Merge branch 'main-fix' into main
@@ -101,7 +101,7 @@
|
|||||||
|
|
||||||
<div align="center">
|
<div align="center">
|
||||||
<a href="https://www.bilibili.com/video/BV1amAneGE3P" target="_blank">
|
<a href="https://www.bilibili.com/video/BV1amAneGE3P" target="_blank">
|
||||||
<img src="docs/video.png" width="300" alt="麦麦演示视频">
|
<img src="docs/pic/video.png" width="300" alt="麦麦演示视频">
|
||||||
<br>
|
<br>
|
||||||
👆 点击观看麦麦演示视频 👆
|
👆 点击观看麦麦演示视频 👆
|
||||||
|
|
||||||
@@ -149,6 +149,8 @@ MaiMBot是一个开源项目,我们非常欢迎你的参与。你的贡献,
|
|||||||
|
|
||||||
- [📦 Linux 手动部署指南 ](docs/manual_deploy_linux.md)
|
- [📦 Linux 手动部署指南 ](docs/manual_deploy_linux.md)
|
||||||
|
|
||||||
|
- [📦 macOS 手动部署指南 ](docs/manual_deploy_macos.md)
|
||||||
|
|
||||||
如果你不知道Docker是什么,建议寻找相关教程或使用手动部署 **(现在不建议使用docker,更新慢,可能不适配)**
|
如果你不知道Docker是什么,建议寻找相关教程或使用手动部署 **(现在不建议使用docker,更新慢,可能不适配)**
|
||||||
|
|
||||||
- [🐳 Docker部署指南](docs/docker_deploy.md)
|
- [🐳 Docker部署指南](docs/docker_deploy.md)
|
||||||
|
|||||||
14
bot.py
@@ -204,8 +204,8 @@ def check_eula():
|
|||||||
eula_confirmed = True
|
eula_confirmed = True
|
||||||
eula_updated = False
|
eula_updated = False
|
||||||
if eula_new_hash == os.getenv("EULA_AGREE"):
|
if eula_new_hash == os.getenv("EULA_AGREE"):
|
||||||
eula_confirmed = True
|
eula_confirmed = True
|
||||||
eula_updated = False
|
eula_updated = False
|
||||||
|
|
||||||
# 检查隐私条款确认文件是否存在
|
# 检查隐私条款确认文件是否存在
|
||||||
if privacy_confirm_file.exists():
|
if privacy_confirm_file.exists():
|
||||||
@@ -214,14 +214,16 @@ def check_eula():
|
|||||||
if privacy_new_hash == confirmed_content:
|
if privacy_new_hash == confirmed_content:
|
||||||
privacy_confirmed = True
|
privacy_confirmed = True
|
||||||
privacy_updated = False
|
privacy_updated = False
|
||||||
if privacy_new_hash == os.getenv("PRIVACY_AGREE"):
|
if privacy_new_hash == os.getenv("PRIVACY_AGREE"):
|
||||||
privacy_confirmed = True
|
privacy_confirmed = True
|
||||||
privacy_updated = False
|
privacy_updated = False
|
||||||
|
|
||||||
# 如果EULA或隐私条款有更新,提示用户重新确认
|
# 如果EULA或隐私条款有更新,提示用户重新确认
|
||||||
if eula_updated or privacy_updated:
|
if eula_updated or privacy_updated:
|
||||||
print("EULA或隐私条款内容已更新,请在阅读后重新确认,继续运行视为同意更新后的以上两款协议")
|
print("EULA或隐私条款内容已更新,请在阅读后重新确认,继续运行视为同意更新后的以上两款协议")
|
||||||
print(f'输入"同意"或"confirmed"或设置环境变量"EULA_AGREE={eula_new_hash}"和"PRIVACY_AGREE={privacy_new_hash}"继续运行')
|
print(
|
||||||
|
f'输入"同意"或"confirmed"或设置环境变量"EULA_AGREE={eula_new_hash}"和"PRIVACY_AGREE={privacy_new_hash}"继续运行'
|
||||||
|
)
|
||||||
while True:
|
while True:
|
||||||
user_input = input().strip().lower()
|
user_input = input().strip().lower()
|
||||||
if user_input in ["同意", "confirmed"]:
|
if user_input in ["同意", "confirmed"]:
|
||||||
|
|||||||
@@ -10,7 +10,7 @@
|
|||||||
|
|
||||||
- 为什么显示:"缺失必要的API KEY" ❓
|
- 为什么显示:"缺失必要的API KEY" ❓
|
||||||
|
|
||||||
<img src="API_KEY.png" width=650>
|
<img src="./pic/API_KEY.png" width=650>
|
||||||
|
|
||||||
>你需要在 [Silicon Flow Api](https://cloud.siliconflow.cn/account/ak) 网站上注册一个账号,然后点击这个链接打开API KEY获取页面。
|
>你需要在 [Silicon Flow Api](https://cloud.siliconflow.cn/account/ak) 网站上注册一个账号,然后点击这个链接打开API KEY获取页面。
|
||||||
>
|
>
|
||||||
@@ -41,19 +41,19 @@
|
|||||||
|
|
||||||
>打开你的MongoDB Compass软件,你会在左上角看到这样的一个界面:
|
>打开你的MongoDB Compass软件,你会在左上角看到这样的一个界面:
|
||||||
>
|
>
|
||||||
><img src="MONGO_DB_0.png" width=250>
|
><img src="./pic/MONGO_DB_0.png" width=250>
|
||||||
>
|
>
|
||||||
><br>
|
><br>
|
||||||
>
|
>
|
||||||
>点击 "CONNECT" 之后,点击展开 MegBot 标签栏
|
>点击 "CONNECT" 之后,点击展开 MegBot 标签栏
|
||||||
>
|
>
|
||||||
><img src="MONGO_DB_1.png" width=250>
|
><img src="./pic/MONGO_DB_1.png" width=250>
|
||||||
>
|
>
|
||||||
><br>
|
><br>
|
||||||
>
|
>
|
||||||
>点进 "emoji" 再点击 "DELETE" 删掉所有条目,如图所示
|
>点进 "emoji" 再点击 "DELETE" 删掉所有条目,如图所示
|
||||||
>
|
>
|
||||||
><img src="MONGO_DB_2.png" width=450>
|
><img src="./pic/MONGO_DB_2.png" width=450>
|
||||||
>
|
>
|
||||||
><br>
|
><br>
|
||||||
>
|
>
|
||||||
|
|||||||
@@ -147,9 +147,7 @@ enable_check = false # 是否要检查表情包是不是合适的喵
|
|||||||
check_prompt = "符合公序良俗" # 检查表情包的标准呢
|
check_prompt = "符合公序良俗" # 检查表情包的标准呢
|
||||||
|
|
||||||
[others]
|
[others]
|
||||||
enable_advance_output = true # 是否要显示更多的运行信息呢
|
|
||||||
enable_kuuki_read = true # 让机器人能够"察言观色"喵
|
enable_kuuki_read = true # 让机器人能够"察言观色"喵
|
||||||
enable_debug_output = false # 是否启用调试输出喵
|
|
||||||
enable_friend_chat = false # 是否启用好友聊天喵
|
enable_friend_chat = false # 是否启用好友聊天喵
|
||||||
|
|
||||||
[groups]
|
[groups]
|
||||||
|
|||||||
@@ -115,9 +115,7 @@ talk_frequency_down = [] # 降低回复频率的群号
|
|||||||
ban_user_id = [] # 禁止回复的用户QQ号
|
ban_user_id = [] # 禁止回复的用户QQ号
|
||||||
|
|
||||||
[others]
|
[others]
|
||||||
enable_advance_output = true # 是否启用高级输出
|
|
||||||
enable_kuuki_read = true # 是否启用读空气功能
|
enable_kuuki_read = true # 是否启用读空气功能
|
||||||
enable_debug_output = false # 是否启用调试输出
|
|
||||||
enable_friend_chat = false # 是否启用好友聊天
|
enable_friend_chat = false # 是否启用好友聊天
|
||||||
|
|
||||||
# 模型配置
|
# 模型配置
|
||||||
|
|||||||
@@ -1,48 +1,51 @@
|
|||||||
# 面向纯新手的Linux服务器麦麦部署指南
|
# 面向纯新手的Linux服务器麦麦部署指南
|
||||||
|
|
||||||
## 你得先有一个服务器
|
|
||||||
|
|
||||||
为了能使麦麦在你的电脑关机之后还能运行,你需要一台不间断开机的主机,也就是我们常说的服务器。
|
## 事前准备
|
||||||
|
为了能使麦麦不间断的运行,你需要一台一直开着的主机。
|
||||||
|
|
||||||
|
### 如果你想购买服务器
|
||||||
华为云、阿里云、腾讯云等等都是在国内可以选择的选择。
|
华为云、阿里云、腾讯云等等都是在国内可以选择的选择。
|
||||||
|
|
||||||
你可以去租一台最低配置的就足敷需要了,按月租大概十几块钱就能租到了。
|
租一台最低配置的就足敷需要了,按月租大概十几块钱就能租到了。
|
||||||
|
|
||||||
我们假设你已经租好了一台Linux架构的云服务器。我用的是阿里云ubuntu24.04,其他的原理相似。
|
### 如果你不想购买服务器
|
||||||
|
你可以准备一台可以一直开着的电脑/主机,只需要保证能够正常访问互联网即可
|
||||||
|
|
||||||
|
我们假设你已经有了一台Linux架构的服务器。举例使用的是Ubuntu24.04,其他的原理相似。
|
||||||
|
|
||||||
## 0.我们就从零开始吧
|
## 0.我们就从零开始吧
|
||||||
|
|
||||||
### 网络问题
|
### 网络问题
|
||||||
|
|
||||||
为访问github相关界面,推荐去下一款加速器,新手可以试试watttoolkit。
|
为访问Github相关界面,推荐去下一款加速器,新手可以试试[Watt Toolkit](https://gitee.com/rmbgame/SteamTools/releases/latest)。
|
||||||
|
|
||||||
### 安装包下载
|
### 安装包下载
|
||||||
|
|
||||||
#### MongoDB
|
#### MongoDB
|
||||||
|
进入[MongoDB下载页](https://www.mongodb.com/try/download/community-kubernetes-operator),并选择版本
|
||||||
|
|
||||||
对于ubuntu24.04 x86来说是这个:
|
以Ubuntu24.04 x86为例,保持如图所示选项,点击`Download`即可,如果是其他系统,请在`Platform`中自行选择:
|
||||||
|
|
||||||
https://repo.mongodb.org/apt/ubuntu/dists/noble/mongodb-org/8.0/multiverse/binary-amd64/mongodb-org-server_8.0.5_amd64.deb
|

|
||||||
|
|
||||||
如果不是就在这里自行选择对应版本
|
|
||||||
|
|
||||||
https://www.mongodb.com/try/download/community-kubernetes-operator
|
不想使用上述方式?你也可以参考[官方文档](https://www.mongodb.com/zh-cn/docs/manual/administration/install-on-linux/#std-label-install-mdb-community-edition-linux)进行安装,进入后选择自己的系统版本即可
|
||||||
|
|
||||||
#### Napcat
|
#### QQ(可选)/Napcat
|
||||||
|
*如果你使用Napcat的脚本安装,可以忽略此步*
|
||||||
在这里选择对应版本。
|
访问https://github.com/NapNeko/NapCatQQ/releases/latest
|
||||||
|
在图中所示区域可以找到QQ的下载链接,选择对应版本下载即可
|
||||||
https://github.com/NapNeko/NapCatQQ/releases/tag/v4.6.7
|
从这里下载,可以保证你下载到的QQ版本兼容最新版Napcat
|
||||||
|

|
||||||
对于ubuntu24.04 x86来说是这个:
|
如果你不想使用Napcat的脚本安装,还需参考[Napcat-Linux手动安装](https://www.napcat.wiki/guide/boot/Shell-Linux-SemiAuto)
|
||||||
|
|
||||||
https://dldir1.qq.com/qqfile/qq/QQNT/ee4bd910/linuxqq_3.2.16-32793_amd64.deb
|
|
||||||
|
|
||||||
#### 麦麦
|
#### 麦麦
|
||||||
|
|
||||||
https://github.com/SengokuCola/MaiMBot/archive/refs/tags/0.5.8-alpha.zip
|
先打开https://github.com/MaiM-with-u/MaiBot/releases
|
||||||
|
往下滑找到这个
|
||||||
下载这个官方压缩包。
|

|
||||||
|
下载箭头所指这个压缩包。
|
||||||
|
|
||||||
### 路径
|
### 路径
|
||||||
|
|
||||||
@@ -53,10 +56,10 @@ https://github.com/SengokuCola/MaiMBot/archive/refs/tags/0.5.8-alpha.zip
|
|||||||
```
|
```
|
||||||
moi
|
moi
|
||||||
└─ mai
|
└─ mai
|
||||||
├─ linuxqq_3.2.16-32793_amd64.deb
|
├─ linuxqq_3.2.16-32793_amd64.deb # linuxqq安装包
|
||||||
├─ mongodb-org-server_8.0.5_amd64.deb
|
├─ mongodb-org-server_8.0.5_amd64.deb # MongoDB的安装包
|
||||||
└─ bot
|
└─ bot
|
||||||
└─ MaiMBot-0.5.8-alpha.zip
|
└─ MaiMBot-0.5.8-alpha.zip # 麦麦的压缩包
|
||||||
```
|
```
|
||||||
|
|
||||||
### 网络
|
### 网络
|
||||||
@@ -69,7 +72,7 @@ moi
|
|||||||
|
|
||||||
## 2. Python的安装
|
## 2. Python的安装
|
||||||
|
|
||||||
- 导入 Python 的稳定版 PPA:
|
- 导入 Python 的稳定版 PPA(Ubuntu需执行此步,Debian可忽略):
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
sudo add-apt-repository ppa:deadsnakes/ppa
|
sudo add-apt-repository ppa:deadsnakes/ppa
|
||||||
@@ -92,6 +95,11 @@ sudo apt install python3.12
|
|||||||
```bash
|
```bash
|
||||||
python3.12 --version
|
python3.12 --version
|
||||||
```
|
```
|
||||||
|
- (可选)更新替代方案,设置 python3.12 为默认的 python3 版本:
|
||||||
|
```bash
|
||||||
|
sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 1
|
||||||
|
sudo update-alternatives --config python3
|
||||||
|
```
|
||||||
|
|
||||||
- 在「终端」中,执行以下命令安装 pip:
|
- 在「终端」中,执行以下命令安装 pip:
|
||||||
|
|
||||||
@@ -141,23 +149,17 @@ systemctl status mongod #通过这条指令检查运行状态
|
|||||||
sudo systemctl enable mongod
|
sudo systemctl enable mongod
|
||||||
```
|
```
|
||||||
|
|
||||||
## 5.napcat的安装
|
## 5.Napcat的安装
|
||||||
|
|
||||||
``` bash
|
``` bash
|
||||||
|
# 该脚本适用于支持Ubuntu 20+/Debian 10+/Centos9
|
||||||
curl -o napcat.sh https://nclatest.znin.net/NapNeko/NapCat-Installer/main/script/install.sh && sudo bash napcat.sh
|
curl -o napcat.sh https://nclatest.znin.net/NapNeko/NapCat-Installer/main/script/install.sh && sudo bash napcat.sh
|
||||||
```
|
```
|
||||||
|
执行后,脚本会自动帮你部署好QQ及Napcat
|
||||||
上面的不行试试下面的
|
|
||||||
|
|
||||||
``` bash
|
|
||||||
dpkg -i linuxqq_3.2.16-32793_amd64.deb
|
|
||||||
apt-get install -f
|
|
||||||
dpkg -i linuxqq_3.2.16-32793_amd64.deb
|
|
||||||
```
|
|
||||||
|
|
||||||
成功的标志是输入``` napcat ```出来炫酷的彩虹色界面
|
成功的标志是输入``` napcat ```出来炫酷的彩虹色界面
|
||||||
|
|
||||||
## 6.napcat的运行
|
## 6.Napcat的运行
|
||||||
|
|
||||||
此时你就可以根据提示在```napcat```里面登录你的QQ号了。
|
此时你就可以根据提示在```napcat```里面登录你的QQ号了。
|
||||||
|
|
||||||
@@ -170,6 +172,13 @@ napcat status #检查运行状态
|
|||||||
|
|
||||||
```http://<你服务器的公网IP>:6099/webui?token=napcat```
|
```http://<你服务器的公网IP>:6099/webui?token=napcat```
|
||||||
|
|
||||||
|
如果你部署在自己的电脑上:
|
||||||
|
```http://127.0.0.1:6099/webui?token=napcat```
|
||||||
|
|
||||||
|
> [!WARNING]
|
||||||
|
> 如果你的麦麦部署在公网,请**务必**修改Napcat的默认密码
|
||||||
|
|
||||||
|
|
||||||
第一次是这个,后续改了密码之后token就会对应修改。你也可以使用```napcat log <你的QQ号>```来查看webui地址。把里面的```127.0.0.1```改成<你服务器的公网IP>即可。
|
第一次是这个,后续改了密码之后token就会对应修改。你也可以使用```napcat log <你的QQ号>```来查看webui地址。把里面的```127.0.0.1```改成<你服务器的公网IP>即可。
|
||||||
|
|
||||||
登录上之后在网络配置界面添加websocket客户端,名称随便输一个,url改成`ws://127.0.0.1:8080/onebot/v11/ws`保存之后点启用,就大功告成了。
|
登录上之后在网络配置界面添加websocket客户端,名称随便输一个,url改成`ws://127.0.0.1:8080/onebot/v11/ws`保存之后点启用,就大功告成了。
|
||||||
@@ -178,7 +187,7 @@ napcat status #检查运行状态
|
|||||||
|
|
||||||
### step 1 安装解压软件
|
### step 1 安装解压软件
|
||||||
|
|
||||||
```
|
```bash
|
||||||
sudo apt-get install unzip
|
sudo apt-get install unzip
|
||||||
```
|
```
|
||||||
|
|
||||||
@@ -229,138 +238,11 @@ bot
|
|||||||
|
|
||||||
你可以注册一个硅基流动的账号,通过邀请码注册有14块钱的免费额度:https://cloud.siliconflow.cn/i/7Yld7cfg。
|
你可以注册一个硅基流动的账号,通过邀请码注册有14块钱的免费额度:https://cloud.siliconflow.cn/i/7Yld7cfg。
|
||||||
|
|
||||||
#### 在.env.prod中定义API凭证:
|
#### 修改配置文件
|
||||||
|
请参考
|
||||||
|
- [🎀 新手配置指南](./installation_cute.md) - 通俗易懂的配置教程,适合初次使用的猫娘
|
||||||
|
- [⚙️ 标准配置指南](./installation_standard.md) - 简明专业的配置说明,适合有经验的用户
|
||||||
|
|
||||||
```
|
|
||||||
# API凭证配置
|
|
||||||
SILICONFLOW_KEY=your_key # 硅基流动API密钥
|
|
||||||
SILICONFLOW_BASE_URL=https://api.siliconflow.cn/v1/ # 硅基流动API地址
|
|
||||||
|
|
||||||
DEEP_SEEK_KEY=your_key # DeepSeek API密钥
|
|
||||||
DEEP_SEEK_BASE_URL=https://api.deepseek.com/v1 # DeepSeek API地址
|
|
||||||
|
|
||||||
CHAT_ANY_WHERE_KEY=your_key # ChatAnyWhere API密钥
|
|
||||||
CHAT_ANY_WHERE_BASE_URL=https://api.chatanywhere.tech/v1 # ChatAnyWhere API地址
|
|
||||||
```
|
|
||||||
|
|
||||||
#### 在bot_config.toml中引用API凭证:
|
|
||||||
|
|
||||||
```
|
|
||||||
[model.llm_reasoning]
|
|
||||||
name = "Pro/deepseek-ai/DeepSeek-R1"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL" # 引用.env.prod中定义的地址
|
|
||||||
key = "SILICONFLOW_KEY" # 引用.env.prod中定义的密钥
|
|
||||||
```
|
|
||||||
|
|
||||||
如需切换到其他API服务,只需修改引用:
|
|
||||||
|
|
||||||
```
|
|
||||||
[model.llm_reasoning]
|
|
||||||
name = "Pro/deepseek-ai/DeepSeek-R1"
|
|
||||||
base_url = "DEEP_SEEK_BASE_URL" # 切换为DeepSeek服务
|
|
||||||
key = "DEEP_SEEK_KEY" # 使用DeepSeek密钥
|
|
||||||
```
|
|
||||||
|
|
||||||
#### 配置文件详解
|
|
||||||
|
|
||||||
##### 环境配置文件 (.env.prod)
|
|
||||||
|
|
||||||
```
|
|
||||||
# API配置
|
|
||||||
SILICONFLOW_KEY=your_key
|
|
||||||
SILICONFLOW_BASE_URL=https://api.siliconflow.cn/v1/
|
|
||||||
DEEP_SEEK_KEY=your_key
|
|
||||||
DEEP_SEEK_BASE_URL=https://api.deepseek.com/v1
|
|
||||||
CHAT_ANY_WHERE_KEY=your_key
|
|
||||||
CHAT_ANY_WHERE_BASE_URL=https://api.chatanywhere.tech/v1
|
|
||||||
|
|
||||||
# 服务配置
|
|
||||||
HOST=127.0.0.1 # 如果使用Docker部署,需要改成0.0.0.0,否则QQ消息无法传入
|
|
||||||
PORT=8080
|
|
||||||
|
|
||||||
# 数据库配置
|
|
||||||
MONGODB_HOST=127.0.0.1 # 如果使用Docker部署,需要改成数据库容器的名字,默认是mongodb
|
|
||||||
MONGODB_PORT=27017
|
|
||||||
DATABASE_NAME=MegBot
|
|
||||||
MONGODB_USERNAME = "" # 数据库用户名
|
|
||||||
MONGODB_PASSWORD = "" # 数据库密码
|
|
||||||
MONGODB_AUTH_SOURCE = "" # 认证数据库
|
|
||||||
|
|
||||||
# 插件配置
|
|
||||||
PLUGINS=["src2.plugins.chat"]
|
|
||||||
```
|
|
||||||
|
|
||||||
##### 机器人配置文件 (bot_config.toml)
|
|
||||||
|
|
||||||
```
|
|
||||||
[bot]
|
|
||||||
qq = "机器人QQ号" # 必填
|
|
||||||
nickname = "麦麦" # 机器人昵称(你希望机器人怎么称呼它自己)
|
|
||||||
|
|
||||||
[personality]
|
|
||||||
prompt_personality = [
|
|
||||||
"曾经是一个学习地质的女大学生,现在学习心理学和脑科学,你会刷贴吧",
|
|
||||||
"是一个女大学生,你有黑色头发,你会刷小红书"
|
|
||||||
]
|
|
||||||
prompt_schedule = "一个曾经学习地质,现在学习心理学和脑科学的女大学生,喜欢刷qq,贴吧,知乎和小红书"
|
|
||||||
|
|
||||||
[message]
|
|
||||||
min_text_length = 2 # 最小回复长度
|
|
||||||
max_context_size = 15 # 上下文记忆条数
|
|
||||||
emoji_chance = 0.2 # 表情使用概率
|
|
||||||
ban_words = [] # 禁用词列表
|
|
||||||
|
|
||||||
[emoji]
|
|
||||||
auto_save = true # 自动保存表情
|
|
||||||
enable_check = false # 启用表情审核
|
|
||||||
check_prompt = "符合公序良俗"
|
|
||||||
|
|
||||||
[groups]
|
|
||||||
talk_allowed = [] # 允许对话的群号
|
|
||||||
talk_frequency_down = [] # 降低回复频率的群号
|
|
||||||
ban_user_id = [] # 禁止回复的用户QQ号
|
|
||||||
|
|
||||||
[others]
|
|
||||||
enable_advance_output = true # 启用详细日志
|
|
||||||
enable_kuuki_read = true # 启用场景理解
|
|
||||||
|
|
||||||
# 模型配置
|
|
||||||
[model.llm_reasoning] # 推理模型
|
|
||||||
name = "Pro/deepseek-ai/DeepSeek-R1"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
[model.llm_reasoning_minor] # 轻量推理模型
|
|
||||||
name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
[model.llm_normal] # 对话模型
|
|
||||||
name = "Pro/deepseek-ai/DeepSeek-V3"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
[model.llm_normal_minor] # 备用对话模型
|
|
||||||
name = "deepseek-ai/DeepSeek-V2.5"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
[model.vlm] # 图像识别模型
|
|
||||||
name = "deepseek-ai/deepseek-vl2"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
[model.embedding] # 文本向量模型
|
|
||||||
name = "BAAI/bge-m3"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
|
|
||||||
|
|
||||||
[topic.llm_topic]
|
|
||||||
name = "Pro/deepseek-ai/DeepSeek-V3"
|
|
||||||
base_url = "SILICONFLOW_BASE_URL"
|
|
||||||
key = "SILICONFLOW_KEY"
|
|
||||||
```
|
|
||||||
|
|
||||||
**step # 6** 运行
|
**step # 6** 运行
|
||||||
|
|
||||||
@@ -438,7 +320,7 @@ sudo systemctl enable bot.service # 启动bot服务
|
|||||||
sudo systemctl status bot.service # 检查bot服务状态
|
sudo systemctl status bot.service # 检查bot服务状态
|
||||||
```
|
```
|
||||||
|
|
||||||
```
|
```bash
|
||||||
python bot.py
|
python bot.py # 运行麦麦
|
||||||
```
|
```
|
||||||
|
|
||||||
|
|||||||
@@ -6,7 +6,7 @@
|
|||||||
- QQ小号(QQ框架的使用可能导致qq被风控,严重(小概率)可能会导致账号封禁,强烈不推荐使用大号)
|
- QQ小号(QQ框架的使用可能导致qq被风控,严重(小概率)可能会导致账号封禁,强烈不推荐使用大号)
|
||||||
- 可用的大模型API
|
- 可用的大模型API
|
||||||
- 一个AI助手,网上随便搜一家打开来用都行,可以帮你解决一些不懂的问题
|
- 一个AI助手,网上随便搜一家打开来用都行,可以帮你解决一些不懂的问题
|
||||||
- 以下内容假设你对Linux系统有一定的了解,如果觉得难以理解,请直接用Windows系统部署[Windows系统部署指南](./manual_deploy_windows.md)
|
- 以下内容假设你对Linux系统有一定的了解,如果觉得难以理解,请直接用Windows系统部署[Windows系统部署指南](./manual_deploy_windows.md)或[使用Windows一键包部署](https://github.com/MaiM-with-u/MaiBot/releases/tag/EasyInstall-windows)
