Compare commits

...

20 Commits
1.5.9 ... 1.6.5

Author SHA1 Message Date
zhayujie
e381d1bfb8 feat: support gpt-4o model 2024-05-14 09:50:03 +08:00
zhayujie
a6ef3bc0ce fix: add channel login exception log 2024-05-08 12:54:13 +08:00
zhayujie
118122c541 docs: update README.md 2024-05-08 12:07:59 +08:00
zhayujie
bfdf33ac09 Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat 2024-05-07 11:37:53 +08:00
zhayujie
fa3370df5b fix: image model check 2024-05-07 11:37:27 +08:00
zhayujie
f1e51672c5 Merge pull request #1944 from alvinsuDL/patch-1
Update README.md
2024-05-07 11:20:43 +08:00
alvinsuDL
91f97b2728 Update README.md 2024-05-07 11:16:41 +08:00
zhayujie
2c542e03fe Merge branch 'master' of github.com:zhayujie/chatgpt-on-wechat 2024-05-07 11:10:41 +08:00
zhayujie
71a11b4267 feat: support mj client config 2024-05-07 11:09:49 +08:00
zhayujie
ea642757db docs: update README.md 2024-05-06 22:19:49 +08:00
zhayujie
fb72b601aa fix: model config 2024-05-03 19:41:12 +08:00
zhayujie
27e507e744 fix: update client sdk version 2024-05-03 19:10:27 +08:00
zhayujie
4db19f816f feat: update service url 2024-05-03 14:10:07 +08:00
zhayujie
096d5776d1 feat: v1.6.0 verson update 2024-04-26 16:13:53 +08:00
zhayujie
3d799eb4d9 Merge pull request #1893 from uxfion/fix-openai-whisper
fix openai voice_to_text whisper
2024-04-26 15:37:34 +08:00
zhayujie
e4ac3afa4d Merge pull request #1849 from wayshall/kimi
feat: 增加moonshot api集成
2024-04-26 15:17:52 +08:00
zhayujie
d38e4eed5b Merge pull request #1904 from fatwang2/master
新增url解析逻辑,解决itchat中分享卡片无法解析的问题
2024-04-20 11:09:51 +08:00
fatwang2
97787fac91 新增url解析逻辑,解决itchat中分享卡片无法解析的问题 2024-04-20 00:48:33 +08:00
Lecter
b494ee2f1c fix openai voice_to_text whisper 2024-04-14 14:33:17 +08:00
weishao zeng
38e1db7a37 feat: 增加moonshot api集成
moonshot本来可直接使用openai sdk,
但是要求openai sdk必须在1.0以上,与本项目冲突,
故现使用http接口对接的方式集成
2024-03-27 15:02:51 +08:00
22 changed files with 316 additions and 69 deletions

101
README.md
View File

@@ -1,39 +1,47 @@
# 简介
> 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。
> chatgpt-on-wechat简称CoW项目是基于大模型的智能对话机器人,支持微信公众号、企业微信应用、微信、飞书、钉钉接入可选择GPT3.5/GPT4.0/Claude/Gemini/LinkAI/ChatGLM/KIMI/文心一言/讯飞星火/通义千问/LinkAI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
- [x] **知识库:** 通过上传知识库文件自定义专属机器人,可作为数字分身、智能客服、私域助手使用,基于 [LinkAI](https://link-ai.tech) 实现
- **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
- **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, GPT-4o, Claude-3, Gemini, 文心一言, 讯飞星火, 通义千问ChatGLM-4Kimi(月之暗面)
- **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
- **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
- **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
- **知识库:** 通过上传知识库文件自定义专属机器人,可作为数字分身、智能客服、私域助手使用,基于 [LinkAI](https://link-ai.tech) 实现
# 演示
## 演示
https://github.com/zhayujie/chatgpt-on-wechat/assets/26161723/d5154020-36e3-41db-8706-40ce9f3f1b1e
Demo made by [Visionn](https://www.wangpc.cc/)
# 商业支持
> 我们还提供企业级的 **AI应用平台**包含知识库、Agent插件、应用管理等能力支持多平台聚合的应用接入、客户端管理、对话管理以及提供
SaaS服务、私有化部署、稳定托管接入 等多种模式。
>
> 目前已在私域运营、智能客服、企业效率助手等场景积累了丰富的 AI 解决方案, 在电商、文教、健康、新消费等各行业沉淀了 AI 落地的最佳实践,致力于打造助力中小企业拥抱 AI 的一站式平台。
企业服务和商用咨询可联系产品顾问:
<img width="240" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/product-manager-qrcode.jpg">
# 开源社区
## 社区
添加小助手微信加入开源项目交流群:
<img width="240" src="./docs/images/contact.jpg">
