Explorar el Código

Merge branch 'zhayujie:master' into master

master
Haowei GitHub hace 7 meses
padre
commit
3d47be1f49
No se encontró ninguna clave conocida en la base de datos para esta firma ID de clave GPG: B5690EEEBB952194
Se han modificado 18 ficheros con 260 adiciones y 37 borrados
  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. +3
    -2
      bot/gemini/google_gemini_bot.py
  6. +10
    -4
      bot/linkai/link_ai_bot.py
  7. +2
    -1
      bot/xunfei/xunfei_spark_bot.py
  8. +5
    -2
      bridge/bridge.py
  9. +5
    -2
      common/const.py
  10. +1
    -0
      config-template.json
  11. +3
    -1
      config.py
  12. +13
    -0
      docs/version/old-version.md
  13. +2
    -2
      plugins/godcmd/godcmd.py
  14. +5
    -1
      plugins/source.json
  15. +3
    -0
      requirements-optional.txt
  16. +1
    -1
      requirements.txt
  17. +50
    -0
      voice/edge/edge_voice.py
  18. +4
    -0
      voice/factory.py

+ 13
- 18
README.md Ver fichero

@@ -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 Ver fichero

@@ -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 Ver fichero

@@ -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 Ver fichero

@@ -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

+ 3
- 2
bot/gemini/google_gemini_bot.py Ver fichero

@@ -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)
@@ -61,7 +61,8 @@ class GoogleGeminiBot(Bot):
})
return res

def _filter_messages(self, messages: list):
@staticmethod
def filter_messages(messages: list):
res = []
turn = "user"
if not messages:


+ 10
- 4
bot/linkai/link_ai_bot.py Ver fichero

@@ -130,9 +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
@@ -161,7 +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 Ver fichero

@@ -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 Ver fichero

@@ -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))


+ 5
- 2
common/const.py Ver fichero

@@ -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 Ver fichero

@@ -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 Ver fichero

@@ -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 Ver fichero

@@ -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 Ver fichero

@@ -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"


+ 5
- 1
plugins/source.json Ver fichero

@@ -19,10 +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 Ver fichero

@@ -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 Ver fichero

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

+ 50
- 0
voice/edge/edge_voice.py Ver fichero

@@ -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 Ver fichero

@@ -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

Cargando…
Cancelar
Guardar