|
||||||
|
|
||||||
## 你需要知道什么?
|
## 你需要知道什么?
|
||||||
|
|
||||||
@@ -24,6 +24,9 @@
|
|||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
## 一键部署
|
||||||
|
请下载并运行项目根目录中的run.sh并按照提示安装,部署完成后请参照后续配置指南进行配置
|
||||||
|
|
||||||
## 环境配置
|
## 环境配置
|
||||||
|
|
||||||
### 1️⃣ **确认Python版本**
|
### 1️⃣ **确认Python版本**
|
||||||
@@ -36,17 +39,26 @@ python --version
|
|||||||
python3 --version
|
python3 --version
|
||||||
```
|
```
|
||||||
|
|
||||||
如果版本低于3.9,请更新Python版本。
|
如果版本低于3.9,请更新Python版本,目前建议使用python3.12
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# Ubuntu/Debian
|
# Debian
|
||||||
sudo apt update
|
sudo apt update
|
||||||
sudo apt install python3.9
|
sudo apt install python3.12
|
||||||
# 如执行了这一步,建议在执行时将python3指向python3.9
|
# Ubuntu
|
||||||
# 更新替代方案,设置 python3.9 为默认的 python3 版本:
|
sudo add-apt-repository ppa:deadsnakes/ppa
|
||||||
sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1
|
sudo apt update
|
||||||
|
sudo apt install python3.12
|
||||||
|
|
||||||
|
# 执行完以上命令后,建议在执行时将python3指向python3.12
|
||||||
|
# 更新替代方案,设置 python3.12 为默认的 python3 版本:
|
||||||
|
sudo update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.12 1
|
||||||
sudo update-alternatives --config python3
|
sudo update-alternatives --config python3
|
||||||
```
|
```
|
||||||
|
建议再执行以下命令,使后续运行命令中的`python3`等同于`python`
|
||||||
|
```bash
|
||||||
|
sudo apt install python-is-python3
|
||||||
|
```
|
||||||
|
|
||||||
### 2️⃣ **创建虚拟环境**
|
### 2️⃣ **创建虚拟环境**
|
||||||
|
|
||||||
@@ -73,7 +85,7 @@ pip install -r requirements.txt
|
|||||||
|
|
||||||
### 3️⃣ **安装并启动MongoDB**
|
### 3️⃣ **安装并启动MongoDB**
|
||||||
|
|
||||||
- 安装与启动:Debian参考[官方文档](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-debian/),Ubuntu参考[官方文档](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-ubuntu/)
|
- 安装与启动:请参考[官方文档](https://www.mongodb.com/zh-cn/docs/manual/administration/install-on-linux/#std-label-install-mdb-community-edition-linux),进入后选择自己的系统版本即可
|
||||||
- 默认连接本地27017端口
|
- 默认连接本地27017端口
|
||||||
|
|
||||||
---
|
---
|
||||||
@@ -82,7 +94,11 @@ pip install -r requirements.txt
|
|||||||
|
|
||||||
### 4️⃣ **安装NapCat框架**
|
### 4️⃣ **安装NapCat框架**
|
||||||
|
|
||||||
- 参考[NapCat官方文档](https://www.napcat.wiki/guide/boot/Shell#napcat-installer-linux%E4%B8%80%E9%94%AE%E4%BD%BF%E7%94%A8%E8%84%9A%E6%9C%AC-%E6%94%AF%E6%8C%81ubuntu-20-debian-10-centos9)安装
|
- 执行NapCat的Linux一键使用脚本(支持Ubuntu 20+/Debian 10+/Centos9)
|
||||||
|
```bash
|
||||||
|
curl -o napcat.sh https://nclatest.znin.net/NapNeko/NapCat-Installer/main/script/install.sh && sudo bash napcat.sh
|
||||||
|
```
|
||||||
|
- 如果你不想使用Napcat的脚本安装,可参考[Napcat-Linux手动安装](https://www.napcat.wiki/guide/boot/Shell-Linux-SemiAuto)
|
||||||
|
|
||||||
- 使用QQ小号登录,添加反向WS地址: `ws://127.0.0.1:8080/onebot/v11/ws`
|
- 使用QQ小号登录,添加反向WS地址: `ws://127.0.0.1:8080/onebot/v11/ws`
|
||||||
|
|
||||||
@@ -91,9 +107,17 @@ pip install -r requirements.txt
|
|||||||
## 配置文件设置
|
## 配置文件设置
|
||||||
|
|
||||||
### 5️⃣ **配置文件设置,让麦麦Bot正常工作**
|
### 5️⃣ **配置文件设置,让麦麦Bot正常工作**
|
||||||
|
可先运行一次
|
||||||
- 修改环境配置文件:`.env.prod`
|
```bash
|
||||||
- 修改机器人配置文件:`bot_config.toml`
|
# 在项目目录下操作
|
||||||
|
nb run
|
||||||
|
# 或
|
||||||
|
python3 bot.py
|
||||||
|
```
|
||||||
|
之后你就可以找到`.env.prod`和`bot_config.toml`这两个文件了
|
||||||
|
关于文件内容的配置请参考:
|
||||||
|
- [🎀 新手配置指南](./installation_cute.md) - 通俗易懂的配置教程,适合初次使用的猫娘
|
||||||
|
- [⚙️ 标准配置指南](./installation_standard.md) - 简明专业的配置说明,适合有经验的用户
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
|
|||||||
201
docs/manual_deploy_macos.md
Normal file
@@ -0,0 +1,201 @@
|
|||||||
|
# 📦 macOS系统手动部署MaiMbot麦麦指南
|
||||||
|
|
||||||
|
## 准备工作
|
||||||
|
|
||||||
|
- 一台搭载了macOS系统的设备(macOS 12.0 或以上)
|
||||||
|
- QQ小号(QQ框架的使用可能导致qq被风控,严重(小概率)可能会导致账号封禁,强烈不推荐使用大号)
|
||||||
|
- Homebrew包管理器
|
||||||
|
- 如未安装,你可以在https://github.com/Homebrew/brew/releases/latest 找到.pkg格式的安装包
|
||||||
|
- 可用的大模型API
|
||||||
|
- 一个AI助手,网上随便搜一家打开来用都行,可以帮你解决一些不懂的问题
|
||||||
|
- 以下内容假设你对macOS系统有一定的了解,如果觉得难以理解,请直接用Windows系统部署[Windows系统部署指南](./manual_deploy_windows.md)或[使用Windows一键包部署](https://github.com/MaiM-with-u/MaiBot/releases/tag/EasyInstall-windows)
|
||||||
|
- 终端应用(iTerm2等)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 环境配置
|
||||||
|
|
||||||
|
### 1️⃣ **Python环境配置**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 检查Python版本(macOS自带python可能为2.7)
|
||||||
|
python3 --version
|
||||||
|
|
||||||
|
# 通过Homebrew安装Python
|
||||||
|
brew install python@3.12
|
||||||
|
|
||||||
|
# 设置环境变量(如使用zsh)
|
||||||
|
echo 'export PATH="/usr/local/opt/python@3.12/bin:$PATH"' >> ~/.zshrc
|
||||||
|
source ~/.zshrc
|
||||||
|
|
||||||
|
# 验证安装
|
||||||
|
python3 --version # 应显示3.12.x
|
||||||
|
pip3 --version # 应关联3.12版本
|
||||||
|
```
|
||||||
|
|
||||||
|
### 2️⃣ **创建虚拟环境**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 方法1:使用venv(推荐)
|
||||||
|
python3 -m venv maimbot-venv
|
||||||
|
source maimbot-venv/bin/activate # 激活虚拟环境
|
||||||
|
|
||||||
|
# 方法2:使用conda
|
||||||
|
brew install --cask miniconda
|
||||||
|
conda create -n maimbot python=3.9
|
||||||
|
conda activate maimbot # 激活虚拟环境
|
||||||
|
|
||||||
|
# 安装项目依赖
|
||||||
|
# 请确保已经进入虚拟环境再执行
|
||||||
|
pip install -r requirements.txt
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 数据库配置
|
||||||
|
|
||||||
|
### 3️⃣ **安装MongoDB**
|
||||||
|
|
||||||
|
请参考[官方文档](https://www.mongodb.com/zh-cn/docs/manual/tutorial/install-mongodb-on-os-x/#install-mongodb-community-edition)
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## NapCat
|
||||||
|
|
||||||
|
### 4️⃣ **安装与配置Napcat**
|
||||||
|
- 安装
|
||||||
|
可以使用Napcat官方提供的[macOS安装工具](https://github.com/NapNeko/NapCat-Mac-Installer/releases/)
|
||||||
|
由于权限问题,补丁过程需要手动替换 package.json,请注意备份原文件~
|
||||||
|
- 配置
|
||||||
|
使用QQ小号登录,添加反向WS地址: `ws://127.0.0.1:8080/onebot/v11/ws`
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 配置文件设置
|
||||||
|
|
||||||
|
### 5️⃣ **生成配置文件**
|
||||||
|
可先运行一次
|
||||||
|
```bash
|
||||||
|
# 在项目目录下操作
|
||||||
|
nb run
|
||||||
|
# 或
|
||||||
|
python3 bot.py
|
||||||
|
```
|
||||||
|
|
||||||
|
之后你就可以找到`.env.prod`和`bot_config.toml`这两个文件了
|
||||||
|
|
||||||
|
关于文件内容的配置请参考:
|
||||||
|
- [🎀 新手配置指南](./installation_cute.md) - 通俗易懂的配置教程,适合初次使用的猫娘
|
||||||
|
- [⚙️ 标准配置指南](./installation_standard.md) - 简明专业的配置说明,适合有经验的用户
|
||||||
|
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 启动机器人
|
||||||
|
|
||||||
|
### 6️⃣ **启动麦麦机器人**
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# 在项目目录下操作
|
||||||
|
nb run
|
||||||
|
# 或
|
||||||
|
python3 bot.py
|
||||||
|
```
|
||||||
|
|
||||||
|
## 启动管理
|
||||||
|
|
||||||
|
### 7️⃣ **通过launchd管理服务**
|
||||||
|
|
||||||
|
创建plist文件:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
nano ~/Library/LaunchAgents/com.maimbot.plist
|
||||||
|
```
|
||||||
|
|
||||||
|
内容示例(需替换实际路径):
|
||||||
|
|
||||||
|
```xml
|
||||||
|
<?xml version="1.0" encoding="UTF-8"?>
|
||||||
|
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
|
||||||
|
<plist version="1.0">
|
||||||
|
<dict>
|
||||||
|
<key>Label</key>
|
||||||
|
<string>com.maimbot</string>
|
||||||
|
|
||||||
|
<key>ProgramArguments</key>
|
||||||
|
<array>
|
||||||
|
<string>/path/to/maimbot-venv/bin/python</string>
|
||||||
|
<string>/path/to/MaiMbot/bot.py</string>
|
||||||
|
</array>
|
||||||
|
|
||||||
|
<key>WorkingDirectory</key>
|
||||||
|
<string>/path/to/MaiMbot</string>
|
||||||
|
|
||||||
|
<key>StandardOutPath</key>
|
||||||
|
<string>/tmp/maimbot.log</string>
|
||||||
|
<key>StandardErrorPath</key>
|
||||||
|
<string>/tmp/maimbot.err</string>
|
||||||
|
|
||||||
|
<key>RunAtLoad</key>
|
||||||
|
<true/>
|
||||||
|
<key>KeepAlive</key>
|
||||||
|
<true/>
|
||||||
|
</dict>
|
||||||
|
</plist>
|
||||||
|
```
|
||||||
|
|
||||||
|
加载服务:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
launchctl load ~/Library/LaunchAgents/com.maimbot.plist
|
||||||
|
launchctl start com.maimbot
|
||||||
|
```
|
||||||
|
|
||||||
|
查看日志:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
tail -f /tmp/maimbot.log
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 常见问题处理
|
||||||
|
|
||||||
|
1. **权限问题**
|
||||||
|
```bash
|
||||||
|
# 遇到文件权限错误时
|
||||||
|
chmod -R 755 ~/Documents/MaiMbot
|
||||||
|
```
|
||||||
|
|
||||||
|
2. **Python模块缺失**
|
||||||
|
```bash
|
||||||
|
# 确保在虚拟环境中
|
||||||
|
source maimbot-venv/bin/activate # 或 conda 激活
|
||||||
|
pip install --force-reinstall -r requirements.txt
|
||||||
|
```
|
||||||
|
|
||||||
|
3. **MongoDB连接失败**
|
||||||
|
```bash
|
||||||
|
# 检查服务状态
|
||||||
|
brew services list
|
||||||
|
# 重置数据库权限
|
||||||
|
mongosh --eval "db.adminCommand({setFeatureCompatibilityVersion: '5.0'})"
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## 系统优化建议
|
||||||
|
|
||||||
|
1. **关闭App Nap**
|
||||||
|
```bash
|
||||||
|
# 防止系统休眠NapCat进程
|
||||||
|
defaults write NSGlobalDomain NSAppSleepDisabled -bool YES
|
||||||
|
```
|
||||||
|
|
||||||
|
2. **电源管理设置**
|
||||||
|
```bash
|
||||||
|
# 防止睡眠影响机器人运行
|
||||||
|
sudo systemsetup -setcomputersleep Never
|
||||||
|
```
|
||||||
|
|
||||||
|
---
|
||||||
|
Before Width: | Height: | Size: 47 KiB After Width: | Height: | Size: 47 KiB |
|
Before Width: | Height: | Size: 13 KiB After Width: | Height: | Size: 13 KiB |
|
Before Width: | Height: | Size: 27 KiB After Width: | Height: | Size: 27 KiB |
|
Before Width: | Height: | Size: 31 KiB After Width: | Height: | Size: 31 KiB |
BIN
docs/pic/MongoDB_Ubuntu_guide.png
Normal file
|
After Width: | Height: | Size: 14 KiB |
BIN
docs/pic/QQ_Download_guide_Linux.png
Normal file
|
After Width: | Height: | Size: 37 KiB |
BIN
docs/pic/linux_beginner_downloadguide.png
Normal file
|
After Width: | Height: | Size: 10 KiB |
|
Before Width: | Height: | Size: 107 KiB After Width: | Height: | Size: 107 KiB |
|
Before Width: | Height: | Size: 208 KiB After Width: | Height: | Size: 208 KiB |
|
Before Width: | Height: | Size: 170 KiB After Width: | Height: | Size: 170 KiB |
|
Before Width: | Height: | Size: 133 KiB After Width: | Height: | Size: 133 KiB |
|
Before Width: | Height: | Size: 27 KiB After Width: | Height: | Size: 27 KiB |
@@ -16,7 +16,7 @@
|
|||||||
|
|
||||||
docker-compose.yml: https://github.com/SengokuCola/MaiMBot/blob/main/docker-compose.yml
|
docker-compose.yml: https://github.com/SengokuCola/MaiMBot/blob/main/docker-compose.yml
|
||||||
下载后打开,将 `services-mongodb-image` 修改为 `mongo:4.4.24`。这是因为最新的 MongoDB 强制要求 AVX 指令集,而群晖似乎不支持这个指令集
|
下载后打开,将 `services-mongodb-image` 修改为 `mongo:4.4.24`。这是因为最新的 MongoDB 强制要求 AVX 指令集,而群晖似乎不支持这个指令集
|
||||||

|

|
||||||
|
|
||||||
bot_config.toml: https://github.com/SengokuCola/MaiMBot/blob/main/template/bot_config_template.toml
|
bot_config.toml: https://github.com/SengokuCola/MaiMBot/blob/main/template/bot_config_template.toml
|
||||||
下载后,重命名为 `bot_config.toml`
|
下载后,重命名为 `bot_config.toml`
|
||||||
@@ -26,13 +26,13 @@ bot_config.toml: https://github.com/SengokuCola/MaiMBot/blob/main/template/bot_c
|
|||||||
下载后,重命名为 `.env.prod`
|
下载后,重命名为 `.env.prod`
|
||||||
将 `HOST` 修改为 `0.0.0.0`,确保 maimbot 能被 napcat 访问
|
将 `HOST` 修改为 `0.0.0.0`,确保 maimbot 能被 napcat 访问
|
||||||
按下图修改 mongodb 设置,使用 `MONGODB_URI`
|
按下图修改 mongodb 设置,使用 `MONGODB_URI`
|
||||||

|

|
||||||
|
|
||||||
把 `bot_config.toml` 和 `.env.prod` 放入之前创建的 `MaiMBot`文件夹
|
把 `bot_config.toml` 和 `.env.prod` 放入之前创建的 `MaiMBot`文件夹
|
||||||
|
|
||||||
#### 如何下载?
|
#### 如何下载?
|
||||||
|
|
||||||
点这里!
|
点这里!
|
||||||
|
|
||||||
### 创建项目
|
### 创建项目
|
||||||
|
|
||||||
@@ -45,7 +45,7 @@ bot_config.toml: https://github.com/SengokuCola/MaiMBot/blob/main/template/bot_c
|
|||||||
|
|
||||||
图例:
|
图例:
|
||||||
|
|
||||||

|

|
||||||
|
|
||||||
一路点下一步,等待项目创建完成
|
一路点下一步,等待项目创建完成
|
||||||
|
|
||||||
|
|||||||
@@ -31,9 +31,10 @@ _handler_registry: Dict[str, List[int]] = {}
|
|||||||
current_file_path = Path(__file__).resolve()
|
current_file_path = Path(__file__).resolve()
|
||||||
LOG_ROOT = "logs"
|
LOG_ROOT = "logs"
|
||||||
|
|
||||||
ENABLE_ADVANCE_OUTPUT = False
|
SIMPLE_OUTPUT = os.getenv("SIMPLE_OUTPUT", "false")
|
||||||
|
print(f"SIMPLE_OUTPUT: {SIMPLE_OUTPUT}")
|
||||||
|
|
||||||
if ENABLE_ADVANCE_OUTPUT:
|
if not SIMPLE_OUTPUT:
|
||||||
# 默认全局配置
|
# 默认全局配置
|
||||||
DEFAULT_CONFIG = {
|
DEFAULT_CONFIG = {
|
||||||
# 日志级别配置
|
# 日志级别配置
|
||||||
@@ -85,7 +86,6 @@ MEMORY_STYLE_CONFIG = {
|
|||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
# 海马体日志样式配置
|
|
||||||
SENDER_STYLE_CONFIG = {
|
SENDER_STYLE_CONFIG = {
|
||||||
"advanced": {
|
"advanced": {
|
||||||
"console_format": (
|
"console_format": (
|
||||||
@@ -152,17 +152,17 @@ CHAT_STYLE_CONFIG = {
|
|||||||
"file_format": ("{time:YYYY-MM-DD HH:mm:ss} | {level: <8} | {extra[module]: <15} | 见闻 | {message}"),
|
"file_format": ("{time:YYYY-MM-DD HH:mm:ss} | {level: <8} | {extra[module]: <15} | 见闻 | {message}"),
|
||||||
},
|
},
|
||||||
"simple": {
|
"simple": {
|
||||||
"console_format": ("<green>{time:MM-DD HH:mm}</green> | <light-blue>见闻</light-blue> | {message}"),
|
"console_format": ("<green>{time:MM-DD HH:mm}</green> | <light-blue>见闻</light-blue> | <green>{message}</green>"), # noqa: E501
|
||||||
"file_format": ("{time:YYYY-MM-DD HH:mm:ss} | {level: <8} | {extra[module]: <15} | 见闻 | {message}"),
|
"file_format": ("{time:YYYY-MM-DD HH:mm:ss} | {level: <8} | {extra[module]: <15} | 见闻 | {message}"),
|
||||||
},
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
# 根据ENABLE_ADVANCE_OUTPUT选择配置
|
# 根据SIMPLE_OUTPUT选择配置
|
||||||
MEMORY_STYLE_CONFIG = MEMORY_STYLE_CONFIG["advanced"] if ENABLE_ADVANCE_OUTPUT else MEMORY_STYLE_CONFIG["simple"]
|
MEMORY_STYLE_CONFIG = MEMORY_STYLE_CONFIG["simple"] if SIMPLE_OUTPUT else MEMORY_STYLE_CONFIG["advanced"]
|
||||||
TOPIC_STYLE_CONFIG = TOPIC_STYLE_CONFIG["advanced"] if ENABLE_ADVANCE_OUTPUT else TOPIC_STYLE_CONFIG["simple"]
|
TOPIC_STYLE_CONFIG = TOPIC_STYLE_CONFIG["simple"] if SIMPLE_OUTPUT else TOPIC_STYLE_CONFIG["advanced"]
|
||||||
SENDER_STYLE_CONFIG = SENDER_STYLE_CONFIG["advanced"] if ENABLE_ADVANCE_OUTPUT else SENDER_STYLE_CONFIG["simple"]
|
SENDER_STYLE_CONFIG = SENDER_STYLE_CONFIG["simple"] if SIMPLE_OUTPUT else SENDER_STYLE_CONFIG["advanced"]
|
||||||
LLM_STYLE_CONFIG = LLM_STYLE_CONFIG["advanced"] if ENABLE_ADVANCE_OUTPUT else LLM_STYLE_CONFIG["simple"]
|
LLM_STYLE_CONFIG = LLM_STYLE_CONFIG["simple"] if SIMPLE_OUTPUT else LLM_STYLE_CONFIG["advanced"]
|
||||||
CHAT_STYLE_CONFIG = CHAT_STYLE_CONFIG["advanced"] if ENABLE_ADVANCE_OUTPUT else CHAT_STYLE_CONFIG["simple"]
|
CHAT_STYLE_CONFIG = CHAT_STYLE_CONFIG["simple"] if SIMPLE_OUTPUT else CHAT_STYLE_CONFIG["advanced"]
|
||||||
|
|
||||||
|
|
||||||
def is_registered_module(record: dict) -> bool:
|
def is_registered_module(record: dict) -> bool:
|
||||||
|
|||||||
@@ -92,12 +92,13 @@ async def _(bot: Bot):
|
|||||||
|
|
||||||
@msg_in.handle()
|
@msg_in.handle()
|
||||||
async def _(bot: Bot, event: MessageEvent, state: T_State):
|
async def _(bot: Bot, event: MessageEvent, state: T_State):
|
||||||
#处理合并转发消息
|
# 处理合并转发消息
|
||||||
if "forward" in event.message:
|
if "forward" in event.message:
|
||||||
await chat_bot.handle_forward_message(event , bot)
|
await chat_bot.handle_forward_message(event, bot)
|
||||||
else :
|
else:
|
||||||
await chat_bot.handle_message(event, bot)
|
await chat_bot.handle_message(event, bot)
|
||||||
|
|
||||||
|
|
||||||
@notice_matcher.handle()
|
@notice_matcher.handle()
|
||||||
async def _(bot: Bot, event: NoticeEvent, state: T_State):
|
async def _(bot: Bot, event: NoticeEvent, state: T_State):
|
||||||
logger.debug(f"收到通知:{event}")
|
logger.debug(f"收到通知:{event}")
|
||||||
@@ -110,7 +111,7 @@ async def build_memory_task():
|
|||||||
"""每build_memory_interval秒执行一次记忆构建"""
|
"""每build_memory_interval秒执行一次记忆构建"""
|
||||||
logger.debug("[记忆构建]------------------------------------开始构建记忆--------------------------------------")
|
logger.debug("[记忆构建]------------------------------------开始构建记忆--------------------------------------")
|
||||||
start_time = time.time()
|
start_time = time.time()
|
||||||
await hippocampus.operation_build_memory(chat_size=20)
|
await hippocampus.operation_build_memory()
|
||||||
end_time = time.time()
|
end_time = time.time()
|
||||||
logger.success(
|
logger.success(
|
||||||
f"[记忆构建]--------------------------记忆构建完成:耗时: {end_time - start_time:.2f} "
|
f"[记忆构建]--------------------------记忆构建完成:耗时: {end_time - start_time:.2f} "
|
||||||
|
|||||||
@@ -154,7 +154,7 @@ class ChatBot:
|
|||||||
)
|
)
|
||||||
# 开始思考的时间点
|
# 开始思考的时间点
|
||||||
thinking_time_point = round(time.time(), 2)
|
thinking_time_point = round(time.time(), 2)
|
||||||
logger.info(f"开始思考的时间点: {thinking_time_point}")
|
# logger.debug(f"开始思考的时间点: {thinking_time_point}")
|
||||||
think_id = "mt" + str(thinking_time_point)
|
think_id = "mt" + str(thinking_time_point)
|
||||||
thinking_message = MessageThinking(
|
thinking_message = MessageThinking(
|
||||||
message_id=think_id,
|
message_id=think_id,
|
||||||
@@ -418,13 +418,12 @@ class ChatBot:
|
|||||||
# 用户屏蔽,不区分私聊/群聊
|
# 用户屏蔽,不区分私聊/群聊
|
||||||
if event.user_id in global_config.ban_user_id:
|
if event.user_id in global_config.ban_user_id:
|
||||||
return
|
return
|
||||||
|
|
||||||
if isinstance(event, GroupMessageEvent):
|
if isinstance(event, GroupMessageEvent):
|
||||||
if event.group_id:
|
if event.group_id:
|
||||||
if event.group_id not in global_config.talk_allowed_groups:
|
if event.group_id not in global_config.talk_allowed_groups:
|
||||||
return
|
return
|
||||||
|
|
||||||
|
|
||||||
# 获取合并转发消息的详细信息
|
# 获取合并转发消息的详细信息
|
||||||
forward_info = await bot.get_forward_msg(message_id=event.message_id)
|
forward_info = await bot.get_forward_msg(message_id=event.message_id)
|
||||||
messages = forward_info["messages"]
|
messages = forward_info["messages"]
|
||||||
@@ -434,17 +433,17 @@ class ChatBot:
|
|||||||
for node in messages:
|
for node in messages:
|
||||||
# 提取发送者昵称
|
# 提取发送者昵称
|
||||||
nickname = node["sender"].get("nickname", "未知用户")
|
nickname = node["sender"].get("nickname", "未知用户")
|
||||||
|
|
||||||
# 递归处理消息内容
|
# 递归处理消息内容
|
||||||
message_content = await self.process_message_segments(node["message"],layer=0)
|
message_content = await self.process_message_segments(node["message"], layer=0)
|
||||||
|
|
||||||
# 拼接为【昵称】+ 内容
|
# 拼接为【昵称】+ 内容
|
||||||
processed_messages.append(f"【{nickname}】{message_content}")
|
processed_messages.append(f"【{nickname}】{message_content}")
|
||||||
|
|
||||||
# 组合所有消息
|
# 组合所有消息
|
||||||
combined_message = "\n".join(processed_messages)
|
combined_message = "\n".join(processed_messages)
|
||||||
combined_message = f"合并转发消息内容:\n{combined_message}"
|
combined_message = f"合并转发消息内容:\n{combined_message}"
|
||||||
|
|
||||||
# 构建用户信息(使用转发消息的发送者)
|
# 构建用户信息(使用转发消息的发送者)
|
||||||
user_info = UserInfo(
|
user_info = UserInfo(
|
||||||
user_id=event.user_id,
|
user_id=event.user_id,
|
||||||
@@ -456,11 +455,7 @@ class ChatBot:
|
|||||||
# 构建群聊信息(如果是群聊)
|
# 构建群聊信息(如果是群聊)
|
||||||
group_info = None
|
group_info = None
|
||||||
if isinstance(event, GroupMessageEvent):
|
if isinstance(event, GroupMessageEvent):
|
||||||
group_info = GroupInfo(
|
group_info = GroupInfo(group_id=event.group_id, group_name=None, platform="qq")
|
||||||
group_id=event.group_id,
|
|
||||||
group_name=None,
|
|
||||||
platform="qq"
|
|
||||||
)
|
|
||||||
|
|
||||||
# 创建消息对象
|
# 创建消息对象
|
||||||
message_cq = MessageRecvCQ(
|
message_cq = MessageRecvCQ(
|
||||||
@@ -475,19 +470,19 @@ class ChatBot:
|
|||||||
# 进入标准消息处理流程
|
# 进入标准消息处理流程
|
||||||
await self.message_process(message_cq)
|
await self.message_process(message_cq)
|
||||||
|
|
||||||
async def process_message_segments(self, segments: list,layer:int) -> str:
|
async def process_message_segments(self, segments: list, layer: int) -> str:
|
||||||
"""递归处理消息段"""
|
"""递归处理消息段"""
|
||||||
parts = []
|
parts = []
|
||||||
for seg in segments:
|
for seg in segments:
|
||||||
part = await self.process_segment(seg,layer+1)
|
part = await self.process_segment(seg, layer + 1)
|
||||||
parts.append(part)
|
parts.append(part)
|
||||||
return "".join(parts)
|
return "".join(parts)
|
||||||
|
|
||||||
async def process_segment(self, seg: dict , layer:int) -> str:
|
async def process_segment(self, seg: dict, layer: int) -> str:
|
||||||
"""处理单个消息段"""
|
"""处理单个消息段"""
|
||||||
seg_type = seg["type"]
|
seg_type = seg["type"]
|
||||||
if layer > 3 :
|
if layer > 3:
|
||||||
#防止有那种100层转发消息炸飞麦麦
|
# 防止有那种100层转发消息炸飞麦麦
|
||||||
return "【转发消息】"
|
return "【转发消息】"
|
||||||
if seg_type == "text":
|
if seg_type == "text":
|
||||||
return seg["data"]["text"]
|
return seg["data"]["text"]
|
||||||
@@ -504,13 +499,14 @@ class ChatBot:
|
|||||||
nested_messages.append("合并转发消息内容:")
|
nested_messages.append("合并转发消息内容:")
|
||||||
for node in nested_nodes:
|
for node in nested_nodes:
|
||||||
nickname = node["sender"].get("nickname", "未知用户")
|
nickname = node["sender"].get("nickname", "未知用户")
|
||||||
content = await self.process_message_segments(node["message"],layer=layer)
|
content = await self.process_message_segments(node["message"], layer=layer)
|
||||||
# nested_messages.append('-' * layer)
|
# nested_messages.append('-' * layer)
|
||||||
nested_messages.append(f"{'--' * layer}【{nickname}】{content}")
|
nested_messages.append(f"{'--' * layer}【{nickname}】{content}")
|
||||||
# nested_messages.append(f"{'--' * layer}合并转发第【{layer}】层结束")
|
# nested_messages.append(f"{'--' * layer}合并转发第【{layer}】层结束")
|
||||||
return "\n".join(nested_messages)
|
return "\n".join(nested_messages)
|
||||||
else:
|
else:
|
||||||
return f"[{seg_type}]"
|
return f"[{seg_type}]"
|
||||||
|
|
||||||
|
|
||||||
# 创建全局ChatBot实例
|
# 创建全局ChatBot实例
|
||||||
chat_bot = ChatBot()
|
chat_bot = ChatBot()
|
||||||
|
|||||||
@@ -56,7 +56,6 @@ class BotConfig:
|
|||||||
llm_reasoning: Dict[str, str] = field(default_factory=lambda: {})
|
llm_reasoning: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
llm_reasoning_minor: Dict[str, str] = field(default_factory=lambda: {})
|
llm_reasoning_minor: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
llm_normal: Dict[str, str] = field(default_factory=lambda: {})
|
llm_normal: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
llm_normal_minor: Dict[str, str] = field(default_factory=lambda: {})
|
|
||||||
llm_topic_judge: Dict[str, str] = field(default_factory=lambda: {})
|
llm_topic_judge: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
llm_summary_by_topic: Dict[str, str] = field(default_factory=lambda: {})
|
llm_summary_by_topic: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
llm_emotion_judge: Dict[str, str] = field(default_factory=lambda: {})
|
llm_emotion_judge: Dict[str, str] = field(default_factory=lambda: {})
|
||||||
@@ -68,9 +67,9 @@ class BotConfig:
|
|||||||
MODEL_V3_PROBABILITY: float = 0.1 # V3模型概率
|
MODEL_V3_PROBABILITY: float = 0.1 # V3模型概率
|
||||||
MODEL_R1_DISTILL_PROBABILITY: float = 0.1 # R1蒸馏模型概率
|
MODEL_R1_DISTILL_PROBABILITY: float = 0.1 # R1蒸馏模型概率
|
||||||
|
|
||||||
enable_advance_output: bool = False # 是否启用高级输出
|
# enable_advance_output: bool = False # 是否启用高级输出
|
||||||
enable_kuuki_read: bool = True # 是否启用读空气功能
|
enable_kuuki_read: bool = True # 是否启用读空气功能
|
||||||
enable_debug_output: bool = False # 是否启用调试输出
|
# enable_debug_output: bool = False # 是否启用调试输出
|
||||||
enable_friend_chat: bool = False # 是否启用好友聊天
|
enable_friend_chat: bool = False # 是否启用好友聊天
|
||||||
|
|
||||||
mood_update_interval: float = 1.0 # 情绪更新间隔 单位秒
|
mood_update_interval: float = 1.0 # 情绪更新间隔 单位秒
|
||||||
@@ -106,6 +105,11 @@ class BotConfig:
|
|||||||
memory_forget_time: int = 24 # 记忆遗忘时间(小时)
|
memory_forget_time: int = 24 # 记忆遗忘时间(小时)
|
||||||
memory_forget_percentage: float = 0.01 # 记忆遗忘比例
|
memory_forget_percentage: float = 0.01 # 记忆遗忘比例
|
||||||
memory_compress_rate: float = 0.1 # 记忆压缩率
|
memory_compress_rate: float = 0.1 # 记忆压缩率