<img width="160" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/open-community.png">
# 更新日志
<br>
# 企业服务
<a href="https://link-ai.tech" target="_blank"><img width="800" src="https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/github-linkai-intro-v2.png"></a>
> [LinkAI](https://link-ai.tech/) 是面向企业和开发者的一站式AI应用平台聚合多模态大模型、知识库、Agent 插件、工作流等能力支持一键接入主流平台并进行管理支持SaaS、私有化部署多种模式。
>
> LinkAI 目前 已在私域运营、智能客服、企业效率助手等场景积累了丰富的 AI 解决方案, 在电商、文教、健康、新消费、科技制造等各行业沉淀了大模型落地应用的最佳实践,致力于帮助更多企业和开发者拥抱 AI 生产力。
**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">
<br>
# 🏷 更新日志
>**2024.05.14** [1.6.5版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.5),新增 gpt-4o 模型支持
>**2024.04.26** [1.6.0版本](https://github.com/zhayujie/chatgpt-on-wechat/releases/tag/1.6.0),新增 Kimi 接入、gpt-4-turbo版本升级、文件总结和语音识别问题修复
>**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
@@ -55,11 +63,13 @@ SaaS服务、私有化部署、稳定托管接入 等多种模式。
更早更新日志查看: [归档日志](/docs/version/old-version.md)
# 快速开始
<br>
快速开始文档:[项目搭建文档](https://docs.link-ai.tech/cow/quick-start)
# 🚀 快速开始
## 准备
快速开始详细文档:[项目搭建文档](https://docs.link-ai.tech/cow/quick-start)
## 一、准备
### 1. 账号注册
@@ -98,7 +108,7 @@ pip3 install -r requirements-optional.txt
```
> 如果某项依赖安装失败可注释掉对应的行再继续
## 配置
## 二、配置
配置文件的模板在根目录的`config-template.json`中,需复制该模板创建最终生效的 `config.json` 文件:
@@ -106,14 +116,13 @@ pip3 install -r requirements-optional.txt
cp config-template.json config.json
```
然后在`config.json`中填入配置,以下是对默认配置的说明,可根据需要进行自定义修改(请去掉注释
然后在`config.json`中填入配置,以下是对默认配置的说明,可根据需要进行自定义修改(注意实际使用时请去掉注释保证JSON格式的完整
```bash
# 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, 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
"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
"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
@@ -124,10 +133,8 @@ pip3 install -r requirements-optional.txt
"conversation_max_tokens": 1000, # 支持上下文记忆的最多字符数
"speech_recognition": false, # 是否开启语音识别
"group_speech_recognition": false, # 是否开启群组语音识别
"use_azure_chatgpt": false, # 是否使用Azure ChatGPT service代替openai ChatGPT service. 当设置为true时需要设置 open_ai_api_base如 https://xxx.openai.azure.com/
"azure_deployment_id": "", # 采用Azure ChatGPT时模型部署名称
"azure_api_version": "", # 采用Azure ChatGPT时API版本
"character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题,并且可以使用多种语言与人交流。", # 人格描述
"voice_reply_voice": false, # 是否使用语音回复语音
"character_desc": "你是基于大语言模型的AI智能助手旨在回答并解决人们的任何问题并且可以使用多种语言与人交流。", # 人格描述
# 订阅消息公众号和企业微信channel中请填写当被订阅时会自动回复可使用特殊占位符。目前支持的占位符有{trigger_prefix}在程序中它会自动替换成bot的触发词。
"subscribe_msg": "感谢您的关注!\n这里是ChatGPT可以自由对话。\n支持语音对话。\n支持图片输出画字开头的消息将按要求创作图片。\n支持角色扮演和文字冒险等丰富插件。\n输入{trigger_prefix}#help 查看详细指令。",
"use_linkai": false, # 是否使用LinkAI接口默认关闭开启后可国内访问使用知识库和MJ
@@ -157,7 +164,7 @@ pip3 install -r requirements-optional.txt
**4.其他配置**
+ `model`: 模型名称,目前支持 `gpt-3.5-turbo`, `text-davinci-003`, `gpt-4`, `gpt-4-32k`, `wenxin` , `claude` , `xunfei`(其中gpt-4 api暂未完全开放申请通过后可使用)
+ `model`: 模型名称,目前支持 `gpt-3.5-turbo`, `gpt-4o`, `gpt-4-turbo`, `gpt-4`, `wenxin` , `claude` , `gemini`, `glm-4`, `xunfei`, `moonshot`
+ `temperature`,`frequency_penalty`,`presence_penalty`: Chat API接口参数详情参考[OpenAI官方文档。](https://platform.openai.com/docs/api-reference/chat)
+ `proxy`:由于目前 `openai` 接口国内无法访问,需配置代理客户端的地址,详情参考 [#351](https://github.com/zhayujie/chatgpt-on-wechat/issues/351)
+ 对于图像生成,在满足个人或群组触发条件外,还需要额外的关键词前缀来触发,对应配置 `image_create_prefix `
