://link-ai.tech/console) 平台，可在线创建领域知识库，打造专属客服机器人。使用参考 [接入文档](https://link-ai.tech/platform/link-app/wechat)。

>**2023.02.09：** 扫码登录存在账号限制风险，请谨慎使用，参考[#58](https://github.com/AutumnWhj/ChatGPT-wechat-bot/issues/158)
更早更新日志查看: [归档日志](/docs/version/old-version.md)

# 快速开始

@@ -118,7 +112,8 @@ pip3 install -r requirements-optional.txt
# config.json文件内容示例
{
"open_ai_api_key": "YOUR API KEY", # 填入上面创建的 OpenAI API KEY
"model": "gpt-3.5-turbo", # 模型名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei
"model": "gpt-3.5-turbo", # 模型名称, 支持 gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-4, wenxin, xunfei, claude-3-opus-20240229
"claude_api_key":"YOUR API KEY" # 如果选用claude3模型的话，配置这个key，同时如想使用生图，语音等功能，仍需配置open_ai_api_key
"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
@@ -192,7 +187,7 @@ pip3 install -r requirements-optional.txt
python3 app.py # windows环境下该命令通常为 python app.py
```

终端输出二维码后，使用微信进行扫码，当输出 "Start auto replying" 时表示自动回复程序已经成功运行了（注意：用于登录的微信需要在支付处已完成实名认证）。扫码登录后你的账号就成为机器人了，可以在微信手机端通过配置的关键词触发自动回复 (任意好友发送消息给你，或是自己发消息给好友)，参考[#142](https://github.com/zhayujie/chatgpt-on-wechat/issues/142)。
终端输出二维码后，使用微信进行扫码，当输出 "Start auto replying" 时表示自动回复程序已经成功运行了（注意：用于登录的微信需要在支付处已完成实名认证）。扫码登录后你的账号就成为机器人了，可以在手机端通过配置的关键词触发自动回复 (任意好友发送消息给你，或是自己发消息给好友)，参考[#142](https://github.com/zhayujie/chatgpt-on-wechat/issues/142)。

### 2.服务器部署



+ 4
- 1
bot/bot_factory.py View File

@@ -2,6 +2,7 @@
channel factory
"""
from common import const
from common.log import logger


def create_bot(bot_type):
@@ -43,7 +44,9 @@ def create_bot(bot_type):
elif bot_type == const.CLAUDEAI:
from bot.claude.claude_ai_bot import ClaudeAIBot
return ClaudeAIBot()

elif bot_type == const.CLAUDEAPI:
from bot.claudeapi.claude_api_bot import ClaudeAPIBot
return ClaudeAPIBot()
elif bot_type == const.QWEN:
from bot.ali.ali_qwen_bot import AliQwenBot
return AliQwenBot()


+ 3
- 2
bot/chatgpt/chat_gpt_session.py View File

@@ -62,13 +62,14 @@ def num_tokens_from_messages(messages, model):

import tiktoken

if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106"]:
if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106", "moonshot"]:
return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
elif model in ["gpt-4-0314", "gpt-4-0613", "gpt-4-32k", "gpt-4-32k-0613", "gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k", "gpt-3.5-turbo-16k-0613", "gpt-35-turbo-16k", "gpt-4-turbo-preview",
"gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW]:
return num_tokens_from_messages(messages, model="gpt-4")

elif model.startswith("claude-3"):
return num_tokens_from_messages(messages, model="gpt-3.5-turbo")
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:


+ 133
- 0
bot/claudeapi/claude_api_bot.py View File

@@ -0,0 +1,133 @@
# encoding:utf-8

import time

import openai
import openai.error
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.session_manager import SessionManager
from bridge.context import ContextType
from bridge.reply import Reply, ReplyType
from common.log import logger
from config import conf

user_session = dict()


# OpenAI对话模型API (可用)
class ClaudeAPIBot(Bot, OpenAIImage):
def __init__(self):
super().__init__()
self.claudeClient = anthropic.Anthropic(
api_key=conf().get("claude_api_key")
)
openai.api_key = conf().get("open_ai_api_key")
if conf().get("open_ai_api_base"):
openai.api_base = conf().get("open_ai_api_base")
proxy = conf().get("proxy")
if proxy:
openai.proxy = proxy

self.sessions = SessionManager(ChatGPTSession, model=conf().get("model") or "text-davinci-003")

def reply(self, query, context=None):