|
||||||
|
build_memory_sample_num: int = 10 # 记忆构建采样数量
|
||||||
|
build_memory_sample_length: int = 20 # 记忆构建采样长度
|
||||||
|
memory_build_distribution: list = field(
|
||||||
|
default_factory=lambda: [4,2,0.6,24,8,0.4]
|
||||||
|
) # 记忆构建分布,参数:分布1均值,标准差,权重,分布2均值,标准差,权重
|
||||||
memory_ban_words: list = field(
|
memory_ban_words: list = field(
|
||||||
default_factory=lambda: ["表情包", "图片", "回复", "聊天记录"]
|
default_factory=lambda: ["表情包", "图片", "回复", "聊天记录"]
|
||||||
) # 添加新的配置项默认值
|
) # 添加新的配置项默认值
|
||||||
@@ -230,7 +234,6 @@ class BotConfig:
|
|||||||
"llm_reasoning",
|
"llm_reasoning",
|
||||||
"llm_reasoning_minor",
|
"llm_reasoning_minor",
|
||||||
"llm_normal",
|
"llm_normal",
|
||||||
"llm_normal_minor",
|
|
||||||
"llm_topic_judge",
|
"llm_topic_judge",
|
||||||
"llm_summary_by_topic",
|
"llm_summary_by_topic",
|
||||||
"llm_emotion_judge",
|
"llm_emotion_judge",
|
||||||
@@ -315,6 +318,20 @@ class BotConfig:
|
|||||||
"memory_forget_percentage", config.memory_forget_percentage
|
"memory_forget_percentage", config.memory_forget_percentage
|
||||||
)
|
)
|
||||||
config.memory_compress_rate = memory_config.get("memory_compress_rate", config.memory_compress_rate)
|
config.memory_compress_rate = memory_config.get("memory_compress_rate", config.memory_compress_rate)
|
||||||
|
if config.INNER_VERSION in SpecifierSet(">=0.0.11"):
|
||||||
|
config.memory_build_distribution = memory_config.get(
|
||||||
|
"memory_build_distribution",
|
||||||
|
config.memory_build_distribution
|
||||||
|
)
|
||||||
|
config.build_memory_sample_num = memory_config.get(
|
||||||
|
"build_memory_sample_num",
|
||||||
|
config.build_memory_sample_num
|
||||||
|
)
|
||||||
|
config.build_memory_sample_length = memory_config.get(
|
||||||
|
"build_memory_sample_length",
|
||||||
|
config.build_memory_sample_length
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def remote(parent: dict):
|
def remote(parent: dict):
|
||||||
remote_config = parent["remote"]
|
remote_config = parent["remote"]
|
||||||
@@ -351,10 +368,10 @@ class BotConfig:
|
|||||||
|
|
||||||
def others(parent: dict):
|
def others(parent: dict):
|
||||||
others_config = parent["others"]
|
others_config = parent["others"]
|
||||||
config.enable_advance_output = others_config.get("enable_advance_output", config.enable_advance_output)
|
# config.enable_advance_output = others_config.get("enable_advance_output", config.enable_advance_output)
|
||||||
config.enable_kuuki_read = others_config.get("enable_kuuki_read", config.enable_kuuki_read)
|
config.enable_kuuki_read = others_config.get("enable_kuuki_read", config.enable_kuuki_read)
|
||||||
if config.INNER_VERSION in SpecifierSet(">=0.0.7"):
|
if config.INNER_VERSION in SpecifierSet(">=0.0.7"):
|
||||||
config.enable_debug_output = others_config.get("enable_debug_output", config.enable_debug_output)
|
# config.enable_debug_output = others_config.get("enable_debug_output", config.enable_debug_output)
|
||||||
config.enable_friend_chat = others_config.get("enable_friend_chat", config.enable_friend_chat)
|
config.enable_friend_chat = others_config.get("enable_friend_chat", config.enable_friend_chat)
|
||||||
|
|
||||||
# 版本表达式:>=1.0.0,<2.0.0
|
# 版本表达式:>=1.0.0,<2.0.0
|
||||||
|
|||||||
@@ -38,9 +38,9 @@ class EmojiManager:
|
|||||||
|
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
self._scan_task = None
|
self._scan_task = None
|
||||||
self.vlm = LLM_request(model=global_config.vlm, temperature=0.3, max_tokens=1000, request_type="image")
|
self.vlm = LLM_request(model=global_config.vlm, temperature=0.3, max_tokens=1000, request_type="emoji")
|
||||||
self.llm_emotion_judge = LLM_request(
|
self.llm_emotion_judge = LLM_request(
|
||||||
model=global_config.llm_emotion_judge, max_tokens=600, temperature=0.8, request_type="image"
|
model=global_config.llm_emotion_judge, max_tokens=600, temperature=0.8, request_type="emoji"
|
||||||
) # 更高的温度,更少的token(后续可以根据情绪来调整温度)
|
) # 更高的温度,更少的token(后续可以根据情绪来调整温度)
|
||||||
|
|
||||||
def _ensure_emoji_dir(self):
|
def _ensure_emoji_dir(self):
|
||||||
@@ -111,7 +111,7 @@ class EmojiManager:
|
|||||||
if not text_for_search:
|
if not text_for_search:
|
||||||
logger.error("无法获取文本的情绪")
|
logger.error("无法获取文本的情绪")
|
||||||
return None
|
return None
|
||||||
text_embedding = await get_embedding(text_for_search)
|
text_embedding = await get_embedding(text_for_search, request_type="emoji")
|
||||||
if not text_embedding:
|
if not text_embedding:
|
||||||
logger.error("无法获取文本的embedding")
|
logger.error("无法获取文本的embedding")
|
||||||
return None
|
return None
|
||||||
@@ -242,7 +242,33 @@ class EmojiManager:
|
|||||||
image_hash = hashlib.md5(image_bytes).hexdigest()
|
image_hash = hashlib.md5(image_bytes).hexdigest()
|
||||||
image_format = Image.open(io.BytesIO(image_bytes)).format.lower()
|
image_format = Image.open(io.BytesIO(image_bytes)).format.lower()
|
||||||
# 检查是否已经注册过
|
# 检查是否已经注册过
|
||||||
existing_emoji = db["emoji"].find_one({"hash": image_hash})
|
existing_emoji_by_path = db["emoji"].find_one({"filename": filename})
|
||||||
|
existing_emoji_by_hash = db["emoji"].find_one({"hash": image_hash})
|
||||||
|
if existing_emoji_by_path and existing_emoji_by_hash:
|
||||||
|
if existing_emoji_by_path["_id"] != existing_emoji_by_hash["_id"]:
|
||||||
|
logger.error(f"[错误] 表情包已存在但记录不一致: {filename}")
|
||||||
|
db.emoji.delete_one({"_id": existing_emoji_by_path["_id"]})
|
||||||
|
db.emoji.update_one(
|
||||||
|
{"_id": existing_emoji_by_hash["_id"]}, {"$set": {"path": image_path, "filename": filename}}
|
||||||
|
)
|
||||||
|
existing_emoji_by_hash["path"] = image_path
|
||||||
|
existing_emoji_by_hash["filename"] = filename
|
||||||
|
existing_emoji = existing_emoji_by_hash
|
||||||
|
elif existing_emoji_by_hash:
|
||||||
|
logger.error(f"[错误] 表情包hash已存在但path不存在: {filename}")
|
||||||
|
db.emoji.update_one(
|
||||||
|
{"_id": existing_emoji_by_hash["_id"]}, {"$set": {"path": image_path, "filename": filename}}
|
||||||
|
)
|
||||||
|
existing_emoji_by_hash["path"] = image_path
|
||||||
|
existing_emoji_by_hash["filename"] = filename
|
||||||
|
existing_emoji = existing_emoji_by_hash
|
||||||
|
elif existing_emoji_by_path:
|
||||||
|
logger.error(f"[错误] 表情包path已存在但hash不存在: {filename}")
|
||||||
|
db.emoji.delete_one({"_id": existing_emoji_by_path["_id"]})
|
||||||
|
existing_emoji = None
|
||||||
|
else:
|
||||||
|
existing_emoji = None
|
||||||
|
|
||||||
description = None
|
description = None
|
||||||
|
|
||||||
if existing_emoji:
|
if existing_emoji:
|
||||||
@@ -284,7 +310,7 @@ class EmojiManager:
|
|||||||
logger.info(f"[检查] 表情包检查通过: {check}")
|
logger.info(f"[检查] 表情包检查通过: {check}")
|
||||||
|
|
||||||
if description is not None:
|
if description is not None:
|
||||||
embedding = await get_embedding(description)
|
embedding = await get_embedding(description, request_type="emoji")
|
||||||
# 准备数据库记录
|
# 准备数据库记录
|
||||||
emoji_record = {
|
emoji_record = {
|
||||||
"filename": filename,
|
"filename": filename,
|
||||||
@@ -366,6 +392,12 @@ class EmojiManager:
|
|||||||
logger.warning(f"[检查] 发现缺失记录(缺少hash字段),ID: {emoji.get('_id', 'unknown')}")
|
logger.warning(f"[检查] 发现缺失记录(缺少hash字段),ID: {emoji.get('_id', 'unknown')}")
|
||||||
hash = hashlib.md5(open(emoji["path"], "rb").read()).hexdigest()
|
hash = hashlib.md5(open(emoji["path"], "rb").read()).hexdigest()
|
||||||
db.emoji.update_one({"_id": emoji["_id"]}, {"$set": {"hash": hash}})
|
db.emoji.update_one({"_id": emoji["_id"]}, {"$set": {"hash": hash}})
|
||||||
|
else:
|
||||||
|
file_hash = hashlib.md5(open(emoji["path"], "rb").read()).hexdigest()
|
||||||
|
if emoji["hash"] != file_hash:
|
||||||
|
logger.warning(f"[检查] 表情包文件hash不匹配,ID: {emoji.get('_id', 'unknown')}")
|
||||||
|
db.emoji.delete_one({"_id": emoji["_id"]})
|
||||||
|
removed_count += 1
|
||||||
|
|
||||||
except Exception as item_error:
|
except Exception as item_error:
|
||||||
logger.error(f"[错误] 处理表情包记录时出错: {str(item_error)}")
|
logger.error(f"[错误] 处理表情包记录时出错: {str(item_error)}")
|
||||||
|
|||||||
@@ -32,11 +32,19 @@ class ResponseGenerator:
|
|||||||
temperature=0.7,
|
temperature=0.7,
|
||||||
max_tokens=1000,
|
max_tokens=1000,
|
||||||
stream=True,
|
stream=True,
|
||||||
|
request_type="response",
|
||||||
|
)
|
||||||
|
self.model_v3 = LLM_request(
|
||||||
|
model=global_config.llm_normal, temperature=0.7, max_tokens=3000, request_type="response"
|
||||||
|
)
|
||||||
|
self.model_r1_distill = LLM_request(
|
||||||
|
model=global_config.llm_reasoning_minor, temperature=0.7, max_tokens=3000, request_type="response"
|
||||||
|
)
|
||||||
|
self.model_sum = LLM_request(
|
||||||
|
model=global_config.llm_summary_by_topic, temperature=0.7, max_tokens=3000, request_type="relation"
|
||||||
)
|
)
|
||||||
self.model_v3 = LLM_request(model=global_config.llm_normal, temperature=0.7, max_tokens=3000)
|
|
||||||
self.model_r1_distill = LLM_request(model=global_config.llm_reasoning_minor, temperature=0.7, max_tokens=3000)
|
|
||||||
self.model_v25 = LLM_request(model=global_config.llm_normal_minor, temperature=0.7, max_tokens=3000)
|
|
||||||
self.current_model_type = "r1" # 默认使用 R1
|
self.current_model_type = "r1" # 默认使用 R1
|
||||||
|
self.current_model_name = "unknown model"
|
||||||
|
|
||||||
async def generate_response(self, message: MessageThinking) -> Optional[Union[str, List[str]]]:
|
async def generate_response(self, message: MessageThinking) -> Optional[Union[str, List[str]]]:
|
||||||
"""根据当前模型类型选择对应的生成函数"""
|
"""根据当前模型类型选择对应的生成函数"""
|
||||||
@@ -107,7 +115,7 @@ class ResponseGenerator:
|
|||||||
|
|
||||||
# 生成回复
|
# 生成回复
|
||||||
try:
|
try:
|
||||||
content, reasoning_content = await model.generate_response(prompt)
|
content, reasoning_content, self.current_model_name = await model.generate_response(prompt)
|
||||||
except Exception:
|
except Exception:
|
||||||
logger.exception("生成回复时出错")
|
logger.exception("生成回复时出错")
|
||||||
return None
|
return None
|
||||||
@@ -144,7 +152,7 @@ class ResponseGenerator:
|
|||||||
"chat_id": message.chat_stream.stream_id,
|
"chat_id": message.chat_stream.stream_id,
|
||||||
"user": sender_name,
|
"user": sender_name,
|
||||||
"message": message.processed_plain_text,
|
"message": message.processed_plain_text,
|
||||||
"model": self.current_model_type,
|
"model": self.current_model_name,
|
||||||
# 'reasoning_check': reasoning_content_check,
|
# 'reasoning_check': reasoning_content_check,
|
||||||
# 'response_check': content_check,
|
# 'response_check': content_check,
|
||||||
"reasoning": reasoning_content,
|
"reasoning": reasoning_content,
|
||||||
@@ -174,7 +182,7 @@ class ResponseGenerator:
|
|||||||
"""
|
"""
|
||||||
|
|
||||||
# 调用模型生成结果
|
# 调用模型生成结果
|
||||||
result, _ = await self.model_v25.generate_response(prompt)
|
result, _, _ = await self.model_sum.generate_response(prompt)
|
||||||
result = result.strip()
|
result = result.strip()
|
||||||
|
|
||||||
# 解析模型输出的结果
|
# 解析模型输出的结果
|
||||||
@@ -215,7 +223,7 @@ class InitiativeMessageGenerate:
|
|||||||
topic_select_prompt, dots_for_select, prompt_template = prompt_builder._build_initiative_prompt_select(
|
topic_select_prompt, dots_for_select, prompt_template = prompt_builder._build_initiative_prompt_select(
|
||||||
message.group_id
|
message.group_id
|
||||||
)
|
)
|
||||||
content_select, reasoning = self.model_v3.generate_response(topic_select_prompt)
|
content_select, reasoning, _ = self.model_v3.generate_response(topic_select_prompt)
|
||||||
logger.debug(f"{content_select} {reasoning}")
|
logger.debug(f"{content_select} {reasoning}")
|
||||||
topics_list = [dot[0] for dot in dots_for_select]
|
topics_list = [dot[0] for dot in dots_for_select]
|
||||||
if content_select:
|
if content_select:
|
||||||
@@ -226,7 +234,7 @@ class InitiativeMessageGenerate:
|
|||||||
else:
|
else:
|
||||||
return None
|
return None
|
||||||
prompt_check, memory = prompt_builder._build_initiative_prompt_check(select_dot[1], prompt_template)
|
prompt_check, memory = prompt_builder._build_initiative_prompt_check(select_dot[1], prompt_template)
|
||||||
content_check, reasoning_check = self.model_v3.generate_response(prompt_check)
|
content_check, reasoning_check, _ = self.model_v3.generate_response(prompt_check)
|
||||||
logger.info(f"{content_check} {reasoning_check}")
|
logger.info(f"{content_check} {reasoning_check}")
|
||||||
if "yes" not in content_check.lower():
|
if "yes" not in content_check.lower():
|
||||||
return None
|
return None
|
||||||
|
|||||||
@@ -220,7 +220,7 @@ class MessageManager:
|
|||||||
|
|
||||||
message_timeout = container.get_timeout_messages()
|
message_timeout = container.get_timeout_messages()
|
||||||
if message_timeout:
|
if message_timeout:
|
||||||
logger.warning(f"发现{len(message_timeout)}条超时消息")
|
logger.debug(f"发现{len(message_timeout)}条超时消息")
|
||||||
for msg in message_timeout:
|
for msg in message_timeout:
|
||||||
if msg == message_earliest:
|
if msg == message_earliest:
|
||||||
continue
|
continue
|
||||||
|
|||||||
@@ -141,21 +141,21 @@ class PromptBuilder:
|
|||||||
logger.debug(f"知识检索耗时: {(end_time - start_time):.3f}秒")
|
logger.debug(f"知识检索耗时: {(end_time - start_time):.3f}秒")
|
||||||
|
|
||||||
prompt = f"""
|
prompt = f"""
|
||||||
今天是{current_date},现在是{current_time},你今天的日程是:\
|
今天是{current_date},现在是{current_time},你今天的日程是:
|
||||||
`<schedule>`\n
|
`<schedule>`
|
||||||
{bot_schedule.today_schedule}\n
|
{bot_schedule.today_schedule}
|
||||||
`</schedule>`\n
|
`</schedule>`
|
||||||
{prompt_info}\n
|
{prompt_info}
|
||||||
{memory_prompt}\n
|
{memory_prompt}
|
||||||
{chat_target}\n
|
{chat_target}
|
||||||
{chat_talking_prompt}\n
|
{chat_talking_prompt}
|
||||||
现在"{sender_name}"说的:\n
|
现在"{sender_name}"说的:
|
||||||
`<UserMessage>`\n
|
`<UserMessage>`
|
||||||
{message_txt}\n
|
{message_txt}
|
||||||
`</UserMessage>`\n
|
`</UserMessage>`
|
||||||
引起了你的注意,{relation_prompt_all}{mood_prompt}\n
|
引起了你的注意,{relation_prompt_all}{mood_prompt}\n
|
||||||
`<MainRule>`
|
`<MainRule>`
|
||||||
你的网名叫{global_config.BOT_NICKNAME},{prompt_personality}。
|
你的网名叫{global_config.BOT_NICKNAME},有人也叫你{"/".join(global_config.BOT_ALIAS_NAMES)},{prompt_personality},{prompt_personality}。
|
||||||
正在{bot_schedule_now_activity}的你同时也在一边{chat_target_2},现在请你读读之前的聊天记录,然后给出日常且口语化的回复,平淡一些,
|
正在{bot_schedule_now_activity}的你同时也在一边{chat_target_2},现在请你读读之前的聊天记录,然后给出日常且口语化的回复,平淡一些,
|
||||||
尽量简短一些。{keywords_reaction_prompt}请注意把握聊天内容,不要刻意突出自身学科背景,不要回复的太有条理,可以有个性。
|
尽量简短一些。{keywords_reaction_prompt}请注意把握聊天内容,不要刻意突出自身学科背景,不要回复的太有条理,可以有个性。
|
||||||
{prompt_ger}
|
{prompt_ger}
|
||||||
|
|||||||
@@ -33,7 +33,7 @@ class TopicIdentifier:
|
|||||||
消息内容:{text}"""
|
消息内容:{text}"""
|
||||||
|
|
||||||
# 使用 LLM_request 类进行请求
|
# 使用 LLM_request 类进行请求
|
||||||
topic, _ = await self.llm_topic_judge.generate_response(prompt)
|
topic, _, _ = await self.llm_topic_judge.generate_response(prompt)
|
||||||
|
|
||||||
if not topic:
|
if not topic:
|
||||||
logger.error("LLM API 返回为空")
|
logger.error("LLM API 返回为空")
|
||||||
|
|||||||
@@ -55,9 +55,9 @@ def is_mentioned_bot_in_message(message: MessageRecv) -> bool:
|
|||||||
return False
|
return False
|
||||||
|
|
||||||
|
|
||||||
async def get_embedding(text):
|
async def get_embedding(text, request_type="embedding"):
|
||||||
"""获取文本的embedding向量"""
|
"""获取文本的embedding向量"""
|
||||||
llm = LLM_request(model=global_config.embedding, request_type="embedding")
|
llm = LLM_request(model=global_config.embedding, request_type=request_type)
|
||||||
# return llm.get_embedding_sync(text)
|
# return llm.get_embedding_sync(text)
|
||||||
return await llm.get_embedding(text)
|
return await llm.get_embedding(text)
|
||||||
|
|
||||||
@@ -76,18 +76,11 @@ def calculate_information_content(text):
|
|||||||
|
|
||||||
|
|
||||||
def get_closest_chat_from_db(length: int, timestamp: str):
|
def get_closest_chat_from_db(length: int, timestamp: str):
|
||||||
"""从数据库中获取最接近指定时间戳的聊天记录
|
# print(f"获取最接近指定时间戳的聊天记录,长度: {length}, 时间戳: {timestamp}")
|
||||||
|
# print(f"当前时间: {timestamp},转换后时间: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(timestamp))}")
|
||||||
Args:
|
|
||||||
length: 要获取的消息数量
|
|
||||||
timestamp: 时间戳
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
list: 消息记录列表,每个记录包含时间和文本信息
|
|
||||||
"""
|
|
||||||
chat_records = []
|
chat_records = []
|
||||||
closest_record = db.messages.find_one({"time": {"$lte": timestamp}}, sort=[("time", -1)])
|
closest_record = db.messages.find_one({"time": {"$lte": timestamp}}, sort=[("time", -1)])
|
||||||
|
# print(f"最接近的记录: {closest_record}")
|
||||||
if closest_record:
|
if closest_record:
|
||||||
closest_time = closest_record["time"]
|
closest_time = closest_record["time"]
|
||||||
chat_id = closest_record["chat_id"] # 获取chat_id
|
chat_id = closest_record["chat_id"] # 获取chat_id
|
||||||
@@ -102,7 +95,9 @@ def get_closest_chat_from_db(length: int, timestamp: str):
|
|||||||
.sort("time", 1)
|
.sort("time", 1)
|
||||||
.limit(length)
|
.limit(length)
|
||||||
)
|
)
|
||||||
|
# print(f"获取到的记录: {chat_records}")
|
||||||
|
length = len(chat_records)
|
||||||
|
# print(f"获取到的记录长度: {length}")
|
||||||
# 转换记录格式
|
# 转换记录格式
|
||||||
formatted_records = []
|
formatted_records = []
|
||||||
for record in chat_records:
|
for record in chat_records:
|
||||||
@@ -319,7 +314,7 @@ def split_into_sentences_w_remove_punctuation(text: str) -> List[str]:
|
|||||||
sentence = sentence.replace(",", " ").replace(",", " ")
|
sentence = sentence.replace(",", " ").replace(",", " ")
|
||||||
sentences_done.append(sentence)
|
sentences_done.append(sentence)
|
||||||
|
|
||||||
logger.info(f"处理后的句子: {sentences_done}")
|
logger.debug(f"处理后的句子: {sentences_done}")
|
||||||
return sentences_done
|
return sentences_done
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -112,7 +112,7 @@ class ImageManager:
|
|||||||
# 查询缓存的描述
|
# 查询缓存的描述
|
||||||
cached_description = self._get_description_from_db(image_hash, "emoji")
|
cached_description = self._get_description_from_db(image_hash, "emoji")
|
||||||
if cached_description:
|
if cached_description:
|
||||||
logger.info(f"缓存表情包描述: {cached_description}")
|
logger.debug(f"缓存表情包描述: {cached_description}")
|
||||||
return f"[表情包:{cached_description}]"
|
return f"[表情包:{cached_description}]"
|
||||||
|
|
||||||
# 调用AI获取描述
|
# 调用AI获取描述
|
||||||
@@ -184,7 +184,7 @@ class ImageManager:
|
|||||||
logger.warning(f"虽然生成了描述,但是找到缓存图片描述 {cached_description}")
|
logger.warning(f"虽然生成了描述,但是找到缓存图片描述 {cached_description}")
|
||||||
return f"[图片:{cached_description}]"
|
return f"[图片:{cached_description}]"
|
||||||
|
|
||||||
logger.info(f"描述是{description}")
|
logger.debug(f"描述是{description}")
|
||||||
|
|
||||||
if description is None:
|
if description is None:
|
||||||
logger.warning("AI未能生成图片描述")
|
logger.warning("AI未能生成图片描述")
|
||||||
|
|||||||
@@ -18,6 +18,7 @@ from ..chat.utils import (
|
|||||||
)
|
)
|
||||||
from ..models.utils_model import LLM_request
|
from ..models.utils_model import LLM_request
|
||||||
from src.common.logger import get_module_logger, LogConfig, MEMORY_STYLE_CONFIG
|
from src.common.logger import get_module_logger, LogConfig, MEMORY_STYLE_CONFIG
|
||||||
|
from src.plugins.memory_system.sample_distribution import MemoryBuildScheduler
|
||||||
|
|
||||||
# 定义日志配置
|
# 定义日志配置
|
||||||
memory_config = LogConfig(
|
memory_config = LogConfig(
|
||||||
@@ -25,6 +26,11 @@ memory_config = LogConfig(
|
|||||||
console_format=MEMORY_STYLE_CONFIG["console_format"],
|
console_format=MEMORY_STYLE_CONFIG["console_format"],
|
||||||
file_format=MEMORY_STYLE_CONFIG["file_format"],
|
file_format=MEMORY_STYLE_CONFIG["file_format"],
|
||||||
)
|
)
|
||||||
|
# print(f"memory_config: {memory_config}")
|
||||||
|
# print(f"MEMORY_STYLE_CONFIG: {MEMORY_STYLE_CONFIG}")
|
||||||
|
# print(f"MEMORY_STYLE_CONFIG['console_format']: {MEMORY_STYLE_CONFIG['console_format']}")
|
||||||
|
# print(f"MEMORY_STYLE_CONFIG['file_format']: {MEMORY_STYLE_CONFIG['file_format']}")
|
||||||
|
|
||||||
|
|
||||||
logger = get_module_logger("memory_system", config=memory_config)
|
logger = get_module_logger("memory_system", config=memory_config)
|
||||||
|
|
||||||
@@ -168,9 +174,9 @@ class Memory_graph:
|
|||||||
class Hippocampus:
|
class Hippocampus:
|
||||||
def __init__(self, memory_graph: Memory_graph):
|
def __init__(self, memory_graph: Memory_graph):
|
||||||
self.memory_graph = memory_graph
|
self.memory_graph = memory_graph
|
||||||
self.llm_topic_judge = LLM_request(model=global_config.llm_topic_judge, temperature=0.5, request_type="topic")
|
self.llm_topic_judge = LLM_request(model=global_config.llm_topic_judge, temperature=0.5, request_type="memory")
|
||||||
self.llm_summary_by_topic = LLM_request(
|
self.llm_summary_by_topic = LLM_request(
|
||||||
model=global_config.llm_summary_by_topic, temperature=0.5, request_type="topic"
|
model=global_config.llm_summary_by_topic, temperature=0.5, request_type="memory"
|
||||||
)
|
)
|
||||||
|
|
||||||
def get_all_node_names(self) -> list:
|
def get_all_node_names(self) -> list:
|
||||||
@@ -195,25 +201,17 @@ class Hippocampus:
|
|||||||
return hash(f"{nodes[0]}:{nodes[1]}")
|
return hash(f"{nodes[0]}:{nodes[1]}")
|
||||||
|
|
||||||
def random_get_msg_snippet(self, target_timestamp: float, chat_size: int, max_memorized_time_per_msg: int) -> list:
|
def random_get_msg_snippet(self, target_timestamp: float, chat_size: int, max_memorized_time_per_msg: int) -> list:
|
||||||
"""随机抽取一段时间内的消息片段
|
|
||||||
Args:
|
|
||||||
- target_timestamp: 目标时间戳
|
|
||||||
- chat_size: 抽取的消息数量
|
|
||||||
- max_memorized_time_per_msg: 每条消息的最大记忆次数
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
- list: 抽取出的消息记录列表
|
|
||||||
|
|
||||||
"""
|
|
||||||
try_count = 0
|
try_count = 0
|
||||||
# 最多尝试三次抽取
|
# 最多尝试2次抽取
|
||||||
while try_count < 3:
|
while try_count < 3:
|
||||||
messages = get_closest_chat_from_db(length=chat_size, timestamp=target_timestamp)
|
messages = get_closest_chat_from_db(length=chat_size, timestamp=target_timestamp)
|
||||||
if messages:
|
if messages:
|
||||||
|
# print(f"抽取到的消息: {messages}")
|
||||||
# 检查messages是否均没有达到记忆次数限制
|
# 检查messages是否均没有达到记忆次数限制
|
||||||
for message in messages:
|
for message in messages:
|
||||||
if message["memorized_times"] >= max_memorized_time_per_msg:
|
if message["memorized_times"] >= max_memorized_time_per_msg:
|
||||||
messages = None
|
messages = None
|
||||||
|
# print(f"抽取到的消息提取次数达到限制,跳过")
|
||||||
break
|
break
|
||||||
if messages:
|
if messages:
|
||||||
# 成功抽取短期消息样本
|
# 成功抽取短期消息样本
|
||||||
@@ -224,63 +222,48 @@ class Hippocampus:
|
|||||||
)
|
)
|
||||||
return messages
|
return messages
|
||||||
try_count += 1
|
try_count += 1
|
||||||
# 三次尝试均失败
|
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def get_memory_sample(self, chat_size=20, time_frequency=None):
|
def get_memory_sample(self):
|
||||||
"""获取记忆样本
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
list: 消息记录列表,每个元素是一个消息记录字典列表
|
|
||||||
"""
|
|
||||||
# 硬编码:每条消息最大记忆次数
|
# 硬编码:每条消息最大记忆次数
|
||||||
# 如有需求可写入global_config
|
# 如有需求可写入global_config
|
||||||
if time_frequency is None:
|
|
||||||
time_frequency = {"near": 2, "mid": 4, "far": 3}
|
|
||||||
max_memorized_time_per_msg = 3
|
max_memorized_time_per_msg = 3
|
||||||
|
|
||||||
current_timestamp = datetime.datetime.now().timestamp()
|
# 创建双峰分布的记忆调度器
|
||||||
|
scheduler = MemoryBuildScheduler(
|
||||||
|
n_hours1=global_config.memory_build_distribution[0], # 第一个分布均值(4小时前)
|
||||||
|
std_hours1=global_config.memory_build_distribution[1], # 第一个分布标准差
|
||||||
|
weight1=global_config.memory_build_distribution[2], # 第一个分布权重 60%
|
||||||
|
n_hours2=global_config.memory_build_distribution[3], # 第二个分布均值(24小时前)
|
||||||
|
std_hours2=global_config.memory_build_distribution[4], # 第二个分布标准差