@@ -177,7 +184,7 @@ pip3 install -r requirements-optional.txt
**本说明文档可能会未及时更新,当前所有可选的配置项均在该[`config.py`](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/config.py)中列出。**
## 运行
## 三、运行
### 1.本地运行
@@ -209,7 +216,7 @@ nohup python3 app.py & tail -f nohup.out # 在后台运行程序并通
> 前提是需要安装好 `docker` 及 `docker-compose`,安装成功的表现是执行 `docker -v` 和 `docker-compose version` (或 docker compose version) 可以查看到版本号,可前往 [docker官网](https://docs.docker.com/engine/install/) 进行下载。
#### (1) 下载 docker-compose.yml 文件
**(1) 下载 docker-compose.yml 文件**
```bash
wget https://open-1317903499.cos.ap-guangzhou.myqcloud.com/docker-compose.yml
@@ -217,7 +224,7 @@ wget https://open-1317903499.cos.ap-guangzhou.myqcloud.com/docker-compose.yml
下载完成后打开 `docker-compose.yml` 修改所需配置,如 `OPEN_AI_API_KEY``GROUP_NAME_WHITE_LIST` 等。
#### (2) 启动容器
**(2) 启动容器**
`docker-compose.yml` 所在目录下执行以下命令启动容器:
@@ -238,7 +245,7 @@ sudo docker compose up -d
sudo docker logs -f chatgpt-on-wechat
```
#### (3) 插件使用
**(3) 插件使用**
如果需要在docker容器中修改插件配置可通过挂载的方式完成将 [插件配置文件](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/plugins/config.json.template)
重命名为 `config.json`,放置于 `docker-compose.yml` 相同目录下,并在 `docker-compose.yml` 中的 `chatgpt-on-wechat` 部分下添加 `volumes` 映射:
@@ -260,16 +267,22 @@ volumes:
[![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/template/qApznZ?referralCode=RC3znh)
## 常见问题
<br>
# 🔎 常见问题
FAQs <https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs>
或直接在线咨询 [项目小助手](https://link-ai.tech/app/Kv2fXJcH) (beta版本语料完善中,回复仅供参考)
或直接在线咨询 [项目小助手](https://link-ai.tech/app/Kv2fXJcH) (语料持续完善中,回复仅供参考)
## 开发
# 🛠️ 开发
欢迎接入更多应用,参考 [Terminal代码](https://github.com/zhayujie/chatgpt-on-wechat/blob/master/channel/terminal/terminal_channel.py) 实现接收和发送消息逻辑即可接入。 同时欢迎增加新的插件,参考 [插件说明文档](https://github.com/zhayujie/chatgpt-on-wechat/tree/master/plugins)。
## 联系
# ✉ 联系
欢迎提交PR、Issues以及Star支持一下。程序运行遇到问题可以查看 [常见问题列表](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs) ,其次前往 [Issues](https://github.com/zhayujie/chatgpt-on-wechat/issues) 中搜索。个人开发者可加入开源交流群参与更多讨论,企业用户可联系[产品顾问](https://img-1317903499.cos.ap-guangzhou.myqcloud.com/docs/product-manager-qrcode.jpg)咨询。
# 🌟 贡献者
![cow contributors](https://contrib.rocks/image?repo=zhayujie/chatgpt-on-wechat&max=1000)

View File

@@ -61,5 +61,9 @@ def create_bot(bot_type):
from bot.zhipuai.zhipuai_bot import ZHIPUAIBot
return ZHIPUAIBot()
elif bot_type == const.MOONSHOT:
from bot.moonshot.moonshot_bot import MoonshotBot
return MoonshotBot()
raise RuntimeError

View File

@@ -62,11 +62,12 @@ 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", "moonshot"]:
if model in ["gpt-3.5-turbo-0301", "gpt-35-turbo", "gpt-3.5-turbo-1106", "moonshot", const.LINKAI_35]:
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]:
"gpt-4-1106-preview", const.GPT4_TURBO_PREVIEW, const.GPT4_VISION_PREVIEW, const.GPT4_TURBO_01_25,
const.GPT_4o, const.LINKAI_4o, const.LINKAI_4_TURBO]:
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")

View File

@@ -122,7 +122,7 @@ class LinkAIBot(Bot):
headers = {"Authorization": "Bearer " + linkai_api_key}
# do http request
base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
timeout=conf().get("request_timeout", 180))
if res.status_code == 200:
@@ -261,7 +261,7 @@ class LinkAIBot(Bot):
headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
# do http request
base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