# acquire reply content
if context and context.type:
if context.type == ContextType.TEXT:
logger.info("[CLAUDE_API] query={}".format(query))
session_id = context["session_id"]
reply = None
if query == "#清除记忆":
self.sessions.clear_session(session_id)
reply = Reply(ReplyType.INFO, "记忆已清除")
elif query == "#清除所有":
self.sessions.clear_all_session()
reply = Reply(ReplyType.INFO, "所有人记忆已清除")
else:
session = self.sessions.session_query(query, session_id)
result = self.reply_text(session)
logger.info(result)
total_tokens, completion_tokens, reply_content = (
result["total_tokens"],
result["completion_tokens"],
result["content"],
)
logger.debug(
"[CLAUDE_API] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(str(session), session_id, reply_content, completion_tokens)
)

if total_tokens == 0:
reply = Reply(ReplyType.ERROR, reply_content)
else:
self.sessions.session_reply(reply_content, session_id, total_tokens)
reply = Reply(ReplyType.TEXT, reply_content)
return reply
elif context.type == ContextType.IMAGE_CREATE:
ok, retstring = self.create_img(query, 0)
reply = None
if ok:
reply = Reply(ReplyType.IMAGE_URL, retstring)
else:
reply = Reply(ReplyType.ERROR, retstring)
return reply

def reply_text(self, session: ChatGPTSession, 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)
)
# response = openai.Completion.create(prompt=str(session), **self.args)
res_content = response.content[0].text.strip().replace("<|endoftext|>", "")
total_tokens = response.usage.input_tokens+response.usage.output_tokens
completion_tokens = response.usage.output_tokens
logger.info("[CLAUDE_API] reply={}".format(res_content))
return {
"total_tokens": total_tokens,
"completion_tokens": completion_tokens,
"content": res_content,
}
except Exception as e:
need_retry = retry_count < 2
result = {"completion_tokens": 0, "content": "我现在有点累了，等会再来吧"}
if isinstance(e, openai.error.RateLimitError):
logger.warn("[CLAUDE_API] RateLimitError: {}".format(e))
result["content"] = "提问太快啦，请休息一下再问我吧"
if need_retry:
time.sleep(20)
elif isinstance(e, openai.error.Timeout):
logger.warn("[CLAUDE_API] Timeout: {}".format(e))
result["content"] = "我没有收到你的消息"
if need_retry:
time.sleep(5)
elif isinstance(e, openai.error.APIConnectionError):
logger.warn("[CLAUDE_API] APIConnectionError: {}".format(e))
need_retry = False
result["content"] = "我连接不到你的网络"
else:
logger.warn("[CLAUDE_API] Exception: {}".format(e))
need_retry = False
self.sessions.clear_session(session.session_id)

if need_retry:
logger.warn("[CLAUDE_API] 第{}次重试".format(retry_count + 1))
return self.reply_text(session, retry_count + 1)
else:
return result

def _model_mapping(self, model) -> str:
if model == "claude-3-opus":
return "claude-3-opus-20240229"
elif model == "claude-3-sonnet":
return "claude-3-sonnet-20240229"
elif model == "claude-3-haiku":
return "claude-3-haiku-20240307"
return model

+ 6
- 2
bot/gemini/google_gemini_bot.py View File

@@ -33,7 +33,7 @@ class GoogleGeminiBot(Bot):
logger.info(f"[Gemini] query={query}")
session_id = context["session_id"]
session = self.sessions.session_query(query, session_id)
gemini_messages = self._convert_to_gemini_messages(self._filter_messages(session.messages))
gemini_messages = self._convert_to_gemini_messages(self.filter_messages(session.messages))
genai.configure(api_key=self.api_key)
model = genai.GenerativeModel('gemini-pro')
response = model.generate_content(gemini_messages)
@@ -44,6 +44,7 @@ class GoogleGeminiBot(Bot):
except Exception as e:
logger.error("[Gemini] fetch reply error, may contain unsafe content")
logger.error(e)
return Reply(ReplyType.ERROR, "invoke [Gemini] api failed!")