|
||||||
|
weight2=global_config.memory_build_distribution[5], # 第二个分布权重 40%
|
||||||
|
total_samples=global_config.build_memory_sample_num # 总共生成10个时间点
|
||||||
|
)
|
||||||
|
|
||||||
|
# 生成时间戳数组
|
||||||
|
timestamps = scheduler.get_timestamp_array()
|
||||||
|
# logger.debug(f"生成的时间戳数组: {timestamps}")
|
||||||
|
# print(f"生成的时间戳数组: {timestamps}")
|
||||||
|
# print(f"时间戳的实际时间: {[time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(ts)) for ts in timestamps]}")
|
||||||
|
logger.info(f"回忆往事: {[time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(ts)) for ts in timestamps]}")
|
||||||
chat_samples = []
|
chat_samples = []
|
||||||
|
for timestamp in timestamps:
|
||||||
# 短期:1h 中期:4h 长期:24h
|
messages = self.random_get_msg_snippet(
|
||||||
logger.debug("正在抽取短期消息样本")
|
timestamp,
|
||||||
for i in range(time_frequency.get("near")):
|
global_config.build_memory_sample_length,
|
||||||
random_time = current_timestamp - random.randint(1, 3600)
|
max_memorized_time_per_msg
|
||||||
messages = self.random_get_msg_snippet(random_time, chat_size, max_memorized_time_per_msg)
|
)
|
||||||
if messages:
|
if messages:
|
||||||
logger.debug(f"成功抽取短期消息样本{len(messages)}条")
|
time_diff = (datetime.datetime.now().timestamp() - timestamp) / 3600
|
||||||
|
logger.debug(f"成功抽取 {time_diff:.1f} 小时前的消息样本,共{len(messages)}条")
|
||||||
|
# print(f"成功抽取 {time_diff:.1f} 小时前的消息样本,共{len(messages)}条")
|
||||||
chat_samples.append(messages)
|
chat_samples.append(messages)
|
||||||
else:
|
else:
|
||||||
logger.warning(f"第{i}次短期消息样本抽取失败")
|
logger.debug(f"时间戳 {timestamp} 的消息样本抽取失败")
|
||||||
|
|
||||||
logger.debug("正在抽取中期消息样本")
|
|
||||||
for i in range(time_frequency.get("mid")):
|
|
||||||
random_time = current_timestamp - random.randint(3600, 3600 * 4)
|
|
||||||
messages = self.random_get_msg_snippet(random_time, chat_size, max_memorized_time_per_msg)
|
|
||||||
if messages:
|
|
||||||
logger.debug(f"成功抽取中期消息样本{len(messages)}条")
|
|
||||||
chat_samples.append(messages)
|
|
||||||
else:
|
|
||||||
logger.warning(f"第{i}次中期消息样本抽取失败")
|
|
||||||
|
|
||||||
logger.debug("正在抽取长期消息样本")
|
|
||||||
for i in range(time_frequency.get("far")):
|
|
||||||
random_time = current_timestamp - random.randint(3600 * 4, 3600 * 24)
|
|
||||||
messages = self.random_get_msg_snippet(random_time, chat_size, max_memorized_time_per_msg)
|
|
||||||
if messages:
|
|
||||||
logger.debug(f"成功抽取长期消息样本{len(messages)}条")
|
|
||||||
chat_samples.append(messages)
|
|
||||||
else:
|
|
||||||
logger.warning(f"第{i}次长期消息样本抽取失败")
|
|
||||||
|
|
||||||
return chat_samples
|
return chat_samples
|
||||||
|
|
||||||
async def memory_compress(self, messages: list, compress_rate=0.1):
|
async def memory_compress(self, messages: list, compress_rate=0.1):
|
||||||
"""压缩消息记录为记忆
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
tuple: (压缩记忆集合, 相似主题字典)
|
|
||||||
"""
|
|
||||||
if not messages:
|
if not messages:
|
||||||
return set(), {}
|
return set(), {}
|
||||||
|
|
||||||
@@ -313,15 +296,23 @@ class Hippocampus:
|
|||||||
topics_response = await self.llm_topic_judge.generate_response(self.find_topic_llm(input_text, topic_num))
|
topics_response = await self.llm_topic_judge.generate_response(self.find_topic_llm(input_text, topic_num))
|
||||||
|
|
||||||
# 过滤topics
|
# 过滤topics
|
||||||
|
# 从配置文件获取需要过滤的关键词列表
|
||||||
filter_keywords = global_config.memory_ban_words
|
filter_keywords = global_config.memory_ban_words
|
||||||
|
|
||||||
|
# 将topics_response[0]中的中文逗号、顿号、空格都替换成英文逗号
|
||||||
|
# 然后按逗号分割成列表,并去除每个topic前后的空白字符
|
||||||
topics = [
|
topics = [
|
||||||
topic.strip()
|
topic.strip()
|
||||||
for topic in topics_response[0].replace(",", ",").replace("、", ",").replace(" ", ",").split(",")
|
for topic in topics_response[0].replace(",", ",").replace("、", ",").replace(" ", ",").split(",")
|
||||||
if topic.strip()
|
if topic.strip()
|
||||||
]
|
]
|
||||||
|
|
||||||
|
# 过滤掉包含禁用关键词的topic
|
||||||
|
# any()检查topic中是否包含任何一个filter_keywords中的关键词
|
||||||
|
# 只保留不包含禁用关键词的topic
|
||||||
filtered_topics = [topic for topic in topics if not any(keyword in topic for keyword in filter_keywords)]
|
filtered_topics = [topic for topic in topics if not any(keyword in topic for keyword in filter_keywords)]
|
||||||
|
|
||||||
logger.info(f"过滤后话题: {filtered_topics}")
|
logger.debug(f"过滤后话题: {filtered_topics}")
|
||||||
|
|
||||||
# 创建所有话题的请求任务
|
# 创建所有话题的请求任务
|
||||||
tasks = []
|
tasks = []
|
||||||
@@ -331,31 +322,42 @@ class Hippocampus:
|
|||||||
tasks.append((topic.strip(), task))
|
tasks.append((topic.strip(), task))
|
||||||
|
|
||||||
# 等待所有任务完成
|
# 等待所有任务完成
|
||||||
compressed_memory = set()
|
# 初始化压缩后的记忆集合和相似主题字典
|
||||||
|
compressed_memory = set() # 存储压缩后的(主题,内容)元组
|
||||||
similar_topics_dict = {} # 存储每个话题的相似主题列表
|
similar_topics_dict = {} # 存储每个话题的相似主题列表
|
||||||
|
|
||||||
|
# 遍历每个主题及其对应的LLM任务
|
||||||
for topic, task in tasks:
|
for topic, task in tasks:
|
||||||
response = await task
|
response = await task
|
||||||
if response:
|
if response:
|
||||||
|
# 将主题和LLM生成的内容添加到压缩记忆中
|
||||||
compressed_memory.add((topic, response[0]))
|
compressed_memory.add((topic, response[0]))
|
||||||
# 为每个话题查找相似的已存在主题
|
|
||||||
|
# 为当前主题寻找相似的已存在主题
|
||||||
existing_topics = list(self.memory_graph.G.nodes())
|
existing_topics = list(self.memory_graph.G.nodes())
|
||||||
similar_topics = []
|
similar_topics = []
|
||||||
|
|
||||||
|
# 计算当前主题与每个已存在主题的相似度
|
||||||
for existing_topic in existing_topics:
|
for existing_topic in existing_topics:
|
||||||
|
# 使用jieba分词,将主题转换为词集合
|
||||||
topic_words = set(jieba.cut(topic))
|
topic_words = set(jieba.cut(topic))
|
||||||
existing_words = set(jieba.cut(existing_topic))
|
existing_words = set(jieba.cut(existing_topic))
|
||||||
|
|
||||||
all_words = topic_words | existing_words
|
# 构建词向量用于计算余弦相似度
|
||||||
v1 = [1 if word in topic_words else 0 for word in all_words]
|
all_words = topic_words | existing_words # 所有不重复的词
|
||||||
v2 = [1 if word in existing_words else 0 for word in all_words]
|
v1 = [1 if word in topic_words else 0 for word in all_words] # 当前主题的词向量
|
||||||
|
v2 = [1 if word in existing_words else 0 for word in all_words] # 已存在主题的词向量
|
||||||
|
|
||||||
|
# 计算余弦相似度
|
||||||
similarity = cosine_similarity(v1, v2)
|
similarity = cosine_similarity(v1, v2)
|
||||||
|
|
||||||
if similarity >= 0.6:
|
# 如果相似度超过阈值,添加到相似主题列表
|
||||||
|
if similarity >= 0.7:
|
||||||
similar_topics.append((existing_topic, similarity))
|
similar_topics.append((existing_topic, similarity))
|
||||||
|
|
||||||
|
# 按相似度降序排序,只保留前3个最相似的主题
|
||||||
similar_topics.sort(key=lambda x: x[1], reverse=True)
|
similar_topics.sort(key=lambda x: x[1], reverse=True)
|
||||||
similar_topics = similar_topics[:5]
|
similar_topics = similar_topics[:3]
|
||||||
similar_topics_dict[topic] = similar_topics
|
similar_topics_dict[topic] = similar_topics
|
||||||
|
|
||||||
return compressed_memory, similar_topics_dict
|
return compressed_memory, similar_topics_dict
|
||||||
@@ -372,10 +374,13 @@ class Hippocampus:
|
|||||||
)
|
)
|
||||||
return topic_num
|
return topic_num
|
||||||
|
|
||||||
async def operation_build_memory(self, chat_size=20):
|
async def operation_build_memory(self):
|
||||||
time_frequency = {"near": 1, "mid": 4, "far": 4}
|
logger.debug("------------------------------------开始构建记忆--------------------------------------")
|
||||||
memory_samples = self.get_memory_sample(chat_size, time_frequency)
|
start_time = time.time()
|
||||||
|
memory_samples = self.get_memory_sample()
|
||||||
|
all_added_nodes = []
|
||||||
|
all_connected_nodes = []
|
||||||
|
all_added_edges = []
|
||||||
for i, messages in enumerate(memory_samples, 1):
|
for i, messages in enumerate(memory_samples, 1):
|
||||||
all_topics = []
|
all_topics = []
|
||||||
# 加载进度可视化
|
# 加载进度可视化
|
||||||
@@ -387,12 +392,14 @@ class Hippocampus:
|
|||||||
|
|
||||||
compress_rate = global_config.memory_compress_rate
|
compress_rate = global_config.memory_compress_rate
|
||||||
compressed_memory, similar_topics_dict = await self.memory_compress(messages, compress_rate)
|
compressed_memory, similar_topics_dict = await self.memory_compress(messages, compress_rate)
|
||||||
logger.info(f"压缩后记忆数量: {len(compressed_memory)},似曾相识的话题: {len(similar_topics_dict)}")
|
logger.debug(f"压缩后记忆数量: {compressed_memory},似曾相识的话题: {similar_topics_dict}")
|
||||||
|
|
||||||
current_time = datetime.datetime.now().timestamp()
|
current_time = datetime.datetime.now().timestamp()
|
||||||
|
logger.debug(f"添加节点: {', '.join(topic for topic, _ in compressed_memory)}")
|
||||||
|
all_added_nodes.extend(topic for topic, _ in compressed_memory)
|
||||||
|
# all_connected_nodes.extend(topic for topic, _ in similar_topics_dict)
|
||||||
|
|
||||||
for topic, memory in compressed_memory:
|
for topic, memory in compressed_memory:
|
||||||
logger.info(f"添加节点: {topic}")
|
|
||||||
self.memory_graph.add_dot(topic, memory)
|
self.memory_graph.add_dot(topic, memory)
|
||||||
all_topics.append(topic)
|
all_topics.append(topic)
|
||||||
|
|
||||||
@@ -402,7 +409,13 @@ class Hippocampus:
|
|||||||
for similar_topic, similarity in similar_topics:
|
for similar_topic, similarity in similar_topics:
|
||||||
if topic != similar_topic:
|
if topic != similar_topic:
|
||||||
strength = int(similarity * 10)
|
strength = int(similarity * 10)
|
||||||
logger.info(f"连接相似节点: {topic} 和 {similar_topic} (强度: {strength})")
|
|
||||||
|
logger.debug(f"连接相似节点: {topic} 和 {similar_topic} (强度: {strength})")
|
||||||
|
all_added_edges.append(f"{topic}-{similar_topic}")
|
||||||
|
|
||||||
|
all_connected_nodes.append(topic)
|
||||||
|
all_connected_nodes.append(similar_topic)
|
||||||
|
|
||||||
self.memory_graph.G.add_edge(
|
self.memory_graph.G.add_edge(
|
||||||
topic,
|
topic,
|
||||||
similar_topic,
|
similar_topic,
|
||||||
@@ -414,10 +427,21 @@ class Hippocampus:
|
|||||||
# 连接同批次的相关话题
|
# 连接同批次的相关话题
|
||||||
for i in range(len(all_topics)):
|
for i in range(len(all_topics)):
|
||||||
for j in range(i + 1, len(all_topics)):
|
for j in range(i + 1, len(all_topics)):
|
||||||
logger.info(f"连接同批次节点: {all_topics[i]} 和 {all_topics[j]}")
|
logger.debug(f"连接同批次节点: {all_topics[i]} 和 {all_topics[j]}")
|
||||||
|
all_added_edges.append(f"{all_topics[i]}-{all_topics[j]}")
|
||||||
self.memory_graph.connect_dot(all_topics[i], all_topics[j])
|
self.memory_graph.connect_dot(all_topics[i], all_topics[j])
|
||||||
|
|
||||||
|
logger.success(f"更新记忆: {', '.join(all_added_nodes)}")
|
||||||
|
logger.debug(f"强化连接: {', '.join(all_added_edges)}")
|
||||||
|
logger.info(f"强化连接节点: {', '.join(all_connected_nodes)}")
|
||||||
|
# logger.success(f"强化连接: {', '.join(all_added_edges)}")
|
||||||
self.sync_memory_to_db()
|
self.sync_memory_to_db()
|
||||||
|
|
||||||
|
end_time = time.time()
|
||||||
|
logger.success(
|
||||||
|
f"--------------------------记忆构建完成:耗时: {end_time - start_time:.2f} "
|
||||||
|
"秒--------------------------"
|
||||||
|
)
|
||||||
|
|
||||||
def sync_memory_to_db(self):
|
def sync_memory_to_db(self):
|
||||||
"""检查并同步内存中的图结构与数据库"""
|
"""检查并同步内存中的图结构与数据库"""
|
||||||
@@ -844,10 +868,9 @@ class Hippocampus:
|
|||||||
|
|
||||||
async def memory_activate_value(self, text: str, max_topics: int = 5, similarity_threshold: float = 0.3) -> int:
|
async def memory_activate_value(self, text: str, max_topics: int = 5, similarity_threshold: float = 0.3) -> int:
|
||||||
"""计算输入文本对记忆的激活程度"""
|
"""计算输入文本对记忆的激活程度"""
|
||||||
logger.info(f"识别主题: {await self._identify_topics(text)}")
|
|
||||||
|
|
||||||
# 识别主题
|
# 识别主题
|
||||||
identified_topics = await self._identify_topics(text)
|
identified_topics = await self._identify_topics(text)
|
||||||
|
|
||||||
if not identified_topics:
|
if not identified_topics:
|
||||||
return 0
|
return 0
|
||||||
|
|
||||||
@@ -908,7 +931,8 @@ class Hippocampus:
|
|||||||
|
|
||||||
# 计算最终激活值
|
# 计算最终激活值
|
||||||
activation = int((topic_match + average_similarities) / 2 * 100)
|
activation = int((topic_match + average_similarities) / 2 * 100)
|
||||||
logger.info(f"匹配率: {topic_match:.3f}, 平均相似度: {average_similarities:.3f}, 激活值: {activation}")
|
|
||||||
|
logger.info(f"识别主题: {identified_topics}, 匹配率: {topic_match:.3f}, 激活值: {activation}")
|
||||||
|
|
||||||
return activation
|
return activation
|
||||||
|
|
||||||
|
|||||||
@@ -7,7 +7,6 @@ import sys
|
|||||||
import time
|
import time
|
||||||
from collections import Counter
|
from collections import Counter
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
|
|
||||||
import matplotlib.pyplot as plt
|
import matplotlib.pyplot as plt
|
||||||
import networkx as nx
|
import networkx as nx
|
||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
@@ -16,7 +15,6 @@ sys.path.insert(0, sys.path[0]+"/../")
|
|||||||
sys.path.insert(0, sys.path[0]+"/../")
|
sys.path.insert(0, sys.path[0]+"/../")
|
||||||
sys.path.insert(0, sys.path[0]+"/../")
|
sys.path.insert(0, sys.path[0]+"/../")
|
||||||
sys.path.insert(0, sys.path[0]+"/../")
|
sys.path.insert(0, sys.path[0]+"/../")
|
||||||
print(sys.path)
|
|
||||||
from src.common.logger import get_module_logger
|
from src.common.logger import get_module_logger
|
||||||
import jieba
|
import jieba
|
||||||
|
|
||||||
@@ -25,6 +23,7 @@ import jieba
|
|||||||
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
||||||
sys.path.append(root_path)
|
sys.path.append(root_path)
|
||||||
|
|
||||||
|
from src.common.logger import get_module_logger # noqa: E402
|
||||||
from src.common.database import db # noqa E402
|
from src.common.database import db # noqa E402
|
||||||
from src.plugins.memory_system.offline_llm import LLMModel # noqa E402
|
from src.plugins.memory_system.offline_llm import LLMModel # noqa E402
|
||||||
|
|
||||||
|
|||||||
170
src/plugins/memory_system/sample_distribution.py
Normal file
@@ -0,0 +1,170 @@
|
|||||||
|
import numpy as np
|
||||||
|
from scipy import stats
|
||||||
|
from datetime import datetime, timedelta
|
||||||
|
|
||||||
|
class DistributionVisualizer:
|
||||||
|
def __init__(self, mean=0, std=1, skewness=0, sample_size=10):
|
||||||
|
"""
|
||||||
|
初始化分布可视化器
|
||||||
|
|
||||||
|
参数:
|
||||||
|
mean (float): 期望均值
|
||||||
|
std (float): 标准差
|
||||||
|
skewness (float): 偏度
|
||||||
|
sample_size (int): 样本大小
|
||||||
|
"""
|
||||||
|
self.mean = mean
|
||||||
|
self.std = std
|
||||||
|
self.skewness = skewness
|
||||||
|
self.sample_size = sample_size
|
||||||
|
self.samples = None
|
||||||
|
|
||||||
|
def generate_samples(self):
|
||||||
|
"""生成具有指定参数的样本"""
|
||||||
|
if self.skewness == 0:
|
||||||
|
# 对于无偏度的情况,直接使用正态分布
|
||||||
|
self.samples = np.random.normal(loc=self.mean, scale=self.std, size=self.sample_size)
|
||||||
|
else:
|
||||||
|
# 使用 scipy.stats 生成具有偏度的分布
|
||||||
|
self.samples = stats.skewnorm.rvs(a=self.skewness,
|
||||||
|
loc=self.mean,
|
||||||
|
scale=self.std,
|
||||||
|
size=self.sample_size)
|
||||||
|
|
||||||
|
def get_weighted_samples(self):
|
||||||
|
"""获取加权后的样本数列"""
|
||||||
|
if self.samples is None:
|
||||||
|
self.generate_samples()
|
||||||
|
# 将样本值乘以样本大小
|
||||||
|
return self.samples * self.sample_size
|
||||||
|
|
||||||
|
def get_statistics(self):
|
||||||
|
"""获取分布的统计信息"""
|
||||||
|
if self.samples is None:
|
||||||
|
self.generate_samples()
|
||||||
|
|
||||||
|
return {
|
||||||
|
"均值": np.mean(self.samples),
|
||||||
|
"标准差": np.std(self.samples),
|
||||||
|
"实际偏度": stats.skew(self.samples)
|
||||||
|
}
|
||||||
|
|
||||||
|
class MemoryBuildScheduler:
|
||||||
|
def __init__(self,
|
||||||
|
n_hours1, std_hours1, weight1,
|
||||||
|
n_hours2, std_hours2, weight2,
|
||||||
|
total_samples=50):
|
||||||
|
"""
|
||||||
|
初始化记忆构建调度器
|
||||||
|
|
||||||
|
参数:
|
||||||
|
n_hours1 (float): 第一个分布的均值(距离现在的小时数)
|
||||||
|
std_hours1 (float): 第一个分布的标准差(小时)
|
||||||
|
weight1 (float): 第一个分布的权重
|
||||||
|
n_hours2 (float): 第二个分布的均值(距离现在的小时数)
|
||||||
|
std_hours2 (float): 第二个分布的标准差(小时)
|
||||||
|
weight2 (float): 第二个分布的权重
|
||||||
|
total_samples (int): 要生成的总时间点数量
|
||||||
|
"""
|
||||||
|
# 归一化权重
|
||||||
|
total_weight = weight1 + weight2
|
||||||
|
self.weight1 = weight1 / total_weight
|
||||||
|
self.weight2 = weight2 / total_weight
|
||||||
|
|
||||||
|
self.n_hours1 = n_hours1
|
||||||
|
self.std_hours1 = std_hours1
|
||||||
|
self.n_hours2 = n_hours2
|
||||||
|
self.std_hours2 = std_hours2
|
||||||
|
self.total_samples = total_samples
|
||||||
|
self.base_time = datetime.now()
|
||||||
|
|
||||||
|
def generate_time_samples(self):
|
||||||
|
"""生成混合分布的时间采样点"""
|
||||||
|
# 根据权重计算每个分布的样本数
|
||||||
|
samples1 = int(self.total_samples * self.weight1)
|
||||||
|
samples2 = self.total_samples - samples1
|
||||||
|
|
||||||
|
# 生成两个正态分布的小时偏移
|
||||||
|
hours_offset1 = np.random.normal(
|
||||||
|
loc=self.n_hours1,
|
||||||
|
scale=self.std_hours1,
|
||||||
|
size=samples1
|
||||||
|
)
|
||||||
|
|
||||||
|
hours_offset2 = np.random.normal(
|
||||||
|
loc=self.n_hours2,
|
||||||
|
scale=self.std_hours2,
|
||||||
|
size=samples2
|
||||||
|
)
|
||||||
|
|
||||||
|
# 合并两个分布的偏移
|
||||||
|
hours_offset = np.concatenate([hours_offset1, hours_offset2])
|
||||||
|
|
||||||
|
# 将偏移转换为实际时间戳(使用绝对值确保时间点在过去)
|
||||||
|
timestamps = [self.base_time - timedelta(hours=abs(offset)) for offset in hours_offset]
|
||||||
|
|
||||||
|
# 按时间排序(从最早到最近)
|
||||||
|
return sorted(timestamps)
|
||||||
|
|
||||||
|
def get_timestamp_array(self):
|
||||||
|
"""返回时间戳数组"""
|
||||||
|
timestamps = self.generate_time_samples()
|
||||||
|
return [int(t.timestamp()) for t in timestamps]
|
||||||
|
|
||||||
|
def print_time_samples(timestamps, show_distribution=True):
|
||||||
|
"""打印时间样本和分布信息"""
|
||||||
|
print(f"\n生成的{len(timestamps)}个时间点分布:")
|
||||||
|
print("序号".ljust(5), "时间戳".ljust(25), "距现在(小时)")
|
||||||
|
print("-" * 50)
|
||||||
|
|
||||||
|
now = datetime.now()
|
||||||
|
time_diffs = []
|
||||||
|
|
||||||
|
for i, timestamp in enumerate(timestamps, 1):
|
||||||
|
hours_diff = (now - timestamp).total_seconds() / 3600
|
||||||
|
time_diffs.append(hours_diff)
|
||||||
|
print(f"{str(i).ljust(5)} {timestamp.strftime('%Y-%m-%d %H:%M:%S').ljust(25)} {hours_diff:.2f}")
|
||||||
|
|
||||||
|
# 打印统计信息
|
||||||
|
print("\n统计信息:")
|
||||||
|
print(f"平均时间偏移:{np.mean(time_diffs):.2f}小时")
|
||||||
|
print(f"标准差:{np.std(time_diffs):.2f}小时")
|
||||||
|
print(f"最早时间:{min(timestamps).strftime('%Y-%m-%d %H:%M:%S')} ({max(time_diffs):.2f}小时前)")
|
||||||
|
print(f"最近时间:{max(timestamps).strftime('%Y-%m-%d %H:%M:%S')} ({min(time_diffs):.2f}小时前)")
|
||||||
|
|
||||||
|
if show_distribution:
|
||||||
|
# 计算时间分布的直方图
|
||||||
|
hist, bins = np.histogram(time_diffs, bins=40)
|
||||||
|
print("\n时间分布(每个*代表一个时间点):")
|
||||||
|
for i in range(len(hist)):
|
||||||
|
if hist[i] > 0:
|
||||||
|
print(f"{bins[i]:6.1f}-{bins[i+1]:6.1f}小时: {'*' * int(hist[i])}")
|
||||||
|
|
||||||
|
# 使用示例
|
||||||
|
if __name__ == "__main__":
|
||||||
|
# 创建一个双峰分布的记忆调度器
|
||||||
|
scheduler = MemoryBuildScheduler(
|
||||||
|
n_hours1=12, # 第一个分布均值(12小时前)
|
||||||
|
std_hours1=8, # 第一个分布标准差
|
||||||
|
weight1=0.7, # 第一个分布权重 70%
|
||||||
|
n_hours2=36, # 第二个分布均值(36小时前)
|
||||||
|
std_hours2=24, # 第二个分布标准差
|
||||||
|
weight2=0.3, # 第二个分布权重 30%
|
||||||
|
total_samples=50 # 总共生成50个时间点
|
||||||
|
)
|
||||||
|
|
||||||
|
# 生成时间分布
|
||||||
|
timestamps = scheduler.generate_time_samples()
|
||||||
|
|
||||||
|
# 打印结果,包含分布可视化
|
||||||
|
print_time_samples(timestamps, show_distribution=True)
|
||||||
|
|
||||||
|
# 打印时间戳数组
|
||||||
|
timestamp_array = scheduler.get_timestamp_array()
|
||||||
|
print("\n时间戳数组(Unix时间戳):")
|
||||||
|
print("[", end="")
|
||||||
|
for i, ts in enumerate(timestamp_array):
|
||||||
|
if i > 0:
|
||||||
|
print(", ", end="")
|
||||||
|
print(ts, end="")
|
||||||
|
print("]")
|
||||||
@@ -524,11 +524,11 @@ class LLM_request:
|
|||||||
return {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
return {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
||||||
# 防止小朋友们截图自己的key
|
# 防止小朋友们截图自己的key
|
||||||
|
|
||||||
async def generate_response(self, prompt: str) -> Tuple[str, str]:
|
async def generate_response(self, prompt: str) -> Tuple[str, str, str]:
|
||||||
"""根据输入的提示生成模型的异步响应"""
|
"""根据输入的提示生成模型的异步响应"""
|
||||||
|
|
||||||
content, reasoning_content = await self._execute_request(endpoint="/chat/completions", prompt=prompt)
|
content, reasoning_content = await self._execute_request(endpoint="/chat/completions", prompt=prompt)
|
||||||
return content, reasoning_content
|
return content, reasoning_content, self.model_name
|
||||||
|
|
||||||
async def generate_response_for_image(self, prompt: str, image_base64: str, image_format: str) -> Tuple[str, str]:
|
async def generate_response_for_image(self, prompt: str, image_base64: str, image_format: str) -> Tuple[str, str]:
|
||||||
"""根据输入的提示和图片生成模型的异步响应"""
|
"""根据输入的提示和图片生成模型的异步响应"""
|
||||||
@@ -583,7 +583,8 @@ class LLM_request:
|
|||||||
completion_tokens=completion_tokens,
|
completion_tokens=completion_tokens,
|
||||||
total_tokens=total_tokens,
|
total_tokens=total_tokens,
|
||||||
user_id="system", # 可以根据需要修改 user_id
|
user_id="system", # 可以根据需要修改 user_id
|
||||||
request_type="embedding", # 请求类型为 embedding
|
# request_type="embedding", # 请求类型为 embedding
|
||||||
|
request_type=self.request_type, # 请求类型为 text
|
||||||
endpoint="/embeddings", # API 端点
|
endpoint="/embeddings", # API 端点
|
||||||
)
|
)
|
||||||
return result["data"][0].get("embedding", None)
|
return result["data"][0].get("embedding", None)
|
||||||
|
|||||||
@@ -15,17 +15,14 @@ env_path = project_root / ".env.prod"
|
|||||||
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
||||||
sys.path.append(root_path)
|
sys.path.append(root_path)
|
||||||
|
|
||||||
from src.plugins.personality.scene import get_scene_by_factor,get_all_scenes,PERSONALITY_SCENES
|
from src.plugins.personality.questionnaire import PERSONALITY_QUESTIONS, FACTOR_DESCRIPTIONS # noqa: E402
|
||||||
from src.plugins.personality.questionnaire import PERSONALITY_QUESTIONS,FACTOR_DESCRIPTIONS
|
|
||||||
from src.plugins.personality.offline_llm import LLMModel
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
class BigFiveTest:
|
class BigFiveTest:
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.questions = PERSONALITY_QUESTIONS
|
self.questions = PERSONALITY_QUESTIONS
|
||||||
self.factors = FACTOR_DESCRIPTIONS
|
self.factors = FACTOR_DESCRIPTIONS
|
||||||
|
|
||||||
def run_test(self):
|
def run_test(self):
|
||||||
"""运行测试并收集答案"""
|
"""运行测试并收集答案"""
|
||||||
print("\n欢迎参加中国大五人格测试!")
|
print("\n欢迎参加中国大五人格测试!")
|
||||||
@@ -37,17 +34,17 @@ class BigFiveTest:
|
|||||||
print("5 = 比较符合")
|
print("5 = 比较符合")
|
||||||
print("6 = 完全符合")
|
print("6 = 完全符合")
|
||||||
print("\n请认真阅读每个描述,选择最符合您实际情况的选项。\n")
|
print("\n请认真阅读每个描述,选择最符合您实际情况的选项。\n")
|
||||||
|
|
||||||
# 创建题目序号到题目的映射
|
# 创建题目序号到题目的映射
|
||||||
questions_map = {q['id']: q for q in self.questions}
|
questions_map = {q["id"]: q for q in self.questions}
|
||||||
|
|
||||||
# 获取所有题目ID并随机打乱顺序
|
# 获取所有题目ID并随机打乱顺序
|
||||||
question_ids = list(questions_map.keys())
|
question_ids = list(questions_map.keys())
|
||||||
random.shuffle(question_ids)
|
random.shuffle(question_ids)
|
||||||
|
|
||||||
answers = {}
|
answers = {}
|
||||||
total_questions = len(question_ids)
|
total_questions = len(question_ids)
|
||||||
|
|
||||||
for i, question_id in enumerate(question_ids, 1):
|
for i, question_id in enumerate(question_ids, 1):
|
||||||
question = questions_map[question_id]
|
question = questions_map[question_id]
|
||||||
while True:
|
while True:
|
||||||
@@ -61,52 +58,43 @@ class BigFiveTest:
|
|||||||
print("请输入1-6之间的数字!")
|
print("请输入1-6之间的数字!")
|
||||||
except ValueError:
|
except ValueError:
|
||||||
print("请输入有效的数字!")
|
print("请输入有效的数字!")