base_url = conf().get("linkai_api_base", "https://api.link-ai.tech")
res = requests.post(url=base_url + "/v1/chat/completions", json=body, headers=headers,
timeout=conf().get("request_timeout", 180))
if res.status_code == 200:
@@ -304,7 +304,7 @@ class LinkAIBot(Bot):
def _fetch_app_info(self, app_code: str):
headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
# do http request
base_url = conf().get("linkai_api_base", "https://api.link-ai.chat")
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:
@@ -326,7 +326,7 @@ class LinkAIBot(Bot):
"response_format": "url",
"img_proxy": conf().get("image_proxy")
}
url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/images/generations"
url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/images/generations"
res = requests.post(url, headers=headers, json=data, timeout=(5, 90))
t2 = time.time()
image_url = res.json()["data"][0]["url"]

View File

@@ -0,0 +1,143 @@
# encoding:utf-8
import time
import openai
import openai.error
from bot.bot import Bot
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, load_config
from .moonshot_session import MoonshotSession
import requests
# ZhipuAI对话模型API
class MoonshotBot(Bot):
def __init__(self):
super().__init__()
self.sessions = SessionManager(MoonshotSession, model=conf().get("model") or "moonshot-v1-128k")
self.args = {
"model": conf().get("model") or "moonshot-v1-128k", # 对话模型的名称
"temperature": conf().get("temperature", 0.3), # 如果设置,值域须为 [0, 1] 我们推荐 0.3,以达到较合适的效果。
"top_p": conf().get("top_p", 1.0), # 使用默认值
}
self.api_key = conf().get("moonshot_api_key")
self.base_url = conf().get("moonshot_base_url", "https://api.moonshot.cn/v1/chat/completions")
def reply(self, query, context=None):
# acquire reply content
if context.type == ContextType.TEXT:
logger.info("[MOONSHOT_AI] query={}".format(query))
session_id = context["session_id"]
reply = None
clear_memory_commands = conf().get("clear_memory_commands", ["#清除记忆"])
if query in clear_memory_commands:
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")
elif query == "#更新配置":
load_config()
reply = Reply(ReplyType.INFO, "配置已更新")
if reply:
return reply
session = self.sessions.session_query(query, session_id)
logger.debug("[MOONSHOT_AI] session query={}".format(session.messages))
model = context.get("moonshot_model")
new_args = self.args.copy()
if model:
new_args["model"] = model
# if context.get('stream'):
# # reply in stream
# return self.reply_text_stream(query, new_query, session_id)
reply_content = self.reply_text(session, args=new_args)
logger.debug(
"[MOONSHOT_AI] new_query={}, session_id={}, reply_cont={}, completion_tokens={}".format(
session.messages,
session_id,
reply_content["content"],
reply_content["completion_tokens"],
)
)
if reply_content["completion_tokens"] == 0 and len(reply_content["content"]) > 0:
reply = Reply(ReplyType.ERROR, reply_content["content"])
elif reply_content["completion_tokens"] > 0:
self.sessions.session_reply(reply_content["content"], session_id, reply_content["total_tokens"])
reply = Reply(ReplyType.TEXT, reply_content["content"])
else:
reply = Reply(ReplyType.ERROR, reply_content["content"])
logger.debug("[MOONSHOT_AI] reply {} used 0 tokens.".format(reply_content))
return reply
else:
reply = Reply(ReplyType.ERROR, "Bot不支持处理{}类型的消息".format(context.type))
return reply