def _convert_to_gemini_messages(self, messages: list):
res = []
@@ -60,9 +61,12 @@ class GoogleGeminiBot(Bot):
})
return res

def _filter_messages(self, messages: list):
@staticmethod
def filter_messages(messages: list):
res = []
turn = "user"
if not messages:
return res
for i in range(len(messages) - 1, -1, -1):
message = messages[i]
if message.get("role") != turn:


+ 11
- 4
bot/linkai/link_ai_bot.py View File

@@ -92,6 +92,7 @@ class LinkAIBot(Bot):
"frequency_penalty": conf().get("frequency_penalty", 0.0), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"presence_penalty": conf().get("presence_penalty", 0.0), # [-2,2]之间，该值越大则更倾向于产生不同的内容
"session_id": session_id,
"sender_id": session_id,
"channel_type": conf().get("channel_type", "wx")
}
try:
@@ -129,9 +130,12 @@ class LinkAIBot(Bot):
response = res.json()
reply_content = response["choices"][0]["message"]["content"]
total_tokens = response["usage"]["total_tokens"]
logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}")
self.sessions.session_reply(reply_content, session_id, total_tokens, query=query)
res_code = response.get('code')
logger.info(f"[LINKAI] reply={reply_content}, total_tokens={total_tokens}, res_code={res_code}")
if res_code == 429:
logger.warn(f"[LINKAI] 用户访问超出限流配置，sender_id={body.get('sender_id')}")
else:
self.sessions.session_reply(reply_content, session_id, total_tokens, query=query)
agent_suffix = self._fetch_agent_suffix(response)
if agent_suffix:
reply_content += agent_suffix
@@ -160,7 +164,10 @@ class LinkAIBot(Bot):
logger.warn(f"[LINKAI] do retry, times={retry_count}")
return self._chat(query, context, retry_count + 1)

return Reply(ReplyType.TEXT, "提问太快啦，请休息一下再问我吧")
error_reply = "提问太快啦，请休息一下再问我吧"
if res.status_code == 409:
error_reply = "这个问题我还没有学会，请问我其它问题吧"
return Reply(ReplyType.TEXT, error_reply)

except Exception as e:
logger.exception(e)


+ 2
- 1
bot/xunfei/xunfei_spark_bot.py View File

@@ -47,7 +47,8 @@ class XunFeiBot(Bot):
# 默认使用v2.0版本: "ws://spark-api.xf-yun.com/v2.1/chat"
# v1.5版本为: "ws://spark-api.xf-yun.com/v1.1/chat"
# v3.0版本为: "ws://spark-api.xf-yun.com/v3.1/chat"
self.spark_url = "ws://spark-api.xf-yun.com/v3.1/chat"
# v3.5版本为: "wss://spark-api.xf-yun.com/v3.5/chat"
self.spark_url = "wss://spark-api.xf-yun.com/v3.5/chat"
self.host = urlparse(self.spark_url).netloc
self.path = urlparse(self.spark_url).path
# 和wenxin使用相同的session机制


+ 5
- 2
bridge/bridge.py View File

@@ -18,6 +18,7 @@ class Bridge(object):
"text_to_voice": conf().get("text_to_voice", "google"),
"translate": conf().get("translate", "baidu"),
}
# 这边取配置的模型
model_type = conf().get("model") or const.GPT35
if model_type in ["text-davinci-003"]:
self.btype["chat"] = const.OPEN_AI
@@ -33,6 +34,8 @@ class Bridge(object):
self.btype["chat"] = const.GEMINI
if model_type in [const.ZHIPU_AI]:
self.btype["chat"] = const.ZHIPU_AI
if model_type and model_type.startswith("claude-3"):
self.btype["chat"] = const.CLAUDEAPI

if conf().get("use_linkai") and conf().get("linkai_api_key"):
self.btype["chat"] = const.LINKAI
@@ -40,12 +43,12 @@ class Bridge(object):
self.btype["voice_to_text"] = const.LINKAI
if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:
self.btype["text_to_voice"] = const.LINKAI

if model_type in ["claude"]:
self.btype["chat"] = const.CLAUDEAI

self.bots = {}
self.chat_bots = {}
# 模型对应的接口
def get_bot(self, typename):
if self.bots.get(typename) is None:
logger.info("create bot {} for {}".format(self.btype[typename], typename))


+ 1
- 1
bridge/reply.py View File

@@ -11,7 +11,7 @@ class ReplyType(Enum):
VIDEO_URL = 5 # 视频URL
FILE = 6 # 文件
CARD = 7 # 微信名片，仅支持ntchat
InviteRoom = 8 # 邀请好友进群
INVITE_ROOM = 8 # 邀请好友进群
INFO = 9
ERROR = 10
TEXT_ = 11 # 强制文本


+ 5
- 3
channel/chat_channel.py View File

@@ -170,11 +170,13 @@ class ChatChannel(Channel):
reply = self._generate_reply(context)

logger.debug("[WX] ready to decorate reply: {}".format(reply))

# reply的包装步骤
reply = self._decorate_reply(context, reply)
if reply and reply.content:
reply = self._decorate_reply(context, reply)

# reply的发送步骤
self._send_reply(context, reply)
# reply的发送步骤
self._send_reply(context, reply)

def _generate_reply(self, context: Context, reply: Reply = Reply()) -> Reply:
e_context = PluginManager().emit_event(


+ 0
- 1
channel/wechat/wechat_channel.py View File

@@ -233,7 +233,6 @@ class WechatChannel(ChatChannel):
logger.info("[WX] sendImage url={}, receiver={}".format(img_url, receiver))
elif reply.type == ReplyType.IMAGE: # 从文件读取图片
image_storage = reply.content
image_storage.seek(0)
itchat.send_image(image_storage, toUserName=receiver)
logger.info("[WX] sendImage, receiver={}".format(receiver))
elif reply.type == ReplyType.FILE: # 新增文件回复类型


+ 5
- 2
common/const.py View File

@@ -6,12 +6,15 @@ XUNFEI = "xunfei"
CHATGPTONAZURE = "chatGPTOnAzure"
LINKAI = "linkai"
CLAUDEAI = "claude"
CLAUDEAPI= "claudeAPI"
QWEN = "qwen"
GEMINI = "gemini"
ZHIPU_AI = "glm-4"
MOONSHOT = "moonshot"


# model
CLAUDE3 = "claude-3-opus-20240229"
GPT35 = "gpt-3.5-turbo"
GPT4 = "gpt-4"
GPT4_TURBO_PREVIEW = "gpt-4-0125-preview"
@@ -20,8 +23,8 @@ WHISPER_1 = "whisper-1"
TTS_1 = "tts-1"
TTS_1_HD = "tts-1-hd"

MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "wenxin-4", "xunfei", "claude", "gpt-4-turbo",
"gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, QWEN, GEMINI, ZHIPU_AI]
MODEL_LIST = ["gpt-3.5-turbo", "gpt-3.5-turbo-16k", "gpt-4", "wenxin", "wenxin-4", "xunfei", "claude","claude-3-opus-20240229", "gpt-4-turbo",
"gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, QWEN, GEMINI, ZHIPU_AI, MOONSHOT]

# channel
FEISHU = "feishu"


+ 1
- 0
config-template.json View File

@@ -2,6 +2,7 @@
"channel_type": "wx",
"model": "",
"open_ai_api_key": "YOUR API KEY",
"claude_api_key": "YOUR API KEY",
"text_to_image": "dall-e-2",
"voice_to_text": "openai",
"text_to_voice": "openai",


+ 3
- 1
config.py View File

@@ -74,6 +74,8 @@ available_setting = {
# claude 配置
"claude_api_cookie": "",
"claude_uuid": "",
# claude api key
"claude_api_key":"",
# 通义千问API, 获取方式查看文档 https://help.aliyun.com/document_detail/2587494.html
"qwen_access_key_id": "",
"qwen_access_key_secret": "",
@@ -90,7 +92,7 @@ available_setting = {
"voice_reply_voice": False, # 是否使用语音回复语音，需要设置对应语音合成引擎的api key
"always_reply_voice": False, # 是否一直使用语音回复
"voice_to_text": "openai", # 语音识别引擎，支持openai,baidu,google,azure
"text_to_voice": "openai", # 语音合成引擎，支持openai,baidu,google,pytts(offline),azure,elevenlabs
"text_to_voice": "openai", # 语音合成引擎，支持openai,baidu,google,pytts(offline),azure,elevenlabs,edge(online)
"text_to_voice_model": "tts-1",
"tts_voice_id": "alloy",
# baidu 语音api配置， 使用百度语音识别和语音合成时需要


+ 13
- 0
docs/version/old-version.md View File

@@ -0,0 +1,13 @@
## 归档更新日志

2023.04.26： 支持企业微信应用号部署，兼容插件，并支持语音图片交互，私人助理理想选择，使用文档。(contributed by @lanvent in #944)

2023.04.05： 支持微信公众号部署，兼容插件，并支持语音图片交互，使用文档。(contributed by @JS00000 in #686)

2023.04.05： 增加能让ChatGPT使用工具的tool插件，使用文档。工具相关issue可反馈至chatgpt-tool-hub。(contributed by @goldfishh in #663)

2023.03.25： 支持插件化开发，目前已实现 多角色切换、文字冒险游戏、管理员指令、Stable Diffusion等插件，使用参考 #578。(contributed by @lanvent in #565)

2023.03.09： 基于 whisper API(后续已接入更多的语音API服务) 实现对微信语音消息的解析和回复，添加配置项 "speech_recognition":true 即可启用，使用参考 #415。(contributed by wanggang1987 in #385)

2023.02.09： 扫码登录存在账号限制风险，请谨慎使用，参考#58

+ 2
- 2
plugins/godcmd/godcmd.py 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]:
if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI, const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI]:
bot.sessions.clear_session(session_id)
if Bridge().chat_bots.get(bottype):
Bridge().chat_bots.get(bottype).sessions.clear_session(session_id)
@@ -339,7 +339,7 @@ class Godcmd(Plugin):
ok, result = True, "配置已重载"
elif cmd == "resetall":
if bottype in [const.OPEN_AI, const.CHATGPT, const.CHATGPTONAZURE, const.LINKAI,
const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI]:
const.BAIDU, const.XUNFEI, const.QWEN, const.GEMINI, const.ZHIPU_AI, const.MOONSHOT]:
channel.cancel_all_session()
bot.sessions.clear_all_session()
ok, result = True, "重置所有会话成功"


+ 16
- 14
plugins/plugin_manager.py View File

@@ -99,7 +99,7 @@ class PluginManager:
try:
self.current_plugin_path = plugin_path
if plugin_path in self.loaded:
if self.loaded[plugin_path] == None:
if plugin_name.upper() != 'GODCMD':
logger.info("reload module %s" % plugin_name)
self.loaded[plugin_path] = importlib.reload(sys.modules[import_path])
dependent_module_names = [name for name in sys.modules.keys() if name.startswith(import_path + ".")]
@@ -141,19 +141,21 @@ class PluginManager:
failed_plugins = []
for name, plugincls in self.plugins.items():
if plugincls.enabled:
if name not in self.instances:
try:
instance = plugincls()
except Exception as e:
logger.warn("Failed to init %s, diabled. %s" % (name, e))
self.disable_plugin(name)
failed_plugins.append(name)
continue
self.instances[name] = instance
for event in instance.handlers:
if event not in self.listening_plugins:
self.listening_plugins[event] = []
self.listening_plugins[event].append(name)
if 'GODCMD' in self.instances and name == 'GODCMD':
continue
# if name not in self.instances:
try:
instance = plugincls()
except Exception as e:
logger.warn("Failed to init %s, diabled. %s" % (name, e))
self.disable_plugin(name)
failed_plugins.append(name)
continue
self.instances[name] = instance
for event in instance.handlers:
if event not in self.listening_plugins:
self.listening_plugins[event] = []
self.listening_plugins[event].append(name)
self.refresh_order()
return failed_plugins



+ 8
- 0
plugins/source.json View File

@@ -19,6 +19,14 @@
"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"
},
"pictureChange": {
"url": "https://github.com/Yanyutin753/pictureChange.git",
"desc": "利用stable-diffusion和百度Ai进行图生图或者画图的插件"
},
"Blackroom": {
"url": "https://github.com/dividduang/blackroom.git",
"desc": "小黑屋插件，被拉进小黑屋的人将不能使用@bot的功能的插件"
}
}
}

+ 3
- 0
requirements-optional.txt View File

@@ -7,6 +7,7 @@ gTTS>=2.3.1 # google text to speech
pyttsx3>=2.90 # pytsx text to speech
baidu_aip>=4.16.10 # baidu voice
azure-cognitiveservices-speech # azure voice
edge-tts # edge-tts
numpy<=1.24.2
langid # language detect

@@ -25,6 +26,8 @@ websocket-client==1.2.0

# claude bot
curl_cffi
# claude API
anthropic

# tongyi qwen
broadscope_bailian


+ 1
- 1
requirements.txt View File

@@ -6,4 +6,4 @@ requests>=2.28.2
chardet>=5.1.0
Pillow
pre-commit
web.py
web.py

+ 3
- 1
voice/audio_convert.py View File

@@ -64,7 +64,9 @@ def any_to_wav(any_path, wav_path):
if any_path.endswith(".sil") or any_path.endswith(".silk") or any_path.endswith(".slk"):
return sil_to_wav(any_path, wav_path)
audio = AudioSegment.from_file(any_path)
audio.export(wav_path, format="wav")
audio.set_frame_rate(8000) # 百度语音转写支持8000采样率, pcm_s16le, 单通道语音识别
audio.set_channels(1)
audio.export(wav_path, format="wav", codec='pcm_s16le')


def any_to_sil(any_path, sil_path):


+ 1
- 1
voice/baidu/baidu_voice.py View File

@@ -62,7 +62,7 @@ class BaiduVoice(Voice):
# 识别本地文件
logger.debug("[Baidu] voice file name={}".format(voice_file))
pcm = get_pcm_from_wav(voice_file)
res = self.client.asr(pcm, "pcm", 16000, {"dev_pid": self.dev_id})
res = self.client.asr(pcm, "pcm", 8000, {"dev_pid": self.dev_id})
if res["err_no"] == 0:
logger.info("百度语音识别到了：{}".format(res["result"]))
text = "".join(res["result"])


+ 50
- 0
voice/edge/edge_voice.py View File

@@ -0,0 +1,50 @@
import time

import edge_tts
import asyncio

from bridge.reply import Reply, ReplyType
from common.log import logger
from common.tmp_dir import TmpDir
from voice.voice import Voice


class EdgeVoice(Voice):

def __init__(self):
'''
# 普通话
zh-CN-XiaoxiaoNeural
zh-CN-XiaoyiNeural
zh-CN-YunjianNeural
zh-CN-YunxiNeural
zh-CN-YunxiaNeural
zh-CN-YunyangNeural
# 地方口音
zh-CN-liaoning-XiaobeiNeural
zh-CN-shaanxi-XiaoniNeural
# 粤语
zh-HK-HiuGaaiNeural
zh-HK-HiuMaanNeural
zh-HK-WanLungNeural
# 湾湾腔
zh-TW-HsiaoChenNeural
zh-TW-HsiaoYuNeural
zh-TW-YunJheNeural
'''
self.voice = "zh-CN-YunjianNeural"

def voiceToText(self, voice_file):
pass

async def gen_voice(self, text, fileName):
communicate = edge_tts.Communicate(text, self.voice)
await communicate.save(fileName)

def textToVoice(self, text):
fileName = TmpDir().path() + "reply-" + str(int(time.time())) + "-" + str(hash(text) & 0x7FFFFFFF) + ".mp3"

asyncio.run(self.gen_voice(text, fileName))

logger.info("[EdgeTTS] textToVoice text={} voice file name={}".format(text, fileName))
return Reply(ReplyType.VOICE, fileName)

+ 4
- 0
voice/factory.py View File

@@ -42,4 +42,8 @@ def create_voice(voice_type):
from voice.ali.ali_voice import AliVoice

return AliVoice()
elif voice_type == "edge":
from voice.edge.edge_voice import EdgeVoice

return EdgeVoice()
raise RuntimeError

Write Preview
Loading…
Cancel
Save