|
||||||
|
|
||||||
return self.calculate_scores(answers)
|
return self.calculate_scores(answers)
|
||||||
|
|
||||||
def calculate_scores(self, answers):
|
def calculate_scores(self, answers):
|
||||||
"""计算各维度得分"""
|
"""计算各维度得分"""
|
||||||
results = {}
|
results = {}
|
||||||
factor_questions = {
|
factor_questions = {"外向性": [], "神经质": [], "严谨性": [], "开放性": [], "宜人性": []}
|
||||||
"外向性": [],
|
|
||||||
"神经质": [],
|
|
||||||
"严谨性": [],
|
|
||||||
"开放性": [],
|
|
||||||
"宜人性": []
|
|
||||||
}
|
|
||||||
|
|
||||||
# 将题目按因子分类
|
# 将题目按因子分类
|
||||||
for q in self.questions:
|
for q in self.questions:
|
||||||
factor_questions[q['factor']].append(q)
|
factor_questions[q["factor"]].append(q)
|
||||||
|
|
||||||
# 计算每个维度的得分
|
# 计算每个维度的得分
|
||||||
for factor, questions in factor_questions.items():
|
for factor, questions in factor_questions.items():
|
||||||
total_score = 0
|
total_score = 0
|
||||||
for q in questions:
|
for q in questions:
|
||||||
score = answers[q['id']]
|
score = answers[q["id"]]
|
||||||
# 处理反向计分题目
|
# 处理反向计分题目
|
||||||
if q['reverse_scoring']:
|
if q["reverse_scoring"]:
|
||||||
score = 7 - score # 6分量表反向计分为7减原始分
|
score = 7 - score # 6分量表反向计分为7减原始分
|
||||||
total_score += score
|
total_score += score
|
||||||
|
|
||||||
# 计算平均分
|
# 计算平均分
|
||||||
avg_score = round(total_score / len(questions), 2)
|
avg_score = round(total_score / len(questions), 2)
|
||||||
results[factor] = {
|
results[factor] = {"得分": avg_score, "题目数": len(questions), "总分": total_score}
|
||||||
"得分": avg_score,
|
|
||||||
"题目数": len(questions),
|
|
||||||
"总分": total_score
|
|
||||||
}
|
|
||||||
|
|
||||||
return results
|
return results
|
||||||
|
|
||||||
def get_factor_description(self, factor):
|
def get_factor_description(self, factor):
|
||||||
"""获取因子的详细描述"""
|
"""获取因子的详细描述"""
|
||||||
return self.factors[factor]
|
return self.factors[factor]
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
test = BigFiveTest()
|
test = BigFiveTest()
|
||||||
results = test.run_test()
|
results = test.run_test()
|
||||||
|
|
||||||
print("\n测试结果:")
|
print("\n测试结果:")
|
||||||
print("=" * 50)
|
print("=" * 50)
|
||||||
for factor, data in results.items():
|
for factor, data in results.items():
|
||||||
@@ -114,9 +102,10 @@ def main():
|
|||||||
print(f"平均分: {data['得分']} (总分: {data['总分']}, 题目数: {data['题目数']})")
|
print(f"平均分: {data['得分']} (总分: {data['总分']}, 题目数: {data['题目数']})")
|
||||||
print("-" * 30)
|
print("-" * 30)
|
||||||
description = test.get_factor_description(factor)
|
description = test.get_factor_description(factor)
|
||||||
print("维度说明:", description['description'][:100] + "...")
|
print("维度说明:", description["description"][:100] + "...")
|
||||||
print("\n特征词:", ", ".join(description['trait_words']))
|
print("\n特征词:", ", ".join(description["trait_words"]))
|
||||||
print("=" * 50)
|
print("=" * 50)
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
from typing import Dict, List
|
from typing import Dict
|
||||||
import json
|
import json
|
||||||
import os
|
import os
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
@@ -14,16 +14,17 @@ env_path = project_root / ".env.prod"
|
|||||||
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
||||||
sys.path.append(root_path)
|
sys.path.append(root_path)
|
||||||
|
|
||||||
from src.plugins.personality.big5_test import BigFiveTest
|
from src.plugins.personality.big5_test import BigFiveTest # noqa: E402
|
||||||
from src.plugins.personality.renqingziji import PersonalityEvaluator_direct
|
from src.plugins.personality.renqingziji import PersonalityEvaluator_direct # noqa: E402
|
||||||
from src.plugins.personality.questionnaire import FACTOR_DESCRIPTIONS, PERSONALITY_QUESTIONS
|
from src.plugins.personality.questionnaire import FACTOR_DESCRIPTIONS, PERSONALITY_QUESTIONS # noqa: E402
|
||||||
|
|
||||||
|
|
||||||
class CombinedPersonalityTest:
|
class CombinedPersonalityTest:
|
||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.big5_test = BigFiveTest()
|
self.big5_test = BigFiveTest()
|
||||||
self.scenario_test = PersonalityEvaluator_direct()
|
self.scenario_test = PersonalityEvaluator_direct()
|
||||||
self.dimensions = ["开放性", "严谨性", "外向性", "宜人性", "神经质"]
|
self.dimensions = ["开放性", "严谨性", "外向性", "宜人性", "神经质"]
|
||||||
|
|
||||||
def run_combined_test(self):
|
def run_combined_test(self):
|
||||||
"""运行组合测试"""
|
"""运行组合测试"""
|
||||||
print("\n=== 人格特征综合评估系统 ===")
|
print("\n=== 人格特征综合评估系统 ===")
|
||||||
@@ -32,12 +33,12 @@ class CombinedPersonalityTest:
|
|||||||
print("2. 情景反应测评(15个场景)")
|
print("2. 情景反应测评(15个场景)")
|
||||||
print("\n两种测评完成后,将对比分析结果的异同。")
|
print("\n两种测评完成后,将对比分析结果的异同。")
|
||||||
input("\n准备好开始第一部分(问卷测评)了吗?按回车继续...")
|
input("\n准备好开始第一部分(问卷测评)了吗?按回车继续...")
|
||||||
|
|
||||||
# 运行问卷测试
|
# 运行问卷测试
|
||||||
print("\n=== 第一部分:问卷测评 ===")
|
print("\n=== 第一部分:问卷测评 ===")
|
||||||
print("本部分采用六级评分,请根据每个描述与您的符合程度进行打分:")
|
print("本部分采用六级评分,请根据每个描述与您的符合程度进行打分:")
|
||||||
print("1 = 完全不符合")
|
print("1 = 完全不符合")
|
||||||
print("2 = 比较不符合")
|
print("2 = 比较不符合")
|
||||||
print("3 = 有点不符合")
|
print("3 = 有点不符合")
|
||||||
print("4 = 有点符合")
|
print("4 = 有点符合")
|
||||||
print("5 = 比较符合")
|
print("5 = 比较符合")
|
||||||
@@ -47,42 +48,39 @@ class CombinedPersonalityTest:
|
|||||||
print("2. 根据您想要扮演的角色特征来回答")
|
print("2. 根据您想要扮演的角色特征来回答")
|
||||||
print("\n无论选择哪种方式,请保持一致并认真回答每个问题。")
|
print("\n无论选择哪种方式,请保持一致并认真回答每个问题。")
|
||||||
input("\n按回车开始答题...")
|
input("\n按回车开始答题...")
|
||||||
|
|
||||||
questionnaire_results = self.run_questionnaire()
|
questionnaire_results = self.run_questionnaire()
|
||||||
|
|
||||||
# 转换问卷结果格式以便比较
|
# 转换问卷结果格式以便比较
|
||||||
questionnaire_scores = {
|
questionnaire_scores = {factor: data["得分"] for factor, data in questionnaire_results.items()}
|
||||||
factor: data["得分"]
|
|
||||||
for factor, data in questionnaire_results.items()
|
|
||||||
}
|
|
||||||
|
|
||||||
# 运行情景测试
|
# 运行情景测试
|
||||||
print("\n=== 第二部分:情景反应测评 ===")
|
print("\n=== 第二部分:情景反应测评 ===")
|
||||||
print("接下来,您将面对一系列具体场景,请描述您在每个场景中可能的反应。")
|
print("接下来,您将面对一系列具体场景,请描述您在每个场景中可能的反应。")
|
||||||
print("每个场景都会评估不同的人格维度,共15个场景。")
|
print("每个场景都会评估不同的人格维度,共15个场景。")
|
||||||
print("您可以选择提供自己的真实反应,也可以选择扮演一个您创作的角色来回答。")
|
print("您可以选择提供自己的真实反应,也可以选择扮演一个您创作的角色来回答。")
|
||||||
input("\n准备好开始了吗?按回车继续...")
|
input("\n准备好开始了吗?按回车继续...")
|
||||||
|
|
||||||
scenario_results = self.run_scenario_test()
|
scenario_results = self.run_scenario_test()
|
||||||
|
|
||||||
# 比较和展示结果
|
# 比较和展示结果
|
||||||
self.compare_and_display_results(questionnaire_scores, scenario_results)
|
self.compare_and_display_results(questionnaire_scores, scenario_results)
|
||||||
|
|
||||||
# 保存结果
|
# 保存结果
|
||||||
self.save_results(questionnaire_scores, scenario_results)
|
self.save_results(questionnaire_scores, scenario_results)
|
||||||
|
|
||||||
def run_questionnaire(self):
|
def run_questionnaire(self):
|
||||||
"""运行问卷测试部分"""
|
"""运行问卷测试部分"""
|
||||||
# 创建题目序号到题目的映射
|
# 创建题目序号到题目的映射
|
||||||
questions_map = {q['id']: q for q in PERSONALITY_QUESTIONS}
|
questions_map = {q["id"]: q for q in PERSONALITY_QUESTIONS}
|
||||||
|
|
||||||
# 获取所有题目ID并随机打乱顺序
|
# 获取所有题目ID并随机打乱顺序
|
||||||
question_ids = list(questions_map.keys())
|
question_ids = list(questions_map.keys())
|
||||||
random.shuffle(question_ids)
|
random.shuffle(question_ids)
|
||||||
|
|
||||||
answers = {}
|
answers = {}
|
||||||
total_questions = len(question_ids)
|
total_questions = len(question_ids)
|
||||||
|
|
||||||
for i, question_id in enumerate(question_ids, 1):
|
for i, question_id in enumerate(question_ids, 1):
|
||||||
question = questions_map[question_id]
|
question = questions_map[question_id]
|
||||||
while True:
|
while True:
|
||||||
@@ -97,48 +95,38 @@ class CombinedPersonalityTest:
|
|||||||
print("请输入1-6之间的数字!")
|
print("请输入1-6之间的数字!")
|
||||||
except ValueError:
|
except ValueError:
|
||||||
print("请输入有效的数字!")
|
print("请输入有效的数字!")
|
||||||
|
|
||||||
# 每10题显示一次进度
|
# 每10题显示一次进度
|
||||||
if i % 10 == 0:
|
if i % 10 == 0:
|
||||||
print(f"\n已完成 {i}/{total_questions} 题 ({int(i/total_questions*100)}%)")
|
print(f"\n已完成 {i}/{total_questions} 题 ({int(i / total_questions * 100)}%)")
|
||||||
|
|
||||||
return self.calculate_questionnaire_scores(answers)
|
return self.calculate_questionnaire_scores(answers)
|
||||||
|
|
||||||
def calculate_questionnaire_scores(self, answers):
|
def calculate_questionnaire_scores(self, answers):
|
||||||
"""计算问卷测试的维度得分"""
|
"""计算问卷测试的维度得分"""
|
||||||
results = {}
|
results = {}
|
||||||
factor_questions = {
|
factor_questions = {"外向性": [], "神经质": [], "严谨性": [], "开放性": [], "宜人性": []}
|
||||||
"外向性": [],
|
|
||||||
"神经质": [],
|
|
||||||
"严谨性": [],
|
|
||||||
"开放性": [],
|
|
||||||
"宜人性": []
|
|
||||||
}
|
|
||||||
|
|
||||||
# 将题目按因子分类
|
# 将题目按因子分类
|
||||||
for q in PERSONALITY_QUESTIONS:
|
for q in PERSONALITY_QUESTIONS:
|
||||||
factor_questions[q['factor']].append(q)
|
factor_questions[q["factor"]].append(q)
|
||||||
|
|
||||||
# 计算每个维度的得分
|
# 计算每个维度的得分
|
||||||
for factor, questions in factor_questions.items():
|
for factor, questions in factor_questions.items():
|
||||||
total_score = 0
|
total_score = 0
|
||||||
for q in questions:
|
for q in questions:
|
||||||
score = answers[q['id']]
|
score = answers[q["id"]]
|
||||||
# 处理反向计分题目
|
# 处理反向计分题目
|
||||||
if q['reverse_scoring']:
|
if q["reverse_scoring"]:
|
||||||
score = 7 - score # 6分量表反向计分为7减原始分
|
score = 7 - score # 6分量表反向计分为7减原始分
|
||||||
total_score += score
|
total_score += score
|
||||||
|
|
||||||
# 计算平均分
|
# 计算平均分
|
||||||
avg_score = round(total_score / len(questions), 2)
|
avg_score = round(total_score / len(questions), 2)
|
||||||
results[factor] = {
|
results[factor] = {"得分": avg_score, "题目数": len(questions), "总分": total_score}
|
||||||
"得分": avg_score,
|
|
||||||
"题目数": len(questions),
|
|
||||||
"总分": total_score
|
|
||||||
}
|
|
||||||
|
|
||||||
return results
|
return results
|
||||||
|
|
||||||
def run_scenario_test(self):
|
def run_scenario_test(self):
|
||||||
"""运行情景测试部分"""
|
"""运行情景测试部分"""
|
||||||
final_scores = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
final_scores = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
||||||
@@ -160,11 +148,7 @@ class CombinedPersonalityTest:
|
|||||||
continue
|
continue
|
||||||
|
|
||||||
print("\n正在评估您的描述...")
|
print("\n正在评估您的描述...")
|
||||||
scores = self.scenario_test.evaluate_response(
|
scores = self.scenario_test.evaluate_response(scenario_data["场景"], response, scenario_data["评估维度"])
|
||||||
scenario_data["场景"],
|
|
||||||
response,
|
|
||||||
scenario_data["评估维度"]
|
|
||||||
)
|
|
||||||
|
|
||||||
# 更新分数
|
# 更新分数
|
||||||
for dimension, score in scores.items():
|
for dimension, score in scores.items():
|
||||||
@@ -178,7 +162,7 @@ class CombinedPersonalityTest:
|
|||||||
|
|
||||||
# 每5个场景显示一次总进度
|
# 每5个场景显示一次总进度
|
||||||
if i % 5 == 0:
|
if i % 5 == 0:
|
||||||
print(f"\n已完成 {i}/{len(scenarios)} 个场景 ({int(i/len(scenarios)*100)}%)")
|
print(f"\n已完成 {i}/{len(scenarios)} 个场景 ({int(i / len(scenarios) * 100)}%)")
|
||||||
|
|
||||||
if i < len(scenarios):
|
if i < len(scenarios):
|
||||||
input("\n按回车继续下一个场景...")
|
input("\n按回车继续下一个场景...")
|
||||||
@@ -186,11 +170,8 @@ class CombinedPersonalityTest:
|
|||||||
# 计算平均分
|
# 计算平均分
|
||||||
for dimension in final_scores:
|
for dimension in final_scores:
|
||||||
if dimension_counts[dimension] > 0:
|
if dimension_counts[dimension] > 0:
|
||||||
final_scores[dimension] = round(
|
final_scores[dimension] = round(final_scores[dimension] / dimension_counts[dimension], 2)
|
||||||
final_scores[dimension] / dimension_counts[dimension],
|
|
||||||
2
|
|
||||||
)
|
|
||||||
|
|
||||||
return final_scores
|
return final_scores
|
||||||
|
|
||||||
def compare_and_display_results(self, questionnaire_scores: Dict, scenario_scores: Dict):
|
def compare_and_display_results(self, questionnaire_scores: Dict, scenario_scores: Dict):
|
||||||
@@ -199,39 +180,43 @@ class CombinedPersonalityTest:
|
|||||||
print("\n" + "=" * 60)
|
print("\n" + "=" * 60)
|
||||||
print(f"{'维度':<8} {'问卷得分':>10} {'情景得分':>10} {'差异':>10} {'差异程度':>10}")
|
print(f"{'维度':<8} {'问卷得分':>10} {'情景得分':>10} {'差异':>10} {'差异程度':>10}")
|
||||||
print("-" * 60)
|
print("-" * 60)
|
||||||
|
|
||||||
# 收集每个维度的得分用于统计分析
|
# 收集每个维度的得分用于统计分析
|
||||||
questionnaire_values = []
|
questionnaire_values = []
|
||||||
scenario_values = []
|
scenario_values = []
|
||||||
diffs = []
|
diffs = []
|
||||||
|
|
||||||
for dimension in self.dimensions:
|
for dimension in self.dimensions:
|
||||||
q_score = questionnaire_scores[dimension]
|
q_score = questionnaire_scores[dimension]
|
||||||
s_score = scenario_scores[dimension]
|
s_score = scenario_scores[dimension]
|
||||||
diff = round(abs(q_score - s_score), 2)
|
diff = round(abs(q_score - s_score), 2)
|
||||||
|
|
||||||
questionnaire_values.append(q_score)
|
questionnaire_values.append(q_score)
|
||||||
scenario_values.append(s_score)
|
scenario_values.append(s_score)
|
||||||
diffs.append(diff)
|
diffs.append(diff)
|
||||||
|
|
||||||
# 计算差异程度
|
# 计算差异程度
|
||||||
diff_level = "低" if diff < 0.5 else "中" if diff < 1.0 else "高"
|
diff_level = "低" if diff < 0.5 else "中" if diff < 1.0 else "高"
|
||||||
print(f"{dimension:<8} {q_score:>10.2f} {s_score:>10.2f} {diff:>10.2f} {diff_level:>10}")
|
print(f"{dimension:<8} {q_score:>10.2f} {s_score:>10.2f} {diff:>10.2f} {diff_level:>10}")
|
||||||
|
|
||||||
print("=" * 60)
|
print("=" * 60)
|
||||||
|
|
||||||
# 计算整体统计指标
|
# 计算整体统计指标
|
||||||
mean_diff = sum(diffs) / len(diffs)
|
mean_diff = sum(diffs) / len(diffs)
|
||||||
std_diff = (sum((x - mean_diff) ** 2 for x in diffs) / (len(diffs) - 1)) ** 0.5
|
std_diff = (sum((x - mean_diff) ** 2 for x in diffs) / (len(diffs) - 1)) ** 0.5
|
||||||
|
|
||||||
# 计算效应量 (Cohen's d)
|
# 计算效应量 (Cohen's d)
|
||||||
pooled_std = ((sum((x - sum(questionnaire_values)/len(questionnaire_values))**2 for x in questionnaire_values) +
|
pooled_std = (
|
||||||
sum((x - sum(scenario_values)/len(scenario_values))**2 for x in scenario_values)) /
|
(
|
||||||
(2 * len(self.dimensions) - 2)) ** 0.5
|
sum((x - sum(questionnaire_values) / len(questionnaire_values)) ** 2 for x in questionnaire_values)
|
||||||
|
+ sum((x - sum(scenario_values) / len(scenario_values)) ** 2 for x in scenario_values)
|
||||||
|
)
|
||||||
|
/ (2 * len(self.dimensions) - 2)
|
||||||
|
) ** 0.5
|
||||||
|
|
||||||
if pooled_std != 0:
|
if pooled_std != 0:
|
||||||
cohens_d = abs(mean_diff / pooled_std)
|
cohens_d = abs(mean_diff / pooled_std)
|
||||||
|
|
||||||
# 解释效应量
|
# 解释效应量
|
||||||
if cohens_d < 0.2:
|
if cohens_d < 0.2:
|
||||||
effect_size = "微小"
|
effect_size = "微小"
|
||||||
@@ -241,41 +226,43 @@ class CombinedPersonalityTest:
|
|||||||
effect_size = "中等"
|
effect_size = "中等"
|
||||||
else:
|
else:
|
||||||
effect_size = "大"
|
effect_size = "大"
|
||||||
|
|
||||||
# 对所有维度进行整体t检验
|
# 对所有维度进行整体t检验
|
||||||
t_stat, p_value = stats.ttest_rel(questionnaire_values, scenario_values)
|
t_stat, p_value = stats.ttest_rel(questionnaire_values, scenario_values)
|
||||||
print(f"\n整体统计分析:")
|
print("\n整体统计分析:")
|
||||||
print(f"平均差异: {mean_diff:.3f}")
|
print(f"平均差异: {mean_diff:.3f}")
|
||||||
print(f"差异标准差: {std_diff:.3f}")
|
print(f"差异标准差: {std_diff:.3f}")
|
||||||
print(f"效应量(Cohen's d): {cohens_d:.3f}")
|
print(f"效应量(Cohen's d): {cohens_d:.3f}")
|
||||||
print(f"效应量大小: {effect_size}")
|
print(f"效应量大小: {effect_size}")
|
||||||
print(f"t统计量: {t_stat:.3f}")
|
print(f"t统计量: {t_stat:.3f}")
|
||||||
print(f"p值: {p_value:.3f}")
|
print(f"p值: {p_value:.3f}")
|
||||||
|
|
||||||
if p_value < 0.05:
|
if p_value < 0.05:
|
||||||
print("结论: 两种测评方法的结果存在显著差异 (p < 0.05)")
|
print("结论: 两种测评方法的结果存在显著差异 (p < 0.05)")
|
||||||
else:
|
else:
|
||||||
print("结论: 两种测评方法的结果无显著差异 (p >= 0.05)")
|
print("结论: 两种测评方法的结果无显著差异 (p >= 0.05)")
|
||||||
|
|
||||||
print("\n维度说明:")
|
print("\n维度说明:")
|
||||||
for dimension in self.dimensions:
|
for dimension in self.dimensions:
|
||||||
print(f"\n{dimension}:")
|
print(f"\n{dimension}:")
|
||||||
desc = FACTOR_DESCRIPTIONS[dimension]
|
desc = FACTOR_DESCRIPTIONS[dimension]
|
||||||
print(f"定义:{desc['description']}")
|
print(f"定义:{desc['description']}")
|
||||||
print(f"特征词:{', '.join(desc['trait_words'])}")
|
print(f"特征词:{', '.join(desc['trait_words'])}")
|
||||||
|
|
||||||
# 分析显著差异
|
# 分析显著差异
|
||||||
significant_diffs = []
|
significant_diffs = []
|
||||||
for dimension in self.dimensions:
|
for dimension in self.dimensions:
|
||||||
diff = abs(questionnaire_scores[dimension] - scenario_scores[dimension])
|
diff = abs(questionnaire_scores[dimension] - scenario_scores[dimension])
|
||||||
if diff >= 1.0: # 差异大于等于1分视为显著
|
if diff >= 1.0: # 差异大于等于1分视为显著
|
||||||
significant_diffs.append({
|
significant_diffs.append(
|
||||||
"dimension": dimension,
|
{
|
||||||
"diff": diff,
|
"dimension": dimension,
|
||||||
"questionnaire": questionnaire_scores[dimension],
|
"diff": diff,
|
||||||
"scenario": scenario_scores[dimension]
|
"questionnaire": questionnaire_scores[dimension],
|
||||||
})
|
"scenario": scenario_scores[dimension],
|
||||||
|
}
|
||||||
|
)
|
||||||
|
|
||||||
if significant_diffs:
|
if significant_diffs:
|
||||||
print("\n\n显著差异分析:")
|
print("\n\n显著差异分析:")
|
||||||
print("-" * 40)
|
print("-" * 40)
|
||||||
@@ -284,9 +271,9 @@ class CombinedPersonalityTest:
|
|||||||
print(f"问卷得分:{diff['questionnaire']:.2f}")
|
print(f"问卷得分:{diff['questionnaire']:.2f}")
|
||||||
print(f"情景得分:{diff['scenario']:.2f}")
|
print(f"情景得分:{diff['scenario']:.2f}")
|
||||||
print(f"差异值:{diff['diff']:.2f}")
|
print(f"差异值:{diff['diff']:.2f}")
|
||||||
|
|
||||||
# 分析可能的原因
|
# 分析可能的原因
|
||||||
if diff['questionnaire'] > diff['scenario']:
|
if diff["questionnaire"] > diff["scenario"]:
|
||||||
print("可能原因:在问卷中的自我评价较高,但在具体情景中的表现较为保守。")
|
print("可能原因:在问卷中的自我评价较高,但在具体情景中的表现较为保守。")
|
||||||
else:
|
else:
|
||||||
print("可能原因:在具体情景中表现出更多该维度特征,而在问卷自评时较为保守。")
|
print("可能原因:在具体情景中表现出更多该维度特征,而在问卷自评时较为保守。")
|
||||||
@@ -297,38 +284,37 @@ class CombinedPersonalityTest:
|
|||||||
"测试时间": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
"测试时间": datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
|
||||||
"问卷测评结果": questionnaire_scores,
|
"问卷测评结果": questionnaire_scores,
|
||||||
"情景测评结果": scenario_scores,
|
"情景测评结果": scenario_scores,
|
||||||
"维度说明": FACTOR_DESCRIPTIONS
|
"维度说明": FACTOR_DESCRIPTIONS,
|
||||||
}
|
}
|
||||||
|
|
||||||
# 确保目录存在
|
# 确保目录存在
|
||||||
os.makedirs("results", exist_ok=True)
|
os.makedirs("results", exist_ok=True)
|
||||||
|
|
||||||
# 生成带时间戳的文件名
|
# 生成带时间戳的文件名
|
||||||
filename = f"results/personality_combined_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
|
filename = f"results/personality_combined_{datetime.now().strftime('%Y%m%d_%H%M%S')}.json"
|
||||||
|
|
||||||
# 保存到文件
|
# 保存到文件
|
||||||
with open(filename, "w", encoding="utf-8") as f:
|
with open(filename, "w", encoding="utf-8") as f:
|
||||||
json.dump(results, f, ensure_ascii=False, indent=2)
|
json.dump(results, f, ensure_ascii=False, indent=2)
|
||||||
|
|
||||||
print(f"\n完整的测评结果已保存到:{filename}")
|
print(f"\n完整的测评结果已保存到:{filename}")
|
||||||
|
|
||||||
|
|
||||||
def load_existing_results():
|
def load_existing_results():
|
||||||
"""检查并加载已有的测试结果"""
|
"""检查并加载已有的测试结果"""
|
||||||
results_dir = "results"
|
results_dir = "results"
|
||||||
if not os.path.exists(results_dir):
|
if not os.path.exists(results_dir):
|
||||||
return None
|
return None
|
||||||
|
|
||||||
# 获取所有personality_combined开头的文件
|
# 获取所有personality_combined开头的文件
|
||||||
result_files = [f for f in os.listdir(results_dir)
|
result_files = [f for f in os.listdir(results_dir) if f.startswith("personality_combined_") and f.endswith(".json")]
|
||||||
if f.startswith("personality_combined_") and f.endswith(".json")]
|
|
||||||
|
|
||||||
if not result_files:
|
if not result_files:
|
||||||
return None
|
return None
|
||||||
|
|
||||||
# 按文件修改时间排序,获取最新的结果文件
|
# 按文件修改时间排序,获取最新的结果文件
|
||||||
latest_file = max(result_files,
|
latest_file = max(result_files, key=lambda f: os.path.getmtime(os.path.join(results_dir, f)))
|
||||||
key=lambda f: os.path.getmtime(os.path.join(results_dir, f)))
|
|
||||||
|
|
||||||
print(f"\n发现已有的测试结果:{latest_file}")
|
print(f"\n发现已有的测试结果:{latest_file}")
|
||||||
try:
|
try:
|
||||||
with open(os.path.join(results_dir, latest_file), "r", encoding="utf-8") as f:
|
with open(os.path.join(results_dir, latest_file), "r", encoding="utf-8") as f:
|
||||||
@@ -338,24 +324,26 @@ def load_existing_results():
|
|||||||
print(f"读取结果文件时出错:{str(e)}")
|
print(f"读取结果文件时出错:{str(e)}")
|
||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
def main():
|
def main():
|
||||||
test = CombinedPersonalityTest()
|
test = CombinedPersonalityTest()
|
||||||
|
|
||||||
# 检查是否存在已有结果
|
# 检查是否存在已有结果
|
||||||
existing_results = load_existing_results()
|
existing_results = load_existing_results()
|
||||||
|
|
||||||
if existing_results:
|
if existing_results:
|
||||||
print("\n=== 使用已有测试结果进行分析 ===")
|
print("\n=== 使用已有测试结果进行分析 ===")
|
||||||
print(f"测试时间:{existing_results['测试时间']}")
|
print(f"测试时间:{existing_results['测试时间']}")
|
||||||
|
|
||||||
questionnaire_scores = existing_results["问卷测评结果"]
|
questionnaire_scores = existing_results["问卷测评结果"]
|
||||||
scenario_scores = existing_results["情景测评结果"]
|
scenario_scores = existing_results["情景测评结果"]
|
||||||
|
|
||||||
# 直接进行结果对比分析
|
# 直接进行结果对比分析
|
||||||
test.compare_and_display_results(questionnaire_scores, scenario_scores)
|
test.compare_and_display_results(questionnaire_scores, scenario_scores)
|
||||||
else:
|
else:
|
||||||
print("\n未找到已有的测试结果,开始新的测试...")
|
print("\n未找到已有的测试结果,开始新的测试...")
|
||||||
test.run_combined_test()
|
test.run_combined_test()
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
main()
|
main()
|
||||||
|
|||||||
@@ -1,5 +1,9 @@
|
|||||||
# 人格测试问卷题目 王孟成, 戴晓阳, & 姚树桥. (2011). 中国大五人格问卷的初步编制Ⅲ:简式版的制定及信效度检验. 中国临床心理学杂志, 19(04), Article 04.
|
# 人格测试问卷题目
|
||||||
# 王孟成, 戴晓阳, & 姚树桥. (2010). 中国大五人格问卷的初步编制Ⅰ:理论框架与信度分析. 中国临床心理学杂志, 18(05), Article 05.
|
# 王孟成, 戴晓阳, & 姚树桥. (2011).
|
||||||
|
# 中国大五人格问卷的初步编制Ⅲ:简式版的制定及信效度检验. 中国临床心理学杂志, 19(04), Article 04.
|
||||||
|
|
||||||
|
# 王孟成, 戴晓阳, & 姚树桥. (2010).
|
||||||
|
# 中国大五人格问卷的初步编制Ⅰ:理论框架与信度分析. 中国临床心理学杂志, 18(05), Article 05.
|
||||||
|
|
||||||
PERSONALITY_QUESTIONS = [
|
PERSONALITY_QUESTIONS = [
|
||||||
# 神经质维度 (F1)
|
# 神经质维度 (F1)
|
||||||
@@ -11,7 +15,6 @@ PERSONALITY_QUESTIONS = [
|
|||||||
{"id": 6, "content": "在面对压力时,我有种快要崩溃的感觉", "factor": "神经质", "reverse_scoring": False},
|
{"id": 6, "content": "在面对压力时,我有种快要崩溃的感觉", "factor": "神经质", "reverse_scoring": False},
|
||||||
{"id": 7, "content": "我常担忧一些无关紧要的事情", "factor": "神经质", "reverse_scoring": False},
|
{"id": 7, "content": "我常担忧一些无关紧要的事情", "factor": "神经质", "reverse_scoring": False},
|
||||||
{"id": 8, "content": "我常常感到内心不踏实", "factor": "神经质", "reverse_scoring": False},
|
{"id": 8, "content": "我常常感到内心不踏实", "factor": "神经质", "reverse_scoring": False},
|
||||||
|
|
||||||
# 严谨性维度 (F2)
|
# 严谨性维度 (F2)
|
||||||
{"id": 9, "content": "在工作上,我常只求能应付过去便可", "factor": "严谨性", "reverse_scoring": True},
|
{"id": 9, "content": "在工作上,我常只求能应付过去便可", "factor": "严谨性", "reverse_scoring": True},
|
||||||
{"id": 10, "content": "一旦确定了目标,我会坚持努力地实现它", "factor": "严谨性", "reverse_scoring": False},
|
{"id": 10, "content": "一旦确定了目标,我会坚持努力地实现它", "factor": "严谨性", "reverse_scoring": False},
|
||||||
@@ -21,9 +24,13 @@ PERSONALITY_QUESTIONS = [
|
|||||||
{"id": 14, "content": "我喜欢一开头就把事情计划好", "factor": "严谨性", "reverse_scoring": False},
|
{"id": 14, "content": "我喜欢一开头就把事情计划好", "factor": "严谨性", "reverse_scoring": False},
|
||||||
{"id": 15, "content": "我工作或学习很勤奋", "factor": "严谨性", "reverse_scoring": False},
|
{"id": 15, "content": "我工作或学习很勤奋", "factor": "严谨性", "reverse_scoring": False},
|
||||||
{"id": 16, "content": "我是个倾尽全力做事的人", "factor": "严谨性", "reverse_scoring": False},
|
{"id": 16, "content": "我是个倾尽全力做事的人", "factor": "严谨性", "reverse_scoring": False},
|
||||||
|
|
||||||
# 宜人性维度 (F3)
|
# 宜人性维度 (F3)
|
||||||
{"id": 17, "content": "尽管人类社会存在着一些阴暗的东西(如战争、罪恶、欺诈),我仍然相信人性总的来说是善良的", "factor": "宜人性", "reverse_scoring": False},
|
{
|
||||||
|
"id": 17,
|
||||||
|
"content": "尽管人类社会存在着一些阴暗的东西(如战争、罪恶、欺诈),我仍然相信人性总的来说是善良的",
|
||||||
|
"factor": "宜人性",
|
||||||
|
"reverse_scoring": False,
|
||||||
|
},
|
||||||
{"id": 18, "content": "我觉得大部分人基本上是心怀善意的", "factor": "宜人性", "reverse_scoring": False},
|
{"id": 18, "content": "我觉得大部分人基本上是心怀善意的", "factor": "宜人性", "reverse_scoring": False},
|
||||||
{"id": 19, "content": "虽然社会上有骗子,但我觉得大部分人还是可信的", "factor": "宜人性", "reverse_scoring": False},
|
{"id": 19, "content": "虽然社会上有骗子,但我觉得大部分人还是可信的", "factor": "宜人性", "reverse_scoring": False},
|
||||||
{"id": 20, "content": "我不太关心别人是否受到不公正的待遇", "factor": "宜人性", "reverse_scoring": True},
|
{"id": 20, "content": "我不太关心别人是否受到不公正的待遇", "factor": "宜人性", "reverse_scoring": True},
|
||||||
@@ -31,7 +38,6 @@ PERSONALITY_QUESTIONS = [
|
|||||||
{"id": 22, "content": "我常为那些遭遇不幸的人感到难过", "factor": "宜人性", "reverse_scoring": False},
|
{"id": 22, "content": "我常为那些遭遇不幸的人感到难过", "factor": "宜人性", "reverse_scoring": False},
|
||||||
{"id": 23, "content": "我是那种只照顾好自己,不替别人担忧的人", "factor": "宜人性", "reverse_scoring": True},
|
{"id": 23, "content": "我是那种只照顾好自己,不替别人担忧的人", "factor": "宜人性", "reverse_scoring": True},
|
||||||
{"id": 24, "content": "当别人向我诉说不幸时,我常感到难过", "factor": "宜人性", "reverse_scoring": False},
|
{"id": 24, "content": "当别人向我诉说不幸时,我常感到难过", "factor": "宜人性", "reverse_scoring": False},
|
||||||
|
|
||||||
# 开放性维度 (F4)
|
# 开放性维度 (F4)
|
||||||
{"id": 25, "content": "我的想象力相当丰富", "factor": "开放性", "reverse_scoring": False},
|
{"id": 25, "content": "我的想象力相当丰富", "factor": "开放性", "reverse_scoring": False},
|
||||||
{"id": 26, "content": "我头脑中经常充满生动的画面", "factor": "开放性", "reverse_scoring": False},
|
{"id": 26, "content": "我头脑中经常充满生动的画面", "factor": "开放性", "reverse_scoring": False},
|
||||||
@@ -39,9 +45,18 @@ PERSONALITY_QUESTIONS = [
|
|||||||
{"id": 28, "content": "我喜欢冒险", "factor": "开放性", "reverse_scoring": False},
|
{"id": 28, "content": "我喜欢冒险", "factor": "开放性", "reverse_scoring": False},
|
||||||
{"id": 29, "content": "我是个勇于冒险,突破常规的人", "factor": "开放性", "reverse_scoring": False},
|
{"id": 29, "content": "我是个勇于冒险,突破常规的人", "factor": "开放性", "reverse_scoring": False},
|
||||||
{"id": 30, "content": "我身上具有别人没有的冒险精神", "factor": "开放性", "reverse_scoring": False},
|
{"id": 30, "content": "我身上具有别人没有的冒险精神", "factor": "开放性", "reverse_scoring": False},
|
||||||
{"id": 31, "content": "我渴望学习一些新东西,即使它们与我的日常生活无关", "factor": "开放性", "reverse_scoring": False},
|
{
|
||||||
{"id": 32, "content": "我很愿意也很容易接受那些新事物、新观点、新想法", "factor": "开放性", "reverse_scoring": False},
|
"id": 31,
|
||||||
|
"content": "我渴望学习一些新东西,即使它们与我的日常生活无关",
|
||||||
|
"factor": "开放性",
|
||||||
|
"reverse_scoring": False,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"id": 32,
|
||||||
|
"content": "我很愿意也很容易接受那些新事物、新观点、新想法",
|
||||||
|
"factor": "开放性",
|
||||||
|
"reverse_scoring": False,
|
||||||
|
},
|
||||||
# 外向性维度 (F5)
|
# 外向性维度 (F5)
|
||||||
{"id": 33, "content": "我喜欢参加社交与娱乐聚会", "factor": "外向性", "reverse_scoring": False},
|
{"id": 33, "content": "我喜欢参加社交与娱乐聚会", "factor": "外向性", "reverse_scoring": False},
|
||||||
{"id": 34, "content": "我对人多的聚会感到乏味", "factor": "外向性", "reverse_scoring": True},
|
{"id": 34, "content": "我对人多的聚会感到乏味", "factor": "外向性", "reverse_scoring": True},
|
||||||
@@ -50,61 +65,78 @@ PERSONALITY_QUESTIONS = [
|
|||||||
{"id": 37, "content": "有我在的场合一般不会冷场", "factor": "外向性", "reverse_scoring": False},
|
{"id": 37, "content": "有我在的场合一般不会冷场", "factor": "外向性", "reverse_scoring": False},
|
||||||
{"id": 38, "content": "我希望成为领导者而不是被领导者", "factor": "外向性", "reverse_scoring": False},
|
{"id": 38, "content": "我希望成为领导者而不是被领导者", "factor": "外向性", "reverse_scoring": False},
|
||||||
{"id": 39, "content": "在一个团体中,我希望处于领导地位", "factor": "外向性", "reverse_scoring": False},
|
{"id": 39, "content": "在一个团体中,我希望处于领导地位", "factor": "外向性", "reverse_scoring": False},
|
||||||
{"id": 40, "content": "别人多认为我是一个热情和友好的人", "factor": "外向性", "reverse_scoring": False}
|
{"id": 40, "content": "别人多认为我是一个热情和友好的人", "factor": "外向性", "reverse_scoring": False},
|
||||||
]
|
]
|
||||||
|
|
||||||
# 因子维度说明
|
# 因子维度说明
|
||||||
FACTOR_DESCRIPTIONS = {
|
FACTOR_DESCRIPTIONS = {
|
||||||
"外向性": {
|
"外向性": {
|
||||||
"description": "反映个体神经系统的强弱和动力特征。外向性主要表现为个体在人际交往和社交活动中的倾向性,包括对社交活动的兴趣、对人群的态度、社交互动中的主动程度以及在群体中的影响力。高分者倾向于积极参与社交活动,乐于与人交往,善于表达自我,并往往在群体中发挥领导作用;低分者则倾向于独处,不喜欢热闹的社交场合,表现出内向、安静的特征。",
|
"description": "反映个体神经系统的强弱和动力特征。外向性主要表现为个体在人际交往和社交活动中的倾向性,"
|
||||||
|
"包括对社交活动的兴趣、"
|
||||||
|
"对人群的态度、社交互动中的主动程度以及在群体中的影响力。高分者倾向于积极参与社交活动,乐于与人交往,善于表达自我,"
|
||||||
|
"并往往在群体中发挥领导作用;低分者则倾向于独处,不喜欢热闹的社交场合,表现出内向、安静的特征。",
|
||||||
"trait_words": ["热情", "活力", "社交", "主动"],
|
"trait_words": ["热情", "活力", "社交", "主动"],
|
||||||
"subfactors": {
|
"subfactors": {
|
||||||
"合群性": "个体愿意与他人聚在一起,即接近人群的倾向;高分表现乐群、好交际,低分表现封闭、独处",
|
"合群性": "个体愿意与他人聚在一起,即接近人群的倾向;高分表现乐群、好交际,低分表现封闭、独处",
|
||||||
"热情": "个体对待别人时所表现出的态度;高分表现热情好客,低分表现冷淡",
|
"热情": "个体对待别人时所表现出的态度;高分表现热情好客,低分表现冷淡",
|
||||||
"支配性": "个体喜欢指使、操纵他人,倾向于领导别人的特点;高分表现好强、发号施令,低分表现顺从、低调",
|
"支配性": "个体喜欢指使、操纵他人,倾向于领导别人的特点;高分表现好强、发号施令,低分表现顺从、低调",
|
||||||
"活跃": "个体精力充沛,活跃、主动性等特点;高分表现活跃,低分表现安静"
|
"活跃": "个体精力充沛,活跃、主动性等特点;高分表现活跃,低分表现安静",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
"神经质": {
|
"神经质": {
|
||||||
"description": "反映个体情绪的状态和体验内心苦恼的倾向性。这个维度主要关注个体在面对压力、挫折和日常生活挑战时的情绪稳定性和适应能力。它包含了对焦虑、抑郁、愤怒等负面情绪的敏感程度,以及个体对这些情绪的调节和控制能力。高分者容易体验负面情绪,对压力较为敏感,情绪波动较大;低分者则表现出较强的情绪稳定性,能够较好地应对压力和挫折。",
|
"description": "反映个体情绪的状态和体验内心苦恼的倾向性。这个维度主要关注个体在面对压力、"
|
||||||
|
"挫折和日常生活挑战时的情绪稳定性和适应能力。它包含了对焦虑、抑郁、愤怒等负面情绪的敏感程度,"
|
||||||
|
"以及个体对这些情绪的调节和控制能力。高分者容易体验负面情绪,对压力较为敏感,情绪波动较大;"
|
||||||
|
"低分者则表现出较强的情绪稳定性,能够较好地应对压力和挫折。",
|
||||||
"trait_words": ["稳定", "沉着", "从容", "坚韧"],
|
"trait_words": ["稳定", "沉着", "从容", "坚韧"],
|
||||||
"subfactors": {
|
"subfactors": {
|
||||||
"焦虑": "个体体验焦虑感的个体差异;高分表现坐立不安,低分表现平静",
|
"焦虑": "个体体验焦虑感的个体差异;高分表现坐立不安,低分表现平静",
|
||||||
"抑郁": "个体体验抑郁情感的个体差异;高分表现郁郁寡欢,低分表现平静",
|
"抑郁": "个体体验抑郁情感的个体差异;高分表现郁郁寡欢,低分表现平静",
|
||||||
"敏感多疑": "个体常常关注自己的内心活动,行为和过于意识人对自己的看法、评价;高分表现敏感多疑,低分表现淡定、自信",
|
"敏感多疑": "个体常常关注自己的内心活动,行为和过于意识人对自己的看法、评价;高分表现敏感多疑,"
|
||||||
|
"低分表现淡定、自信",
|
||||||
"脆弱性": "个体在危机或困难面前无力、脆弱的特点;高分表现无能、易受伤、逃避,低分表现坚强",
|
"脆弱性": "个体在危机或困难面前无力、脆弱的特点;高分表现无能、易受伤、逃避,低分表现坚强",
|
||||||
"愤怒-敌意": "个体准备体验愤怒,及相关情绪的状态;高分表现暴躁易怒,低分表现平静"
|
"愤怒-敌意": "个体准备体验愤怒,及相关情绪的状态;高分表现暴躁易怒,低分表现平静",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
"严谨性": {
|
"严谨性": {
|
||||||
"description": "反映个体在目标导向行为上的组织、坚持和动机特征。这个维度体现了个体在工作、学习等目标性活动中的自我约束和行为管理能力。它涉及到个体的责任感、自律性、计划性、条理性以及完成任务的态度。高分者往往表现出强烈的责任心、良好的组织能力、谨慎的决策风格和持续的努力精神;低分者则可能表现出随意性强、缺乏规划、做事马虎或易放弃的特点。",
|
"description": "反映个体在目标导向行为上的组织、坚持和动机特征。这个维度体现了个体在工作、"
|
||||||
|
"学习等目标性活动中的自我约束和行为管理能力。它涉及到个体的责任感、自律性、计划性、条理性以及完成任务的态度。"
|
||||||
|
"高分者往往表现出强烈的责任心、良好的组织能力、谨慎的决策风格和持续的努力精神;低分者则可能表现出随意性强、"
|
||||||
|
"缺乏规划、做事马虎或易放弃的特点。",
|
||||||
"trait_words": ["负责", "自律", "条理", "勤奋"],
|
"trait_words": ["负责", "自律", "条理", "勤奋"],
|
||||||
"subfactors": {
|
"subfactors": {
|
||||||
"责任心": "个体对待任务和他人认真负责,以及对自己承诺的信守;高分表现有责任心、负责任,低分表现推卸责任、逃避处罚",
|
"责任心": "个体对待任务和他人认真负责,以及对自己承诺的信守;高分表现有责任心、负责任,"
|
||||||
|
"低分表现推卸责任、逃避处罚",
|
||||||
"自我控制": "个体约束自己的能力,及自始至终的坚持性;高分表现自制、有毅力,低分表现冲动、无毅力",
|
"自我控制": "个体约束自己的能力,及自始至终的坚持性;高分表现自制、有毅力,低分表现冲动、无毅力",
|
||||||
"审慎性": "个体在采取具体行动前的心理状态;高分表现谨慎、小心,低分表现鲁莽、草率",
|
"审慎性": "个体在采取具体行动前的心理状态;高分表现谨慎、小心,低分表现鲁莽、草率",
|
||||||
"条理性": "个体处理事务和工作的秩序,条理和逻辑性;高分表现整洁、有秩序,低分表现混乱、遗漏",
|
"条理性": "个体处理事务和工作的秩序,条理和逻辑性;高分表现整洁、有秩序,低分表现混乱、遗漏",
|
||||||
"勤奋": "个体工作和学习的努力程度及为达到目标而表现出的进取精神;高分表现勤奋、刻苦,低分表现懒散"
|
"勤奋": "个体工作和学习的努力程度及为达到目标而表现出的进取精神;高分表现勤奋、刻苦,低分表现懒散",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
"开放性": {
|
"开放性": {
|
||||||
"description": "反映个体对新异事物、新观念和新经验的接受程度,以及在思维和行为方面的创新倾向。这个维度体现了个体在认知和体验方面的广度、深度和灵活性。它包括对艺术的欣赏能力、对知识的求知欲、想象力的丰富程度,以及对冒险和创新的态度。高分者往往具有丰富的想象力、广泛的兴趣、开放的思维方式和创新的倾向;低分者则倾向于保守、传统,喜欢熟悉和常规的事物。",
|
"description": "反映个体对新异事物、新观念和新经验的接受程度,以及在思维和行为方面的创新倾向。"
|
||||||
|
"这个维度体现了个体在认知和体验方面的广度、深度和灵活性。它包括对艺术的欣赏能力、对知识的求知欲、想象力的丰富程度,"
|
||||||
|
"以及对冒险和创新的态度。高分者往往具有丰富的想象力、广泛的兴趣、开放的思维方式和创新的倾向;低分者则倾向于保守、"
|
||||||
|
"传统,喜欢熟悉和常规的事物。",
|
||||||
"trait_words": ["创新", "好奇", "艺术", "冒险"],
|
"trait_words": ["创新", "好奇", "艺术", "冒险"],
|
||||||
"subfactors": {
|
"subfactors": {
|
||||||
"幻想": "个体富于幻想和想象的水平;高分表现想象力丰富,低分表现想象力匮乏",
|
"幻想": "个体富于幻想和想象的水平;高分表现想象力丰富,低分表现想象力匮乏",
|
||||||
"审美": "个体对于艺术和美的敏感与热爱程度;高分表现富有艺术气息,低分表现一般对艺术不敏感",
|
"审美": "个体对于艺术和美的敏感与热爱程度;高分表现富有艺术气息,低分表现一般对艺术不敏感",
|
||||||
"好奇心": "个体对未知事物的态度;高分表现兴趣广泛、好奇心浓,低分表现兴趣少、无好奇心",
|
"好奇心": "个体对未知事物的态度;高分表现兴趣广泛、好奇心浓,低分表现兴趣少、无好奇心",
|
||||||
"冒险精神": "个体愿意尝试有风险活动的个体差异;高分表现好冒险,低分表现保守",
|
"冒险精神": "个体愿意尝试有风险活动的个体差异;高分表现好冒险,低分表现保守",
|
||||||
"价值观念": "个体对新事物、新观念、怪异想法的态度;高分表现开放、坦然接受新事物,低分则相反"
|
"价值观念": "个体对新事物、新观念、怪异想法的态度;高分表现开放、坦然接受新事物,低分则相反",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
"宜人性": {
|
"宜人性": {
|
||||||
"description": "反映个体在人际关系中的亲和倾向,体现了对他人的关心、同情和合作意愿。这个维度主要关注个体与他人互动时的态度和行为特征,包括对他人的信任程度、同理心水平、助人意愿以及在人际冲突中的处理方式。高分者通常表现出友善、富有同情心、乐于助人的特质,善于与他人建立和谐关系;低分者则可能表现出较少的人际关注,在社交互动中更注重自身利益,较少考虑他人感受。",
|
"description": "反映个体在人际关系中的亲和倾向,体现了对他人的关心、同情和合作意愿。"
|
||||||
|
"这个维度主要关注个体与他人互动时的态度和行为特征,包括对他人的信任程度、同理心水平、"
|
||||||
|
"助人意愿以及在人际冲突中的处理方式。高分者通常表现出友善、富有同情心、乐于助人的特质,善于与他人建立和谐关系;"
|
||||||
|
"低分者则可能表现出较少的人际关注,在社交互动中更注重自身利益,较少考虑他人感受。",
|
||||||
"trait_words": ["友善", "同理", "信任", "合作"],
|
"trait_words": ["友善", "同理", "信任", "合作"],
|
||||||
"subfactors": {
|
"subfactors": {
|
||||||
"信任": "个体对他人和/或他人言论的相信程度;高分表现信任他人,低分表现怀疑",
|
"信任": "个体对他人和/或他人言论的相信程度;高分表现信任他人,低分表现怀疑",
|
||||||
"体贴": "个体对别人的兴趣和需要的关注程度;高分表现体贴、温存,低分表现冷漠、不在乎",
|
"体贴": "个体对别人的兴趣和需要的关注程度;高分表现体贴、温存,低分表现冷漠、不在乎",
|
||||||
"同情": "个体对处于不利地位的人或物的态度;高分表现富有同情心,低分表现冷漠"
|
"同情": "个体对处于不利地位的人或物的态度;高分表现富有同情心,低分表现冷漠",
|
||||||
}
|
},
|
||||||
}
|
},
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -1,10 +1,12 @@
|
|||||||
'''
|
"""
|
||||||
The definition of artificial personality in this paper follows the dispositional para-digm and adapts a definition of personality developed for humans [17]:
|
The definition of artificial personality in this paper follows the dispositional para-digm and adapts a definition of
|
||||||
Personality for a human is the "whole and organisation of relatively stable tendencies and patterns of experience and
|
personality developed for humans [17]:
|
||||||
behaviour within one person (distinguishing it from other persons)". This definition is modified for artificial personality:
|
Personality for a human is the "whole and organisation of relatively stable tendencies and patterns of experience and
|
||||||
Artificial personality describes the relatively stable tendencies and patterns of behav-iour of an AI-based machine that
|
behaviour within one person (distinguishing it from other persons)". This definition is modified for artificial
|
||||||
can be designed by developers and designers via different modalities, such as language, creating the impression
|
personality:
|
||||||
of individuality of a humanized social agent when users interact with the machine.'''
|
Artificial personality describes the relatively stable tendencies and patterns of behav-iour of an AI-based machine that
|
||||||
|
can be designed by developers and designers via different modalities, such as language, creating the impression
|
||||||
|
of individuality of a humanized social agent when users interact with the machine."""
|
||||||
|
|
||||||
from typing import Dict, List
|
from typing import Dict, List
|
||||||
import json
|
import json
|
||||||
@@ -13,9 +15,9 @@ from pathlib import Path
|
|||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
import sys
|
import sys
|
||||||
|
|
||||||
'''
|
"""
|
||||||
第一种方案:基于情景评估的人格测定
|
第一种方案:基于情景评估的人格测定
|
||||||
'''
|
"""
|
||||||
current_dir = Path(__file__).resolve().parent
|
current_dir = Path(__file__).resolve().parent
|
||||||
project_root = current_dir.parent.parent.parent
|
project_root = current_dir.parent.parent.parent
|
||||||
env_path = project_root / ".env.prod"
|
env_path = project_root / ".env.prod"
|
||||||
@@ -23,9 +25,9 @@ env_path = project_root / ".env.prod"
|
|||||||
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
||||||
sys.path.append(root_path)
|
sys.path.append(root_path)
|
||||||
|
|
||||||
from src.plugins.personality.scene import get_scene_by_factor,get_all_scenes,PERSONALITY_SCENES
|
from src.plugins.personality.scene import get_scene_by_factor, PERSONALITY_SCENES # noqa: E402
|
||||||
from src.plugins.personality.questionnaire import PERSONALITY_QUESTIONS,FACTOR_DESCRIPTIONS
|
from src.plugins.personality.questionnaire import FACTOR_DESCRIPTIONS # noqa: E402
|
||||||
from src.plugins.personality.offline_llm import LLMModel
|
from src.plugins.personality.offline_llm import LLMModel # noqa: E402
|
||||||
|
|
||||||
# 加载环境变量
|
# 加载环境变量
|
||||||
if env_path.exists():
|
if env_path.exists():
|
||||||
@@ -40,32 +42,31 @@ class PersonalityEvaluator_direct:
|
|||||||
def __init__(self):
|
def __init__(self):
|
||||||
self.personality_traits = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
self.personality_traits = {"开放性": 0, "严谨性": 0, "外向性": 0, "宜人性": 0, "神经质": 0}
|
||||||
self.scenarios = []
|
self.scenarios = []
|
||||||
|
|
||||||
# 为每个人格特质获取对应的场景
|
# 为每个人格特质获取对应的场景
|
||||||
for trait in PERSONALITY_SCENES:
|
for trait in PERSONALITY_SCENES:
|
||||||
scenes = get_scene_by_factor(trait)
|
scenes = get_scene_by_factor(trait)
|
||||||
if not scenes:
|
if not scenes:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
# 从每个维度选择3个场景
|
# 从每个维度选择3个场景
|
||||||
import random
|
import random
|
||||||
|
|
||||||
scene_keys = list(scenes.keys())
|
scene_keys = list(scenes.keys())
|
||||||
selected_scenes = random.sample(scene_keys, min(3, len(scene_keys)))
|
selected_scenes = random.sample(scene_keys, min(3, len(scene_keys)))
|
||||||
|
|
||||||
for scene_key in selected_scenes:
|
for scene_key in selected_scenes:
|
||||||
scene = scenes[scene_key]
|
scene = scenes[scene_key]
|
||||||
|
|
||||||
# 为每个场景添加评估维度
|
# 为每个场景添加评估维度
|
||||||
# 主维度是当前特质,次维度随机选择一个其他特质
|
# 主维度是当前特质,次维度随机选择一个其他特质
|
||||||
other_traits = [t for t in PERSONALITY_SCENES if t != trait]
|
other_traits = [t for t in PERSONALITY_SCENES if t != trait]
|
||||||
secondary_trait = random.choice(other_traits)
|
secondary_trait = random.choice(other_traits)
|
||||||
|
|
||||||
self.scenarios.append({
|
self.scenarios.append(
|
||||||
"场景": scene["scenario"],
|
{"场景": scene["scenario"], "评估维度": [trait, secondary_trait], "场景编号": scene_key}
|
||||||
"评估维度": [trait, secondary_trait],
|
)
|
||||||
"场景编号": scene_key
|
|
||||||
})
|
|
||||||
|
|
||||||
self.llm = LLMModel()
|
self.llm = LLMModel()
|
||||||
|
|
||||||
def evaluate_response(self, scenario: str, response: str, dimensions: List[str]) -> Dict[str, float]:
|
def evaluate_response(self, scenario: str, response: str, dimensions: List[str]) -> Dict[str, float]:
|
||||||
@@ -78,9 +79,9 @@ class PersonalityEvaluator_direct:
|
|||||||
desc = FACTOR_DESCRIPTIONS.get(dim, "")
|
desc = FACTOR_DESCRIPTIONS.get(dim, "")
|
||||||
if desc:
|
if desc:
|
||||||
dimension_descriptions.append(f"- {dim}:{desc}")
|
dimension_descriptions.append(f"- {dim}:{desc}")
|
||||||
|
|
||||||
dimensions_text = "\n".join(dimension_descriptions)
|
dimensions_text = "\n".join(dimension_descriptions)
|
||||||
|
|
||||||
prompt = f"""请根据以下场景和用户描述,评估用户在大五人格模型中的相关维度得分(1-6分)。
|
prompt = f"""请根据以下场景和用户描述,评估用户在大五人格模型中的相关维度得分(1-6分)。
|
||||||
|
|
||||||
场景描述:
|
场景描述:
|
||||||
@@ -178,11 +179,7 @@ def main():
|
|||||||
print(f"测试场景数:{dimension_counts[trait]}")
|
print(f"测试场景数:{dimension_counts[trait]}")
|
||||||
|
|
||||||
# 保存结果
|
# 保存结果
|
||||||
result = {
|
result = {"final_scores": final_scores, "dimension_counts": dimension_counts, "scenarios": evaluator.scenarios}
|
||||||
"final_scores": final_scores,
|
|
||||||
"dimension_counts": dimension_counts,
|
|
||||||
"scenarios": evaluator.scenarios
|
|
||||||
}
|
|
||||||
|
|
||||||
# 确保目录存在
|
# 确保目录存在
|
||||||
os.makedirs("results", exist_ok=True)
|
os.makedirs("results", exist_ok=True)
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
from typing import Dict, List
|
from typing import Dict
|
||||||
|
|
||||||
PERSONALITY_SCENES = {
|
PERSONALITY_SCENES = {
|
||||||
"外向性": {
|
"外向性": {
|
||||||
@@ -8,7 +8,7 @@ PERSONALITY_SCENES = {
|
|||||||
同事:「嗨!你是新来的同事吧?我是市场部的小林。」
|
同事:「嗨!你是新来的同事吧?我是市场部的小林。」
|
||||||
|
|
||||||
同事看起来很友善,还主动介绍说:「待会午饭时间,我们部门有几个人准备一起去楼下新开的餐厅,你要一起来吗?可以认识一下其他同事。」""",
|
同事看起来很友善,还主动介绍说:「待会午饭时间,我们部门有几个人准备一起去楼下新开的餐厅,你要一起来吗?可以认识一下其他同事。」""",
|
||||||
"explanation": "这个场景通过职场社交情境,观察个体对于新环境、新社交圈的态度和反应倾向。"
|
"explanation": "这个场景通过职场社交情境,观察个体对于新环境、新社交圈的态度和反应倾向。",
|
||||||
},
|
},
|
||||||
"场景2": {
|
"场景2": {
|
||||||
"scenario": """在大学班级群里,班长发起了一个组织班级联谊活动的投票:
|
"scenario": """在大学班级群里,班长发起了一个组织班级联谊活动的投票:
|
||||||
@@ -16,7 +16,7 @@ PERSONALITY_SCENES = {
|
|||||||
班长:「大家好!下周末我们准备举办一次班级联谊活动,地点在学校附近的KTV。想请大家报名参加,也欢迎大家邀请其他班级的同学!」
|
班长:「大家好!下周末我们准备举办一次班级联谊活动,地点在学校附近的KTV。想请大家报名参加,也欢迎大家邀请其他班级的同学!」
|
||||||
|
|
||||||
已经有几个同学在群里积极响应,有人@你问你要不要一起参加。""",
|
已经有几个同学在群里积极响应,有人@你问你要不要一起参加。""",
|
||||||
"explanation": "通过班级活动场景,观察个体对群体社交活动的参与意愿。"
|
"explanation": "通过班级活动场景,观察个体对群体社交活动的参与意愿。",
|
||||||
},
|
},
|
||||||
"场景3": {
|
"场景3": {
|
||||||
"scenario": """你在社交平台上发布了一条动态,收到了很多陌生网友的评论和私信:
|
"scenario": """你在社交平台上发布了一条动态,收到了很多陌生网友的评论和私信:
|
||||||
@@ -24,13 +24,14 @@ PERSONALITY_SCENES = {
|
|||||||
网友A:「你说的这个观点很有意思!想和你多交流一下。」
|
网友A:「你说的这个观点很有意思!想和你多交流一下。」
|
||||||
|
|
||||||
网友B:「我也对这个话题很感兴趣,要不要建个群一起讨论?」""",
|
网友B:「我也对这个话题很感兴趣,要不要建个群一起讨论?」""",
|
||||||
"explanation": "通过网络社交场景,观察个体对线上社交的态度。"
|
"explanation": "通过网络社交场景,观察个体对线上社交的态度。",
|
||||||
},
|
},
|
||||||
"场景4": {
|
"场景4": {
|
||||||
"scenario": """你暗恋的对象今天主动来找你:
|
"scenario": """你暗恋的对象今天主动来找你:
|
||||||
|
|
||||||
对方:「那个...我最近在准备一个演讲比赛,听说你口才很好。能不能请你帮我看看演讲稿,顺便给我一些建议?如果你有时间的话,可以一起吃个饭聊聊。」""",
|
对方:「那个...我最近在准备一个演讲比赛,听说你口才很好。能不能请你帮我看看演讲稿,顺便给我一些建议?"""
|
||||||
"explanation": "通过恋爱情境,观察个体在面对心仪对象时的社交表现。"
|
"""如果你有时间的话,可以一起吃个饭聊聊。」""",
|
||||||
|
"explanation": "通过恋爱情境,观察个体在面对心仪对象时的社交表现。",
|
||||||
},
|
},
|
||||||
"场景5": {
|
"场景5": {
|
||||||
"scenario": """在一次线下读书会上,主持人突然点名让你分享读后感:
|
"scenario": """在一次线下读书会上,主持人突然点名让你分享读后感:
|
||||||
@@ -38,18 +39,18 @@ PERSONALITY_SCENES = {
|
|||||||
主持人:「听说你对这本书很有见解,能不能和大家分享一下你的想法?」
|
主持人:「听说你对这本书很有见解,能不能和大家分享一下你的想法?」
|
||||||
|
|
||||||
现场有二十多个陌生的读书爱好者,都期待地看着你。""",
|
现场有二十多个陌生的读书爱好者,都期待地看着你。""",
|
||||||
"explanation": "通过即兴发言场景,观察个体的社交表现欲和公众表达能力。"
|
"explanation": "通过即兴发言场景,观察个体的社交表现欲和公众表达能力。",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
|
|
||||||
"神经质": {
|
"神经质": {
|
||||||
"场景1": {
|
"场景1": {
|
||||||
"scenario": """你正在准备一个重要的项目演示,这关系到你的晋升机会。就在演示前30分钟,你收到了主管发来的消息:
|
"scenario": """你正在准备一个重要的项目演示,这关系到你的晋升机会。"""
|
||||||
|
"""就在演示前30分钟,你收到了主管发来的消息:
|
||||||
|
|
||||||
主管:「临时有个变动,CEO也会来听你的演示。他对这个项目特别感兴趣。」
|
主管:「临时有个变动,CEO也会来听你的演示。他对这个项目特别感兴趣。」
|
||||||
|
|
||||||
正当你准备回复时,主管又发来一条:「对了,能不能把演示时间压缩到15分钟?CEO下午还有其他安排。你之前准备的是30分钟的版本对吧?」""",
|
正当你准备回复时,主管又发来一条:「对了,能不能把演示时间压缩到15分钟?CEO下午还有其他安排。你之前准备的是30分钟的版本对吧?」""",
|
||||||
"explanation": "这个场景通过突发的压力情境,观察个体在面对计划外变化时的情绪反应和调节能力。"
|
"explanation": "这个场景通过突发的压力情境,观察个体在面对计划外变化时的情绪反应和调节能力。",
|
||||||
},
|
},
|
||||||
"场景2": {
|
"场景2": {
|
||||||
"scenario": """期末考试前一天晚上,你收到了好朋友发来的消息:
|
"scenario": """期末考试前一天晚上,你收到了好朋友发来的消息:
|
||||||
@@ -57,7 +58,7 @@ PERSONALITY_SCENES = {
|
|||||||
好朋友:「不好意思这么晚打扰你...我看你平时成绩很好,能不能帮我解答几个问题?我真的很担心明天的考试。」
|
好朋友:「不好意思这么晚打扰你...我看你平时成绩很好,能不能帮我解答几个问题?我真的很担心明天的考试。」
|
||||||
|
|
||||||
你看了看时间,已经是晚上11点,而你原本计划的复习还没完成。""",
|
你看了看时间,已经是晚上11点,而你原本计划的复习还没完成。""",
|
||||||
"explanation": "通过考试压力场景,观察个体在时间紧张时的情绪管理。"
|
"explanation": "通过考试压力场景,观察个体在时间紧张时的情绪管理。",
|
||||||
},
|
},
|
||||||
"场景3": {
|
"场景3": {
|
||||||
"scenario": """你在社交媒体上发表的一个观点引发了争议,有不少人开始批评你:
|
"scenario": """你在社交媒体上发表的一个观点引发了争议,有不少人开始批评你:
|
||||||
@@ -67,7 +68,7 @@ PERSONALITY_SCENES = {
|
|||||||
网友B:「建议楼主先去补补课再来发言。」
|
网友B:「建议楼主先去补补课再来发言。」
|
||||||
|
|
||||||
评论区里的负面评论越来越多,还有人开始人身攻击。""",
|
评论区里的负面评论越来越多,还有人开始人身攻击。""",
|
||||||
"explanation": "通过网络争议场景,观察个体面对批评时的心理承受能力。"
|
"explanation": "通过网络争议场景,观察个体面对批评时的心理承受能力。",
|
||||||
},
|
},
|
||||||
"场景4": {
|
"场景4": {
|
||||||
"scenario": """你和恋人约好今天一起看电影,但在约定时间前半小时,对方发来消息:
|
"scenario": """你和恋人约好今天一起看电影,但在约定时间前半小时,对方发来消息:
|
||||||
@@ -77,7 +78,7 @@ PERSONALITY_SCENES = {
|
|||||||
二十分钟后,对方又发来消息:「可能要再等等,抱歉!」
|
二十分钟后,对方又发来消息:「可能要再等等,抱歉!」
|
||||||
|
|
||||||
电影快要开始了,但对方还是没有出现。""",
|
电影快要开始了,但对方还是没有出现。""",
|
||||||
"explanation": "通过恋爱情境,观察个体对不确定性的忍耐程度。"
|
"explanation": "通过恋爱情境,观察个体对不确定性的忍耐程度。",
|
||||||
},
|
},
|
||||||
"场景5": {
|
"场景5": {
|
||||||
"scenario": """在一次重要的小组展示中,你的组员在演示途中突然卡壳了:
|
"scenario": """在一次重要的小组展示中,你的组员在演示途中突然卡壳了:
|
||||||
@@ -85,10 +86,9 @@ PERSONALITY_SCENES = {
|
|||||||
组员小声对你说:「我忘词了,接下来的部分是什么来着...」
|
组员小声对你说:「我忘词了,接下来的部分是什么来着...」
|
||||||
|
|
||||||
台下的老师和同学都在等待,气氛有些尴尬。""",
|
台下的老师和同学都在等待,气氛有些尴尬。""",
|
||||||
"explanation": "通过公开场合的突发状况,观察个体的应急反应和压力处理能力。"
|
"explanation": "通过公开场合的突发状况,观察个体的应急反应和压力处理能力。",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
|
|
||||||
"严谨性": {
|
"严谨性": {
|
||||||
"场景1": {
|
"场景1": {
|
||||||
"scenario": """你是团队的项目负责人,刚刚接手了一个为期两个月的重要项目。在第一次团队会议上:
|
"scenario": """你是团队的项目负责人,刚刚接手了一个为期两个月的重要项目。在第一次团队会议上:
|
||||||
@@ -98,7 +98,7 @@ PERSONALITY_SCENES = {
|
|||||||
小张:「要不要先列个时间表?不过感觉太详细的计划也没必要,点到为止就行。」
|
小张:「要不要先列个时间表?不过感觉太详细的计划也没必要,点到为止就行。」
|
||||||
|
|
||||||
小李:「客户那边说如果能提前完成有奖励,我觉得我们可以先做快一点的部分。」""",
|
小李:「客户那边说如果能提前完成有奖励,我觉得我们可以先做快一点的部分。」""",
|
||||||
"explanation": "这个场景通过项目管理情境,体现个体在工作方法、计划性和责任心方面的特征。"
|
"explanation": "这个场景通过项目管理情境,体现个体在工作方法、计划性和责任心方面的特征。",
|
||||||
},
|
},
|
||||||
"场景2": {
|
"场景2": {
|
||||||
"scenario": """期末小组作业,组长让大家分工完成一份研究报告。在截止日期前三天:
|
"scenario": """期末小组作业,组长让大家分工完成一份研究报告。在截止日期前三天:
|
||||||
@@ -108,7 +108,7 @@ PERSONALITY_SCENES = {
|
|||||||
组员B:「我这边可能还要一天才能完成,最近太忙了。」
|
组员B:「我这边可能还要一天才能完成,最近太忙了。」
|
||||||
|
|
||||||
组员C发来一份没有任何引用出处、可能存在抄袭的内容:「我写完了,你们看看怎么样?」""",
|
组员C发来一份没有任何引用出处、可能存在抄袭的内容:「我写完了,你们看看怎么样?」""",
|
||||||
"explanation": "通过学习场景,观察个体对学术规范和质量要求的重视程度。"
|
"explanation": "通过学习场景,观察个体对学术规范和质量要求的重视程度。",
|
||||||
},
|
},
|
||||||
"场景3": {
|
"场景3": {
|
||||||
"scenario": """你在一个兴趣小组的群聊中,大家正在讨论举办一次线下活动:
|
"scenario": """你在一个兴趣小组的群聊中,大家正在讨论举办一次线下活动:
|
||||||
@@ -118,7 +118,7 @@ PERSONALITY_SCENES = {
|
|||||||
成员B:「对啊,随意一点挺好的。」
|
成员B:「对啊,随意一点挺好的。」
|
||||||
|
|
||||||
成员C:「人来了自然就热闹了。」""",
|
成员C:「人来了自然就热闹了。」""",
|
||||||
"explanation": "通过活动组织场景,观察个体对活动计划的态度。"
|
"explanation": "通过活动组织场景,观察个体对活动计划的态度。",
|
||||||
},
|
},
|
||||||
"场景4": {
|
"场景4": {
|
||||||
"scenario": """你和恋人计划一起去旅游,对方说:
|
"scenario": """你和恋人计划一起去旅游,对方说:
|
||||||
@@ -126,7 +126,7 @@ PERSONALITY_SCENES = {
|
|||||||
恋人:「我们就随心而行吧!订个目的地,其他的到了再说,这样更有意思。」
|
恋人:「我们就随心而行吧!订个目的地,其他的到了再说,这样更有意思。」
|
||||||
|
|
||||||
距离出发还有一周时间,但机票、住宿和具体行程都还没有确定。""",
|
距离出发还有一周时间,但机票、住宿和具体行程都还没有确定。""",
|
||||||
"explanation": "通过旅行规划场景,观察个体的计划性和对不确定性的接受程度。"
|
"explanation": "通过旅行规划场景,观察个体的计划性和对不确定性的接受程度。",
|
||||||
},
|
},
|
||||||
"场景5": {
|
"场景5": {
|
||||||
"scenario": """在一个重要的团队项目中,你发现一个同事的工作存在明显错误:
|
"scenario": """在一个重要的团队项目中,你发现一个同事的工作存在明显错误:
|
||||||
@@ -134,18 +134,19 @@ PERSONALITY_SCENES = {
|
|||||||
同事:「差不多就行了,反正领导也看不出来。」
|
同事:「差不多就行了,反正领导也看不出来。」
|
||||||
|
|
||||||
这个错误可能不会立即造成问题,但长期来看可能会影响项目质量。""",
|
这个错误可能不会立即造成问题,但长期来看可能会影响项目质量。""",
|
||||||
"explanation": "通过工作质量场景,观察个体对细节和标准的坚持程度。"
|
"explanation": "通过工作质量场景,观察个体对细节和标准的坚持程度。",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
|
|
||||||
"开放性": {
|
"开放性": {
|
||||||
"场景1": {
|
"场景1": {
|
||||||
"scenario": """周末下午,你的好友小美兴致勃勃地给你打电话:
|
"scenario": """周末下午,你的好友小美兴致勃勃地给你打电话:
|
||||||
|
|
||||||
小美:「我刚发现一个特别有意思的沉浸式艺术展!不是传统那种挂画的展览,而是把整个空间都变成了艺术品。观众要穿特制的服装,还要带上VR眼镜,好像还有AI实时互动!」
|
小美:「我刚发现一个特别有意思的沉浸式艺术展!不是传统那种挂画的展览,而是把整个空间都变成了艺术品。"""
|
||||||
|
"""观众要穿特制的服装,还要带上VR眼镜,好像还有AI实时互动!」
|
||||||
|
|
||||||
小美继续说:「虽然票价不便宜,但听说体验很独特。网上评价两极分化,有人说是前所未有的艺术革新,也有人说是哗众取宠。要不要周末一起去体验一下?」""",
|
小美继续说:「虽然票价不便宜,但听说体验很独特。网上评价两极分化,有人说是前所未有的艺术革新,也有人说是哗众取宠。"""
|
||||||
"explanation": "这个场景通过新型艺术体验,反映个体对创新事物的接受程度和尝试意愿。"
|
"""要不要周末一起去体验一下?」""",
|
||||||
|
"explanation": "这个场景通过新型艺术体验,反映个体对创新事物的接受程度和尝试意愿。",
|
||||||
},
|
},
|
||||||
"场景2": {
|
"场景2": {
|
||||||
"scenario": """在一节创意写作课上,老师提出了一个特别的作业:
|
"scenario": """在一节创意写作课上,老师提出了一个特别的作业:
|
||||||
@@ -153,15 +154,16 @@ PERSONALITY_SCENES = {
|
|||||||
老师:「下周的作业是用AI写作工具协助创作一篇小说。你们可以自由探索如何与AI合作,打破传统写作方式。」
|
老师:「下周的作业是用AI写作工具协助创作一篇小说。你们可以自由探索如何与AI合作,打破传统写作方式。」
|
||||||
|
|
||||||
班上随即展开了激烈讨论,有人认为这是对创作的亵渎,也有人对这种新形式感到兴奋。""",
|
班上随即展开了激烈讨论,有人认为这是对创作的亵渎,也有人对这种新形式感到兴奋。""",
|
||||||
"explanation": "通过新技术应用场景,观察个体对创新学习方式的态度。"
|
"explanation": "通过新技术应用场景,观察个体对创新学习方式的态度。",
|
||||||
},
|
},
|
||||||
"场景3": {
|
"场景3": {
|
||||||
"scenario": """在社交媒体上,你看到一个朋友分享了一种新的生活方式:
|
"scenario": """在社交媒体上,你看到一个朋友分享了一种新的生活方式:
|
||||||
|
|
||||||
「最近我在尝试'数字游牧'生活,就是一边远程工作一边环游世界。没有固定住所,住青旅或短租,认识来自世界各地的朋友。虽然有时会很不稳定,但这种自由的生活方式真的很棒!」
|
「最近我在尝试'数字游牧'生活,就是一边远程工作一边环游世界。"""
|
||||||
|
"""没有固定住所,住青旅或短租,认识来自世界各地的朋友。虽然有时会很不稳定,但这种自由的生活方式真的很棒!」
|
||||||
|
|
||||||
评论区里争论不断,有人向往这种生活,也有人觉得太冒险。""",
|
评论区里争论不断,有人向往这种生活,也有人觉得太冒险。""",
|
||||||
"explanation": "通过另类生活方式,观察个体对非传统选择的态度。"
|
"explanation": "通过另类生活方式,观察个体对非传统选择的态度。",
|
||||||
},
|
},
|
||||||
"场景4": {
|
"场景4": {
|
||||||
"scenario": """你的恋人突然提出了一个想法:
|
"scenario": """你的恋人突然提出了一个想法:
|
||||||
@@ -169,7 +171,7 @@ PERSONALITY_SCENES = {
|
|||||||
恋人:「我们要不要尝试一下开放式关系?就是在保持彼此关系的同时,也允许和其他人发展感情。现在国外很多年轻人都这样。」
|
恋人:「我们要不要尝试一下开放式关系?就是在保持彼此关系的同时,也允许和其他人发展感情。现在国外很多年轻人都这样。」
|
||||||
|
|
||||||
这个提议让你感到意外,你之前从未考虑过这种可能性。""",
|
这个提议让你感到意外,你之前从未考虑过这种可能性。""",
|
||||||
"explanation": "通过感情观念场景,观察个体对非传统关系模式的接受度。"
|
"explanation": "通过感情观念场景,观察个体对非传统关系模式的接受度。",
|
||||||
},
|
},
|
||||||
"场景5": {
|
"场景5": {
|
||||||
"scenario": """在一次朋友聚会上,大家正在讨论未来职业规划:
|
"scenario": """在一次朋友聚会上,大家正在讨论未来职业规划:
|
||||||
@@ -179,10 +181,9 @@ PERSONALITY_SCENES = {
|
|||||||
朋友B:「我想去学习生物科技,准备转行做人造肉研发。」
|
朋友B:「我想去学习生物科技,准备转行做人造肉研发。」
|
||||||
|
|
||||||
朋友C:「我在考虑加入一个区块链创业项目,虽然风险很大。」""",
|
朋友C:「我在考虑加入一个区块链创业项目,虽然风险很大。」""",
|
||||||
"explanation": "通过职业选择场景,观察个体对新兴领域的探索意愿。"
|
"explanation": "通过职业选择场景,观察个体对新兴领域的探索意愿。",
|
||||||
}
|
},
|
||||||
},
|
},
|
||||||
|
|
||||||
"宜人性": {
|
"宜人性": {
|
||||||
"场景1": {
|
"场景1": {
|
||||||
"scenario": """在回家的公交车上,你遇到这样一幕:
|
"scenario": """在回家的公交车上,你遇到这样一幕:
|
||||||
@@ -194,7 +195,7 @@ PERSONALITY_SCENES = {
|
|||||||
年轻人B:「现在的老年人真是...我看她包里还有菜,肯定是去菜市场买完菜回来的,这么多人都不知道叫子女开车接送。」
|
年轻人B:「现在的老年人真是...我看她包里还有菜,肯定是去菜市场买完菜回来的,这么多人都不知道叫子女开车接送。」
|
||||||
|
|
||||||
就在这时,老奶奶一个趔趄,差点摔倒。她扶住了扶手,但包里的东西洒了一些出来。""",
|
就在这时,老奶奶一个趔趄,差点摔倒。她扶住了扶手,但包里的东西洒了一些出来。""",
|
||||||
"explanation": "这个场景通过公共场合的助人情境,体现个体的同理心和对他人需求的关注程度。"
|
"explanation": "这个场景通过公共场合的助人情境,体现个体的同理心和对他人需求的关注程度。",
|
||||||
},
|
},
|
||||||
"场景2": {
|
"场景2": {
|
||||||
"scenario": """在班级群里,有同学发起为生病住院的同学捐款:
|
"scenario": """在班级群里,有同学发起为生病住院的同学捐款:
|
||||||
@@ -204,7 +205,7 @@ PERSONALITY_SCENES = {
|
|||||||
同学B:「我觉得这是他家里的事,我们不方便参与吧。」
|
同学B:「我觉得这是他家里的事,我们不方便参与吧。」
|
||||||
|
|
||||||
同学C:「但是都是同学一场,帮帮忙也是应该的。」""",
|
同学C:「但是都是同学一场,帮帮忙也是应该的。」""",
|
||||||
"explanation": "通过同学互助场景,观察个体的助人意愿和同理心。"
|
"explanation": "通过同学互助场景,观察个体的助人意愿和同理心。",
|
||||||
},
|
},
|
||||||
"场景3": {
|
"场景3": {
|
||||||
"scenario": """在一个网络讨论组里,有人发布了求助信息:
|
"scenario": """在一个网络讨论组里,有人发布了求助信息:
|
||||||
@@ -215,7 +216,7 @@ PERSONALITY_SCENES = {
|
|||||||
「生活本来就是这样,想开点!」
|
「生活本来就是这样,想开点!」
|
||||||
「你这样子太消极了,要积极面对。」
|
「你这样子太消极了,要积极面对。」
|
||||||
「谁还没点烦心事啊,过段时间就好了。」""",
|
「谁还没点烦心事啊,过段时间就好了。」""",
|
||||||
"explanation": "通过网络互助场景,观察个体的共情能力和安慰方式。"
|
"explanation": "通过网络互助场景,观察个体的共情能力和安慰方式。",
|
||||||
},
|
},
|
||||||
"场景4": {
|
"场景4": {
|
||||||
"scenario": """你的恋人向你倾诉工作压力:
|
"scenario": """你的恋人向你倾诉工作压力:
|
||||||
@@ -223,7 +224,7 @@ PERSONALITY_SCENES = {
|
|||||||
恋人:「最近工作真的好累,感觉快坚持不下去了...」
|
恋人:「最近工作真的好累,感觉快坚持不下去了...」
|
||||||
|
|
||||||
但今天你也遇到了很多烦心事,心情也不太好。""",
|
但今天你也遇到了很多烦心事,心情也不太好。""",
|
||||||
"explanation": "通过感情关系场景,观察个体在自身状态不佳时的关怀能力。"
|
"explanation": "通过感情关系场景,观察个体在自身状态不佳时的关怀能力。",
|
||||||
},
|
},
|
||||||
"场景5": {
|
"场景5": {
|
||||||
"scenario": """在一次团队项目中,新来的同事小王因为经验不足,造成了一个严重的错误。在部门会议上:
|
"scenario": """在一次团队项目中,新来的同事小王因为经验不足,造成了一个严重的错误。在部门会议上:
|
||||||
@@ -231,27 +232,29 @@ PERSONALITY_SCENES = {
|
|||||||
主管:「这个错误造成了很大的损失,是谁负责的这部分?」
|
主管:「这个错误造成了很大的损失,是谁负责的这部分?」
|
||||||
|
|
||||||
小王看起来很紧张,欲言又止。你知道是他造成的错误,同时你也是这个项目的共同负责人。""",
|
小王看起来很紧张,欲言又止。你知道是他造成的错误,同时你也是这个项目的共同负责人。""",
|
||||||
"explanation": "通过职场情境,观察个体在面对他人过错时的态度和处理方式。"
|
"explanation": "通过职场情境,观察个体在面对他人过错时的态度和处理方式。",
|
||||||
}
|
},
|
||||||
}
|
},
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
def get_scene_by_factor(factor: str) -> Dict:
|
def get_scene_by_factor(factor: str) -> Dict:
|
||||||
"""
|
"""
|
||||||
根据人格因子获取对应的情景测试
|
根据人格因子获取对应的情景测试
|
||||||
|
|
||||||
Args:
|
Args:
|
||||||
factor (str): 人格因子名称
|
factor (str): 人格因子名称
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
Dict: 包含情景描述的字典
|
Dict: 包含情景描述的字典
|
||||||
"""
|
"""
|
||||||
return PERSONALITY_SCENES.get(factor, None)
|
return PERSONALITY_SCENES.get(factor, None)
|
||||||
|
|
||||||
|
|
||||||
def get_all_scenes() -> Dict:
|
def get_all_scenes() -> Dict:
|
||||||
"""
|
"""
|
||||||
获取所有情景测试
|
获取所有情景测试
|
||||||
|
|
||||||
Returns:
|
Returns:
|
||||||
Dict: 所有情景测试的字典
|
Dict: 所有情景测试的字典
|
||||||
"""
|
"""
|
||||||
|
|||||||
123
src/plugins/schedule/offline_llm.py
Normal file
@@ -0,0 +1,123 @@
|
|||||||
|
import asyncio
|
||||||
|
import os
|
||||||
|
import time
|
||||||
|
from typing import Tuple, Union
|
||||||
|
|
||||||
|
import aiohttp
|
||||||
|
import requests
|
||||||
|
from src.common.logger import get_module_logger
|
||||||
|
|
||||||
|
logger = get_module_logger("offline_llm")
|
||||||
|
|
||||||
|
|
||||||
|
class LLMModel:
|
||||||
|
def __init__(self, model_name="deepseek-ai/DeepSeek-V3", **kwargs):
|
||||||
|
self.model_name = model_name
|
||||||
|
self.params = kwargs
|
||||||
|
self.api_key = os.getenv("SILICONFLOW_KEY")
|
||||||
|
self.base_url = os.getenv("SILICONFLOW_BASE_URL")
|
||||||
|
|
||||||
|
if not self.api_key or not self.base_url:
|
||||||
|
raise ValueError("环境变量未正确加载:SILICONFLOW_KEY 或 SILICONFLOW_BASE_URL 未设置")
|
||||||
|
|
||||||
|
logger.info(f"API URL: {self.base_url}") # 使用 logger 记录 base_url
|
||||||
|
|
||||||
|
def generate_response(self, prompt: str) -> Union[str, Tuple[str, str]]:
|
||||||
|
"""根据输入的提示生成模型的响应"""
|
||||||
|
headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
||||||
|
|
||||||
|
# 构建请求体
|
||||||
|
data = {
|
||||||
|
"model": self.model_name,
|
||||||
|
"messages": [{"role": "user", "content": prompt}],
|
||||||
|
"temperature": 0.5,
|
||||||
|
**self.params,
|
||||||
|
}
|
||||||
|
|
||||||
|
# 发送请求到完整的 chat/completions 端点
|
||||||
|
api_url = f"{self.base_url.rstrip('/')}/chat/completions"
|
||||||
|
logger.info(f"Request URL: {api_url}") # 记录请求的 URL
|
||||||
|
|
||||||
|
max_retries = 3
|
||||||
|
base_wait_time = 15 # 基础等待时间(秒)
|
||||||
|
|
||||||
|
for retry in range(max_retries):
|
||||||
|
try:
|
||||||
|
response = requests.post(api_url, headers=headers, json=data)
|
||||||
|
|
||||||
|
if response.status_code == 429:
|
||||||
|
wait_time = base_wait_time * (2**retry) # 指数退避
|
||||||
|
logger.warning(f"遇到请求限制(429),等待{wait_time}秒后重试...")
|
||||||
|
time.sleep(wait_time)
|
||||||
|
continue
|
||||||
|
|
||||||
|
response.raise_for_status() # 检查其他响应状态
|
||||||
|
|
||||||
|
result = response.json()
|
||||||
|
if "choices" in result and len(result["choices"]) > 0:
|
||||||
|
content = result["choices"][0]["message"]["content"]
|
||||||
|
reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
|
||||||
|
return content, reasoning_content
|
||||||
|
return "没有返回结果", ""
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
if retry < max_retries - 1: # 如果还有重试机会
|
||||||
|
wait_time = base_wait_time * (2**retry)
|
||||||
|
logger.error(f"[回复]请求失败,等待{wait_time}秒后重试... 错误: {str(e)}")
|
||||||
|
time.sleep(wait_time)
|
||||||
|
else:
|
||||||
|
logger.error(f"请求失败: {str(e)}")
|
||||||
|
return f"请求失败: {str(e)}", ""
|
||||||
|
|
||||||
|
logger.error("达到最大重试次数,请求仍然失败")
|
||||||
|
return "达到最大重试次数,请求仍然失败", ""
|
||||||
|
|
||||||
|
async def generate_response_async(self, prompt: str) -> Union[str, Tuple[str, str]]:
|
||||||
|
"""异步方式根据输入的提示生成模型的响应"""
|
||||||
|
headers = {"Authorization": f"Bearer {self.api_key}", "Content-Type": "application/json"}
|
||||||
|
|
||||||
|
# 构建请求体
|
||||||
|
data = {
|
||||||
|
"model": self.model_name,
|
||||||
|
"messages": [{"role": "user", "content": prompt}],
|
||||||
|
"temperature": 0.5,
|
||||||
|
**self.params,
|
||||||
|
}
|
||||||
|
|
||||||
|
# 发送请求到完整的 chat/completions 端点
|
||||||
|
api_url = f"{self.base_url.rstrip('/')}/chat/completions"
|
||||||
|
logger.info(f"Request URL: {api_url}") # 记录请求的 URL
|
||||||
|
|
||||||
|
max_retries = 3
|
||||||
|
base_wait_time = 15
|
||||||
|
|
||||||
|
async with aiohttp.ClientSession() as session:
|
||||||
|
for retry in range(max_retries):
|
||||||
|
try:
|
||||||
|
async with session.post(api_url, headers=headers, json=data) as response:
|
||||||
|
if response.status == 429:
|
||||||
|
wait_time = base_wait_time * (2**retry) # 指数退避
|
||||||
|
logger.warning(f"遇到请求限制(429),等待{wait_time}秒后重试...")