def reply_text(self, session: MoonshotSession, args=None, retry_count=0) -> dict:
"""
call openai's ChatCompletion to get the answer
:param session: a conversation session
:param session_id: session id
:param retry_count: retry count
:return: {}
"""
try:
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer " + self.api_key
}
body = args
body["messages"] = session.messages
# logger.debug("[MOONSHOT_AI] response={}".format(response))
# logger.info("[MOONSHOT_AI] reply={}, total_tokens={}".format(response.choices[0]['message']['content'], response["usage"]["total_tokens"]))
res = requests.post(
self.base_url,
headers=headers,
json=body
)
if res.status_code == 200:
response = res.json()
return {
"total_tokens": response["usage"]["total_tokens"],
"completion_tokens": response["usage"]["completion_tokens"],
"content": response["choices"][0]["message"]["content"]
}
else:
response = res.json()
error = response.get("error")
logger.error(f"[MOONSHOT_AI] chat failed, status_code={res.status_code}, "
f"msg={error.get('message')}, type={error.get('type')}")
result = {"completion_tokens": 0, "content": "提问太快啦,请休息一下再问我吧"}
need_retry = False
if res.status_code >= 500:
# server error, need retry
logger.warn(f"[MOONSHOT_AI] do retry, times={retry_count}")
need_retry = retry_count < 2
elif res.status_code == 401:
result["content"] = "授权失败请检查API Key是否正确"
elif res.status_code == 429:
result["content"] = "请求过于频繁,请稍后再试"
need_retry = retry_count < 2
else:
need_retry = False
if need_retry:
time.sleep(3)
return self.reply_text(session, args, retry_count + 1)
else:
return result
except Exception as e:
logger.exception(e)
need_retry = retry_count < 2
result = {"completion_tokens": 0, "content": "我现在有点累了,等会再来吧"}
if need_retry:
return self.reply_text(session, args, retry_count + 1)
else:
return result

View File

@@ -0,0 +1,51 @@
from bot.session_manager import Session
from common.log import logger
class MoonshotSession(Session):
def __init__(self, session_id, system_prompt=None, model="moonshot-v1-128k"):
super().__init__(session_id, system_prompt)
self.model = model
self.reset()
def discard_exceeding(self, max_tokens, cur_tokens=None):
precise = True
try:
cur_tokens = self.calc_tokens()
except Exception as e:
precise = False
if cur_tokens is None:
raise e
logger.debug("Exception when counting tokens precisely for query: {}".format(e))
while cur_tokens > max_tokens:
if len(self.messages) > 2:
self.messages.pop(1)
elif len(self.messages) == 2 and self.messages[1]["role"] == "assistant":
self.messages.pop(1)
if precise:
cur_tokens = self.calc_tokens()
else:
cur_tokens = cur_tokens - max_tokens
break
elif len(self.messages) == 2 and self.messages[1]["role"] == "user":
logger.warn("user message exceed max_tokens. total_tokens={}".format(cur_tokens))
break
else:
logger.debug("max_tokens={}, total_tokens={}, len(messages)={}".format(max_tokens, cur_tokens,
len(self.messages)))
break
if precise:
cur_tokens = self.calc_tokens()
else:
cur_tokens = cur_tokens - max_tokens
return cur_tokens
def calc_tokens(self):
return num_tokens_from_messages(self.messages, self.model)
def num_tokens_from_messages(messages, model):
tokens = 0
for msg in messages:
tokens += len(msg["content"])
return tokens

View File

@@ -39,17 +39,22 @@ class Bridge(object):
if model_type and model_type.startswith("claude-3"):
self.btype["chat"] = const.CLAUDEAPI