|
||||||
|
await asyncio.sleep(wait_time)
|
||||||
|
continue
|
||||||
|
|
||||||
|
response.raise_for_status() # 检查其他响应状态
|
||||||
|
|
||||||
|
result = await response.json()
|
||||||
|
if "choices" in result and len(result["choices"]) > 0:
|
||||||
|
content = result["choices"][0]["message"]["content"]
|
||||||
|
reasoning_content = result["choices"][0]["message"].get("reasoning_content", "")
|
||||||
|
return content, reasoning_content
|
||||||
|
return "没有返回结果", ""
|
||||||
|
|
||||||
|
except Exception as e:
|
||||||
|
if retry < max_retries - 1: # 如果还有重试机会
|
||||||
|
wait_time = base_wait_time * (2**retry)
|
||||||
|
logger.error(f"[回复]请求失败,等待{wait_time}秒后重试... 错误: {str(e)}")
|
||||||
|
await asyncio.sleep(wait_time)
|
||||||
|
else:
|
||||||
|
logger.error(f"请求失败: {str(e)}")
|
||||||
|
return f"请求失败: {str(e)}", ""
|
||||||
|
|
||||||
|
logger.error("达到最大重试次数,请求仍然失败")
|
||||||
|
return "达到最大重试次数,请求仍然失败", ""
|
||||||
191
src/plugins/schedule/schedule_generator copy.py
Normal file
@@ -0,0 +1,191 @@
|
|||||||
|
import datetime
|
||||||
|
import json
|
||||||
|
import re
|
||||||
|
import os
|
||||||
|
import sys
|
||||||
|
from typing import Dict, Union
|
||||||
|
|
||||||
|
|
||||||
|
# 添加项目根目录到 Python 路径
|
||||||
|
root_path = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
|
||||||
|
sys.path.append(root_path)
|
||||||
|
|
||||||
|
from src.common.database import db # noqa: E402
|
||||||
|
from src.common.logger import get_module_logger # noqa: E402
|
||||||
|
from src.plugins.schedule.offline_llm import LLMModel # noqa: E402
|
||||||
|
from src.plugins.chat.config import global_config # noqa: E402
|
||||||
|
|
||||||
|
logger = get_module_logger("scheduler")
|
||||||
|
|
||||||
|
|
||||||
|
class ScheduleGenerator:
|
||||||
|
enable_output: bool = True
|
||||||
|
|
||||||
|
def __init__(self):
|
||||||
|
# 使用离线LLM模型
|
||||||
|
self.llm_scheduler = LLMModel(model_name="Pro/deepseek-ai/DeepSeek-V3", temperature=0.9)
|
||||||
|
self.today_schedule_text = ""
|
||||||
|
self.today_schedule = {}
|
||||||
|
self.tomorrow_schedule_text = ""
|
||||||
|
self.tomorrow_schedule = {}
|
||||||
|
self.yesterday_schedule_text = ""
|
||||||
|
self.yesterday_schedule = {}
|
||||||
|
|
||||||
|
async def initialize(self):
|
||||||
|
today = datetime.datetime.now()
|
||||||
|
tomorrow = datetime.datetime.now() + datetime.timedelta(days=1)
|
||||||
|
yesterday = datetime.datetime.now() - datetime.timedelta(days=1)
|
||||||
|
|
||||||
|
self.today_schedule_text, self.today_schedule = await self.generate_daily_schedule(target_date=today)
|
||||||
|
self.tomorrow_schedule_text, self.tomorrow_schedule = await self.generate_daily_schedule(
|
||||||
|
target_date=tomorrow, read_only=True
|
||||||
|
)
|
||||||
|
self.yesterday_schedule_text, self.yesterday_schedule = await self.generate_daily_schedule(
|
||||||
|
target_date=yesterday, read_only=True
|
||||||
|
)
|
||||||
|
|
||||||
|
async def generate_daily_schedule(
|
||||||
|
self, target_date: datetime.datetime = None, read_only: bool = False
|
||||||
|
) -> Dict[str, str]:
|
||||||
|
date_str = target_date.strftime("%Y-%m-%d")
|
||||||
|
weekday = target_date.strftime("%A")
|
||||||
|
|
||||||
|
schedule_text = str
|
||||||
|
|
||||||
|
existing_schedule = db.schedule.find_one({"date": date_str})
|
||||||
|
if existing_schedule:
|
||||||
|
if self.enable_output:
|
||||||
|
logger.debug(f"{date_str}的日程已存在:")
|
||||||
|
schedule_text = existing_schedule["schedule"]
|
||||||
|
# print(self.schedule_text)
|
||||||
|
|
||||||
|
elif not read_only:
|
||||||
|
logger.debug(f"{date_str}的日程不存在,准备生成新的日程。")
|
||||||
|
prompt = (
|
||||||
|
f"""我是{global_config.BOT_NICKNAME},{global_config.PROMPT_SCHEDULE_GEN},请为我生成{date_str}({weekday})的日程安排,包括:"""
|
||||||
|
+ """
|
||||||
|
1. 早上的学习和工作安排
|
||||||
|
2. 下午的活动和任务
|
||||||
|
3. 晚上的计划和休息时间
|
||||||
|
请按照时间顺序列出具体时间点和对应的活动,用一个时间点而不是时间段来表示时间,用JSON格式返回日程表,
|
||||||
|
仅返回内容,不要返回注释,不要添加任何markdown或代码块样式,时间采用24小时制,
|
||||||
|
格式为{"时间": "活动","时间": "活动",...}。"""
|
||||||
|
)
|
||||||
|
|
||||||
|
try:
|
||||||
|
schedule_text, _ = self.llm_scheduler.generate_response(prompt)
|
||||||
|
db.schedule.insert_one({"date": date_str, "schedule": schedule_text})
|
||||||
|
self.enable_output = True
|
||||||
|
except Exception as e:
|
||||||
|
logger.error(f"生成日程失败: {str(e)}")
|
||||||
|
schedule_text = "生成日程时出错了"
|
||||||
|
# print(self.schedule_text)
|
||||||
|
else:
|
||||||
|
if self.enable_output:
|
||||||
|
logger.debug(f"{date_str}的日程不存在。")
|
||||||
|
schedule_text = "忘了"
|
||||||
|
|
||||||
|
return schedule_text, None
|
||||||
|
|
||||||
|
schedule_form = self._parse_schedule(schedule_text)
|
||||||
|
return schedule_text, schedule_form
|
||||||
|
|
||||||
|
def _parse_schedule(self, schedule_text: str) -> Union[bool, Dict[str, str]]:
|
||||||
|
"""解析日程文本,转换为时间和活动的字典"""
|
||||||
|
try:
|
||||||
|
reg = r"\{(.|\r|\n)+\}"
|
||||||
|
matched = re.search(reg, schedule_text)[0]
|
||||||
|
schedule_dict = json.loads(matched)
|
||||||
|
return schedule_dict
|
||||||
|
except json.JSONDecodeError:
|
||||||
|
logger.exception("解析日程失败: {}".format(schedule_text))
|
||||||
|
return False
|
||||||
|
|
||||||
|
def _parse_time(self, time_str: str) -> str:
|
||||||
|
"""解析时间字符串,转换为时间"""
|
||||||
|
return datetime.datetime.strptime(time_str, "%H:%M")
|
||||||
|
|
||||||
|
def get_current_task(self) -> str:
|
||||||
|
"""获取当前时间应该进行的任务"""
|
||||||
|
current_time = datetime.datetime.now().strftime("%H:%M")
|
||||||
|
|
||||||
|
# 找到最接近当前时间的任务
|
||||||
|
closest_time = None
|
||||||
|
min_diff = float("inf")
|
||||||
|
|
||||||
|
# 检查今天的日程
|
||||||
|
if not self.today_schedule:
|
||||||
|
return "摸鱼"
|
||||||
|
for time_str in self.today_schedule.keys():
|
||||||
|
diff = abs(self._time_diff(current_time, time_str))
|
||||||
|
if closest_time is None or diff < min_diff:
|
||||||
|
closest_time = time_str
|
||||||
|
min_diff = diff
|
||||||
|
|
||||||
|
# 检查昨天的日程中的晚间任务
|
||||||
|
if self.yesterday_schedule:
|
||||||
|
for time_str in self.yesterday_schedule.keys():
|
||||||
|
if time_str >= "20:00": # 只考虑晚上8点之后的任务
|
||||||
|
# 计算与昨天这个时间点的差异(需要加24小时)
|
||||||
|
diff = abs(self._time_diff(current_time, time_str))
|
||||||
|
if diff < min_diff:
|
||||||
|
closest_time = time_str
|
||||||
|
min_diff = diff
|
||||||
|
return closest_time, self.yesterday_schedule[closest_time]
|
||||||
|
|
||||||
|
if closest_time:
|
||||||
|
return closest_time, self.today_schedule[closest_time]
|
||||||
|
return "摸鱼"
|
||||||
|
|
||||||
|
def _time_diff(self, time1: str, time2: str) -> int:
|
||||||
|
"""计算两个时间字符串之间的分钟差"""
|
||||||
|
if time1 == "24:00":
|
||||||
|
time1 = "23:59"
|
||||||
|
if time2 == "24:00":
|
||||||
|
time2 = "23:59"
|
||||||
|
t1 = datetime.datetime.strptime(time1, "%H:%M")
|
||||||
|
t2 = datetime.datetime.strptime(time2, "%H:%M")
|
||||||
|
diff = int((t2 - t1).total_seconds() / 60)
|
||||||
|
# 考虑时间的循环性
|
||||||
|
if diff < -720:
|
||||||
|
diff += 1440 # 加一天的分钟
|
||||||
|
elif diff > 720:
|
||||||
|
diff -= 1440 # 减一天的分钟
|
||||||
|
# print(f"时间1[{time1}]: 时间2[{time2}],差值[{diff}]分钟")
|
||||||
|
return diff
|
||||||
|
|
||||||
|
def print_schedule(self):
|
||||||
|
"""打印完整的日程安排"""
|
||||||
|
if not self._parse_schedule(self.today_schedule_text):
|
||||||
|
logger.warning("今日日程有误,将在下次运行时重新生成")
|
||||||
|
db.schedule.delete_one({"date": datetime.datetime.now().strftime("%Y-%m-%d")})
|
||||||
|
else:
|
||||||
|
logger.info("=== 今日日程安排 ===")
|
||||||
|
for time_str, activity in self.today_schedule.items():
|
||||||
|
logger.info(f"时间[{time_str}]: 活动[{activity}]")
|
||||||
|
logger.info("==================")
|
||||||
|
self.enable_output = False
|
||||||
|
|
||||||
|
|
||||||
|
async def main():
|
||||||
|
# 使用示例
|
||||||
|
scheduler = ScheduleGenerator()
|
||||||
|
await scheduler.initialize()
|
||||||
|
scheduler.print_schedule()
|
||||||
|
print("\n当前任务:")
|
||||||
|
print(await scheduler.get_current_task())
|
||||||
|
|
||||||
|
print("昨天日程:")
|
||||||
|
print(scheduler.yesterday_schedule)
|
||||||
|
print("今天日程:")
|
||||||
|
print(scheduler.today_schedule)
|
||||||
|
print("明天日程:")
|
||||||
|
print(scheduler.tomorrow_schedule)
|
||||||
|
|
||||||
|
# 当作为组件导入时使用的实例
|
||||||
|
bot_schedule = ScheduleGenerator()
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
import asyncio
|
||||||
|
# 当直接运行此文件时执行
|
||||||
|
asyncio.run(main())
|
||||||
@@ -5,8 +5,9 @@ from typing import Dict, Union
|
|||||||
|
|
||||||
from nonebot import get_driver
|
from nonebot import get_driver
|
||||||
|
|
||||||
from src.plugins.chat.config import global_config
|
# 添加项目根目录到 Python 路径
|
||||||
|
|
||||||
|
from src.plugins.chat.config import global_config
|
||||||
from ...common.database import db # 使用正确的导入语法
|
from ...common.database import db # 使用正确的导入语法
|
||||||
from ..models.utils_model import LLM_request
|
from ..models.utils_model import LLM_request
|
||||||
from src.common.logger import get_module_logger
|
from src.common.logger import get_module_logger
|
||||||
@@ -73,7 +74,7 @@ class ScheduleGenerator:
|
|||||||
)
|
)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
schedule_text, _ = await self.llm_scheduler.generate_response(prompt)
|
schedule_text, _, _ = await self.llm_scheduler.generate_response(prompt)
|
||||||
db.schedule.insert_one({"date": date_str, "schedule": schedule_text})
|
db.schedule.insert_one({"date": date_str, "schedule": schedule_text})
|
||||||
self.enable_output = True
|
self.enable_output = True
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
@@ -165,24 +166,5 @@ class ScheduleGenerator:
|
|||||||
logger.info(f"时间[{time_str}]: 活动[{activity}]")
|
logger.info(f"时间[{time_str}]: 活动[{activity}]")
|
||||||
logger.info("==================")
|
logger.info("==================")
|
||||||
self.enable_output = False
|
self.enable_output = False
|
||||||
|
# 当作为组件导入时使用的实例
|
||||||
|
|
||||||
# def main():
|
|
||||||
# # 使用示例
|
|
||||||
# scheduler = ScheduleGenerator()
|
|
||||||
# # new_schedule = scheduler.generate_daily_schedule()
|
|
||||||
# scheduler.print_schedule()
|
|
||||||
# print("\n当前任务:")
|
|
||||||
# print(scheduler.get_current_task())
|
|
||||||
|
|
||||||
# print("昨天日程:")
|
|
||||||
# print(scheduler.yesterday_schedule)
|
|
||||||
# print("今天日程:")
|
|
||||||
# print(scheduler.today_schedule)
|
|
||||||
# print("明天日程:")
|
|
||||||
# print(scheduler.tomorrow_schedule)
|
|
||||||
|
|
||||||
# if __name__ == "__main__":
|
|
||||||
# main()
|
|
||||||
|
|
||||||
bot_schedule = ScheduleGenerator()
|
bot_schedule = ScheduleGenerator()
|
||||||
|
|||||||
@@ -1,8 +1,6 @@
|
|||||||
HOST=127.0.0.1
|
HOST=127.0.0.1
|
||||||
PORT=8080
|
PORT=8080
|
||||||
|
|
||||||
ENABLE_ADVANCE_OUTPUT=false
|
|
||||||
|
|
||||||
# 插件配置
|
# 插件配置
|
||||||
PLUGINS=["src2.plugins.chat"]
|
PLUGINS=["src2.plugins.chat"]
|
||||||
|
|
||||||
@@ -31,6 +29,7 @@ CHAT_ANY_WHERE_KEY=
|
|||||||
SILICONFLOW_KEY=
|
SILICONFLOW_KEY=
|
||||||
|
|
||||||
# 定义日志相关配置
|
# 定义日志相关配置
|
||||||
|
SIMPLE_OUTPUT=true # 精简控制台输出格式
|
||||||
CONSOLE_LOG_LEVEL=INFO # 自定义日志的默认控制台输出日志级别
|
CONSOLE_LOG_LEVEL=INFO # 自定义日志的默认控制台输出日志级别
|
||||||
FILE_LOG_LEVEL=DEBUG # 自定义日志的默认文件输出日志级别
|
FILE_LOG_LEVEL=DEBUG # 自定义日志的默认文件输出日志级别
|
||||||
DEFAULT_CONSOLE_LOG_LEVEL=SUCCESS # 原生日志的控制台输出日志级别(nonebot就是这一类)
|
DEFAULT_CONSOLE_LOG_LEVEL=SUCCESS # 原生日志的控制台输出日志级别(nonebot就是这一类)
|
||||||
|
|||||||
@@ -1,5 +1,5 @@
|
|||||||
[inner]
|
[inner]
|
||||||
version = "0.0.10"
|
version = "0.0.11"
|
||||||
|
|
||||||
#以下是给开发人员阅读的,一般用户不需要阅读
|
#以下是给开发人员阅读的,一般用户不需要阅读
|
||||||
#如果你想要修改配置文件,请在修改后将version的值进行变更
|
#如果你想要修改配置文件,请在修改后将version的值进行变更
|
||||||
@@ -66,12 +66,15 @@ model_r1_distill_probability = 0.1 # 麦麦回答时选择次要回复模型3
|
|||||||
max_response_length = 1024 # 麦麦回答的最大token数
|
max_response_length = 1024 # 麦麦回答的最大token数
|
||||||
|
|
||||||
[willing]
|
[willing]
|
||||||
willing_mode = "classical"
|
willing_mode = "classical" # 回复意愿模式 经典模式
|
||||||
# willing_mode = "dynamic"
|
# willing_mode = "dynamic" # 动态模式(可能不兼容)
|
||||||
# willing_mode = "custom"
|
# willing_mode = "custom" # 自定义模式(可自行调整
|
||||||
|
|
||||||
[memory]
|
[memory]
|
||||||
build_memory_interval = 2000 # 记忆构建间隔 单位秒 间隔越低,麦麦学习越多,但是冗余信息也会增多
|
build_memory_interval = 2000 # 记忆构建间隔 单位秒 间隔越低,麦麦学习越多,但是冗余信息也会增多
|
||||||
|
build_memory_distribution = [4,2,0.6,24,8,0.4] # 记忆构建分布,参数:分布1均值,标准差,权重,分布2均值,标准差,权重
|
||||||
|
build_memory_sample_num = 10 # 采样数量,数值越高记忆采样次数越多
|
||||||
|
build_memory_sample_length = 20 # 采样长度,数值越高一段记忆内容越丰富
|
||||||
memory_compress_rate = 0.1 # 记忆压缩率 控制记忆精简程度 建议保持默认,调高可以获得更多信息,但是冗余信息也会增多
|
memory_compress_rate = 0.1 # 记忆压缩率 控制记忆精简程度 建议保持默认,调高可以获得更多信息,但是冗余信息也会增多
|
||||||
|
|
||||||
forget_memory_interval = 1000 # 记忆遗忘间隔 单位秒 间隔越低,麦麦遗忘越频繁,记忆更精简,但更难学习
|
forget_memory_interval = 1000 # 记忆遗忘间隔 单位秒 间隔越低,麦麦遗忘越频繁,记忆更精简,但更难学习
|
||||||
@@ -109,9 +112,7 @@ tone_error_rate=0.2 # 声调错误概率
|
|||||||
word_replace_rate=0.006 # 整词替换概率
|
word_replace_rate=0.006 # 整词替换概率
|
||||||
|
|
||||||
[others]
|
[others]
|
||||||
enable_advance_output = false # 是否启用高级输出
|
|
||||||
enable_kuuki_read = true # 是否启用读空气功能
|
enable_kuuki_read = true # 是否启用读空气功能
|
||||||
enable_debug_output = false # 是否启用调试输出
|
|
||||||
enable_friend_chat = false # 是否启用好友聊天
|
enable_friend_chat = false # 是否启用好友聊天
|
||||||
|
|
||||||
[groups]
|
[groups]
|
||||||
@@ -120,59 +121,67 @@ talk_allowed = [
|
|||||||
123,
|
123,
|
||||||
] #可以回复消息的群
|
] #可以回复消息的群
|
||||||
talk_frequency_down = [] #降低回复频率的群
|
talk_frequency_down = [] #降低回复频率的群
|
||||||
ban_user_id = [] #禁止回复消息的QQ号
|
ban_user_id = [] #禁止回复和读取消息的QQ号
|
||||||
|
|
||||||
[remote] #测试功能,发送统计信息,主要是看全球有多少只麦麦
|
[remote] #发送统计信息,主要是看全球有多少只麦麦
|
||||||
enable = true
|
enable = true
|
||||||
|
|
||||||
|
|
||||||
#下面的模型若使用硅基流动则不需要更改,使用ds官方则改成.env.prod自定义的宏,使用自定义模型则选择定位相似的模型自己填写
|
#下面的模型若使用硅基流动则不需要更改,使用ds官方则改成.env.prod自定义的宏,使用自定义模型则选择定位相似的模型自己填写
|
||||||
#推理模型:
|
#推理模型
|
||||||
|
|
||||||
[model.llm_reasoning] #回复模型1 主要回复模型
|
[model.llm_reasoning] #回复模型1 主要回复模型
|
||||||
name = "Pro/deepseek-ai/DeepSeek-R1"
|
name = "Pro/deepseek-ai/DeepSeek-R1"
|
||||||
|
# name = "Qwen/QwQ-32B"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
pri_in = 0 #模型的输入价格(非必填,可以记录消耗)
|
pri_in = 4 #模型的输入价格(非必填,可以记录消耗)
|
||||||
pri_out = 0 #模型的输出价格(非必填,可以记录消耗)
|
pri_out = 16 #模型的输出价格(非必填,可以记录消耗)
|
||||||
|
|
||||||
[model.llm_reasoning_minor] #回复模型3 次要回复模型
|
[model.llm_reasoning_minor] #回复模型3 次要回复模型
|
||||||
name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
|
name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
|
pri_in = 1.26 #模型的输入价格(非必填,可以记录消耗)
|
||||||
|
pri_out = 1.26 #模型的输出价格(非必填,可以记录消耗)
|
||||||
|
|
||||||
#非推理模型
|
#非推理模型
|
||||||
|
|
||||||
[model.llm_normal] #V3 回复模型2 次要回复模型
|
[model.llm_normal] #V3 回复模型2 次要回复模型
|
||||||
name = "Pro/deepseek-ai/DeepSeek-V3"
|
name = "Pro/deepseek-ai/DeepSeek-V3"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
|
pri_in = 2 #模型的输入价格(非必填,可以记录消耗)
|
||||||
|
pri_out = 8 #模型的输出价格(非必填,可以记录消耗)
|
||||||
|
|
||||||
[model.llm_normal_minor] #V2.5
|
[model.llm_emotion_judge] #表情包判断
|
||||||
name = "deepseek-ai/DeepSeek-V2.5"
|
|
||||||
provider = "SILICONFLOW"
|
|
||||||
|
|
||||||
[model.llm_emotion_judge] #主题判断 0.7/m
|
|
||||||
name = "Qwen/Qwen2.5-14B-Instruct"
|
name = "Qwen/Qwen2.5-14B-Instruct"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
|
pri_in = 0.7
|
||||||
|
pri_out = 0.7
|
||||||
|
|
||||||
[model.llm_topic_judge] #主题判断:建议使用qwen2.5 7b
|
[model.llm_topic_judge] #记忆主题判断:建议使用qwen2.5 7b
|
||||||
name = "Pro/Qwen/Qwen2.5-7B-Instruct"
|
name = "Pro/Qwen/Qwen2.5-7B-Instruct"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
|
pri_in = 0
|
||||||
|
pri_out = 0
|
||||||
|
|
||||||
[model.llm_summary_by_topic] #建议使用qwen2.5 32b 及以上
|
[model.llm_summary_by_topic] #概括模型,建议使用qwen2.5 32b 及以上
|
||||||
name = "Qwen/Qwen2.5-32B-Instruct"
|
name = "Qwen/Qwen2.5-32B-Instruct"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
pri_in = 0
|
pri_in = 1.26
|
||||||
pri_out = 0
|
pri_out = 1.26
|
||||||
|
|
||||||
[model.moderation] #内容审核 未启用
|
[model.moderation] #内容审核,开发中
|
||||||
name = ""
|
name = ""
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
pri_in = 0
|
pri_in = 1.0
|
||||||
pri_out = 0
|
pri_out = 2.0
|
||||||
|
|
||||||
# 识图模型
|
# 识图模型
|
||||||
|
|
||||||
[model.vlm] #图像识别 0.35/m
|
[model.vlm] #图像识别
|
||||||
name = "Pro/Qwen/Qwen2-VL-7B-Instruct"
|
name = "Pro/Qwen/Qwen2.5-VL-7B-Instruct"
|
||||||
provider = "SILICONFLOW"
|
provider = "SILICONFLOW"
|
||||||
|
pri_in = 0.35
|
||||||
|
pri_out = 0.35
|
||||||
|
|
||||||
#嵌入模型
|
#嵌入模型
|
||||||
|
|
||||||
|
|||||||
49
webui.py
@@ -4,11 +4,14 @@ import toml
|
|||||||
import signal
|
import signal
|
||||||
import sys
|
import sys
|
||||||
import requests
|
import requests
|
||||||
|
|
||||||
try:
|
try:
|
||||||
from src.common.logger import get_module_logger
|
from src.common.logger import get_module_logger
|
||||||
|
|
||||||
logger = get_module_logger("webui")
|
logger = get_module_logger("webui")
|
||||||
except ImportError:
|
except ImportError:
|
||||||
from loguru import logger
|
from loguru import logger
|
||||||
|
|
||||||
# 检查并创建日志目录
|
# 检查并创建日志目录
|
||||||
log_dir = "logs/webui"
|
log_dir = "logs/webui"
|
||||||
if not os.path.exists(log_dir):
|
if not os.path.exists(log_dir):
|
||||||
@@ -24,11 +27,13 @@ import ast
|
|||||||
from packaging import version
|
from packaging import version
|
||||||
from decimal import Decimal
|
from decimal import Decimal
|
||||||
|
|
||||||
|
|
||||||
def signal_handler(signum, frame):
|
def signal_handler(signum, frame):
|
||||||
"""处理 Ctrl+C 信号"""
|
"""处理 Ctrl+C 信号"""
|
||||||
logger.info("收到终止信号,正在关闭 Gradio 服务器...")
|
logger.info("收到终止信号,正在关闭 Gradio 服务器...")
|
||||||
sys.exit(0)
|
sys.exit(0)
|
||||||
|
|
||||||
|
|
||||||
# 注册信号处理器
|
# 注册信号处理器
|
||||||
signal.signal(signal.SIGINT, signal_handler)
|
signal.signal(signal.SIGINT, signal_handler)
|
||||||
|
|
||||||
@@ -44,10 +49,10 @@ if not os.path.exists(".env.prod"):
|
|||||||
raise FileNotFoundError("环境配置文件 .env.prod 不存在,请检查配置文件路径")
|
raise FileNotFoundError("环境配置文件 .env.prod 不存在,请检查配置文件路径")
|
||||||
|
|
||||||
config_data = toml.load("config/bot_config.toml")
|
config_data = toml.load("config/bot_config.toml")
|
||||||
#增加对老版本配置文件支持
|
# 增加对老版本配置文件支持
|
||||||
LEGACY_CONFIG_VERSION = version.parse("0.0.1")
|
LEGACY_CONFIG_VERSION = version.parse("0.0.1")
|
||||||
|
|
||||||
#增加最低支持版本
|
# 增加最低支持版本
|
||||||
MIN_SUPPORT_VERSION = version.parse("0.0.8")
|
MIN_SUPPORT_VERSION = version.parse("0.0.8")
|
||||||
MIN_SUPPORT_MAIMAI_VERSION = version.parse("0.5.13")
|
MIN_SUPPORT_MAIMAI_VERSION = version.parse("0.5.13")
|
||||||
|
|
||||||
@@ -66,9 +71,18 @@ else:
|
|||||||
|
|
||||||
HAVE_ONLINE_STATUS_VERSION = version.parse("0.0.9")
|
HAVE_ONLINE_STATUS_VERSION = version.parse("0.0.9")
|
||||||
|
|
||||||
#添加WebUI配置文件版本
|
# 定义意愿模式可选项
|
||||||
|
WILLING_MODE_CHOICES = [
|
||||||
|
"classical",
|
||||||
|
"dynamic",
|
||||||
|
"custom",
|
||||||
|
]
|
||||||
|
|
||||||
|
|
||||||
|
# 添加WebUI配置文件版本
|
||||||
WEBUI_VERSION = version.parse("0.0.9")
|
WEBUI_VERSION = version.parse("0.0.9")
|
||||||
|
|
||||||
|
|
||||||
# ==============================================
|
# ==============================================
|
||||||
# env环境配置文件读取部分
|
# env环境配置文件读取部分
|
||||||
def parse_env_config(config_file):
|
def parse_env_config(config_file):
|
||||||
@@ -84,10 +98,14 @@ def parse_env_config(config_file):
|
|||||||
# 逐行处理配置
|
# 逐行处理配置
|
||||||
for line in lines:
|
for line in lines:
|
||||||
line = line.strip()
|
line = line.strip()
|
||||||
# 忽略空行和注释
|
# 忽略空行和注释行
|
||||||
if not line or line.startswith("#"):
|
if not line or line.startswith("#"):
|
||||||
continue
|
continue
|
||||||
|
|
||||||
|
# 处理行尾注释
|
||||||
|
if "#" in line:
|
||||||
|
line = line.split("#")[0].strip()
|
||||||
|
|
||||||
# 拆分键值对
|
# 拆分键值对
|
||||||
key, value = line.split("=", 1)
|
key, value = line.split("=", 1)
|
||||||
|
|
||||||
@@ -194,7 +212,7 @@ MODEL_PROVIDER_LIST = parse_model_providers(env_config_data)
|
|||||||
# env读取保存结束
|
# env读取保存结束
|
||||||
# ==============================================
|
# ==============================================
|
||||||
|
|
||||||
#获取在线麦麦数量
|
# 获取在线麦麦数量
|
||||||
|
|
||||||
|
|
||||||
def get_online_maimbot(url="http://hyybuth.xyz:10058/api/clients/details", timeout=10):
|
def get_online_maimbot(url="http://hyybuth.xyz:10058/api/clients/details", timeout=10):
|
||||||
@@ -522,6 +540,7 @@ def save_message_and_emoji_config(
|
|||||||
|
|
||||||
|
|
||||||
def save_response_model_config(
|
def save_response_model_config(
|
||||||
|
t_willing_mode,
|
||||||
t_model_r1_probability,
|
t_model_r1_probability,
|
||||||
t_model_r2_probability,
|
t_model_r2_probability,
|
||||||
t_model_r3_probability,
|
t_model_r3_probability,
|
||||||
@@ -543,6 +562,8 @@ def save_response_model_config(
|
|||||||
t_vlm_model_name,
|
t_vlm_model_name,
|
||||||
t_vlm_model_provider,
|
t_vlm_model_provider,
|
||||||
):
|
):
|
||||||
|
if PARSED_CONFIG_VERSION >= version.parse("0.0.10"):
|
||||||
|
config_data["willing"]["willing_mode"] = t_willing_mode
|
||||||
config_data["response"]["model_r1_probability"] = t_model_r1_probability
|
config_data["response"]["model_r1_probability"] = t_model_r1_probability
|
||||||
config_data["response"]["model_v3_probability"] = t_model_r2_probability
|
config_data["response"]["model_v3_probability"] = t_model_r2_probability
|
||||||
config_data["response"]["model_r1_distill_probability"] = t_model_r3_probability
|
config_data["response"]["model_r1_distill_probability"] = t_model_r3_probability
|
||||||
@@ -1182,6 +1203,23 @@ with gr.Blocks(title="MaimBot配置文件编辑") as app:
|
|||||||
with gr.Column(scale=3):
|
with gr.Column(scale=3):
|
||||||
with gr.Row():
|
with gr.Row():
|
||||||
gr.Markdown("""### 回复设置""")
|
gr.Markdown("""### 回复设置""")
|
||||||
|
if PARSED_CONFIG_VERSION >= version.parse("0.0.10"):
|
||||||
|
with gr.Row():
|
||||||
|
gr.Markdown("""#### 回复意愿模式""")
|
||||||
|
with gr.Row():
|
||||||
|
gr.Markdown("""回复意愿模式说明:\n
|
||||||
|
classical为经典回复意愿管理器\n
|
||||||
|
dynamic为动态意愿管理器\n
|
||||||
|
custom为自定义意愿管理器
|
||||||
|
""")
|
||||||
|
with gr.Row():
|
||||||
|
willing_mode = gr.Dropdown(
|
||||||
|
choices=WILLING_MODE_CHOICES,
|
||||||
|
value=config_data["willing"]["willing_mode"],
|
||||||
|
label="回复意愿模式",
|
||||||
|
)
|
||||||
|
else:
|
||||||
|
willing_mode = gr.Textbox(visible=False, value="disabled")
|
||||||
with gr.Row():
|
with gr.Row():
|
||||||
model_r1_probability = gr.Slider(
|
model_r1_probability = gr.Slider(
|
||||||
minimum=0,
|
minimum=0,
|
||||||
@@ -1355,6 +1393,7 @@ with gr.Blocks(title="MaimBot配置文件编辑") as app:
|
|||||||
save_model_btn.click(
|
save_model_btn.click(
|
||||||
save_response_model_config,
|
save_response_model_config,
|
||||||
inputs=[
|
inputs=[
|
||||||
|
willing_mode,
|
||||||
model_r1_probability,
|
model_r1_probability,
|
||||||
model_r2_probability,
|
model_r2_probability,
|
||||||
model_r3_probability,
|
model_r3_probability,
|
||||||
|
|||||||