if model_type in ["claude"]:
self.btype["chat"] = const.CLAUDEAI
if model_type in ["moonshot-v1-8k", "moonshot-v1-32k", "moonshot-v1-128k"]:
self.btype["chat"] = const.MOONSHOT
if conf().get("use_linkai") and conf().get("linkai_api_key"):
self.btype["chat"] = const.LINKAI
if not conf().get("voice_to_text") or conf().get("voice_to_text") in ["openai"]:
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:

View File

@@ -132,7 +132,7 @@ class WechatChannel(ChatChannel):
# start message listener
itchat.run()
except Exception as e:
logger.error(e)
logger.exception(e)
def exitCallback(self):
try:

View File

@@ -23,15 +23,21 @@ MOONSHOT = "moonshot"
CLAUDE3 = "claude-3-opus-20240229"
GPT35 = "gpt-3.5-turbo"
GPT4 = "gpt-4"
GPT4_TURBO_PREVIEW = "gpt-4-0125-preview"
GPT_4o = "gpt-4o"
LINKAI_35 = "linkai-3.5"
LINKAI_4_TURBO = "linkai-4-turbo"
LINKAI_4o = "linkai-4o"
GPT4_TURBO_PREVIEW = "gpt-4-turbo-2024-04-09"
GPT4_TURBO_04_09 = "gpt-4-turbo-2024-04-09"
GPT4_TURBO_01_25 = "gpt-4-0125-preview"
GPT4_VISION_PREVIEW = "gpt-4-vision-preview"
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","claude-3-opus-20240229", "gpt-4-turbo",
"gpt-4-turbo-preview", "gpt-4-1106-preview", GPT4_TURBO_PREVIEW, QWEN, GEMINI, ZHIPU_AI, MOONSHOT,
QWEN_TURBO, QWEN_PLUS, QWEN_MAX]
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, GPT4_TURBO_01_25, GPT_4o, QWEN, GEMINI, ZHIPU_AI, MOONSHOT,
QWEN_TURBO, QWEN_PLUS, QWEN_MAX, LINKAI_35, LINKAI_4_TURBO, LINKAI_4o]
# channel
FEISHU = "feishu"

View File

@@ -45,7 +45,7 @@ class ChatClient(LinkAIClient):
elif reply_voice_mode == "always_reply_voice":
local_config["always_reply_voice"] = True
if config.get("admin_password") and plugin_config["Godcmd"]:
if config.get("admin_password") and plugin_config.get("Godcmd"):
plugin_config["Godcmd"]["password"] = config.get("admin_password")
PluginManager().instances["GODCMD"].reload()
@@ -56,11 +56,18 @@ class ChatClient(LinkAIClient):
pconf("linkai")["group_app_map"] = local_group_map
PluginManager().instances["LINKAI"].reload()
if config.get("text_to_image") and config.get("text_to_image") == "midjourney" and pconf("linkai"):
if pconf("linkai")["midjourney"]:
pconf("linkai")["midjourney"]["enabled"] = True
pconf("linkai")["midjourney"]["use_image_create_prefix"] = True
elif config.get("text_to_image") and config.get("text_to_image") in ["dall-e-2", "dall-e-3"]:
if pconf("linkai")["midjourney"]:
pconf("linkai")["midjourney"]["use_image_create_prefix"] = False
def start(channel):
global chat_client
chat_client = ChatClient(api_key=conf().get("linkai_api_key"),
host="link-ai.chat", channel=channel)
chat_client = ChatClient(api_key=conf().get("linkai_api_key"), host="", channel=channel)
chat_client.config = _build_config()
chat_client.start()
time.sleep(1.5)

View File

@@ -28,7 +28,7 @@
"voice_reply_voice": false,
"conversation_max_tokens": 2500,
"expires_in_seconds": 3600,
"character_desc": "你是ChatGPT, 一个由OpenAI训练的大型语言模型, 你旨在回答并解决人们的任何问题,并且可以使用多种语言与人交流。",
"character_desc": "你是基于大语言模型的AI智能助手旨在回答并解决人们的任何问题,并且可以使用多种语言与人交流。",
"temperature": 0.7,
"subscribe_msg": "感谢您的关注!\n这里是AI智能助手可以自由对话。\n支持语音对话。\n支持图片输入。\n支持图片输出画字开头的消息将按要求创作图片。\n支持tool、角色扮演和文字冒险等丰富的插件。\n输入{trigger_prefix}#help 查看详细指令。",
"use_linkai": false,

View File

@@ -157,11 +157,13 @@ available_setting = {
# 智谱AI 平台配置
"zhipu_ai_api_key": "",
"zhipu_ai_api_base": "https://open.bigmodel.cn/api/paas/v4",
"moonshot_api_key": "",
"moonshot_base_url":"https://api.moonshot.cn/v1/chat/completions",
# LinkAI平台配置
"use_linkai": False,
"linkai_api_key": "",
"linkai_app_code": "",
"linkai_api_base": "https://api.link-ai.chat", # linkAI服务地址,若国内无法访问或延迟较高可改为 https://api.link-ai.tech
"linkai_api_base": "https://api.link-ai.tech", # linkAI服务地址
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 51 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 326 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 382 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 33 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 180 KiB

View File

@@ -68,7 +68,7 @@ class MJTask:
# midjourney bot
class MJBot:
def __init__(self, config):
self.base_url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/img/midjourney"
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.tasks = {}

View File

@@ -2,6 +2,7 @@ import requests
from config import conf
from common.log import logger
import os
import html
class LinkSummary:
@@ -18,6 +19,7 @@ class LinkSummary:
return self._parse_summary_res(res)
def summary_url(self, url: str):
url = html.unescape(url)
body = {
"url": url
}
@@ -59,7 +61,7 @@ class LinkSummary:
return None
def base_url(self):
return conf().get("linkai_api_base", "https://api.link-ai.chat")
return conf().get("linkai_api_base", "https://api.link-ai.tech")
def headers(self):
return {"Authorization": "Bearer " + conf().get("linkai_api_key")}

View File

@@ -7,4 +7,4 @@ chardet>=5.1.0
Pillow
pre-commit
web.py
linkai>=0.0.5.0
linkai>=0.0.6.0

View File

@@ -19,7 +19,7 @@ class LinkAIVoice(Voice):
def voiceToText(self, voice_file):
logger.debug("[LinkVoice] voice file name={}".format(voice_file))
try:
url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/audio/transcriptions"
url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/audio/transcriptions"
headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
model = None
if not conf().get("text_to_voice") or conf().get("voice_to_text") == "openai":
@@ -54,7 +54,7 @@ class LinkAIVoice(Voice):
def textToVoice(self, text):
try:
url = conf().get("linkai_api_base", "https://api.link-ai.chat") + "/v1/audio/speech"
url = conf().get("linkai_api_base", "https://api.link-ai.tech") + "/v1/audio/speech"
headers = {"Authorization": "Bearer " + conf().get("linkai_api_key")}
model = const.TTS_1
if not conf().get("text_to_voice") or conf().get("text_to_voice") in ["openai", const.TTS_1, const.TTS_1_HD]:

View File

@@ -21,8 +21,21 @@ class OpenaiVoice(Voice):
logger.debug("[Openai] voice file name={}".format(voice_file))
try:
file = open(voice_file, "rb")
result = openai.Audio.transcribe("whisper-1", file)
text = result["text"]
api_base = conf().get("open_ai_api_base") or "https://api.openai.com/v1"
url = f'{api_base}/audio/transcriptions'
headers = {
'Authorization': 'Bearer ' + conf().get("open_ai_api_key"),
# 'Content-Type': 'multipart/form-data' # 加了会报错,不知道什么原因
}
files = {
"file": file,
}
data = {
"model": "whisper-1",
}
response = requests.post(url, headers=headers, files=files, data=data)
response_data = response.json()
text = response_data['text']
reply = Reply(ReplyType.TEXT, text)
logger.info("[Openai] voiceToText text={} voice file name={}".format(text, voice_file))
except Exception as e: