Compare commits

..

448 Commits

Author SHA1 Message Date
RockChinQ
c246fb6d8e chore: release v2.6.4 2023-11-12 14:42:48 +08:00
RockChinQ
ec6c041bcf ci(Dockerfile): 修复依赖安装问题 2023-11-12 14:42:07 +08:00
RockChinQ
2da5a9f3c7 ci(Dockerfile): 显式更新httpcore httpx和openai库 2023-11-12 14:18:42 +08:00
Junyan Qin
4e0df52d7c Merge pull request #592 from RockChinQ/fix/plugin-downloading
Feat: 通过 GitHub API 进行插件安装和更新
2023-11-12 14:07:52 +08:00
RockChinQ
71b8bf13e4 fix: 插件加载bug 2023-11-12 13:52:04 +08:00
RockChinQ
a8b1e6ce91 ci: test 2023-11-12 12:05:04 +08:00
RockChinQ
1419d7611d ci(cmdpriv): 本地测试通过 2023-11-12 12:03:52 +08:00
RockChinQ
89c83ebf20 fix: 错误的判空变量 2023-11-12 11:30:10 +08:00
RockChinQ
76d7db88ea feat: 基于元数据记录的插件更新实现 2023-11-11 23:17:28 +08:00
RockChinQ
67a208bc90 feat: 添加插件元数据操作模块 2023-11-11 17:38:52 +08:00
RockChinQ
acbd55ded2 feat: 插件安装改为直接下载源码 2023-11-10 23:01:56 +08:00
Junyan Qin
11a240a6d1 Merge pull request #591 from RockChinQ/feat/new-model-names
Feat: 更新模型索引
2023-11-10 21:23:22 +08:00
RockChinQ
97c85abbe7 feat: 更新模型索引 2023-11-10 21:16:33 +08:00
RockChinQ
06a0cd2a3d chore: 发布兼容性问题公告 2023-11-10 12:20:29 +08:00
GitHub Actions
572b215df8 Update override-all.json 2023-11-10 04:04:45 +00:00
RockChinQ
2c542bf412 chore: 不再默认在启动时升级依赖库 2023-11-10 12:04:25 +08:00
RockChinQ
1576ba7a01 chore: release v2.6.3 2023-11-10 12:01:20 +08:00
Junyan Qin
45e4096a12 Merge pull request #587 from RockChinQ/hotfix/openai-1.0-adaptation
Feat: 适配openai>=1.0.0
2023-11-10 11:49:20 +08:00
GitHub Actions
8a1d4fe287 Update override-all.json 2023-11-10 03:47:30 +00:00
RockChinQ
98f880ebc2 chore: 群内回复不再默认引用原消息 2023-11-10 11:47:10 +08:00
RockChinQ
2b852853f3 feat: 适配completion和chat_completions 2023-11-10 11:31:14 +08:00
RockChinQ
c7a9988033 feat: 以新的方式设置正向代理 2023-11-10 10:54:03 +08:00
RockChinQ
c475eebe1c chore: 不再限制openai版本 2023-11-10 10:14:11 +08:00
RockChinQ
0fe7355ae0 hotfix: 适配openai>=1.0.0 2023-11-10 10:13:50 +08:00
Junyan Qin
57de96e3a2 chore(requirements.txt): 锁定openai版本到0.28.1 2023-11-10 09:31:27 +08:00
Junyan Qin
70571cef50 Update README.md 2023-10-02 17:31:08 +08:00
Junyan Qin
0b6deb3340 Update README.md 2023-10-02 17:23:36 +08:00
Junyan Qin
dcda85a825 Merge pull request #580 from RockChinQ/dependabot/pip/openai-approx-eq-0.28.1
chore(deps): update openai requirement from ~=0.28.0 to ~=0.28.1
2023-10-02 16:10:37 +08:00
dependabot[bot]
9d3bff018b chore(deps): update openai requirement from ~=0.28.0 to ~=0.28.1
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.28.0...v0.28.1)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-10-02 08:09:30 +00:00
RockChinQ
051376e0d2 Release v2.6.1 2023-09-28 12:18:46 +00:00
Junyan Qin
a113785211 Merge pull request #578 from RockChinQ/fix/blocked-audit-upload
[Fix] 阻塞地发送审计报告数据
2023-09-28 20:17:26 +08:00
RockChinQ
3f4ed4dc3c fix: 阻塞地发送审计报告数据 2023-09-28 12:16:30 +00:00
Junyan Qin
ac80764fae Merge pull request #577 from RockChinQ/doc/deadlinks-in-wiki
[Doc] 修复wiki中的死链
2023-09-28 20:04:01 +08:00
RockChinQ
e43afd4891 doc: 修复wiki中的死链 2023-09-28 12:03:27 +00:00
RockChinQ
f1aea1d495 doc: 统一改称指令为命令 2023-09-28 11:46:33 +00:00
GitHub Actions
0e2a5db104 Update override-all.json 2023-09-26 16:10:22 +00:00
Junyan Qin
3a4c9771fa feat(config): 默认超时时间改为两分钟 2023-09-27 00:09:58 +08:00
RockChinQ
f4f8ef9523 ci: 工作流统一双空格缩进 2023-09-13 08:27:47 +00:00
RockChinQ
b9ace69a72 Release v2.6.0 2023-09-13 08:13:24 +00:00
RockChinQ
aef0b2a26e ci: 修复GITHUB_REF判断逻辑 2023-09-13 08:12:46 +00:00
RockChinQ
f7712d71ec feat(pkgmgr): 使用清华源执行pip操作 2023-09-13 07:54:53 +00:00
RockChinQ
e94b44e3b8 chore: 更新.gitignore 2023-09-13 07:22:12 +00:00
Junyan Qin
524e863c78 Merge pull request #567 from ruuuux/patch-1
添加 WikipediaSearch 插件
2023-09-13 11:57:54 +08:00
ruuuux
bbc80ac901 添加 WikipediaSearch 插件 2023-09-13 11:55:11 +08:00
GitHub Actions
f969ddd6ca Update override-all.json 2023-09-13 03:09:55 +00:00
RockChinQ
1cc9781333 chore(config): 添加 One API 的注释说明 2023-09-13 03:09:35 +00:00
Junyan Qin
a609801bae Merge pull request #551 from flashszn/master
加入one-api项目支持的国内大模型
2023-09-13 11:00:21 +08:00
RockChinQ
d8b606d372 doc(README.md): 添加 One API 支持公告 2023-09-13 02:45:04 +00:00
RockChinQ
572a440e65 doc(README.md): 添加 One API 的说明 2023-09-13 02:41:22 +00:00
RockChinQ
6e4eeae9b7 doc: 添加one-api模型注释说明 2023-09-13 02:34:11 +00:00
Shi Zhenning
1a73669df8 加入符合oneapi项目接口的国内模型
oneapi是一个api整合项目,通过这个项目的反代理,可以像使用gpt系列的/v1/completion接口一样调用国内的大模型,仅仅需要更改一下模型名字
2023-09-13 02:34:11 +00:00
RockChinQ
91ebaf1122 doc(README.md): 添加内容 2023-09-12 13:26:41 +00:00
RockChinQ
46703eb906 doc(README.md): docker部署说明 2023-09-12 13:09:42 +00:00
Junyan Qin
b9dd9d5193 Merge pull request #566 from RockChinQ/docker-deployment
[CI] Docker 部署最佳实践
2023-09-12 21:06:53 +08:00
RockChinQ
884481a4ec doc(README.md): 镜像徽章 2023-09-12 13:04:18 +00:00
RockChinQ
9040b37a63 chore: 默认安装PyYaml依赖 2023-09-12 12:53:16 +00:00
RockChinQ
99d47b2fa2 doc: 修改Docker部署指引 2023-09-12 12:53:03 +00:00
RockChinQ
6575359a94 doc: 添加docker部署指南 2023-09-12 12:51:06 +00:00
RockChinQ
a2fc726372 deploy: 添加docker-compose.yaml 2023-09-12 12:50:49 +00:00
RockChinQ
3bfce8ab51 ci: 优化docker镜像构建脚本 2023-09-12 10:21:40 +00:00
RockChinQ
ff9a9830f2 chore: 更新requirements.txt 2023-09-12 10:21:19 +00:00
RockChinQ
e2b59e8efe ci: 更新Dockerfile 2023-09-12 10:21:03 +00:00
Junyan Qin
04dad9757f Merge pull request #565 from RockChinQ/docker-image-test
[CI] Docker 部署脚本同步
2023-09-12 16:34:38 +08:00
Junyan Qin
75ea1080ad Merge pull request #351 from q123458384/patch-2
Create build_docker_image.yml
2023-09-12 15:57:44 +08:00
Junyan Qin
e25b064319 doc(README.md): 为群号添加链接 2023-09-10 23:22:38 +08:00
Junyan Qin
5d0dbc40ce doc(README.md): 添加社区使用手册链接 2023-09-10 23:17:22 +08:00
Junyan Qin
beae8de5eb Merge pull request #563 from RockChinQ/dependabot/pip/dulwich-approx-eq-0.21.6
chore(deps): update dulwich requirement from ~=0.21.5 to ~=0.21.6
2023-09-04 17:23:52 +08:00
dependabot[bot]
c4ff30c722 chore(deps): update dulwich requirement from ~=0.21.5 to ~=0.21.6
Updates the requirements on [dulwich](https://github.com/dulwich/dulwich) to permit the latest version.
- [Release notes](https://github.com/dulwich/dulwich/releases)
- [Changelog](https://github.com/jelmer/dulwich/blob/master/NEWS)
- [Commits](https://github.com/dulwich/dulwich/compare/dulwich-0.21.5...dulwich-0.21.6)

---
updated-dependencies:
- dependency-name: dulwich
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-09-04 09:09:35 +00:00
Junyan Qin
6f4ecb101b Merge pull request #562 from RockChinQ/dependabot/pip/openai-approx-eq-0.28.0
chore(deps): update openai requirement from ~=0.27.9 to ~=0.28.0
2023-09-04 17:08:47 +08:00
dependabot[bot]
9f9b0ef846 chore(deps): update openai requirement from ~=0.27.9 to ~=0.28.0
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.9...v0.28.0)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-09-04 08:06:36 +00:00
RockChinQ
de6957062c chore(config): 修改公用反代地址 2023-09-02 19:48:45 +08:00
Junyan Qin
0a9b43e6fa doc(README.md):社区群群号 2023-09-01 08:49:47 +08:00
Junyan Qin
5b0edd9937 Merge pull request #559 from oliverkirk-sudo/master
新增插件
2023-08-31 18:14:52 +08:00
oliverkirk-sudo
8a400d202a Update README.md
添加插件
2023-08-31 18:10:46 +08:00
RockChinQ
5a1e9f7fb2 doc(README.md): 修改徽章样式 2023-08-31 08:40:11 +00:00
RockChinQ
e03af75cf8 doc: 更新部署节说明 2023-08-31 02:26:13 +00:00
RockChinQ
0da4919255 doc: 整理README.md格式 2023-08-31 02:23:30 +00:00
RockChinQ
914e566d1f doc(README.md): 更新wiki链接 2023-08-30 08:46:17 +00:00
RockChinQ
6ec2b653fe doc(wiki): 为wiki页标号 2023-08-30 08:41:59 +00:00
RockChinQ
ba0a088b9c doc(wiki): 常见问题标号 2023-08-30 08:38:44 +00:00
RockChinQ
478e83bcd9 ci: 更新wiki同步工作流 2023-08-30 08:38:26 +00:00
RockChinQ
386124a3b9 doc(wiki): 页面标号 2023-08-30 08:36:30 +00:00
RockChinQ
ff5e7c16d1 doc(wiki): 插件相关文档typo 2023-08-30 08:34:03 +00:00
RockChinQ
7ff7a66012 doc: 更新gpt4free的说明文档 2023-08-29 14:42:44 +08:00
Junyan Qin
c99dfb8a86 Merge pull request #557 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.9
chore(deps): update openai requirement from ~=0.27.8 to ~=0.27.9
2023-08-28 16:29:55 +08:00
dependabot[bot]
10f9d4c6b3 chore(deps): update openai requirement from ~=0.27.8 to ~=0.27.9
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.8...v0.27.9)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-08-28 08:29:19 +00:00
Junyan Qin
d347813411 Merge pull request #556 from oliverkirk-sudo/master
Update README.md
2023-08-24 17:06:29 +08:00
oliverkirk-sudo
7a93898b3f Update README.md 2023-08-24 17:00:18 +08:00
Junyan Qin
c057ea900f Merge pull request #548 from oliverkirk-sudo/master
修改插件信息
2023-08-15 09:35:55 +08:00
oliverkirk-sudo
512266e74f 修改插件信息 2023-08-14 23:21:51 +08:00
RockChinQ
e36aee11c7 doc(README.md): 更新README.md 2023-08-14 19:12:39 +08:00
RockChinQ
97421299f5 doc(README.md): Claude和Bard的说明 2023-08-14 19:11:48 +08:00
Junyan Qin
bc41e5aa80 Update README.md 2023-08-14 16:57:55 +08:00
RockChinQ
2fa30e7def doc(README.md): 徽章格式 2023-08-14 16:56:50 +08:00
RockChinQ
1c6a7d9ba5 doc(README.md): 添加群号徽章 2023-08-14 16:09:11 +08:00
RockChinQ
47435c42a5 doc(README.md): 更新视频教程 2023-08-12 12:26:00 +08:00
Junyan Qin
39a1b421e6 doc(CONTRIBUTING.md): 添加字段使用规范 2023-08-09 20:12:46 +08:00
Junyan Qin
b5edf2295b doc(CONTRIBUTING.md): 添加代码规范 2023-08-08 20:14:00 +08:00
RockChinQ
fb650a3d7a chore: config.py添加反代地址 2023-08-07 11:43:28 +08:00
Junyan Qin
521541f311 Merge pull request #534 from RockChinQ/doc-add-gif
[Doc] 添加演示GIF图
2023-08-06 17:20:49 +08:00
Junyan Qin
7020abadbf Add files via upload 2023-08-06 17:19:54 +08:00
Junyan Qin
d95fb3b5be Delete webwlkr-demo.gif 2023-08-06 17:18:58 +08:00
Junyan Qin
3e524dc790 Add files via upload 2023-08-06 17:18:00 +08:00
Junyan Qin
a64940bff8 Update README.md 2023-08-06 17:13:10 +08:00
Junyan Qin
c739290f0b Add files via upload 2023-08-06 17:07:22 +08:00
RockChinQ
af292fe050 Release v2.5.2 2023-08-06 14:58:13 +08:00
Junyan Qin
634c7fb302 Merge pull request #533 from RockChinQ/perf-function-call-process
[Perf] 优化函数调用的底层逻辑
2023-08-06 14:52:01 +08:00
RockChinQ
33efb94013 feat: 应用cmdpriv时忽略不存在的命令 2023-08-06 14:50:22 +08:00
GitHub Actions
549e4dc02e Update override-all.json 2023-08-06 06:41:00 +00:00
RockChinQ
3d40909c02 feat: 不再默认启用trace_function_calls 2023-08-06 14:40:35 +08:00
RockChinQ
1aef81e38f perf: 修改网络问题时的报错 2023-08-06 12:17:04 +08:00
RockChinQ
1b0ae8da58 refactor: session append重命名为query 2023-08-05 22:00:32 +08:00
GitHub Actions Bot
7979a8e97f Update cmdpriv-template.json 2023-08-05 13:52:03 +00:00
RockChinQ
080e53d9a9 feat: 刪除continue命令 2023-08-05 21:51:34 +08:00
GitHub Actions
89bb364b16 Update override-all.json 2023-08-05 13:44:30 +00:00
RockChinQ
3586cd941f feat: 支持跟踪函数调用过程并默认启用 2023-08-05 21:44:11 +08:00
RockChinQ
054d0839ac fix: 未序列化的function_call属性 2023-08-04 19:08:48 +08:00
RockChinQ
dd75f98d85 feat: 世界上最先进的调用流程 2023-08-04 18:41:04 +08:00
RockChinQ
ec23bb5268 doc(README.md): 添加视频教程链接 2023-08-04 17:22:13 +08:00
Junyan Qin
bc99db4fc1 Merge pull request #531 from RockChinQ/feat-load-balance
[Feat] api-key主动负载均衡
2023-08-04 17:14:03 +08:00
RockChinQ
c8275fcfbf feat(openai): 支持apikey主动切换策略 2023-08-04 17:10:07 +08:00
GitHub Actions
a345043c30 Update override-all.json 2023-08-04 07:21:52 +00:00
RockChinQ
382d37d479 chore: 添加key切换策略配置项 2023-08-04 15:21:31 +08:00
RockChinQ
32c144a75d doc(README.md): 增加简介 2023-08-03 23:40:01 +08:00
RockChinQ
7ca2aa5e39 doc(wiki): 说明逆向库插件也支持函数调用 2023-08-03 18:44:16 +08:00
RockChinQ
86cc4a23ac fix: func命令列表标号未自增 2023-08-03 17:53:43 +08:00
RockChinQ
08d1e138bd doc: 删除过时公告 2023-08-02 21:46:59 +08:00
Junyan Qin
a9fe86542f Merge pull request #530 from RockChinQ/doc-readme
[Docs] 重新整理README.md格式
2023-08-02 21:09:39 +08:00
RockChinQ
4e29776fcd doc: 整理插件生态章节 2023-08-02 21:07:31 +08:00
RockChinQ
ee3eae8f4d doc: 完善徽章 2023-08-02 21:06:34 +08:00
RockChinQ
a84575858a doc: 整理徽章 2023-08-02 21:04:23 +08:00
RockChinQ
ac472291c7 doc: 赞赏章节 2023-08-02 20:59:01 +08:00
RockChinQ
f304873c6a doc(wiki): 内容函数页 2023-08-02 20:59:01 +08:00
RockChinQ
18caf8face doc: 致谢章节 2023-08-02 20:59:01 +08:00
RockChinQ
d21115aaa8 doc: 优化起始章节 2023-08-02 20:59:01 +08:00
RockChinQ
a05ecd2e7f doc: 更多section 2023-08-02 20:59:01 +08:00
RockChinQ
32a725126d doc: 模型适配一览 2023-08-02 20:59:01 +08:00
RockChinQ
0528690622 doc: 修改logo 2023-08-02 20:51:07 +08:00
Junyan Qin
819339142e Merge pull request #529 from RockChinQ/feat-funcs-called-args
[Feat] NormalMessageResponded添加func_called参数
2023-08-02 18:02:48 +08:00
RockChinQ
1d0573e7ff feat: NormalMessageResponded添加func_called参数 2023-08-02 18:01:02 +08:00
RockChinQ
00623bc431 typo(plugin): 插件执行报错提示 2023-08-02 11:35:20 +08:00
Junyan Qin
c872264456 Merge pull request #525 from RockChinQ/feat-finish-reason-param
[Feat] 为NormalMessageResponded事件添加finish_reason参数
2023-08-01 14:40:14 +08:00
RockChinQ
1336d3cb9a fix: chat_completion不传回finish_reason的问题 2023-08-01 14:39:57 +08:00
RockChinQ
d1459578cd doc(wiki): 插件开发页说明 2023-08-01 14:33:32 +08:00
RockChinQ
8a67fcf40f feat: 为NormalMessageResponded事件添加finish_reason参数 2023-08-01 14:31:38 +08:00
RockChinQ
7930370aa9 chore: 发布函数调用功能公告 2023-08-01 10:50:23 +08:00
RockChinQ
0b854bdcf1 feat(chat_completion): 不生成到stop以使max_tokens参数生效 2023-08-01 10:26:23 +08:00
Junyan Qin
cba6aab48d Merge pull request #524 from RockChinQ/feat-at-sender
[Feat] 支持在群内回复时at发送者
2023-08-01 10:14:34 +08:00
GitHub Actions
12a9ca7a77 Update override-all.json 2023-08-01 02:13:35 +00:00
RockChinQ
a6cbd226e1 feat: 支持设置群内回复时at发送者 2023-08-01 10:13:15 +08:00
RockChinQ
3577e62b41 perf: 简化启动时输出 2023-07-31 21:11:28 +08:00
RockChinQ
f86e69fcd1 perf: 简化启动时的输出信息 2023-07-31 21:05:23 +08:00
RockChinQ
292e00b078 perf: 简化启动时的输出信息 2023-07-31 21:04:59 +08:00
RockChinQ
2a91497bcf chore: .gitignore排除qcapi/ 2023-07-31 20:23:54 +08:00
RockChinQ
b0cca0a4c2 Release v2.5.1 2023-07-31 18:12:59 +08:00
Junyan Qin
a2bda85a9c Merge pull request #523 from RockChinQ/feat-prompt-preprocess-event
[Feat] 新增PromptPreprocessing事件
2023-07-31 17:55:06 +08:00
RockChinQ
20677cff86 doc(wiki): 插件开发页增加版本断言说明 2023-07-31 17:53:33 +08:00
RockChinQ
c8af5d8445 feat: 添加版本断言函数require_ver 2023-07-31 17:46:30 +08:00
RockChinQ
2dbe984539 doc(wiki): 添加事件wiki说明 2023-07-31 17:27:28 +08:00
RockChinQ
6b8fa664f1 feat: 新增PromptPreprocessing事件 2023-07-31 17:21:09 +08:00
RockChinQ
2b9612e933 chore: 提交部分测试文件 2023-07-31 16:24:39 +08:00
RockChinQ
749d0219fb chore: 删除弃用模块 2023-07-31 16:23:31 +08:00
Junyan Qin
a11a152bd7 ci: 解决sync-wiki.yml异常退出问题 2023-07-31 15:41:37 +08:00
Junyan Qin
fc803a3742 Merge pull request #522 from RockChinQ/feat-generating-stop-case
[Feat] 新增!continue命令
2023-07-31 15:34:30 +08:00
GitHub Actions Bot
13a1e15f24 Update cmdpriv-template.json 2023-07-31 07:24:14 +00:00
RockChinQ
3f41b94da5 feat: 完善命令文档 2023-07-31 15:23:42 +08:00
RockChinQ
0fb5bfda20 ci: 添加tiktoken依赖 2023-07-31 15:20:23 +08:00
RockChinQ
dc1fd73ebb feat: 添加continue命令 2023-07-31 15:17:49 +08:00
Junyan Qin
161b694f71 Merge pull request #521 from RockChinQ/fix-usage-not-reported
[Fix] text的使用量未上报
2023-07-31 14:31:48 +08:00
RockChinQ
45d1c89e45 fix: text的使用量未上报 2023-07-31 14:28:48 +08:00
Junyan Qin
e26664aa51 Merge pull request #520 from RockChinQ/feat-accurately-calculate-tokens
feat: 使用tiktoken计算tokens数
2023-07-31 12:16:10 +08:00
RockChinQ
e29691efbd feat: 使用tiktoken计算tokens数 2023-07-31 11:59:22 +08:00
RockChinQ
6d45327882 debug: 接口底层添加返回数据debug信息 2023-07-31 10:37:45 +08:00
RockChinQ
fbd41eef49 chore: 删除devcontainer.json 2023-07-31 10:37:14 +08:00
Junyan Qin
0a30c88322 doc(README.md): 插件列表 2023-07-31 00:07:39 +08:00
Junyan Qin
4f5af0e8c8 Merge pull request #518 from RockChinQ/fix-cannot-disable-funcs-dynamically
[Fix] plugin启用禁用命令对内容函数不生效
2023-07-30 23:56:01 +08:00
RockChinQ
df3f0fd159 fix: plugin启用禁用命令对内容函数不生效 2023-07-30 23:54:56 +08:00
RockChinQ
f2493c79dd doc(wiki): 添加联网内容函数提问示例 2023-07-29 19:34:47 +08:00
RockChinQ
a86a035b6b doc: 更新README.md 2023-07-29 19:26:28 +08:00
RockChinQ
7995793bfd doc(wiki): 添加内容函数页 2023-07-29 19:24:56 +08:00
RockChinQ
a56b340646 Release v2.5.0 2023-07-29 18:59:25 +08:00
Junyan Qin
7473cdfe16 Merge pull request #513 from RockChinQ/feat-function-calling-integration
[Feat] 支持GPT的函数调用功能
2023-07-29 18:57:29 +08:00
RockChinQ
24273ac158 doc: README添加内容函数相关内容 2023-07-29 18:55:18 +08:00
RockChinQ
fe6275000e doc(wiki): 更新wiki插件页 2023-07-29 18:40:49 +08:00
RockChinQ
5fbf369f82 doc(wiki): 更新插件页 2023-07-29 18:37:03 +08:00
Junyan Qin
4400475ffa chore: 添加Webwlkr插件示例 2023-07-29 17:41:56 +08:00
GitHub Actions Bot
796eb7c95d Update cmdpriv-template.json 2023-07-29 09:30:22 +00:00
RockChinQ
89a01378e7 ci: 跑工作流 2023-07-29 17:29:52 +08:00
RockChinQ
f4735e5e30 ci(cmd_priv): 添加CallingGPT依赖 2023-07-29 17:28:11 +08:00
RockChinQ
f1bb3045aa feat: 添加func命令 2023-07-29 17:26:07 +08:00
RockChinQ
96e474a555 feat: 插件开关对其内容函数生效 2023-07-29 17:10:47 +08:00
RockChinQ
833d29b101 typo: enable->enabled 2023-07-29 16:55:01 +08:00
RockChinQ
dce6734ba2 feat: 改为推荐使用func()装饰器注册内容函数 2023-07-29 16:51:19 +08:00
RockChinQ
0481167dc6 feat: 改为在start流程设置openai.proxy 2023-07-29 16:36:31 +08:00
RockChinQ
a002f93f7b chore: 删除过时代码 2023-07-29 16:30:09 +08:00
RockChinQ
3c894fe70e feat: chat_completion的函数开关支持 2023-07-29 16:29:16 +08:00
RockChinQ
8c69b8a1d9 feat: 内容函数全局开关支持 2023-07-29 16:28:18 +08:00
Junyan Qin
a9dae05303 doc(README.md): 修改社区群群号 2023-07-29 13:31:58 +08:00
RockChinQ
ae6994e241 feat(contentPlugin): 完成基本的内容函数调用功能 2023-07-28 19:03:02 +08:00
Rock Chin
caa72fa40c feat: 在插件层面初步支持内容函数 2023-07-27 14:27:36 +08:00
Junyan Qin
46cc9220c3 Merge pull request #506 from RockChinQ/perf-persist-dprompt-when-auto-reset
[Perf] 在session自动重置时保留非default的prompt
2023-07-07 17:53:29 +08:00
Rock Chin
ddb56d7a8e fix: reset命令错误的逻辑 2023-07-07 17:49:43 +08:00
Rock Chin
a0267416d7 fix: 修复reset逻辑导致的无法初始化情景预设问题 2023-07-07 16:37:05 +08:00
Rock Chin
56e1ef3602 fix: 修复reset可能引起的bug 2023-07-07 16:35:37 +08:00
Rock Chin
b4fc1057d1 perf: 在session自动重置时保留非default的prompt (#494) 2023-07-06 23:09:39 +08:00
Rock Chin
06037df607 ci: 仅在master分支运行sync-wiki工作流 2023-06-20 22:42:18 +08:00
Rock Chin
dce134d08d Release v2.4.7 2023-06-16 19:43:13 +08:00
Junyan Qin
cca471d068 Merge pull request #500 from RockChinQ/perf-more-model-support
Perf more model support
2023-06-16 19:40:29 +08:00
Rock Chin
ddb211b74a feat: 支持新的模型 2023-06-16 19:35:26 +08:00
Rock Chin
cef70751ff chore: 修改配置文件说明 2023-06-16 19:35:06 +08:00
JunYan Qin
2d2219fc6e 更新 README.md 2023-06-13 11:59:30 +08:00
JunYan Qin
514a6b4192 更新 README.md 2023-06-13 11:59:07 +08:00
JunYan Qin
7a552b3434 Merge pull request #496 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.8
chore(deps): update openai requirement from ~=0.27.7 to ~=0.27.8
2023-06-12 23:20:02 +08:00
dependabot[bot]
ecebd1b0e0 chore(deps): update openai requirement from ~=0.27.7 to ~=0.27.8
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.7...v0.27.8)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-06-12 09:01:51 +00:00
Rock Chin
8dc34d2a88 doc(README.md): 添加卖号网站 2023-06-12 14:13:36 +08:00
Rock Chin
d52644ceec doc: 更新README.md 2023-06-12 12:24:59 +08:00
Rock Chin
3052510591 Release v2.4.6 2023-06-08 14:01:18 +08:00
Rock Chin
777a5617db Merge pull request #492 from RockChinQ/feat-ignore-major-vernum
[Feat] 更新时忽略主版本号不同的版本
2023-06-08 14:00:32 +08:00
Rock Chin
e17c1087e9 feat(updater.py): 更新时忽略主版本号不同的版本 2023-06-08 13:57:24 +08:00
Rock Chin
633695175a Merge pull request #491 from RockChinQ/feat-tokens-auto-reset
[Feat] token超限报错时自动重置会话
2023-06-08 13:49:49 +08:00
Rock Chin
9e78bf3d21 perf: 更严格的重置条件判断 2023-06-08 13:49:20 +08:00
Rock Chin
43aa68a55d feat: 支持在token超限时自动重置会话 2023-06-08 13:45:54 +08:00
Rock Chin
b8308f8c57 Merge branch 'feat-tokens-auto-reset' of https://github.com/RockChinQ/QChatGPT into feat-tokens-auto-reset 2023-06-08 13:43:36 +08:00
Rock Chin
466bfbddeb perf: 提示语格式 2023-06-08 13:43:33 +08:00
GitHub Actions
b6da07b225 Update override-all.json 2023-06-08 05:20:55 +00:00
Rock Chin
2f2159239a chore: 添加开关和提示语配置项 2023-06-08 13:20:33 +08:00
Rock Chin
67d1ca8a65 Merge pull request #490 from RockChinQ/feat-global-group-private-enable
[Feat] 支持设置全局群聊/私聊消息禁用
2023-06-07 23:49:53 +08:00
Rock Chin
497a393e83 doc: 修改wiki 2023-06-07 23:49:09 +08:00
Rock Chin
782c0e22ea feat: 支持设置全局群聊、私聊禁用 2023-06-07 23:47:13 +08:00
Rock Chin
2932fc6dfd chore(banlist-template.py): 添加配置项 2023-06-07 23:23:21 +08:00
Rock Chin
0a9eab2113 chore(requirements.txt): 更新requests版本 2023-06-06 09:37:00 +08:00
Rock Chin
50a673a8ec doc: 添加插件列表list 2023-06-05 22:37:19 +08:00
Rock Chin
9e25d0f9e4 Release v2.4.5 2023-05-31 18:31:25 +08:00
Rock Chin
23cd7be711 Merge pull request #487 from RockChinQ/feat-banlist-syntax-check
feat: 初始化流程异常处理
2023-05-31 18:25:46 +08:00
Rock Chin
025b9e33f1 feat: 初始化流程异常处理 2023-05-31 18:24:01 +08:00
Rock Chin
bab2f64913 doc(README_en.md): 添加wakapi计时 2023-05-29 11:12:07 +08:00
Rock Chin
b00e09aa9c doc: 添加wakapi计时 2023-05-29 11:10:49 +08:00
Rock Chin
0b109fdc7a Merge pull request #479 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.7
chore(deps): update openai requirement from ~=0.27.6 to ~=0.27.7
2023-05-22 17:13:50 +08:00
dependabot[bot]
018fea2ddb chore(deps): update openai requirement from ~=0.27.6 to ~=0.27.7
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.6...v0.27.7)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-05-22 09:05:00 +00:00
Rock Chin
f8a3cc4352 doc: 折起OpenAI注册步骤 2023-05-21 18:25:35 +08:00
Rock Chin
6ab853acc1 doc: 修改关于HuggingChat的说明 2023-05-21 17:50:35 +08:00
Rock Chin
e825dea02f chore: 排除hugchat.json 2023-05-21 17:47:42 +08:00
Rock Chin
cf8740d16e Merge branch 'master' of https://github.com/RockChinQ/QChatGPT 2023-05-21 17:33:47 +08:00
Rock Chin
9c4809e26f chore: 发布revLibs相关公告 2023-05-21 17:33:44 +08:00
Rock Chin
0a232fd9ef Merge pull request #477 from RockChinQ/feature-detailed-cfg-cmd
[Feat] 支持使用!cfg指令修改子配置项
2023-05-21 15:59:59 +08:00
Rock Chin
23016a0791 doc: 更新wiki说明 2023-05-21 15:58:21 +08:00
Rock Chin
cdcc67ff23 feat(!cfg): 使用eval()函数进行类型转换 2023-05-21 15:53:56 +08:00
Rock Chin
92274bfc34 feat(!cfg): 支持使用点号索引子配置项 2023-05-21 15:49:56 +08:00
Rock Chin
2fed6f61ba Release v2.4.4 2023-05-21 15:15:28 +08:00
Rock Chin
59b2cd26d2 Merge pull request #476 from RockChinQ/hotfix-471-at-no-response-aft-reload
[Fix] 热重载之后不响应群内at
2023-05-21 15:12:43 +08:00
Rock Chin
f7b87e99d2 fix(manager.py): 热重载之后不响应群内at 2023-05-21 15:11:34 +08:00
Rock Chin
70bc985145 perf(nakuru.py): access-token被拒时报警 2023-05-18 21:06:32 +08:00
Rock Chin
070dbe9108 chore: 排除venv/目录 2023-05-18 21:05:45 +08:00
Rock Chin
a63fa6d955 chore: yiri-mirai使用0.2.7 2023-05-18 21:05:30 +08:00
Rock Chin
c7703809b0 Merge pull request #475 from RockChinQ/actively-delay
[Feat] 支持设置消息回复强制延迟以降低风控概率
2023-05-18 20:15:52 +08:00
GitHub Actions
37eb74338f Update override-all.json 2023-05-18 12:14:19 +00:00
Rock Chin
77d5585b7c feat: 修改强制延迟默认范围 2023-05-18 20:13:53 +08:00
Rock Chin
6cab3ef029 Merge branch 'actively-delay' of https://github.com/RockChinQ/QChatGPT into actively-delay 2023-05-18 20:12:39 +08:00
Rock Chin
820a7b78fc feat: 处理过程支持强制延迟 2023-05-18 20:12:36 +08:00
GitHub Actions
c51dffef3a Update override-all.json 2023-05-18 12:10:33 +00:00
Rock Chin
983bc3da3c chore: 添加强制延迟配置项 2023-05-18 20:10:08 +08:00
Rock Chin
09be956a58 Merge pull request #474 from RockChinQ/command-notfound-err
[Perf] 修改指令不存在时的提示信息
2023-05-18 19:45:25 +08:00
Rock Chin
5eded50c53 perf: 修改指令不存在时的提示信息 2023-05-18 19:44:20 +08:00
Rock Chin
6d8eebd314 doc: 添加微信赞赏码 2023-05-16 15:36:07 +08:00
Rock Chin
19a0572b5f Release v2.4.3.1 2023-05-15 17:38:03 +08:00
Rock Chin
6272e98474 Merge pull request #467 from RockChinQ/perf-plugin-update
[Perf] 优化插件更新相关操作
2023-05-14 18:45:36 +08:00
Rock Chin
45042fe7d4 doc: 更新插件更新命令wiki 2023-05-14 18:44:14 +08:00
Rock Chin
d85e840126 perf: 优化插件更新操作,支持更新单个插件 2023-05-14 18:41:20 +08:00
Rock Chin
804889f1de perf: 加载模块的输出改为debug级别 2023-05-14 17:30:05 +08:00
Rock Chin
919c996434 doc: 添加HuggingChat 2023-05-14 17:14:46 +08:00
Rock Chin
00823b3d62 doc(README): 添加HuggingChat 2023-05-14 17:14:28 +08:00
Rock Chin
af54efd24a doc(README.md): 添加系统状态插件 2023-05-14 14:58:48 +08:00
Rock Chin
b1c9b121f6 Update go-cqhttp配置.md 2023-05-08 21:51:03 +08:00
Rock Chin
7b5649d153 Merge pull request #461 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.6
chore(deps): update openai requirement from ~=0.27.5 to ~=0.27.6
2023-05-08 18:48:20 +08:00
dependabot[bot]
52bf716d84 chore(deps): update openai requirement from ~=0.27.5 to ~=0.27.6
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.5...v0.27.6)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-05-08 10:34:21 +00:00
Rock Chin
c149dd7b66 Merge pull request #462 from RockChinQ/dependabot/pip/dulwich-approx-eq-0.21.5
chore(deps): update dulwich requirement from ~=0.21.3 to ~=0.21.5
2023-05-08 18:24:59 +08:00
dependabot[bot]
65d5a1ed63 chore(deps): update dulwich requirement from ~=0.21.3 to ~=0.21.5
Updates the requirements on [dulwich](https://github.com/dulwich/dulwich) to permit the latest version.
- [Release notes](https://github.com/dulwich/dulwich/releases)
- [Changelog](https://github.com/jelmer/dulwich/blob/master/NEWS)
- [Commits](https://github.com/dulwich/dulwich/compare/dulwich-0.21.3...dulwich-0.21.5)

---
updated-dependencies:
- dependency-name: dulwich
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-05-08 09:01:55 +00:00
Rock Chin
5516754bbb doc(README.md): 添加docker部署提示 2023-05-02 14:30:25 +08:00
Rock Chin
08082f2ee3 Merge pull request #452 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.5
chore(deps): update openai requirement from ~=0.27.4 to ~=0.27.5
2023-05-01 17:26:18 +08:00
dependabot[bot]
8489266080 chore(deps): update openai requirement from ~=0.27.4 to ~=0.27.5
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.4...v0.27.5)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-05-01 09:06:44 +00:00
Rock Chin
51c7e0b235 doc(README.md): 四群群号 2023-04-28 00:37:29 +08:00
Rock Chin
628b6b0bb4 Merge branch 'master' of https://github.com/RockChinQ/QChatGPT 2023-04-27 15:01:47 +08:00
Rock Chin
7e024d860d doc: 增加LightQChat的公告 2023-04-27 15:01:44 +08:00
Rock Chin
c2f6273f70 Merge pull request #442 from oliverkirk-sudo/master
修复异常输出时的类型问题
2023-04-26 17:31:19 +08:00
oliverkirk-sudo
96e401ec7b 修复异常输出时的类型问题 2023-04-26 17:27:33 +08:00
Rock Chin
ae8ac65447 feat: 更换使用清华源 (#438) 2023-04-26 11:52:07 +08:00
Rock Chin
2d4f59f36e doc: 强调02 2023-04-26 11:18:07 +08:00
Rock Chin
0e85467e02 Release v2.4.2 2023-04-25 10:27:57 +08:00
Rock Chin
eb41cf5481 fix(plugin.py): 兼容性问题 2023-04-25 10:27:07 +08:00
Rock Chin
b970a42d07 fix(plugin.py): send_message封装实现的兼容性问题 2023-04-25 10:26:03 +08:00
Rock Chin
8c9d123e1c Merge pull request #433 from RockChinQ/detailed-response-rules
[Feat] 细化到单个群的响应规则
2023-04-25 09:39:56 +08:00
Rock Chin
ab2a95e347 Merge branch 'detailed-response-rules' of https://github.com/RockChinQ/QChatGPT into detailed-response-rules 2023-04-25 09:31:56 +08:00
Rock Chin
2184c558a4 feat: 支持配置细化到单个群的响应规则 2023-04-25 09:31:44 +08:00
GitHub Actions
83cb8588fd Update override-all.json 2023-04-25 01:28:56 +00:00
Rock Chin
007e82c533 feat: 配置文件支持 2023-04-25 09:28:31 +08:00
Rock Chin
499f8580a7 doc: 修改wiki格式 2023-04-25 08:45:58 +08:00
Rock Chin
a7dc3c5dab Release v2.4.1 2023-04-25 00:01:40 +08:00
Rock Chin
d01d3a3c53 perf: 启动时提示使用的QQ号 2023-04-24 23:57:57 +08:00
Rock Chin
580e062dbf feat: 上报使用量时带上msg_source_adapter 2023-04-24 23:51:00 +08:00
Rock Chin
c8cee8410c doc: 完善格式 2023-04-24 20:04:33 +08:00
Rock Chin
6bf331c2e3 doc: 完善wiki 2023-04-24 19:53:20 +08:00
Rock Chin
4c4930737c chore: issue模板新增登录框架字段 2023-04-24 19:28:00 +08:00
Rock Chin
9de01e9525 Release v2.4.0 2023-04-24 16:09:46 +08:00
Rock Chin
c6a16f5974 Merge pull request #427 from RockChinQ/nakuru-support
[Feat] 支持通过nakuru-project框架连接go-cqhttp
2023-04-24 16:07:12 +08:00
Rock Chin
253ef44d17 chore: 公告 2023-04-24 16:05:47 +08:00
Rock Chin
15a1f00b73 doc(README.md): 添加go-cqhttp公告 2023-04-24 16:04:25 +08:00
Rock Chin
b5fa2ea8b8 feat(main.py): 添加nakuru-project-idk的依赖更新项 2023-04-24 16:01:43 +08:00
Rock Chin
449e024771 doc: 添加针对老用户的说明 2023-04-24 15:59:07 +08:00
Rock Chin
1bee7a146b feat: 支持语音组件 2023-04-24 15:55:21 +08:00
Rock Chin
270a632789 doc: 修改标号 2023-04-24 15:48:28 +08:00
Rock Chin
418bb05b4c doc: 添加go-cqhttp配置说明 2023-04-24 15:46:58 +08:00
Rock Chin
052b834151 doc: 完善config-template.py的说明 2023-04-24 15:46:26 +08:00
Rock Chin
58ee204a75 doc: wiki添加go-cqhttp配置步骤 2023-04-24 15:41:28 +08:00
Rock Chin
0a02ee8c04 feat: 启动时添加nakuru的提示检查 2023-04-24 15:04:07 +08:00
Rock Chin
950ef4a181 doc: 更新README.md 2023-04-24 14:57:28 +08:00
Rock Chin
7b7cdd8adb perf: 在日志文件包含输出文件路径 2023-04-24 13:52:22 +08:00
Rock Chin
471768e760 feat: 支持发送转发消息 2023-04-24 12:46:33 +08:00
Rock Chin
c7517d31a4 chore: 更换使用nakuru-project-idk包 2023-04-24 11:37:01 +08:00
Rock Chin
7d10d0398e fix: nakuru热重载失败 2023-04-24 11:21:51 +08:00
Rock Chin
a2bc25c08b feat: 支持引用原消息回复 2023-04-24 10:57:43 +08:00
Rock Chin
3cb49fe2d8 feat: 支持检测群内禁言 2023-04-24 10:34:51 +08:00
Rock Chin
5b96ac122f feat: 适配nakuru基本功能 2023-04-23 23:40:08 +08:00
Rock Chin
612033f478 feat: nakuru适配器基础模型 2023-04-23 15:58:37 +08:00
GitHub Actions
48ee940d8e Update override-all.json 2023-04-23 01:32:36 +00:00
Rock Chin
e74df0b37d chore: 添加nakuru相关配置; 使用nakuru-project-test临时包 2023-04-23 09:32:01 +08:00
GitHub Actions
640afdc49c Update override-all.json 2023-04-22 13:51:02 +00:00
Rock Chin
6b39df5b9b chore: 删除NoneBot2相关配置 2023-04-22 21:50:41 +08:00
Rock Chin
e7e698765e fix(plugin.py): 缺少的换行符 2023-04-22 17:40:41 +08:00
Rock Chin
43fea13dab Merge pull request #418 from RockChinQ/im-impl-decoupling
[Refactor] 新增抽象层以解耦消息来源(MessageSource)组件
2023-04-21 18:10:42 +08:00
GitHub Actions
bc899e5bd0 Update override-all.json 2023-04-21 09:52:31 +00:00
Rock Chin
160086feb9 refactor: 完成MessageSource适配器解耦 2023-04-21 17:51:58 +08:00
Rock Chin
016391c976 refactor: 不再向QQBotManager中传递config中可读的参数 2023-04-21 17:15:32 +08:00
Rock Chin
91746448a3 feat: 消息源适配器模型及YiriMirai的适配器 2023-04-21 16:36:59 +08:00
Rock Chin
5cb0543237 doc(README.md): 更新wiki链接 2023-04-20 20:50:00 +08:00
Rock Chin
fac29a24a8 doc(README.md): social.png更改成圆角 2023-04-20 10:54:06 +08:00
Rock Chin
4d3a2a21d0 Update README_en.md 2023-04-20 00:22:05 +08:00
Rock Chin
6d4f88041c Update README.md 2023-04-20 00:21:37 +08:00
Rock Chin
18587d3690 doc(README.md): 修改social图格式 2023-04-20 00:15:11 +08:00
Rock Chin
423090dccd doc(README.md): 更改使用social图 2023-04-20 00:13:11 +08:00
Rock Chin
78e88baab3 doc(README.md): 优化LOGO图格式 2023-04-20 00:08:00 +08:00
Rock Chin
6a276767b3 doc(README.md): 添加LOGO 2023-04-20 00:06:52 +08:00
Rock Chin
2cb26c7c70 doc: 添加LOGO文件 2023-04-20 00:04:01 +08:00
Rock Chin
ff66c88060 doc(README.md): 优化图片格式 2023-04-17 10:18:23 +08:00
Rock Chin
611e82b8f9 doc(README.md): 添加使用截图 2023-04-17 10:15:50 +08:00
Rock Chin
59bdee7137 feat: 添加IM框架模型 2023-04-15 23:38:52 +08:00
Rock Chin
e8dbd426ae Release v2.3.9 2023-04-15 17:36:59 +08:00
Rock Chin
40d6e809a0 Merge pull request #417 from RockChinQ/354-feature-single-concurrency
[Feat] 支持设置单会话内同时仅处理一条消息
2023-04-15 17:35:36 +08:00
GitHub Actions
236c540d18 Update override-all.json 2023-04-15 09:34:16 +00:00
Rock Chin
d6ca059f6c feat: 支持设置单会话内同时仅处理一条消息 2023-04-15 17:33:57 +08:00
Rock Chin
52c06a60ca fix: 公告功能bug 2023-04-15 16:54:50 +08:00
Rock Chin
6353644ec3 test: 测试公告 2023-04-15 16:49:11 +08:00
Rock Chin
20df9ded3d Merge pull request #416 from RockChinQ/413-feature-json-format-anouns
[Feat] 支持JSON格式的公告
2023-04-15 16:47:03 +08:00
Rock Chin
7569b18a4c feat: 支持JSON格式的公告 2023-04-15 16:45:26 +08:00
Rock Chin
b9da4f4951 Merge pull request #415 from RockChinQ/413-feature-json-format-anouns
[Feat] 新增`announcement.json`文件
2023-04-15 16:33:03 +08:00
Rock Chin
89b9e29257 Update pull_request_template.md 2023-04-15 16:25:24 +08:00
Rock Chin
d605de9de4 feat: 添加公告模板及公告发布脚本 2023-04-15 09:38:46 +08:00
Rock Chin
d46c94d7c3 Release v2.3.8 2023-04-14 23:47:00 +08:00
Rock Chin
2db9c00530 Merge pull request #414 from RockChinQ/detailed-rate-limit
[Feat] 速度限制支持细化到单个人或群
2023-04-14 19:46:24 +08:00
GitHub Actions
66d8d159f9 Update override-all.json 2023-04-14 11:44:26 +00:00
Rock Chin
9fa1446284 feat: 支持细化到个人和群的限速 2023-04-14 19:44:03 +08:00
Rock Chin
b3e4cb48c7 Merge pull request #412 from RockChinQ/349-bugfix-auto-deps-solving-failure
[Fix] 循环依赖导致的依赖自动解决失败
2023-04-14 18:44:40 +08:00
Rock Chin
0bca7b2247 fix: 循环引用导致的依赖自动解决失败 2023-04-14 18:42:09 +08:00
Rock Chin
7812e03c9d chore: 删除requirements.txt中对websockets的版本要求以防冲突 2023-04-14 18:27:44 +08:00
Rock Chin
7a852ae5af Merge pull request #410 from 2675hujilo/tips
删除tips-custom-template.py中无用字段
2023-04-14 17:43:30 +08:00
26751
706d9e61c1 删除tips-custom-template.py中无用字段 2023-04-14 02:00:45 +08:00
Rock Chin
8f0ed4ff4b Merge branch 'master' of https://github.com/RockChinQ/QChatGPT 2023-04-12 15:28:59 +08:00
Rock Chin
3415b6f121 doc: 添加lieyanqzu/WeatherPlugin 2023-04-12 15:28:56 +08:00
Rock Chin
256ba6fb86 Merge pull request #406 from RockChinQ/dependabot/pip/openai-approx-eq-0.27.4
chore(deps): update openai requirement from ~=0.27.2 to ~=0.27.4
2023-04-10 18:31:39 +08:00
dependabot[bot]
d30b2b9afe chore(deps): update openai requirement from ~=0.27.2 to ~=0.27.4
Updates the requirements on [openai](https://github.com/openai/openai-python) to permit the latest version.
- [Release notes](https://github.com/openai/openai-python/releases)
- [Commits](https://github.com/openai/openai-python/compare/v0.27.2...v0.27.4)

---
updated-dependencies:
- dependency-name: openai
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-04-10 09:03:02 +00:00
Rock Chin
be943ca1fc doc: 链接文档 2023-04-08 19:39:42 +08:00
Rock Chin
1ddab2a97a doc: README.md in English 2023-04-08 19:32:31 +08:00
Rock Chin
e15fd4695c Merge branch 'master' of https://github.com/RockChinQ/QChatGPT 2023-04-08 18:26:10 +08:00
Rock Chin
ffa4b1b4a1 fix(modelmgr): 使用异步请求时的异常类型丢失 2023-04-08 18:26:08 +08:00
Rock Chin
f8eee3a2a6 Merge pull request #399 from RockChinQ/optional-config-override
[Feat] override.json可选应用
2023-04-08 16:26:56 +08:00
Rock Chin
eeee7a8343 feat: 仅在提供命令行参数时应用override.json的内容 2023-04-08 16:21:40 +08:00
Rock Chin
8447b73fcb doc(README.md): 删除ChatAPI2D插件 2023-04-08 16:15:11 +08:00
Rock Chin
2863945d5f feat(config-template): 更改为常量表示超时时间 2023-04-08 15:36:35 +08:00
Rock Chin
cb1f8ca6f7 doc(README.md): 添加wenyinos/ChatAPI2D插件 2023-04-08 00:33:47 +08:00
Rock Chin
1d9964bcb1 Release v2.3.7 2023-04-08 00:21:21 +08:00
GitHub Actions Bot
15cb8016d3 Update cmdpriv-template.json 2023-04-07 16:20:13 +00:00
Rock Chin
895cc0a2c5 ci: test 2023-04-08 00:19:37 +08:00
Rock Chin
20bf349e4e ci: cmdpriv模板脚本 2023-04-08 00:18:00 +08:00
Rock Chin
e297763da1 fix: !cfg指令失效 2023-04-08 00:13:19 +08:00
Rock Chin
e471970654 ci: test 2023-04-07 20:32:51 +08:00
Rock Chin
12faaaced8 ci: 仅在wiki文件更新时提交 2023-04-07 20:31:33 +08:00
Rock Chin
083cbc55cc Release v2.3.6 2023-04-07 17:15:17 +08:00
Rock Chin
8aa7a3273d Merge pull request #390 from RockChinQ/customizable-tips
[Feat] 支持自定义提示消息
2023-04-07 17:13:28 +08:00
Rock Chin
255e2c4385 doc: 添加自定义提示消息的说明 2023-04-07 17:12:33 +08:00
Rock Chin
9856306870 feat: 修改文件生成顺序 2023-04-07 17:10:44 +08:00
GitHub Actions
527ab8b8a7 Update override-all.json 2023-04-07 09:08:21 +00:00
Rock Chin
f8e19ba9b3 feat: 删除config-template.py中多余的属性 2023-04-07 17:07:43 +08:00
GitHub Actions
7649dbfbbc Update override-all.json 2023-04-07 09:00:40 +00:00
Rock Chin
81e734644d feat: 删除config-template.py中的help_message模板 2023-04-07 17:00:16 +08:00
Rock Chin
ae55cf5b1e feat: 适配help指令 2023-04-07 16:59:51 +08:00
Rock Chin
af539546ef Merge pull request #356 from 2675hujilo/tips
[Feat] 支持自定义提示消息
2023-04-07 16:43:58 +08:00
Rock Chin
0031ce57d0 Merge branch 'customizable-tips' into tips 2023-04-07 16:40:26 +08:00
Rock Chin
2f48a2ce57 Merge branch 'customizable-tips' of https://github.com/RockChinQ/QChatGPT into customizable-tips 2023-04-07 16:39:48 +08:00
Rock Chin
6068ab7100 feat: 修改help_message为主线的内容 2023-04-07 16:39:25 +08:00
GitHub Actions
29a7dccef4 Update override-all.json 2023-04-07 08:34:23 +00:00
Rock Chin
e2073da86e Merge branch '2675hujilo-tips' into customizable-tips 2023-04-07 16:32:32 +08:00
2675hujilo
ae079526f7 删除tips-customs-template.py中不必要注释 2023-04-07 16:29:09 +08:00
26751
947bae8e26 删除tips-customs-template.py中不必要注释
Signed-off-by: 26751 <2675174581@qq.com>
2023-04-07 16:22:22 +08:00
Rock Chin
a68e29dff6 feat: tips模块完整性检查 2023-04-07 16:02:22 +08:00
Rock Chin
a588d7f960 feat: 热重载加上tips模块 2023-04-07 13:28:07 +08:00
Rock Chin
66224e5a32 fix: 热重载后未检查配置文件存在性 2023-04-07 13:25:57 +08:00
Rock Chin
07abad6a14 feat: 将tips的值统一为str类型 2023-04-07 13:23:58 +08:00
Rock Chin
83d02aaaac chore: 修改配置文件名称 2023-04-07 13:20:57 +08:00
Rock Chin
5a27ac165e Merge branch 'master' of https://github.com/RockChinQ/QChatGPT 2023-04-06 21:37:56 +08:00
Rock Chin
bd9a523233 Release v2.3.5 2023-04-06 21:37:51 +08:00
Rock Chin
43959b158f Merge pull request #385 from RockChinQ/impl-337-bugfix-version-ignorance
[Feat] 更新逻辑优化
2023-04-06 21:36:53 +08:00
Rock Chin
d81b457bba feat: 更新完成后不展示更新前版本的更新日志 (#340) 2023-04-06 21:34:30 +08:00
Rock Chin
b40d639785 feat: 忽略第四位版本号 2023-04-06 21:31:56 +08:00
Rock Chin
0a8d8f4f66 Merge pull request #381 from RockChinQ/impl-339-redundance-comp-check
[Chore] 删除冗余的兼容性检查判断
2023-04-06 21:03:33 +08:00
Rock Chin
d16cb25cde chore: 删除冗余的兼容性检查判断 2023-04-06 20:34:56 +08:00
Rock Chin
7aef1758e0 ci: test 2023-04-06 18:41:21 +08:00
Rock Chin
9758756fdd ci: 错误的路径 2023-04-06 18:39:21 +08:00
Rock Chin
13ef35f96f fix: 热重载后!draw无法使用的问题 2023-04-06 18:37:07 +08:00
Rock Chin
6b8c1209b7 chore: 整理根目录文件 2023-04-06 17:23:30 +08:00
Rock Chin
7184f3053a doc: README.md添加社区群说明 2023-04-06 15:55:48 +08:00
Rock Chin
b83eac10e6 doc: 完善wiki 2023-04-06 15:20:08 +08:00
Rock Chin
cb42eaef69 test: Home.md 2023-04-06 15:18:35 +08:00
Rock Chin
0dfd636a7e ci: 工作流 2023-04-06 15:18:02 +08:00
Rock Chin
21ff0fd258 test: 测试wiki同步工作流 2023-04-06 15:13:40 +08:00
Rock Chin
c2eaeb2c72 chore: wiki同步工作流 2023-04-06 15:12:12 +08:00
Rock Chin
2a414a4bea chore: 提交wiki文件到res/wiki 2023-04-06 15:07:25 +08:00
Rock Chin
fc0c38c8af chore: 删除子模块 2023-04-06 10:13:34 +08:00
Rock Chin
595e6c8a0c chore: 删除子模块 2023-04-06 10:13:08 +08:00
Rock Chin
ced16fd221 chore: 移动docker部署教程 2023-04-06 10:10:09 +08:00
Rock Chin
0817c3f148 chore: 将工作流脚本移动到res/scripts 2023-04-06 10:08:15 +08:00
Rock Chin
fb40af81ac doc: 完善文档 2023-04-06 09:44:07 +08:00
Rock Chin
1c5ad05e89 typo: plugin命令的提示错字 2023-04-06 09:29:45 +08:00
Rock Chin
86bef566c4 Release v2.3.4 2023-04-05 17:13:05 +08:00
Rock Chin
0983ccb61e doc: 添加模型切换器插件 2023-04-05 16:59:06 +08:00
Rock Chin
a1d9f469c0 doc: 添加模型切换器插件 2023-04-05 16:58:15 +08:00
Rock Chin
952124f783 feat: 禁用的插件仍进行初始化 2023-04-05 16:50:35 +08:00
GitHub Actions
6be12e8ace Update override-all.json 2023-04-05 07:48:46 +00:00
Rock Chin
0799f380e1 feat: 更改默认help_message 2023-04-05 15:48:21 +08:00
Rock Chin
f65270ee7e feat: 启动时输出mah相关配置项 2023-04-05 15:46:49 +08:00
26751
5865ac017c 增加tips_custom.py提示
Signed-off-by: 26751 <2675174581@qq.com>
2023-04-02 13:46:15 +08:00
26751
4061a92f8e 删除override-all.json中无效的字段
Signed-off-by: 26751 <2675174581@qq.com>
2023-04-02 13:36:51 +08:00
2675hujilo
d37c31b31c Update tips_custom_template.py 2023-04-01 18:43:03 +08:00
2675hujilo
973ef0078f Delete tips_custom.py 2023-04-01 18:36:33 +08:00
26751
48dcd257da Signed-off-by: 26751 <2675174581@qq.com> 2023-04-01 18:33:37 +08:00
26751
da03911610 Signed-off-by: 26751 <2675174581@qq.com> 2023-04-01 16:39:02 +08:00
26751
b6f7f3b73f Signed-off-by: 26751 <2675174581@qq.com> 2023-04-01 02:35:27 +08:00
26751
2050d20ea7 Signed-off-by: 26751 <2675174581@qq.com> 2023-04-01 02:23:40 +08:00
26751
ac1fb4a63a 修改自定义提示语 2023-04-01 01:02:59 +08:00
crosscc
8c67d3c58f Create build_docker_image.yml
利用github action 自动构建docker镜像:
## 1、
`workflow_dispatch:` 是需要作者在action手动点击进行构建

```
  release:
    types: [published]
```
这个是发布release的时候自动构建镜像。根据作者需求启用或者删除注释掉

## 2、
`tag: latest,${{ steps.get_version.outputs.VERSION }}`是可以镜像打标为latest和release发布的版本号

## 3、
docker hub userid 在setting创建secrets, name=DOCKER_USERNAME   value=dockerid
docker hub password,在setting创建secrets, name=DOCKER_PASSWORD   value=dockerpassword

这样作者就不用在自己机器上构建docker镜像,利用action 自动完成全平台镜像 速度也快。
2023-03-31 16:22:20 +08:00
109 changed files with 4961 additions and 1015 deletions

View File

@@ -1,34 +0,0 @@
// For format details, see https://aka.ms/devcontainer.json. For config options, see the
// README at: https://github.com/devcontainers/templates/tree/main/src/python
{
"name": "QChatGPT 3.10",
// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
"image": "mcr.microsoft.com/devcontainers/python:0-3.10",
// Features to add to the dev container. More info: https://containers.dev/features.
// "features": {},
// Use 'forwardPorts' to make a list of ports inside the container available locally.
// "forwardPorts": [],
// Use 'postCreateCommand' to run commands after the container is created.
// "postCreateCommand": "pip3 install --user -r requirements.txt",
// Configure tool-specific properties.
// "customizations": {},
"customizations": {
"codespaces": {
"repositories": {
"RockChinQ/QChatGPT": {
"permissions": "write-all"
},
"RockChinQ/revLibs": {
"permissions": "write-all"
}
}
}
}
// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
// "remoteUser": "root"
}

View File

@@ -14,6 +14,15 @@ body:
- Docker部署
validations:
required: true
- type: dropdown
attributes:
label: 登录框架
description: "连接QQ使用的框架"
options:
- Mirai
- go-cqhttp
validations:
required: false
- type: input
attributes:
label: 系统环境

View File

@@ -4,7 +4,7 @@
### 事务
- [ ] 已阅读仓库[贡献指引](../CONTRIBUTING.md)
- [ ] 已阅读仓库[贡献指引](https://github.com/RockChinQ/QChatGPT/blob/master/CONTRIBUTING.md)
- [ ] 已与维护者在issues或其他平台沟通此PR大致内容
## 以下内容可在起草PR后、合并PR前逐步完成

View File

@@ -0,0 +1,38 @@
name: Build Docker Image
on:
#防止fork乱用action设置只能手动触发构建
workflow_dispatch:
## 发布release的时候会自动构建
release:
types: [published]
jobs:
publish-docker-image:
runs-on: ubuntu-latest
name: Build image
steps:
- name: Checkout
uses: actions/checkout@v2
- name: judge has env GITHUB_REF # 如果没有GITHUB_REF环境变量则把github.ref变量赋值给GITHUB_REF
run: |
if [ -z "$GITHUB_REF" ]; then
export GITHUB_REF=${{ github.ref }}
fi
- name: Check GITHUB_REF env
run: echo $GITHUB_REF
- name: Get version
id: get_version
if: (startsWith(env.GITHUB_REF, 'refs/tags/')||startsWith(github.ref, 'refs/tags/')) && startsWith(github.repository, 'RockChinQ/QChatGPT')
run: echo ::set-output name=VERSION::${GITHUB_REF/refs\/tags\//}
- name: Build # image name: rockchin/qchatgpt:<VERSION>
run: docker build --network=host -t rockchin/qchatgpt:${{ steps.get_version.outputs.VERSION }} -t rockchin/qchatgpt:latest .
- name: Login to Registry
run: docker login --username=${{ secrets.DOCKER_USERNAME }} --password ${{ secrets.DOCKER_PASSWORD }}
- name: Push image
if: (startsWith(env.GITHUB_REF, 'refs/tags/')||startsWith(github.ref, 'refs/tags/')) && startsWith(github.repository, 'RockChinQ/QChatGPT')
run: docker push rockchin/qchatgpt:${{ steps.get_version.outputs.VERSION }}
- name: Push latest image
if: (startsWith(env.GITHUB_REF, 'refs/tags/')||startsWith(github.ref, 'refs/tags/')) && startsWith(github.repository, 'RockChinQ/QChatGPT')
run: docker push rockchin/qchatgpt:latest

48
.github/workflows/sync-wiki.yml vendored Normal file
View File

@@ -0,0 +1,48 @@
name: Update Wiki
on:
pull_request:
branches:
- master
paths:
- 'res/wiki/**'
push:
branches:
- master
paths:
- 'res/wiki/**'
jobs:
update-wiki:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v2
- name: Setup Git
run: |
git config --global user.name "GitHub Actions"
git config --global user.email "github-actions[bot]@users.noreply.github.com"
- name: Clone Wiki Repository
uses: actions/checkout@v2
with:
repository: RockChinQ/QChatGPT.wiki
path: wiki
- name: Delete old wiki content
run: |
rm -rf wiki/*
- name: Copy res/wiki content to wiki
run: |
cp -r res/wiki/* wiki/
- name: Check for changes
run: |
cd wiki
if git diff --quiet; then
echo "No changes to commit."
exit 0
fi
- name: Commit and Push Changes
run: |
cd wiki
git add .
git commit -m "Update wiki"
git push

View File

@@ -21,13 +21,17 @@ jobs:
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.x
python-version: 3.10.13
- name: Install dependencies
run: |
python -m pip install --upgrade pip
python -m pip install --upgrade yiri-mirai openai colorlog func_timeout dulwich Pillow
python -m pip install --upgrade yiri-mirai openai>=1.0.0 colorlog func_timeout dulwich Pillow CallingGPT tiktoken
python -m pip install -U openai>=1.0.0
- name: Copy Scripts
run: |
cp res/scripts/generate_cmdpriv_template.py .
- name: Generate Files
run: |
python main.py
@@ -38,7 +42,7 @@ jobs:
- name: Check for changes in cmdpriv-template.json
id: check_changes
run: |
if git diff --name-only | grep -q "cmdpriv-template.json"; then
if git diff --name-only | grep -q "res/templates/cmdpriv-template.json"; then
echo "::set-output name=changes_detected::true"
else
echo "::set-output name=changes_detected::false"
@@ -49,6 +53,6 @@ jobs:
run: |
git config --global user.name "GitHub Actions Bot"
git config --global user.email "<github-actions@github.com>"
git add cmdpriv-template.json
git add res/templates/cmdpriv-template.json
git commit -m "Update cmdpriv-template.json"
git push

View File

@@ -29,7 +29,10 @@ jobs:
- name: Install dependencies
run: |
python -m pip install --upgrade pip
# 在此处添加您的项目所需的其他依赖
- name: Copy Scripts
run: |
cp res/scripts/generate_override_all.py .
- name: Run generate_override_all.py
run: python3 generate_override_all.py

15
.gitignore vendored
View File

@@ -17,4 +17,17 @@ scenario/
override.json
cookies.json
res/announcement_saved
cmdpriv.json
res/announcement_saved.json
cmdpriv.json
tips.py
.venv
bin/
.vscode
test_*
venv/
hugchat.json
qcapi
claude.json
bard.json
/*yaml
!/docker-compose.yaml

3
.gitmodules vendored
View File

@@ -1,3 +0,0 @@
[submodule "QChatGPT.wiki"]
path = QChatGPT.wiki
url = https://github.com/RockChinQ/QChatGPT.wiki.git

View File

@@ -17,3 +17,10 @@
- 解决本项目或衍生项目的issues中亟待解决的问题
- 阅读并完善本项目文档
- 在各个社交媒体撰写本项目教程等
### 代码规范
- 代码中的注解`务必`符合Google风格的规范
- 模块顶部的引入代码请遵循`系统模块``第三方库模块``自定义模块`的顺序进行引入
- `不要`直接引入模块的特定属性,而是引入这个模块,再通过`xxx.yyy`的形式使用属性
- 任何作用域的字段`必须`先声明后使用,并在声明处注明类型提示

View File

@@ -1,17 +1,15 @@
FROM python:3.9-slim
FROM python:3.10.13-bullseye
WORKDIR /QChatGPT
RUN sed -i "s/deb.debian.org/mirrors.tencent.com/g" /etc/apt/sources.list \
&& sed -i 's|security.debian.org/debian-security|mirrors.tencent.com/debian-security|g' /etc/apt/sources.list \
&& apt-get clean \
&& apt-get update \
&& apt-get -y upgrade \
&& apt-get install -y git \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
COPY . /QChatGPT/
RUN pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
RUN ls
CMD [ "python", "main.py" ]
RUN python -m pip install -r requirements.txt && \
python -m pip install -U websockets==10.0 && \
python -m pip install -U httpcore httpx openai
# 生成配置文件
RUN python main.py
CMD [ "python", "main.py" ]

Submodule QChatGPT.wiki deleted from d0dd0c1ad3

226
README.md
View File

@@ -1,23 +1,59 @@
# QChatGPT🤖
> 2023/3/18 现已支持GPT-4 API内测请查看`config-template.py`中的`completion_api_params`
> 2023/3/15 逆向库已支持New Bing使用方法查看[插件文档](https://github.com/RockChinQ/revLibs)
> 2023/3/15 逆向库已支持GPT-4模型使用方法查看[插件](https://github.com/RockChinQ/revLibs)
> 2023/3/3 现已在主线支持官方ChatGPT接口使用方法查看[#195](https://github.com/RockChinQ/QChatGPT/issues/195)
<p align="center">
<img src="res/logo.png" alt="QChatGPT" width="120" />
</p>
- 到[项目Wiki](https://github.com/RockChinQ/QChatGPT/wiki)可了解项目详细信息
- ~~由bilibili TheLazy制作的[视频教程](https://www.bilibili.com/video/BV15v4y1X7aP)~~(寄了,求大佬做个新的)
- 交流、答疑群: ~~204785790~~(已满)、~~691226829~~已满、656285629
- **进群提问前请您`确保`已经找遍文档和issue均无法解决**
- QQ频道机器人见[QQChannelChatGPT](https://github.com/Soulter/QQChannelChatGPT)
- 欢迎各种形式的贡献,请查看[贡献指引](CONTRIBUTING.md)
<div align="center">
通过调用OpenAI的ChatGPT等语言模型来实现一个更加智能的QQ机器人
# QChatGPT
<!-- 高稳定性/持续迭代/架构清晰/支持插件/高可自定义的 ChatGPT QQ机器人框架 -->
<!-- “当然下面是一个使用Java编写的快速排序算法的示例代码” -->
[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT)](https://github.com/RockChinQ/QChatGPT/releases/latest)
<a href="https://hub.docker.com/repository/docker/rockchin/qchatgpt">
<img src="https://img.shields.io/docker/pulls/rockchin/qchatgpt?color=blue" alt="docker pull">
</a>
![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)
<img src="https://img.shields.io/badge/python-3.9+-blue.svg" alt="python">
<a href="https://github.com/RockChinQ/QChatGPT/wiki">
<img alt="Static Badge" src="https://img.shields.io/badge/%E6%9F%A5%E7%9C%8B-%E9%A1%B9%E7%9B%AEWiki-blue">
</a><br/>
<a href="http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=66-aWvn8cbP4c1ut_1YYkvvGVeEtyTH8&authKey=pTaKBK5C%2B8dFzQ4XlENf6MHTCLaHnlKcCRx7c14EeVVlpX2nRSaS8lJm8YeM4mCU&noverify=0&group_code=195992197">
<img alt="Static Badge" src="https://img.shields.io/badge/%E5%AE%98%E6%96%B9%E7%BE%A4-195992197-purple">
</a>
<a href="http://qm.qq.com/cgi-bin/qm/qr?_wv=1027&k=nC80H57wmKPwRDLFeQrDDjVl81XuC21P&authKey=2wTUTfoQ5v%2BD4C5zfpuR%2BSPMDqdXgDXA%2FS2wHI1NxTfWIG%2B%2FqK08dgyjMMOzhXa9&noverify=0&group_code=738382634">
<img alt="Static Badge" src="https://img.shields.io/badge/%E7%A4%BE%E5%8C%BA%E7%BE%A4-738382634-purple">
</a>
<a href="https://qchatgpt.rockchin.top">
<img alt="Static Badge" src="https://img.shields.io/badge/%E6%9F%A5%E7%9C%8B-%E7%A4%BE%E5%8C%BA%E7%BC%96%E5%86%99%E4%BD%BF%E7%94%A8%E6%89%8B%E5%86%8C-blue">
</a>
<a href="https://www.bilibili.com/video/BV14h4y1w7TC">
<img alt="Static Badge" src="https://img.shields.io/badge/%E8%A7%86%E9%A2%91%E6%95%99%E7%A8%8B-208647">
</a>
<a href="https://www.bilibili.com/video/BV11h4y1y74H">
<img alt="Static Badge" src="https://img.shields.io/badge/Linux%E9%83%A8%E7%BD%B2%E8%A7%86%E9%A2%91-208647">
</a>
## 🍺模型适配一览
<details>
<summary>点击此处展开</summary>
<summary>回复效果演示(带有联网插件)</summary>
<img alt="联网演示GIF" src="res/webwlkr-demo.gif" width="300px">
</details>
</div>
> **NOTE**
> 2023/9/13 现已支持通过[One API](https://github.com/songquanpeng/one-api)接入 Azure、Anthropic Claude、Google PaLM 2、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问以及 360 智脑等模型,欢迎测试并反馈。
> 2023/8/29 [逆向库插件](https://github.com/RockChinQ/revLibs)已支持 gpt4free
> 2023/8/14 [逆向库插件](https://github.com/RockChinQ/revLibs)已支持Claude和Bard
> 2023/7/29 支持使用GPT的Function Calling功能实现类似ChatGPT Plugin的效果请见[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/6-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)
<details>
<summary>
## 🍺模型一览和功能点
</summary>
### 文字对话
@@ -27,6 +63,15 @@
- ChatGPT网页版GPT-3.5模型, 由[插件](https://github.com/RockChinQ/revLibs)接入
- ChatGPT网页版GPT-4模型, 目前需要ChatGPT Plus订阅, 由[插件](https://github.com/RockChinQ/revLibs)接入
- New Bing逆向库, 由[插件](https://github.com/RockChinQ/revLibs)接入
- HuggingChat, 由[插件](https://github.com/RockChinQ/revLibs)接入, 仅支持英文
- Claude, 由[插件](https://github.com/RockChinQ/revLibs)接入
- Google Bard, 由[插件](https://github.com/RockChinQ/revLibs)接入
### 模型聚合平台
- [One API](https://github.com/songquanpeng/one-api), Azure、Anthropic Claude、Google PaLM 2、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问以及 360 智脑等模型的官方接口转换成 OpenAI API 接入QChatGPT 原生支持,您需要先配置 One API之后在`config.py`中设置反向代理和`One API`的密钥后使用。
- [gpt4free](https://github.com/xtekky/gpt4free), 破解以免费使用多个平台的各种文字模型, 由[插件](https://github.com/RockChinQ/revLibs)接入, 无需鉴权, 稳定性较差。
- [Poe](https://poe.com), 破解免费使用Poe上多个平台的模型, 由[oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot)接入(由于 Poe 上可用的大部分模型现已通过[revLibs插件](https://github.com/RockChinQ/revLubs)或其他方式接入,此插件现已停止维护)。
### 故事续写
@@ -34,7 +79,7 @@
### 图片绘制
- OpenAI DALL·E模型, 本项目原生支持, 使用方法查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
- OpenAI DALL·E模型, 本项目原生支持, 使用方法查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
- NovelAI API, 由[插件](https://github.com/dominoar/QCPNovelAi)接入
### 语音生成
@@ -43,12 +88,9 @@
- Plachta/VITS-Umamusume-voice-synthesizer, 由[插件](https://github.com/oliverkirk-sudo/chat_voice)接入
</details>
安装[此插件](https://github.com/RockChinQ/Switcher),即可在使用中切换文字模型。
## 功能
<details>
<summary>点击此处展开概述</summary>
### 功能
<details>
<summary>✅支持敏感词过滤,避免账号风险</summary>
@@ -75,30 +117,31 @@
</details>
<details>
<summary>✅支持预设指令文字</summary>
<summary>✅支持预设文字</summary>
- 支持以自然语言预设文字,自定义机器人人格等信息
- 详见`config.py`中的`default_prompt`部分
- 支持设置多个预设情景,并通过!reset、!default等令控制,详细请查看[wiki](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)
- 支持设置多个预设情景,并通过!reset、!default等令控制,详细请查看[wiki](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)
</details>
<details>
<summary>✅支持对话、绘图等模型,可玩性更高</summary>
- 现已支持OpenAI的对话`Completion API`和绘图`Image API`
- 向机器人发送`!draw <prompt>`即可使用绘图模型
- 向机器人发送`!draw <prompt>`即可使用绘图模型
</details>
<details>
<summary>✅支持令控制热重载、热更新</summary>
<summary>✅支持令控制热重载、热更新</summary>
- 允许在运行期间修改`config.py`或其他代码后,以管理员账号向机器人发送`!reload`进行热重载,无需重启
- 运行期间允许以管理员账号向机器人发送`!update`进行热更新,拉取远程最新代码并执行热重载
- 允许在运行期间修改`config.py`或其他代码后,以管理员账号向机器人发送`!reload`进行热重载,无需重启
- 运行期间允许以管理员账号向机器人发送`!update`进行热更新,拉取远程最新代码并执行热重载
</details>
<details>
<summary>✅支持插件加载🧩</summary>
- 自行实现插件加载器及相关支持
- 详细查看[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
- 支持GPT的Function Calling功能
- 详细查看[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/5-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
</details>
<details>
<summary>✅私聊、群聊黑名单机制</summary>
@@ -127,16 +170,43 @@
- 目前已支持正向代理访问接口
- 详细请查看config.py中的`openai_config`的说明
</details>
<details>
<summary>✅支持自定义提示内容</summary>
- 允许用户自定义报错、帮助等提示信息
- 请查看`tips.py`
</details>
详情请查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
### 🏞️截图
## 🔩部署
<img alt="私聊GPT-3.5" src="res/screenshots/person_gpt3.5.png" width="400"/>
<br/>
<img alt="群聊GPT-3.5" src="res/screenshots/group_gpt3.5.png" width="400"/>
<br/>
<img alt="New Bing" src="res/screenshots/person_newbing.png" width="400"/>
**部署过程中遇到任何问题,请先在[QChatGPT](https://github.com/RockChinQ/QChatGPT/issues)或[qcg-installer](https://github.com/RockChinQ/qcg-installer/issues)的issue里进行搜索**
详情请查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8)
</details>
<details>
<summary>
## 🚀部署和使用
</summary>
> **NOTE**
> - 部署过程中遇到任何问题,请先在[QChatGPT](https://github.com/RockChinQ/QChatGPT/issues)或[qcg-installer](https://github.com/RockChinQ/qcg-installer/issues)的issue里进行搜索
> - QChatGPT需要Python版本>=3.9
> - 官方群和社区群群号请见文档顶部
### - 注册OpenAI账号
<details>
<summary>点此查看步骤</summary>
> 若您要直接使用非OpenAI的模型如New Bing可跳过此步骤直接进行之后的部署完成后按照相关插件的文档进行配置即可
参考以下文章自行注册
@@ -147,15 +217,18 @@
注册成功后请前往[个人中心查看](https://beta.openai.com/account/api-keys)api_key
完成注册后,使用以下自动化或手动部署步骤
### - 自动化部署
</details>
### - Docker或自动化部署
<details>
<summary>展开查看以下方式二选一Linux首选DockerWindows首选安装器</summary>
#### Docker方式
请查看[此文档](docker_deploy.md)
由[@mikumifa](https://github.com/mikumifa)贡献
> docker方式较为复杂若您不**熟悉**docker的操作及相关知识强烈建议您使用其他方式部署我们**不会且难以**解决您主机上多个容器的连接问题。
请查看[此文档](res/docs/docker_deployment.md)
#### 安装器方式
@@ -171,12 +244,29 @@
- 请使用Python 3.9.x以上版本
#### 配置Mirai
#### ① 配置QQ登录框架
按照[此教程](https://yiri-mirai.wybxc.cc/tutorials/01/configuration)配置Mirai及YiriMirai
启动mirai-console后使用`login`命令登录QQ账号保持mirai-console运行状态
目前支持mirai和go-cqhttp配置任意一个即可
#### 配置主程序
<details>
<summary>mirai</summary>
1. 按照[此教程](https://yiri-mirai.wybxc.cc/tutorials/01/configuration)配置Mirai及mirai-api-http
2. 启动mirai-console后使用`login`命令登录QQ账号保持mirai-console运行状态
3. 在下一步配置主程序时请在config.py中将`msg_source_adapter`设为`yirimirai`
</details>
<details>
<summary>go-cqhttp</summary>
1. 按照[此文档](https://github.com/RockChinQ/QChatGPT/wiki/9-go-cqhttp%E9%85%8D%E7%BD%AE)配置go-cqhttp
2. 启动go-cqhttp确保登录成功保持运行
3. 在下一步配置主程序时请在config.py中将`msg_source_adapter`设为`nakuru`
</details>
#### ② 配置主程序
1. 克隆此项目
@@ -188,7 +278,7 @@ cd QChatGPT
2. 安装依赖
```bash
pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow
pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk CallingGPT tiktoken
```
3. 运行一次主程序,生成配置文件
@@ -217,45 +307,57 @@ python3 main.py
</details>
## 🚀使用
**部署完成后必看: [命令说明](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)**
**部署完成后必看: [指令说明](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)**
所有功能查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E4%BD%BF%E7%94%A8%E6%96%B9%E5%BC%8F)
所有功能查看[Wiki功能使用页](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8)
</details>
<details>
<summary>
## 🧩插件生态
现已支持自行开发插件对功能进行扩展或自定义程序行为
详见[Wiki插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
开发教程见[Wiki插件开发页](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91)
</summary>
<details>
<summary>查看插件列表</summary>
⭐我们已经支持了[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling),请查看[Wiki内容函数](https://github.com/RockChinQ/QChatGPT/wiki/6-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0)
### 示例插件
> 使用方法见:[Wiki插件使用](https://github.com/RockChinQ/QChatGPT/wiki/5-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
> 开发教程见:[Wiki插件开发](https://github.com/RockChinQ/QChatGPT/wiki/7-%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91)
`tests/plugin_examples`目录下,将其整个目录复制到`plugins`目录下即可使用
- `cmdcn` - 主程序指令中文形式
- `hello_plugin` - 在收到消息`hello`时回复相应消息
- `urlikethisijustsix` - 收到冒犯性消息时回复相应消息
[所有插件列表](https://github.com/stars/RockChinQ/lists/qchatgpt-%E6%8F%92%E4%BB%B6)欢迎提出issue以提交新的插件
### 更多
### 部分插件
欢迎提交新的插件
- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E4%B8%8EChatGPT%E7%BD%91%E9%A1%B5%E7%89%88)
- [WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin) - 让机器人能联网!!
- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版、Claude、Bard、Hugging Chat等破解版接入此项目关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/8-%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E3%80%81ChatGPT%E7%BD%91%E9%A1%B5%E7%89%88%E3%80%81ChatGPT-API%E5%8C%BA%E5%88%AB)
- [Switcher](https://github.com/RockChinQ/Switcher) - 支持通过命令切换使用的模型
- [hello_plugin](https://github.com/RockChinQ/hello_plugin) - `hello_plugin` 的储存库形式,插件开发模板
- [dominoar/QChatPlugins](https://github.com/dominoar/QchatPlugins) - dominoar编写的诸多新功能插件语音输出、Ranimg、屏蔽词规则等
- [dominoar/QCP-NovelAi](https://github.com/dominoar/QCP-NovelAi) - NovelAI 故事叙述与绘画
- [oliverkirk-sudo/chat_voice](https://github.com/oliverkirk-sudo/chat_voice) - 文字转语音输出使用HuggingFace上的[VITS-Umamusume-voice-synthesizer模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer)
- [oliverkirk-sudo/chat_voice](https://github.com/oliverkirk-sudo/chat_voice) - 文字转语音输出支持HuggingFace上的[VITS模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer),azure语音合成,vits本地语音合成,sovits语音合成
- [RockChinQ/WaitYiYan](https://github.com/RockChinQ/WaitYiYan) - 实时获取百度`文心一言`等待列表人数
- [chordfish-k/QChartGPT_Emoticon_Plugin](https://github.com/chordfish-k/QChartGPT_Emoticon_Plugin) - 使机器人根据回复内容发送表情包
- [oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot) - 接入[Poe](https://poe.com/)上的机器人
- [lieyanqzu/WeatherPlugin](https://github.com/lieyanqzu/WeatherPlugin) - 天气查询插件
- [SysStatPlugin](https://github.com/RockChinQ/SysStatPlugin) - 查看系统状态
- [oliverkirk-sudo/qchat_system_status](https://github.com/oliverkirk-sudo/qchat_system_status) - 以图片的形式输出系统状态
- [oliverkirk-sudo/QChatAIPaint](https://github.com/oliverkirk-sudo/QChatAIPaint) - 基于[Holara](https://holara.ai/)的ai绘图插件
- [oliverkirk-sudo/QChatCodeRunner](https://github.com/oliverkirk-sudo/QChatCodeRunner) - 基于[CodeRunner-Plugin](https://github.com/oliverkirk-sudo/CodeRunner-Plugin)的代码运行与图表生成插件
- [oliverkirk-sudo/QChatWeather](https://github.com/oliverkirk-sudo/QChatWeather) - 生成好看的天气图片,基于和风天气
- [oliverkirk-sudo/QChatMarkdown](https://github.com/oliverkirk-sudo/QChatMarkdown) - 将机器人输出的markdown转换为图片基于[playwright](https://playwright.dev/python/docs/intro)
- [ruuuux/WikipediaSearch](https://github.com/ruuuux/WikipediaSearch) - Wikipedia 搜索插件
</details>
## 😘致谢
<details>
- [@the-lazy-me](https://github.com/the-lazy-me) 为本项目制作[视频教程](https://www.bilibili.com/video/BV15v4y1X7aP)
<summary>
## 😘致谢和赞赏
</summary>
- [@the-lazy-me](https://github.com/the-lazy-me) 为本项目制作[视频教程](https://www.bilibili.com/video/BV1Y14y1Q7kQ)
- [@mikumifa](https://github.com/mikumifa) 本项目Docker部署仓库开发者
- [@dominoar](https://github.com/dominoar) 为本项目开发多种插件
- [@万神的星空](https://github.com/qq255204159) 整合包发行
@@ -263,6 +365,6 @@ python3 main.py
以及所有[贡献者](https://github.com/RockChinQ/QChatGPT/graphs/contributors)和其他为本项目提供支持的朋友们。
<!-- ## 👍赞赏
<img alt="赞赏码" src="res/mm_reward_qrcode_1672840549070.png" width="400" height="400"/>
<img alt="赞赏码" src="res/mm_reward_qrcode_1672840549070.png" width="400" height="400"/> -->
</details>

215
README_en.md Normal file
View File

@@ -0,0 +1,215 @@
# QChatGPT🤖
<p align="center">
<img src="res/social.png" alt="QChatGPT" width="640" />
</p>
English | [简体中文](README.md)
[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
![Wakapi Count](https://wakapi.dev/api/badge/RockChinQ/interval:any/project:QChatGPT)
- Refer to [Wiki](https://github.com/RockChinQ/QChatGPT/wiki) to get further information.
- Official QQ group: 656285629
- Community QQ group: 362515018
- QQ channel robot: [QQChannelChatGPT](https://github.com/Soulter/QQChannelChatGPT)
- Any contribution is welcome, please refer to [CONTRIBUTING.md](CONTRIBUTING.md)
## 🍺List of supported models
<details>
<summary>Details</summary>
### Chat
- OpenAI GPT-3.5 (ChatGPT API), default model
- OpenAI GPT-3, supported natively, switch to it in `config.py`
- OpenAI GPT-4, supported natively, qualification for internal testing required, switch to it in `config.py`
- ChatGPT website edition (GPT-3.5), see [revLibs plugin](https://github.com/RockChinQ/revLibs)
- ChatGPT website edition (GPT-4), ChatGPT plus subscription required, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
- New Bing, see [revLibs plugin](https://github.com/RockChinQ/revLibs)
- HuggingChat, see [revLibs plugin](https://github.com/RockChinQ/revLibs), English only
### Story
- NovelAI API, see [QCPNovelAi plugin](https://github.com/dominoar/QCPNovelAi)
### Image
- OpenAI DALL·E, supported natively, see [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
- NovelAI API, see [QCPNovelAi plugin](https://github.com/dominoar/QCPNovelAi)
### Voice
- TTS+VITS, see [QChatPlugins](https://github.com/dominoar/QChatPlugins)
- Plachta/VITS-Umamusume-voice-synthesizer, see [chat_voice plugin](https://github.com/oliverkirk-sudo/chat_voice)
</details>
Install this [plugin](https://github.com/RockChinQ/Switcher) to switch between different models.
## ✅Function Points
<details>
<summary>Details</summary>
- ✅Sensitive word filtering, avoid being banned
- ✅Multiple responding rules, including regular expression matching
- ✅Multiple api-key management, automatic switching when exceeding
- ✅Support for customizing the preset prompt text
- ✅Chat, story, image, voice, etc. models are supported
- ✅Support for hot reloading and hot updating
- ✅Support for plugin loading
- ✅Blacklist mechanism for private chat and group chat
- ✅Excellent long message processing strategy
- ✅Reply rate limitation
- ✅Support for network proxy
- ✅Support for customizing the output format
</details>
More details, see [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%8A%9F%E8%83%BD%E7%82%B9%E5%88%97%E4%B8%BE)
## 🔩Deployment
**If you encounter any problems during deployment, please search in the issue of [QChatGPT](https://github.com/RockChinQ/QChatGPT/issues) or [qcg-installer](https://github.com/RockChinQ/qcg-installer/issues) first.**
### - Register OpenAI account
> If you want to use a model other than OpenAI (such as New Bing), you can skip this step and directly refer to following steps, and then configure it according to the relevant plugin documentation.
To register OpenAI account, please refer to the following articles(in Chinese):
> [国内注册ChatGPT的方法(100%可用)](https://www.pythonthree.com/register-openai-chatgpt/)
> [手把手教你如何注册ChatGPT超级详细](https://guxiaobei.com/51461)
Check your api-key in [personal center](https://beta.openai.com/account/api-keys) after registration, and then follow the following steps to deploy.
### - Deploy Automatically
<details>
<summary>Details</summary>
#### Docker
See [this document(cn)](res/docs/docker_deploy.md)
Contributed by [@mikumifa](https://github.com/mikumifa)
#### Installer
Use [this installer](https://github.com/RockChinQ/qcg-installer) to deploy.
- The installer currently only supports some platforms, please refer to the repository document for details, and manually deploy for other platforms
</details>
### - Deploy Manually
<details>
<summary>Manually deployment supports any platforms</summary>
- Python 3.9.x or higher
#### 配置QQ登录框架
Currently supports mirai and go-cqhttp, configure either one
<details>
<summary>mirai</summary>
Follow [this tutorial(cn)](https://yiri-mirai.wybxc.cc/tutorials/01/configuration) to configure Mirai and YiriMirai.
After starting mirai-console, use the `login` command to log in to the QQ account, and keep the mirai-console running.
</details>
<details>
<summary>go-cqhttp</summary>
1. Follow [this tutorial(cn)](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE) to configure go-cqhttp.
2. Start go-cqhttp, make sure it is logged in and running.
</details>
#### Configure QChatGPT
1. Clone the repository
```bash
git clone https://github.com/RockChinQ/QChatGPT
cd QChatGPT
```
2. Install dependencies
```bash
pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk
```
3. Generate `config.py`
```bash
python3 main.py
```
4. Edit `config.py`
5. Run
```bash
python3 main.py
```
Any problems, please refer to the issues page.
</details>
## 🚀Usage
**After deployment, please read: [Commands(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4)**
**For more details, please refer to the [Wiki(cn)](https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E4%BD%BF%E7%94%A8%E6%96%B9%E5%BC%8F)**
## 🧩Plugin Ecosystem
Plugin [usage](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8) and [development](https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E5%BC%80%E5%8F%91) are supported.
<details>
<summary>List of plugins (cn)</summary>
### Examples
`tests/plugin_examples`目录下,将其整个目录复制到`plugins`目录下即可使用
- `cmdcn` - 主程序指令中文形式
- `hello_plugin` - 在收到消息`hello`时回复相应消息
- `urlikethisijustsix` - 收到冒犯性消息时回复相应消息
### More Plugins
欢迎提交新的插件
- [revLibs](https://github.com/RockChinQ/revLibs) - 将ChatGPT网页版接入此项目关于[官方接口和网页版有什么区别](https://github.com/RockChinQ/QChatGPT/wiki/%E5%AE%98%E6%96%B9%E6%8E%A5%E5%8F%A3%E4%B8%8EChatGPT%E7%BD%91%E9%A1%B5%E7%89%88)
- [Switcher](https://github.com/RockChinQ/Switcher) - 支持通过指令切换使用的模型
- [hello_plugin](https://github.com/RockChinQ/hello_plugin) - `hello_plugin` 的储存库形式,插件开发模板
- [dominoar/QChatPlugins](https://github.com/dominoar/QchatPlugins) - dominoar编写的诸多新功能插件语音输出、Ranimg、屏蔽词规则等
- [dominoar/QCP-NovelAi](https://github.com/dominoar/QCP-NovelAi) - NovelAI 故事叙述与绘画
- [oliverkirk-sudo/chat_voice](https://github.com/oliverkirk-sudo/chat_voice) - 文字转语音输出使用HuggingFace上的[VITS-Umamusume-voice-synthesizer模型](https://huggingface.co/spaces/Plachta/VITS-Umamusume-voice-synthesizer)
- [RockChinQ/WaitYiYan](https://github.com/RockChinQ/WaitYiYan) - 实时获取百度`文心一言`等待列表人数
- [chordfish-k/QChartGPT_Emoticon_Plugin](https://github.com/chordfish-k/QChartGPT_Emoticon_Plugin) - 使机器人根据回复内容发送表情包
- [oliverkirk-sudo/ChatPoeBot](https://github.com/oliverkirk-sudo/ChatPoeBot) - 接入[Poe](https://poe.com/)上的机器人
- [lieyanqzu/WeatherPlugin](https://github.com/lieyanqzu/WeatherPlugin) - 天气查询插件
</details>
## 😘Thanks
- [@the-lazy-me](https://github.com/the-lazy-me) video tutorial creator
- [@mikumifa](https://github.com/mikumifa) Docker deployment
- [@dominoar](https://github.com/dominoar) Plugin development
- [@万神的星空](https://github.com/qq255204159) Packages publisher
- [@ljcduo](https://github.com/ljcduo) GPT-4 API internal test account
And all [contributors](https://github.com/RockChinQ/QChatGPT/graphs/contributors) and other friends who support this project.
<!-- ## 👍赞赏
<img alt="赞赏码" src="res/mm_reward_qrcode_1672840549070.png" width="400" height="400"/> -->

View File

@@ -1,7 +1,13 @@
# 配置文件: 注释里标[必需]的参数必须修改, 其他参数根据需要修改, 但请勿删除
import logging
# [必需] Mirai的配置
# 消息处理协议适配器
# 目前支持以下适配器:
# - "yirimirai": mirai的通信框架YiriMirai框架适配器, 请同时填写下方mirai_http_api_config
# - "nakuru": go-cqhttp通信框架请同时填写下方nakuru_config
msg_source_adapter = "yirimirai"
# [必需(与nakuru二选一取决于msg_source_adapter)] Mirai的配置
# 请到配置mirai的步骤中的教程查看每个字段的信息
# adapter: 选择适配器目前支持HTTPAdapter和WebSocketAdapter
# host: 运行mirai的主机地址
@@ -18,6 +24,15 @@ mirai_http_api_config = {
"qq": 1234567890
}
# [必需(与mirai二选一取决于msg_source_adapter)]
# 使用nakuru-project框架连接go-cqhttp的配置
nakuru_config = {
"host": "localhost", # go-cqhttp的地址
"port": 6700, # go-cqhttp的正向websocket端口
"http_port": 5700, # go-cqhttp的正向http端口
"token": "" # 若在go-cqhttp的config.yml设置了access_token, 则填写此处
}
# [必需] OpenAI的配置
# api_key: OpenAI的API Key
# http_proxy: 请求OpenAI时使用的代理None为不使用https和socks5暂不能使用
@@ -33,9 +48,9 @@ mirai_http_api_config = {
# },
# "http_proxy": "http://127.0.0.1:12345"
# }
#
#
# 现已支持反向代理可以添加reverse_proxy字段以使用反向代理
# 使用反向代理可以在国内使用OpenAI的API反向代理的配置请参考
# 使用反向代理可以在国内使用OpenAI的API反向代理的配置请参考
# https://github.com/Ice-Hazymoon/openai-scf-proxy
#
# 反向代理填写示例:
@@ -47,6 +62,9 @@ mirai_http_api_config = {
# },
# "reverse_proxy": "http://example.com:12345/v1"
# }
#
# 作者开设公用反向代理地址: https://api.openai.rockchin.top/v1
# 随时可能关闭,仅供测试使用,有条件建议使用正向代理或者自建反向代理
openai_config = {
"api_key": {
"default": "openai_api_key"
@@ -55,6 +73,11 @@ openai_config = {
"reverse_proxy": None
}
# api-key切换策略
# active每次请求时都会切换api-key
# passive仅当api-key超额时才会切换api-key
switch_strategy = "active"
# [必需] 管理员QQ号用于接收报错等通知及执行管理员级别指令
# 支持多个管理员可以使用list形式设置例如
# admin_qq = [12345678, 87654321]
@@ -63,7 +86,7 @@ admin_qq = 0
# 情景预设(机器人人格)
# 每个会话的预设信息,影响所有会话,无视指令重置
# 可以通过这个字段指定某些情况的回复,可直接用自然语言描述指令
# 例如:
# 例如:
# default_prompt = "如果我之后想获取帮助,请你说“输入!help获取帮助”"
# 这样用户在不知所措的时候机器人就会提示其输入!help获取帮助
# 可参考 https://github.com/PlexPt/awesome-chatgpt-prompts-zh
@@ -81,14 +104,14 @@ admin_qq = 0
# 例如:
# !reset linux-terminal
# 若不指定名称,则使用默认情景预设
#
#
# 也可以使用指令:
# !default <名称>
# 将指定的情景预设设置为默认情景预设
# 例如:
# !default linux-terminal
# 之后的会话重置时若不指定名称则使用linux-terminal情景预设
#
#
# 还可以加载文件中的预设文字使用方法请查看https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E9%A2%84%E8%AE%BE%E6%96%87%E5%AD%97
default_prompt = {
"default": "如果我之后想获取帮助,请你说“输入!help获取帮助”",
@@ -108,13 +131,35 @@ preset_mode = "normal"
# 注意:由消息前缀(prefix)匹配的消息中将会删除此前缀,正则表达式(regexp)匹配的消息不会删除匹配的部分
# 前缀匹配优先级高于正则表达式匹配
# 正则表达式简明教程https://www.runoob.com/regexp/regexp-tutorial.html
#
# 支持针对不同群设置不同的响应规则,例如:
# response_rules = {
# "default": {
# "at": True,
# "prefix": ["/ai", "!ai", "ai", "ai"],
# "regexp": [],
# "random_rate": 0.0,
# },
# "12345678": {
# "at": False,
# "prefix": ["/ai", "!ai", "ai", "ai"],
# "regexp": [],
# "random_rate": 0.0,
# },
# }
#
# 以上设置将会在群号为12345678的群中关闭at响应
# 未单独设置的群将使用default规则
response_rules = {
"at": True, # 是否响应at机器人的消息
"prefix": ["/ai", "!ai", "ai", "ai"],
"regexp": [], # "为什么.*", "怎么?样.*", "怎么.*", "如何.*", "[Hh]ow to.*", "[Ww]hy not.*", "[Ww]hat is.*", ".*怎么办", ".*咋办"
"random_rate": 0.0, # 随机响应概率0.0-1.00.0为不随机响应1.0为响应所有消息, 仅在前几项判断不通过时生效
"default": {
"at": True, # 是否响应at机器人的消息
"prefix": ["/ai", "!ai", "ai", "ai"],
"regexp": [], # "为什么.*", "怎么?样.*", "怎么.*", "如何.*", "[Hh]ow to.*", "[Ww]hy not.*", "[Ww]hat is.*", ".*怎么办", ".*咋办"
"random_rate": 0.0, # 随机响应概率0.0-1.00.0为不随机响应1.0为响应所有消息, 仅在前几项判断不通过时生效
},
}
# 消息忽略规则
# 适用于私聊及群聊
# 符合此规则的消息将不会被响应
@@ -157,32 +202,61 @@ encourage_sponsor_at_start = True
# 注意较大的prompt_submit_length会导致OpenAI账户额度消耗更快
prompt_submit_length = 2048
# 是否在token超限报错时自动重置会话
# 可在tips.py中编辑提示语
auto_reset = True
# OpenAI补全API的参数
# 请在下方填写模型,程序自动选择接口
# 模型文档https://platform.openai.com/docs/models
# 现已支持的模型有:
#
# 'gpt-4'
# 'gpt-4-0314'
# 'gpt-4-32k'
# 'gpt-4-32k-0314'
# 'gpt-3.5-turbo'
# 'gpt-3.5-turbo-0301'
# 'text-davinci-003'
# 'text-davinci-002'
# 'code-davinci-002'
# 'code-cushman-001'
# 'text-curie-001'
# 'text-babbage-001'
# 'text-ada-001'
#
# ChatCompletions 接口:
# # GPT 4 系列
# "gpt-4-1106-preview",
# "gpt-4-vision-preview",
# "gpt-4",
# "gpt-4-32k",
# "gpt-4-0613",
# "gpt-4-32k-0613",
# "gpt-4-0314", # legacy
# "gpt-4-32k-0314", # legacy
# # GPT 3.5 系列
# "gpt-3.5-turbo-1106",
# "gpt-3.5-turbo",
# "gpt-3.5-turbo-16k",
# "gpt-3.5-turbo-0613", # legacy
# "gpt-3.5-turbo-16k-0613", # legacy
# "gpt-3.5-turbo-0301", # legacy
#
# Completions接口
# "text-davinci-003", # legacy
# "text-davinci-002", # legacy
# "code-davinci-002", # legacy
# "code-cushman-001", # legacy
# "text-curie-001", # legacy
# "text-babbage-001", # legacy
# "text-ada-001", # legacy
# "gpt-3.5-turbo-instruct",
#
# 具体请查看OpenAI的文档: https://beta.openai.com/docs/api-reference/completions/create
# 请将内容修改到config.py中请勿修改config-template.py
#
# 支持通过 One API 接入多种模型请在上方的openai_config中设置One API的代理地址
# 并在此填写您要使用的模型名称详细请参考https://github.com/songquanpeng/one-api
#
# 支持的 One API 模型:
# "SparkDesk",
# "chatglm_pro",
# "chatglm_std",
# "chatglm_lite",
# "qwen-v1",
# "qwen-plus-v1",
# "ERNIE-Bot",
# "ERNIE-Bot-turbo",
completion_api_params = {
"model": "gpt-3.5-turbo",
"temperature": 0.9, # 数值越低得到的回答越理性,取值范围[0, 1]
"top_p": 1, # 生成的文本的文本与要求的符合度, 取值范围[0, 1]
"frequency_penalty": 0.2,
"presence_penalty": 1.0,
}
# OpenAI的Image API的参数
@@ -191,18 +265,34 @@ image_api_params = {
"size": "256x256", # 图片尺寸支持256x256, 512x512, 1024x1024
}
# 跟踪函数调用
# 为True时在每次GPT进行Function Calling时都会输出发送一条回复给用户
# 同时一次提问内所有的Function Calling和普通回复消息都会单独发送给用户
trace_function_calls = False
# 群内回复消息时是否引用原消息
quote_origin = True
quote_origin = False
# 群内回复消息时是否at发送者
at_sender = False
# 回复绘图时是否包含图片描述
include_image_description = True
# 消息处理的超时时间,单位为秒
process_message_timeout = 30
process_message_timeout = 120
# 回复消息时是否显示[GPT]前缀
show_prefix = False
# 回复前的强制延迟时间,降低机器人被腾讯风控概率
# *此机制对命令和消息、私聊及群聊均生效
# 每次处理时从以下的范围取一个随机秒数,
# 当此次消息处理时间低于此秒数时,将会强制延迟至此秒数
# 例如:[1.5, 3]则每次处理时会随机取一个1.5-3秒的随机数若处理时间低于此随机数则强制延迟至此随机秒数
# 若您不需要此功能请将force_delay_range设置为[0, 0]
force_delay_range = [1.5, 3]
# 应用长消息处理策略的阈值
# 当回复消息长度超过此值时,将使用长消息处理策略
blob_message_threshold = 256
@@ -212,6 +302,12 @@ blob_message_threshold = 256
# - "forward": 将长消息转换为转发消息组件发送
blob_message_strategy = "forward"
# 允许等待
# 同一会话内,是否等待上一条消息处理完成后再处理下一条消息
# 若设置为False若上一条未处理完时收到了新消息将会丢弃新消息
# 丢弃消息时的提示信息可以在tips.py中修改
wait_last_done = True
# 文字转图片时使用的字体文件路径
# 当策略为"image"时生效
# 若在Windows系统下程序会自动使用Windows自带的微软雅黑字体
@@ -226,11 +322,6 @@ retry_times = 3
# 设置为False时向用户及管理员发送错误详细信息
hide_exce_info_to_user = False
# 消息处理出错时向用户发送的提示信息
# 仅当hide_exce_info_to_user为True时生效
# 设置为空字符串时,不发送提示信息
alter_tip_message = '出错了,请稍后再试'
# 线程池相关配置
# 该参数决定机器人可以同时处理几个人的消息,超出线程池数量的请求会被阻塞,不会被丢弃
# 如果你不清楚该参数的意义,请不要更改
@@ -238,34 +329,52 @@ alter_tip_message = '出错了,请稍后再试'
sys_pool_num = 8
# 执行管理员请求和指令的线程池并行线程数量,一般和管理员数量相等
admin_pool_num = 2
admin_pool_num = 4
# 执行用户请求和指令的线程池并行线程数量
# 如需要更高的并发,可以增大该值
user_pool_num = 6
user_pool_num = 8
# 每个会话的过期时间,单位为秒
# 默认值20分钟
session_expire_time = 60 * 20
session_expire_time = 1200
# 会话限速
# 单会话内每分钟可进行的对话次数
# 若不需要限速,可以设置为一个很大的值
# 默认值60次基本上不会触发限速
rate_limitation = 60
#
# 若要设置针对某特定群的限速,请使用如下格式:
# {
# "group_<群号>": 60,
# "default": 60,
# }
# 若要设置针对某特定用户私聊的限速,请使用如下格式:
# {
# "person_<用户QQ>": 60,
# "default": 60,
# }
# 同时设置多个群和私聊的限速,示例:
# {
# "group_12345678": 60,
# "group_87654321": 60,
# "person_234567890": 60,
# "person_345678901": 60,
# "default": 60,
# }
#
# 注意: 未指定的都使用default的限速值default不可删除
rate_limitation = {
"default": 60,
}
# 会话限速策略
# - "wait": 每次对话获取到回复时,等待一定时间再发送回复,保证其不会超过限速均值
# - "drop": 此分钟内,若对话次数超过限速次数,则丢弃之后的对话,每自然分钟重置
rate_limit_strategy = "wait"
# drop策略时超过限速均值时丢弃的对话的提示信息
# 仅当rate_limitation_strategy为"drop"时生效
# 若设置为空字符串,则不发送提示信息
rate_limit_drop_tip = "本分钟对话次数超过限速次数,此对话被丢弃"
rate_limit_strategy = "drop"
# 是否在启动时进行依赖库更新
upgrade_dependencies = True
upgrade_dependencies = False
# 是否上报统计信息
# 用于统计机器人的使用情况,不会收集任何用户信息
@@ -274,13 +383,3 @@ report_usage = True
# 日志级别
logging_level = logging.INFO
# 定制帮助消息
help_message = """此机器人通过调用OpenAI的GPT-3大型语言模型生成回复不具有情感。
你可以用自然语言与其交流,回复的消息中[GPT]开头的为模型生成的语言,[bot]开头的为程序提示。
了解此项目请找QQ 1010553892 联系作者
请不要用其生成整篇文章或大段代码,因为每次只会向模型提交少部分文字,生成大部分文字会产生偏题、前后矛盾等问题
每次会话最后一次交互后{}分钟后会自动结束,结束后将开启新会话,如需继续前一次会话请发送 !last 重新开启
欢迎到github.com/RockChinQ/QChatGPT 给个star
指令帮助信息请查看: https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4""".format(session_expire_time // 60)

18
docker-compose.yaml Normal file
View File

@@ -0,0 +1,18 @@
version: "3"
services:
qchatgpt:
image: rockchin/qchatgpt:latest
volumes:
- ./config.py:/QChatGPT/config.py
- ./banlist.py:/QChatGPT/banlist.py
- ./cmdpriv.json:/QChatGPT/cmdpriv.json
- ./sensitive.json:/QChatGPT/sensitive.json
- ./tips.py:/QChatGPT/tips.py
# 目录映射
- ./plugins:/QChatGPT/plugins
- ./scenario:/QChatGPT/scenario
- ./temp:/QChatGPT/temp
- ./logs:/QChatGPT/logs
restart: always
# 根据具体环境配置网络

397
main.py
View File

@@ -11,6 +11,8 @@ import traceback
sys.path.append(".")
from pkg.utils.log import init_runtime_log_file, reset_logging
try:
import colorlog
except ImportError:
@@ -18,6 +20,7 @@ except ImportError:
import pkg.utils.pkgmgr as pkgmgr
try:
pkgmgr.install_requirements("requirements.txt")
pkgmgr.install_upgrade("websockets")
import colorlog
except ImportError:
print("依赖不满足,请查看 https://github.com/RockChinQ/qcg-installer/issues/15")
@@ -30,13 +33,9 @@ from urllib3.exceptions import InsecureRequestWarning
import pkg.utils.context
log_colors_config = {
'DEBUG': 'green', # cyan white
'INFO': 'white',
'WARNING': 'yellow',
'ERROR': 'red',
'CRITICAL': 'cyan',
}
# 是否使用override.json覆盖配置
# 仅在启动时提供 --override 或 -r 参数时生效
use_override = False
def init_db():
@@ -48,97 +47,83 @@ def init_db():
def ensure_dependencies():
import pkg.utils.pkgmgr as pkgmgr
pkgmgr.run_pip(["install", "openai", "Pillow", "--upgrade",
"-i", "https://pypi.douban.com/simple/",
"--trusted-host", "pypi.douban.com"])
pkgmgr.run_pip(["install", "openai", "Pillow", "nakuru-project-idk", "CallingGPT", "tiktoken", "--upgrade",
"-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
"--trusted-host", "pypi.tuna.tsinghua.edu.cn"])
known_exception_caught = False
log_file_name = "qchatgpt.log"
def init_runtime_log_file():
"""为此次运行生成日志文件
格式: qchatgpt-yyyy-MM-dd-HH-mm-ss.log
"""
global log_file_name
# 检查logs目录是否存在
if not os.path.exists("logs"):
os.mkdir("logs")
# 检查本目录是否有qchatgpt.log若有移动到logs目录
if os.path.exists("qchatgpt.log"):
shutil.move("qchatgpt.log", "logs/qchatgpt.legacy.log")
log_file_name = "logs/qchatgpt-%s.log" % time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
def reset_logging():
global log_file_name
def override_config():
import config
if pkg.utils.context.context['logger_handler'] is not None:
logging.getLogger().removeHandler(pkg.utils.context.context['logger_handler'])
for handler in logging.getLogger().handlers:
logging.getLogger().removeHandler(handler)
logging.basicConfig(level=config.logging_level, # 设置日志输出格式
filename=log_file_name, # log日志输出的文件位置和文件名
format="[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : %(message)s",
# 日志输出的格式
# -8表示占位符让输出左对齐输出长度都为8位
datefmt="%Y-%m-%d %H:%M:%S" # 时间输出的格式
)
sh = logging.StreamHandler()
sh.setLevel(config.logging_level)
sh.setFormatter(colorlog.ColoredFormatter(
fmt="%(log_color)s[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : "
"%(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
log_colors=log_colors_config
))
logging.getLogger().addHandler(sh)
pkg.utils.context.context['logger_handler'] = sh
return sh
# 检查override.json覆盖
if os.path.exists("override.json") and use_override:
override_json = json.load(open("override.json", "r", encoding="utf-8"))
overrided = []
for key in override_json:
if hasattr(config, key):
setattr(config, key, override_json[key])
# logging.info("覆写配置[{}]为[{}]".format(key, override_json[key]))
overrided.append(key)
else:
logging.error("无法覆写配置[{}]为[{}]该配置不存在请检查override.json是否正确".format(key, override_json[key]))
if len(overrided) > 0:
logging.info("已根据override.json覆写配置项: {}".format(", ".join(overrided)))
# 临时函数用于加载config和上下文未来统一放在config类
def load_config():
logging.info("检查config模块完整性.")
# 完整性校验
non_exist_keys = []
is_integrity = True
config_template = importlib.import_module('config-template')
config = importlib.import_module('config')
for key in dir(config_template):
if not key.startswith("__") and not hasattr(config, key):
setattr(config, key, getattr(config_template, key))
logging.warning("[{}]不存在".format(key))
# logging.warning("[{}]不存在".format(key))
non_exist_keys.append(key)
is_integrity = False
if not is_integrity:
logging.warning("配置文件不完整请依据config-template.py检查config.py")
logging.warning("以下配置字段不存在: {}".format(", ".join(non_exist_keys)))
# 检查override.json覆盖
if os.path.exists("override.json"):
override_json = json.load(open("override.json", "r", encoding="utf-8"))
for key in override_json:
if hasattr(config, key):
setattr(config, key, override_json[key])
logging.info("覆写配置[{}]为[{}]".format(key, override_json[key]))
else:
logging.error("无法覆写配置[{}]为[{}]该配置不存在请检查override.json是否正确".format(key, override_json[key]))
override_config()
if not is_integrity:
logging.warning("以上配置已被设为默认值,将在5秒后继续启动... ")
time.sleep(5)
logging.warning("以上不存在的配置已被设为默认值,您可以依据config-template.py检查config.py将在3秒后继续启动... ")
time.sleep(3)
# 存进上下文
pkg.utils.context.set_config(config)
def complete_tips():
"""根据tips-custom-template模块补全tips模块的属性"""
non_exist_keys = []
is_integrity = True
logging.info("检查tips模块完整性.")
tips_template = importlib.import_module('tips-custom-template')
tips = importlib.import_module('tips')
for key in dir(tips_template):
if not key.startswith("__") and not hasattr(tips, key):
setattr(tips, key, getattr(tips_template, key))
# logging.warning("[{}]不存在".format(key))
non_exist_keys.append(key)
is_integrity = False
if not is_integrity:
logging.warning("以下提示语字段不存在: {}".format(", ".join(non_exist_keys)))
logging.warning("tips模块不完整您可以依据tips-custom-template.py检查tips.py")
logging.warning("以上配置已被设为默认值将在3秒后继续启动... ")
time.sleep(3)
def start(first_time_init=False):
"""启动流程reload之后会被执行"""
@@ -160,126 +145,147 @@ def start(first_time_init=False):
known_exception_caught = False
try:
sh = reset_logging()
pkg.utils.context.context['logger_handler'] = sh
# 检查是否设置了管理员
if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
# logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
while True:
try:
config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
# 写入到文件
# 读取文件
config_file_str = ""
with open("config.py", "r", encoding="utf-8") as f:
config_file_str = f.read()
# 替换
config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
# 写入
with open("config.py", "w", encoding="utf-8") as f:
f.write(config_file_str)
print("管理员QQ已设置如需修改请修改config.py中的admin_qq字段")
time.sleep(4)
break
except ValueError:
print("请输入数字")
import pkg.openai.manager
import pkg.database.manager
import pkg.openai.session
import pkg.qqbot.manager
import pkg.openai.dprompt
import pkg.qqbot.cmds.mgr
try:
pkg.openai.dprompt.register_all()
pkg.qqbot.cmds.mgr.register_all()
pkg.qqbot.cmds.mgr.apply_privileges()
except Exception as e:
logging.error(e)
traceback.print_exc()
# 配置openai api_base
if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
sh = reset_logging()
pkg.utils.context.context['logger_handler'] = sh
# 检查是否设置了管理员
if not (hasattr(config, 'admin_qq') and config.admin_qq != 0):
# logging.warning("未设置管理员QQ,管理员权限指令及运行告警将无法使用,如需设置请修改config.py中的admin_qq字段")
while True:
try:
config.admin_qq = int(input("未设置管理员QQ,管理员权限指令及运行告警将无法使用,请输入管理员QQ号: "))
# 写入到文件
# 读取文件
config_file_str = ""
with open("config.py", "r", encoding="utf-8") as f:
config_file_str = f.read()
# 替换
config_file_str = config_file_str.replace("admin_qq = 0", "admin_qq = " + str(config.admin_qq))
# 写入
with open("config.py", "w", encoding="utf-8") as f:
f.write(config_file_str)
print("管理员QQ已设置如需修改请修改config.py中的admin_qq字段")
time.sleep(4)
break
except ValueError:
print("请输入数字")
import pkg.openai.manager
import pkg.database.manager
import pkg.openai.session
import pkg.qqbot.manager
import pkg.openai.dprompt
import pkg.qqbot.cmds.aamgr
try:
pkg.openai.dprompt.register_all()
pkg.qqbot.cmds.aamgr.register_all()
pkg.qqbot.cmds.aamgr.apply_privileges()
except Exception as e:
logging.error(e)
traceback.print_exc()
# 配置OpenAI proxy
import openai
openai.api_base = config.openai_config["reverse_proxy"]
openai.proxies = None # 先重置因为重载后可能需要清除proxy
if "http_proxy" in config.openai_config and config.openai_config["http_proxy"] is not None:
openai.proxies = {
"http": config.openai_config["http_proxy"],
"https": config.openai_config["http_proxy"]
}
# 主启动流程
database = pkg.database.manager.DatabaseManager()
# 配置openai api_base
if "reverse_proxy" in config.openai_config and config.openai_config["reverse_proxy"] is not None:
openai.base_url = config.openai_config["reverse_proxy"]
database.initialize_database()
# 主启动流程
database = pkg.database.manager.DatabaseManager()
openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
database.initialize_database()
# 加载所有未超时的session
pkg.openai.session.load_sessions()
openai_interact = pkg.openai.manager.OpenAIInteract(config.openai_config['api_key'])
# 初始化qq机器人
qqbot = pkg.qqbot.manager.QQBotManager(mirai_http_api_config=config.mirai_http_api_config,
timeout=config.process_message_timeout, retry=config.retry_times,
first_time_init=first_time_init)
# 加载所有未超时的session
pkg.openai.session.load_sessions()
# 加载插件
import pkg.plugin.host
pkg.plugin.host.load_plugins()
# 初始化qq机器人
qqbot = pkg.qqbot.manager.QQBotManager(first_time_init=first_time_init)
pkg.plugin.host.initialize_plugins()
# 加载插件
import pkg.plugin.host
pkg.plugin.host.load_plugins()
if first_time_init: # 不是热重载之后的启动,则启动新的bot线程
pkg.plugin.host.initialize_plugins()
import mirai.exceptions
if first_time_init: # 不是热重载之后的启动,则启动新的bot线程
def run_bot_wrapper():
global known_exception_caught
try:
qqbot.bot.run()
except TypeError as e:
if str(e).__contains__("argument 'debug'"):
logging.error(
"连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
known_exception_caught = True
elif str(e).__contains__("As of 3.10, the *loop*"):
logging.error(
"Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
known_exception_caught = True
import mirai.exceptions
except websockets.exceptions.InvalidStatus as e:
logging.error(
"mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
e))
known_exception_caught = True
except mirai.exceptions.NetworkError as e:
logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
known_exception_caught = True
except Exception as e:
if str(e).__contains__("404"):
def run_bot_wrapper():
global known_exception_caught
try:
logging.debug("使用账号: {}".format(qqbot.bot_account_id))
qqbot.adapter.run_sync()
except TypeError as e:
if str(e).__contains__("argument 'debug'"):
logging.error(
"连接bot失败:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/82".format(e))
known_exception_caught = True
elif str(e).__contains__("As of 3.10, the *loop*"):
logging.error(
"Websockets版本过低:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/5".format(e))
known_exception_caught = True
except websockets.exceptions.InvalidStatus as e:
logging.error(
"mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
e))
known_exception_caught = True
elif str(e).__contains__("signal only works in main thread"):
logging.error(
"hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
e))
except mirai.exceptions.NetworkError as e:
logging.error("连接mirai-api-http失败:{}, 请检查是否已按照文档启动mirai".format(e))
known_exception_caught = True
elif str(e).__contains__("did not receive a valid HTTP"):
logging.error(
"mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
e))
else:
logging.error(
"捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
known_exception_caught = True
raise e
finally:
time.sleep(12)
threading.Thread(
target=run_bot_wrapper
).start()
except Exception as e:
if str(e).__contains__("404"):
logging.error(
"mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
e))
known_exception_caught = True
elif str(e).__contains__("signal only works in main thread"):
logging.error(
"hypercorn异常:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/86".format(
e))
known_exception_caught = True
elif str(e).__contains__("did not receive a valid HTTP"):
logging.error(
"mirai-api-http端口无法使用:{}, 解决方案: https://github.com/RockChinQ/QChatGPT/issues/22".format(
e))
else:
import traceback
traceback.print_exc()
logging.error(
"捕捉到未知异常:{}, 请前往 https://github.com/RockChinQ/QChatGPT/issues 查找或提issue".format(e))
known_exception_caught = True
raise e
finally:
time.sleep(12)
threading.Thread(
target=run_bot_wrapper
).start()
except Exception as e:
traceback.print_exc()
if isinstance(e, KeyboardInterrupt):
logging.info("程序被用户中止")
sys.exit(0)
elif isinstance(e, SyntaxError):
logging.error("配置文件存在语法错误,请检查配置文件:\n1. 是否存在中文符号\n2. 是否已按照文件中的说明填写正确")
sys.exit(1)
else:
logging.error("初始化失败:{}".format(e))
sys.exit(1)
finally:
# 判断若是Windows输出选择模式可能会暂停程序的警告
if os.name == 'nt':
@@ -290,16 +296,21 @@ def start(first_time_init=False):
if first_time_init:
if not known_exception_caught:
logging.info('程序启动完成,如长时间未显示 ”成功登录到账号xxxxx“ ,并且不回复消息,请查看 '
'https://github.com/RockChinQ/QChatGPT/issues/37')
import config
if config.msg_source_adapter == "yirimirai":
logging.info("QQ: {}, MAH: {}".format(config.mirai_http_api_config['qq'], config.mirai_http_api_config['host']+":"+str(config.mirai_http_api_config['port'])))
logging.critical('程序启动完成,如长时间未显示 "成功登录到账号xxxxx" ,并且不回复消息,解决办法(请勿到群里问): '
'https://github.com/RockChinQ/QChatGPT/issues/37')
elif config.msg_source_adapter == 'nakuru':
logging.info("host: {}, port: {}, http_port: {}".format(config.nakuru_config['host'], config.nakuru_config['port'], config.nakuru_config['http_port']))
logging.critical('程序启动完成,如长时间未显示 "Protocol: connected" ,并且不回复消息,请检查config.py中的nakuru_config是否正确')
else:
sys.exit(1)
else:
logging.info('热重载完成')
# 发送赞赏码
if hasattr(config, 'encourage_sponsor_at_start') \
and config.encourage_sponsor_at_start \
if config.encourage_sponsor_at_start \
and pkg.utils.context.get_openai_manager().audit_mgr.get_total_text_length() >= 2048:
logging.info("发送赞赏码")
@@ -321,7 +332,8 @@ def start(first_time_init=False):
if pkg.utils.updater.is_new_version_available():
logging.info("新版本可用,请发送 !update 进行自动更新\n更新日志:\n{}".format("\n".join(pkg.utils.updater.get_rls_notes())))
else:
logging.info("当前已是最新版本")
# logging.info("当前已是最新版本")
pass
except Exception as e:
logging.warning("检查更新失败:{}".format(e))
@@ -329,8 +341,9 @@ def start(first_time_init=False):
try:
import pkg.utils.announcement as announcement
new_announcement = announcement.fetch_new()
if new_announcement != "":
logging.critical("[公告] {}".format(new_announcement))
if len(new_announcement) > 0:
for announcement in new_announcement:
logging.critical("[公告]<{}> {}".format(announcement['time'], announcement['content']))
except Exception as e:
logging.warning("获取公告失败:{}".format(e))
@@ -356,19 +369,13 @@ def stop():
def check_file():
# 配置文件存在性校验
if not os.path.exists('config.py'):
shutil.copy('config-template.py', 'config.py')
print('请先在config.py中填写配置')
sys.exit(0)
# 检查是否有banlist.py,如果没有就把banlist-template.py复制一份
if not os.path.exists('banlist.py'):
shutil.copy('banlist-template.py', 'banlist.py')
shutil.copy('res/templates/banlist-template.py', 'banlist.py')
# 检查是否有sensitive.json
if not os.path.exists("sensitive.json"):
shutil.copy("sensitive-template.json", "sensitive.json")
shutil.copy("res/templates/sensitive-template.json", "sensitive.json")
# 检查是否有scenario/default.json
if not os.path.exists("scenario/default.json"):
@@ -376,7 +383,11 @@ def check_file():
# 检查cmdpriv.json
if not os.path.exists("cmdpriv.json"):
shutil.copy("cmdpriv-template.json", "cmdpriv.json")
shutil.copy("res/templates/cmdpriv-template.json", "cmdpriv.json")
# 检查tips_custom
if not os.path.exists("tips.py"):
shutil.copy("tips-custom-template.py", "tips.py")
# 检查temp目录
if not os.path.exists("temp/"):
@@ -388,8 +399,19 @@ def check_file():
if not os.path.exists(path):
os.mkdir(path)
# 配置文件存在性校验
if not os.path.exists('config.py'):
shutil.copy('config-template.py', 'config.py')
print('请先在config.py中填写配置')
sys.exit(0)
def main():
global use_override
# 检查是否携带了 --override 或 -r 参数
if '--override' in sys.argv or '-r' in sys.argv:
use_override = True
# 初始化相关文件
check_file()
@@ -401,6 +423,9 @@ def main():
load_config()
config = pkg.utils.context.get_config()
# 检查tips模块
complete_tips()
# 配置线程池
from pkg.utils import ThreadCtl
thread_ctl = ThreadCtl(

View File

@@ -1,5 +1,6 @@
{
"comment": "这是override.json支持的字段全集, 关于override.json机制, 请查看https://github.com/RockChinQ/QChatGPT/pull/271",
"msg_source_adapter": "yirimirai",
"mirai_http_api_config": {
"adapter": "WebSocketAdapter",
"host": "localhost",
@@ -7,6 +8,12 @@
"verifyKey": "yirimirai",
"qq": 1234567890
},
"nakuru_config": {
"host": "localhost",
"port": 6700,
"http_port": 5700,
"token": ""
},
"openai_config": {
"api_key": {
"default": "openai_api_key"
@@ -14,21 +21,24 @@
"http_proxy": null,
"reverse_proxy": null
},
"switch_strategy": "active",
"admin_qq": 0,
"default_prompt": {
"default": "如果我之后想获取帮助,请你说“输入!help获取帮助”"
},
"preset_mode": "normal",
"response_rules": {
"at": true,
"prefix": [
"/ai",
"!ai",
"ai",
"ai"
],
"regexp": [],
"random_rate": 0.0
"default": {
"at": true,
"prefix": [
"/ai",
"!ai",
"ai",
"ai"
],
"regexp": [],
"random_rate": 0.0
}
},
"ignore_rules": {
"prefix": [
@@ -44,35 +54,39 @@
"inappropriate_message_tips": "[百度云]请珍惜机器人,当前返回内容不合规",
"encourage_sponsor_at_start": true,
"prompt_submit_length": 2048,
"auto_reset": true,
"completion_api_params": {
"model": "gpt-3.5-turbo",
"temperature": 0.9,
"top_p": 1,
"frequency_penalty": 0.2,
"presence_penalty": 1.0
"temperature": 0.9
},
"image_api_params": {
"size": "256x256"
},
"quote_origin": true,
"trace_function_calls": false,
"quote_origin": false,
"at_sender": false,
"include_image_description": true,
"process_message_timeout": 30,
"process_message_timeout": 120,
"show_prefix": false,
"force_delay_range": [
1.5,
3
],
"blob_message_threshold": 256,
"blob_message_strategy": "forward",
"wait_last_done": true,
"font_path": "",
"retry_times": 3,
"hide_exce_info_to_user": false,
"alter_tip_message": "出错了,请稍后再试",
"sys_pool_num": 8,
"admin_pool_num": 2,
"user_pool_num": 6,
"admin_pool_num": 4,
"user_pool_num": 8,
"session_expire_time": 1200,
"rate_limitation": 60,
"rate_limit_strategy": "wait",
"rate_limit_drop_tip": "本分钟对话次数超过限速次数,此对话被丢弃",
"upgrade_dependencies": true,
"rate_limitation": {
"default": 60
},
"rate_limit_strategy": "drop",
"upgrade_dependencies": false,
"report_usage": true,
"logging_level": 20,
"help_message": "此机器人通过调用OpenAI的GPT-3大型语言模型生成回复不具有情感。\n你可以用自然语言与其交流回复的消息中[GPT]开头的为模型生成的语言,[bot]开头的为程序提示。\n了解此项目请找QQ 1010553892 联系作者\n请不要用其生成整篇文章或大段代码因为每次只会向模型提交少部分文字生成大部分文字会产生偏题、前后矛盾等问题\n每次会话最后一次交互后20分钟后会自动结束结束后将开启新会话如需继续前一次会话请发送 !last 重新开启\n欢迎到github.com/RockChinQ/QChatGPT 给个star\n\n指令帮助信息请查看: https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E6%8C%87%E4%BB%A4"
"logging_level": 20
}

View File

@@ -5,6 +5,7 @@
import hashlib
import json
import logging
import threading
import requests
@@ -42,15 +43,20 @@ class DataGatherer:
只会报告此次请求的使用量,不会报告总量。
不包含除版本号、使用类型、使用量以外的任何信息,仅供开发者分析使用情况。
"""
try:
config = pkg.utils.context.get_config()
if hasattr(config, "report_usage") and not config.report_usage:
def thread_func():
try:
config = pkg.utils.context.get_config()
if not config.report_usage:
return
res = requests.get("http://reports.rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}&msg_source={}".format(subservice_name, self.version_str, count, config.msg_source_adapter))
if res.status_code != 200 or res.text != "ok":
logging.warning("report to server failed, status_code: {}, text: {}".format(res.status_code, res.text))
except:
return
res = requests.get("http://reports.rockchin.top:18989/usage?service_name=qchatgpt.{}&version={}&count={}".format(subservice_name, self.version_str, count))
if res.status_code != 200 or res.text != "ok":
logging.warning("report to server failed, status_code: {}, text: {}".format(res.status_code, res.text))
except:
return
threading.Thread(target=thread_func).start()
def get_usage(self, key_md5):
return self.usage[key_md5] if key_md5 in self.usage else {}

View File

@@ -0,0 +1,221 @@
import openai
from openai.types.chat import chat_completion_message
import json
import logging
from .model import RequestBase
from ..funcmgr import get_func_schema_list, execute_function, get_func, get_func_schema, ContentFunctionNotFoundError
class ChatCompletionRequest(RequestBase):
"""调用ChatCompletion接口的请求类。
此类保证每一次返回的角色为assistant的信息的finish_reason一定为stop。
若有函数调用响应,本类的返回瀑布是:函数调用请求->函数调用结果->...->assistant的信息->stop。
"""
model: str
messages: list[dict[str, str]]
kwargs: dict
stopped: bool = False
pending_func_call: chat_completion_message.FunctionCall = None
pending_msg: str
def flush_pending_msg(self):
self.append_message(
role="assistant",
content=self.pending_msg
)
self.pending_msg = ""
def append_message(self, role: str, content: str, name: str=None, function_call: dict=None):
msg = {
"role": role,
"content": content
}
if name is not None:
msg['name'] = name
if function_call is not None:
msg['function_call'] = function_call
self.messages.append(msg)
def __init__(
self,
client: openai.Client,
model: str,
messages: list[dict[str, str]],
**kwargs
):
self.client = client
self.model = model
self.messages = messages.copy()
self.kwargs = kwargs
self.req_func = self.client.chat.completions.create
self.pending_func_call = None
self.stopped = False
self.pending_msg = ""
def __iter__(self):
return self
def __next__(self) -> dict:
if self.stopped:
raise StopIteration()
if self.pending_func_call is None: # 没有待处理的函数调用请求
args = {
"model": self.model,
"messages": self.messages,
}
funcs = get_func_schema_list()
if len(funcs) > 0:
args['functions'] = funcs
# 拼接kwargs
args = {**args, **self.kwargs}
from openai.types.chat import chat_completion
resp: chat_completion.ChatCompletion = self._req(**args)
choice0 = resp.choices[0]
# 如果不是函数调用且finish_reason为stop则停止迭代
if choice0.finish_reason == 'stop': # and choice0["finish_reason"] == "stop"
self.stopped = True
if hasattr(choice0.message, 'function_call') and choice0.message.function_call is not None:
self.pending_func_call = choice0.message.function_call
self.append_message(
role="assistant",
content=choice0.message.content,
function_call=choice0.message.function_call
)
return {
"id": resp.id,
"choices": [
{
"index": choice0.index,
"message": {
"role": "assistant",
"type": "function_call",
"content": choice0.message.content,
"function_call": {
"name": choice0.message.function_call.name,
"arguments": choice0.message.function_call.arguments
}
},
"finish_reason": "function_call"
}
],
"usage": {
"prompt_tokens": resp.usage.prompt_tokens,
"completion_tokens": resp.usage.completion_tokens,
"total_tokens": resp.usage.total_tokens
}
}
else:
# self.pending_msg += choice0['message']['content']
# 普通回复一定处于最后方故不用再追加进内部messages
return {
"id": resp.id,
"choices": [
{
"index": choice0.index,
"message": {
"role": "assistant",
"type": "text",
"content": choice0.message.content
},
"finish_reason": choice0.finish_reason
}
],
"usage": {
"prompt_tokens": resp.usage.prompt_tokens,
"completion_tokens": resp.usage.completion_tokens,
"total_tokens": resp.usage.total_tokens
}
}
else: # 处理函数调用请求
cp_pending_func_call = self.pending_func_call.copy()
self.pending_func_call = None
func_name = cp_pending_func_call.name
arguments = {}
try:
try:
arguments = json.loads(cp_pending_func_call.arguments)
# 若不是json格式的异常处理
except json.decoder.JSONDecodeError:
# 获取函数的参数列表
func_schema = get_func_schema(func_name)
arguments = {
func_schema['parameters']['required'][0]: cp_pending_func_call.arguments
}
logging.info("执行函数调用: name={}, arguments={}".format(func_name, arguments))
# 执行函数调用
ret = ""
try:
ret = execute_function(func_name, arguments)
logging.info("函数执行完成。")
except Exception as e:
ret = "error: execute function failed: {}".format(str(e))
logging.error("函数执行失败: {}".format(str(e)))
self.append_message(
role="function",
content=json.dumps(ret, ensure_ascii=False),
name=func_name
)
return {
"id": -1,
"choices": [
{
"index": -1,
"message": {
"role": "function",
"type": "function_return",
"function_name": func_name,
"content": json.dumps(ret, ensure_ascii=False)
},
"finish_reason": "function_return"
}
],
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0
}
}
except ContentFunctionNotFoundError:
raise Exception("没有找到函数: {}".format(func_name))

View File

@@ -0,0 +1,100 @@
import openai
from openai.types import completion, completion_choice
from .model import RequestBase
class CompletionRequest(RequestBase):
"""调用Completion接口的请求类。
调用方可以一直next completion直到finish_reason为stop。
"""
model: str
prompt: str
kwargs: dict
stopped: bool = False
def __init__(
self,
client: openai.Client,
model: str,
messages: list[dict[str, str]],
**kwargs
):
self.client = client
self.model = model
self.prompt = ""
for message in messages:
self.prompt += message["role"] + ": " + message["content"] + "\n"
self.prompt += "assistant: "
self.kwargs = kwargs
self.req_func = self.client.completions.create
def __iter__(self):
return self
def __next__(self) -> dict:
"""调用Completion接口返回生成的文本
{
"id": "id",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"type": "text",
"content": "message"
},
"finish_reason": "reason"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 20,
"total_tokens": 30
}
}
"""
if self.stopped:
raise StopIteration()
resp: completion.Completion = self._req(
model=self.model,
prompt=self.prompt,
**self.kwargs
)
if resp.choices[0].finish_reason == "stop":
self.stopped = True
choice0: completion_choice.CompletionChoice = resp.choices[0]
self.prompt += choice0.text
return {
"id": resp.id,
"choices": [
{
"index": choice0.index,
"message": {
"role": "assistant",
"type": "text",
"content": choice0.text
},
"finish_reason": choice0.finish_reason
}
],
"usage": {
"prompt_tokens": resp.usage.prompt_tokens,
"completion_tokens": resp.usage.completion_tokens,
"total_tokens": resp.usage.total_tokens
}
}

40
pkg/openai/api/model.py Normal file
View File

@@ -0,0 +1,40 @@
# 定义不同接口请求的模型
import threading
import asyncio
import logging
import openai
class RequestBase:
client: openai.Client
req_func: callable
def __init__(self, *args, **kwargs):
raise NotImplementedError
def _next_key(self):
import pkg.utils.context as context
switched, name = context.get_openai_manager().key_mgr.auto_switch()
logging.debug("切换api-key: switched={}, name={}".format(switched, name))
self.client.api_key = context.get_openai_manager().key_mgr.get_using_key()
def _req(self, **kwargs):
"""处理代理问题"""
import config
ret = self.req_func(**kwargs)
logging.debug("接口请求返回:%s", str(ret))
if config.switch_strategy == 'active':
self._next_key()
return ret
def __iter__(self):
raise self
def __next__(self):
raise NotImplementedError

47
pkg/openai/funcmgr.py Normal file
View File

@@ -0,0 +1,47 @@
# 封装了function calling的一些支持函数
import logging
from pkg.plugin import host
class ContentFunctionNotFoundError(Exception):
pass
def get_func_schema_list() -> list:
"""从plugin包中的函数结构中获取并处理成受GPT支持的格式"""
if not host.__enable_content_functions__:
return []
schemas = []
for func in host.__callable_functions__:
if func['enabled']:
fun_cp = func.copy()
del fun_cp['enabled']
schemas.append(fun_cp)
return schemas
def get_func(name: str) -> callable:
if name not in host.__function_inst_map__:
raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
return host.__function_inst_map__[name]
def get_func_schema(name: str) -> dict:
for func in host.__callable_functions__:
if func['name'] == name:
return func
raise ContentFunctionNotFoundError("没有找到内容函数: {}".format(name))
def execute_function(name: str, kwargs: dict) -> any:
"""执行函数调用"""
logging.debug("executing function: name='{}', kwargs={}".format(name, kwargs))
func = get_func(name)
return func(**kwargs)

View File

@@ -54,7 +54,24 @@ class KeysManager:
是否切换成功, 切换后的api-key的别名
"""
index = 0
for key_name in self.api_key:
if self.api_key[key_name] == self.using_key:
break
index += 1
# 从当前key开始向后轮询
start_index = index
index += 1
if index >= len(self.api_key):
index = 0
while index != start_index:
key_name = list(self.api_key.keys())[index]
if self.api_key[key_name] not in self.exceeded:
self.using_key = self.api_key[key_name]
@@ -69,10 +86,14 @@ class KeysManager:
return True, key_name
self.using_key = list(self.api_key.values())[0]
logging.info("使用api-key:" + list(self.api_key.keys())[0])
index += 1
if index >= len(self.api_key):
index = 0
return False, ""
self.using_key = list(self.api_key.values())[start_index]
logging.debug("使用api-key:" + list(self.api_key.keys())[start_index])
return False, list(self.api_key.keys())[start_index]
def add(self, key_name, key):
self.api_key[key_name] = key

View File

@@ -5,7 +5,9 @@ import openai
import pkg.openai.keymgr
import pkg.utils.context
import pkg.audit.gatherer
from pkg.openai.modelmgr import ModelRequest, create_openai_model_request
from pkg.openai.modelmgr import select_request_cls
from pkg.openai.api.model import RequestBase
class OpenAIInteract:
@@ -22,56 +24,46 @@ class OpenAIInteract:
"size": "256x256",
}
client: openai.Client = None
def __init__(self, api_key: str):
self.key_mgr = pkg.openai.keymgr.KeysManager(api_key)
self.audit_mgr = pkg.audit.gatherer.DataGatherer()
logging.info("文字总使用量:%d", self.audit_mgr.get_total_text_length())
# logging.info("文字总使用量:%d", self.audit_mgr.get_total_text_length())
openai.api_key = self.key_mgr.get_using_key()
self.client = openai.Client(
api_key=self.key_mgr.get_using_key()
)
pkg.utils.context.set_openai_manager(self)
# 请求OpenAI Completion
def request_completion(self, prompts) -> tuple[str, int]:
"""请求补全接口回复
Parameters:
prompts (str): 提示语
Returns:
str: 回复
def request_completion(self, messages: list):
"""请求补全接口回复=
"""
# 选择接口请求类
config = pkg.utils.context.get_config()
# 根据模型选择使用的接口
ai: ModelRequest = create_openai_model_request(
config.completion_api_params['model'],
'user',
config.openai_config["http_proxy"] if "http_proxy" in config.openai_config else None
)
ai.request(
prompts,
**config.completion_api_params
)
response = ai.get_response()
request: RequestBase
logging.debug("OpenAI response: %s", response)
model: str = config.completion_api_params['model']
# 记录使用量
current_round_token = 0
if 'model' in config.completion_api_params:
self.audit_mgr.report_text_model_usage(config.completion_api_params['model'],
ai.get_total_tokens())
current_round_token = ai.get_total_tokens()
elif 'engine' in config.completion_api_params:
self.audit_mgr.report_text_model_usage(config.completion_api_params['engine'],
response['usage']['total_tokens'])
current_round_token = response['usage']['total_tokens']
cp_parmas = config.completion_api_params.copy()
del cp_parmas['model']
return ai.get_message(), current_round_token
request = select_request_cls(self.client, model, messages, cp_parmas)
# 请求接口
for resp in request:
if resp['usage']['total_tokens'] > 0:
self.audit_mgr.report_text_model_usage(
model,
resp['usage']['total_tokens']
)
yield resp
def request_image(self, prompt) -> dict:
"""请求图片接口回复
@@ -83,7 +75,7 @@ class OpenAIInteract:
dict: 响应
"""
config = pkg.utils.context.get_config()
params = config.image_api_params if hasattr(config, "image_api_params") else self.default_image_api_params
params = config.image_api_params
response = openai.Image.create(
prompt=prompt,

View File

@@ -5,26 +5,50 @@ ChatCompletion - gpt-3.5-turbo 等模型
Completion - text-davinci-003 等模型
此模块封装此两个接口的请求实现,为上层提供统一的调用方式
"""
import openai, logging, threading, asyncio
import openai.error as aiE
import tiktoken
import openai
from pkg.openai.api.model import RequestBase
from pkg.openai.api.completion import CompletionRequest
from pkg.openai.api.chat_completion import ChatCompletionRequest
COMPLETION_MODELS = {
'text-davinci-003',
'text-davinci-002',
'code-davinci-002',
'code-cushman-001',
'text-curie-001',
'text-babbage-001',
'text-ada-001',
"text-davinci-003", # legacy
"text-davinci-002", # legacy
"code-davinci-002", # legacy
"code-cushman-001", # legacy
"text-curie-001", # legacy
"text-babbage-001", # legacy
"text-ada-001", # legacy
"gpt-3.5-turbo-instruct",
}
CHAT_COMPLETION_MODELS = {
'gpt-3.5-turbo',
'gpt-3.5-turbo-0301',
'gpt-4',
'gpt-4-0314',
'gpt-4-32k',
'gpt-4-32k-0314'
# GPT 4 系列
"gpt-4-1106-preview",
"gpt-4-vision-preview",
"gpt-4",
"gpt-4-32k",
"gpt-4-0613",
"gpt-4-32k-0613",
"gpt-4-0314", # legacy
"gpt-4-32k-0314", # legacy
# GPT 3.5 系列
"gpt-3.5-turbo-1106",
"gpt-3.5-turbo",
"gpt-3.5-turbo-16k",
"gpt-3.5-turbo-0613", # legacy
"gpt-3.5-turbo-16k-0613", # legacy
"gpt-3.5-turbo-0301", # legacy
# One-API 接入
"SparkDesk",
"chatglm_pro",
"chatglm_std",
"chatglm_lite",
"qwen-v1",
"qwen-plus-v1",
"ERNIE-Bot",
"ERNIE-Bot-turbo",
}
EDIT_MODELS = {
@@ -36,153 +60,85 @@ IMAGE_MODELS = {
}
class ModelRequest:
"""模型接口请求父类"""
can_chat = False
runtime: threading.Thread = None
ret = {}
proxy: str = None
request_ready = True
error_info: str = "若在没有任何错误的情况下看到这句话请带着配置文件上报Issues"
def __init__(self, model_name, user_name, request_fun, http_proxy:str = None, time_out = None):
self.model_name = model_name
self.user_name = user_name
self.request_fun = request_fun
self.time_out = time_out
if http_proxy != None:
self.proxy = http_proxy
openai.proxy = self.proxy
self.request_ready = False
async def __a_request__(self, **kwargs):
"""异步请求"""
try:
self.ret:dict = await self.request_fun(**kwargs)
self.request_ready = True
except aiE.APIConnectionError as e:
self.error_info = "{}\n请检查网络连接或代理是否正常".format(e)
raise ConnectionError(self.error_info)
except ValueError as e:
self.error_info = "{}\n该错误可能是由于http_proxy格式设置错误引起的"
except Exception as e:
self.error_info = "{}\n由于请求异常产生的未知错误,请查看日志".format(e)
raise Exception(self.error_info)
def request(self, **kwargs):
"""向接口发起请求"""
if self.proxy != None: #异步请求
self.request_ready = False
loop = asyncio.new_event_loop()
self.runtime = threading.Thread(
target=loop.run_until_complete,
args=(self.__a_request__(**kwargs),)
)
self.runtime.start()
else: #同步请求
self.ret = self.request_fun(**kwargs)
def __msg_handle__(self, msg):
"""将prompt dict转换成接口需要的格式"""
return msg
def ret_handle(self):
'''
API消息返回处理函数
若重写该方法应检查异步线程状态或在需要检查处super该方法
'''
if self.runtime != None and isinstance(self.runtime, threading.Thread):
self.runtime.join(self.time_out)
if self.request_ready:
return
raise Exception(self.error_info)
def get_total_tokens(self):
try:
return self.ret['usage']['total_tokens']
except:
return 0
def get_message(self):
return self.message
def get_response(self):
return self.ret
class ChatCompletionModel(ModelRequest):
"""ChatCompletion接口的请求实现"""
Chat_role = ['system', 'user', 'assistant']
def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
if http_proxy == None:
request_fun = openai.ChatCompletion.create
else:
request_fun = openai.ChatCompletion.acreate
self.can_chat = True
super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
def request(self, prompts, **kwargs):
prompts = self.__msg_handle__(prompts)
kwargs['messages'] = prompts
super().request(**kwargs)
self.ret_handle()
def __msg_handle__(self, msgs):
temp_msgs = []
# 把msgs拷贝进temp_msgs
for msg in msgs:
temp_msgs.append(msg.copy())
return temp_msgs
def get_message(self):
return self.ret["choices"][0]["message"]['content'] #需要时直接加载加快请求速度,降低内存消耗
class CompletionModel(ModelRequest):
"""Completion接口的请求实现"""
def __init__(self, model_name, user_name, http_proxy:str = None, **kwargs):
if http_proxy == None:
request_fun = openai.Completion.create
else:
request_fun = openai.Completion.acreate
super().__init__(model_name, user_name, request_fun, http_proxy, **kwargs)
def request(self, prompts, **kwargs):
prompts = self.__msg_handle__(prompts)
kwargs['prompt'] = prompts
super().request(**kwargs)
self.ret_handle()
def __msg_handle__(self, msgs):
prompt = ''
for msg in msgs:
prompt = prompt + "{}: {}\n".format(msg['role'], msg['content'])
# for msg in msgs:
# if msg['role'] == 'assistant':
# prompt = prompt + "{}\n".format(msg['content'])
# else:
# prompt = prompt + "{}:{}\n".format(msg['role'] , msg['content'])
prompt = prompt + "assistant: "
return prompt
def get_message(self):
return self.ret["choices"][0]["text"]
def create_openai_model_request(model_name: str, user_name: str = 'user', http_proxy:str = None) -> ModelRequest:
"""使用给定的模型名称创建模型请求对象"""
def select_request_cls(client: openai.Client, model_name: str, messages: list, args: dict) -> RequestBase:
if model_name in CHAT_COMPLETION_MODELS:
model = ChatCompletionModel(model_name, user_name, http_proxy)
return ChatCompletionRequest(client, model_name, messages, **args)
elif model_name in COMPLETION_MODELS:
model = CompletionModel(model_name, user_name, http_proxy)
else :
log = "找不到模型[{}],请检查配置文件".format(model_name)
logging.error(log)
raise IndexError(log)
logging.debug("使用接口[{}]创建模型请求[{}]".format(model.__class__.__name__, model_name))
return model
return CompletionRequest(client, model_name, messages, **args)
raise ValueError("不支持模型[{}],请检查配置文件".format(model_name))
def count_chat_completion_tokens(messages: list, model: str) -> int:
"""Return the number of tokens used by a list of messages."""
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
print("Warning: model not found. Using cl100k_base encoding.")
encoding = tiktoken.get_encoding("cl100k_base")
if model in {
"gpt-3.5-turbo-0613",
"gpt-3.5-turbo-16k-0613",
"gpt-4-0314",
"gpt-4-32k-0314",
"gpt-4-0613",
"gpt-4-32k-0613",
"SparkDesk",
"chatglm_pro",
"chatglm_std",
"chatglm_lite",
"qwen-v1",
"qwen-plus-v1",
"ERNIE-Bot",
"ERNIE-Bot-turbo",
}:
tokens_per_message = 3
tokens_per_name = 1
elif model == "gpt-3.5-turbo-0301":
tokens_per_message = 4 # every message follows <|start|>{role/name}\n{content}<|end|>\n
tokens_per_name = -1 # if there's a name, the role is omitted
elif "gpt-3.5-turbo" in model:
# print("Warning: gpt-3.5-turbo may update over time. Returning num tokens assuming gpt-3.5-turbo-0613.")
return count_chat_completion_tokens(messages, model="gpt-3.5-turbo-0613")
elif "gpt-4" in model:
# print("Warning: gpt-4 may update over time. Returning num tokens assuming gpt-4-0613.")
return count_chat_completion_tokens(messages, model="gpt-4-0613")
else:
raise NotImplementedError(
f"""count_chat_completion_tokens() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens."""
)
num_tokens = 0
for message in messages:
num_tokens += tokens_per_message
for key, value in message.items():
num_tokens += len(encoding.encode(value))
if key == "name":
num_tokens += tokens_per_name
num_tokens += 3 # every reply is primed with <|start|>assistant<|message|>
return num_tokens
def count_completion_tokens(messages: list, model: str) -> int:
try:
encoding = tiktoken.encoding_for_model(model)
except KeyError:
print("Warning: model not found. Using cl100k_base encoding.")
encoding = tiktoken.get_encoding("cl100k_base")
text = ""
for message in messages:
text += message['role'] + message['content'] + "\n"
text += "assistant: "
return len(encoding.encode(text))
def count_tokens(messages: list, model: str):
if model in CHAT_COMPLETION_MODELS:
return count_chat_completion_tokens(messages, model)
elif model in COMPLETION_MODELS:
return count_completion_tokens(messages, model)
raise ValueError("不支持模型[{}],请检查配置文件".format(model))

View File

@@ -1,28 +0,0 @@
# 计费模块
# 已弃用 https://github.com/RockChinQ/QChatGPT/issues/81
import logging
pricing = {
"base": { # 文字模型单位是1000字符
"text-davinci-003": 0.02,
},
"image": {
"256x256": 0.016,
"512x512": 0.018,
"1024x1024": 0.02,
}
}
def language_base_price(model, text):
salt_rate = 0.93
length = ((len(text.encode('utf-8')) - len(text)) / 2 + len(text)) * salt_rate
logging.debug("text length: %d" % length)
return pricing["base"][model] * length / 1000
def image_price(size):
logging.debug("image size: %s" % size)
return pricing["image"][size]

View File

@@ -16,6 +16,8 @@ import pkg.utils.context
import pkg.plugin.host as plugin_host
import pkg.plugin.models as plugin_models
from pkg.openai.modelmgr import count_tokens
# 运行时保存的所有session
sessions = {}
@@ -64,7 +66,7 @@ def load_sessions():
session_data = db_inst.load_valid_sessions()
for session_name in session_data:
logging.info('加载session: {}'.format(session_name))
logging.debug('加载session: {}'.format(session_name))
temp_session = Session(session_name)
temp_session.name = session_name
@@ -83,7 +85,7 @@ def load_sessions():
# 获取指定名称的session如果不存在则创建一个新的
def get_session(session_name: str):
def get_session(session_name: str) -> 'Session':
global sessions
if session_name not in sessions:
sessions[session_name] = Session(session_name)
@@ -107,9 +109,6 @@ class Session:
prompt = []
"""使用list来保存会话中的回合"""
token_counts = []
"""每个回合的token数量"""
default_prompt = []
"""本session的默认prompt"""
@@ -195,8 +194,15 @@ class Session:
# 请求回复
# 这个函数是阻塞的
def append(self, text: str) -> str:
"""向session中添加一条消息返回接口回复"""
def query(self, text: str=None) -> tuple[str, str, list[str]]:
"""向session中添加一条消息返回接口回复
Args:
text (str): 用户消息
Returns:
tuple[str, str]: (接口回复, finish_reason, 已调用的函数列表)
"""
self.last_interact_timestamp = int(time.time())
@@ -210,40 +216,142 @@ class Session:
event = pkg.plugin.host.emit(plugin_models.SessionFirstMessageReceived, **args)
if event.is_prevented_default():
return None
return None, None, None
config = pkg.utils.context.get_config()
max_length = config.prompt_submit_length if hasattr(config, "prompt_submit_length") else 1024
max_length = config.prompt_submit_length
prompts, counts = self.cut_out(text, max_length)
local_default_prompt = self.default_prompt.copy()
local_prompt = self.prompt.copy()
# 触发PromptPreProcessing事件
args = {
'session_name': self.name,
'default_prompt': self.default_prompt,
'prompt': self.prompt,
'text_message': text,
}
event = pkg.plugin.host.emit(plugin_models.PromptPreProcessing, **args)
if event.get_return_value('default_prompt') is not None:
local_default_prompt = event.get_return_value('default_prompt')
if event.get_return_value('prompt') is not None:
local_prompt = event.get_return_value('prompt')
if event.get_return_value('text_message') is not None:
text = event.get_return_value('text_message')
prompts, _ = self.cut_out(text, max_length, local_default_prompt, local_prompt)
res_text = ""
pending_msgs = []
total_tokens = 0
finish_reason: str = ""
funcs = []
trace_func_calls = config.trace_function_calls
botmgr = pkg.utils.context.get_qqbot_manager()
session_name_spt: list[str] = self.name.split("_")
pending_res_text = ""
# TODO 对不起,我知道这样非常非常屎山,但我之后会重构的
for resp in pkg.utils.context.get_openai_manager().request_completion(prompts):
if pending_res_text != "":
botmgr.adapter.send_message(
session_name_spt[0],
session_name_spt[1],
pending_res_text
)
pending_res_text = ""
finish_reason = resp['choices'][0]['finish_reason']
if resp['choices'][0]['message']['role'] == "assistant" and resp['choices'][0]['message']['content'] != None: # 包含纯文本响应
if not trace_func_calls:
res_text += resp['choices'][0]['message']['content']
else:
res_text = resp['choices'][0]['message']['content']
pending_res_text = resp['choices'][0]['message']['content']
total_tokens += resp['usage']['total_tokens']
msg = {
"role": "assistant",
"content": resp['choices'][0]['message']['content']
}
if 'function_call' in resp['choices'][0]['message']:
msg['function_call'] = json.dumps(resp['choices'][0]['message']['function_call'])
pending_msgs.append(msg)
if resp['choices'][0]['message']['type'] == 'function_call':
# self.prompt.append(
# {
# "role": "assistant",
# "content": "function call: "+json.dumps(resp['choices'][0]['message']['function_call'])
# }
# )
if trace_func_calls:
botmgr.adapter.send_message(
session_name_spt[0],
session_name_spt[1],
"调用函数 "+resp['choices'][0]['message']['function_call']['name'] + "..."
)
total_tokens += resp['usage']['total_tokens']
elif resp['choices'][0]['message']['type'] == 'function_return':
# self.prompt.append(
# {
# "role": "function",
# "name": resp['choices'][0]['message']['function_name'],
# "content": json.dumps(resp['choices'][0]['message']['content'])
# }
# )
# total_tokens += resp['usage']['total_tokens']
funcs.append(
resp['choices'][0]['message']['function_name']
)
pass
# 计算请求前的prompt数量
total_token_before_query = 0
for token_count in counts:
total_token_before_query += token_count
# 向API请求补全
message, total_token = pkg.utils.context.get_openai_manager().request_completion(
prompts,
)
# message, total_token = pkg.utils.context.get_openai_manager().request_completion(
# prompts,
# )
# 成功获取,处理回复
res_test = message
res_ans = res_test.strip()
# res_test = message
res_ans = res_text.strip()
# 将此次对话的双方内容加入到prompt中
self.prompt.append({'role': 'user', 'content': text})
self.prompt.append({'role': 'assistant', 'content': res_ans})
# self.prompt.append({'role': 'user', 'content': text})
# self.prompt.append({'role': 'assistant', 'content': res_ans})
if text:
self.prompt.append({'role': 'user', 'content': text})
# 添加pending_msgs
self.prompt += pending_msgs
# 向token_counts中添加本回合的token数量
self.token_counts.append(total_token-total_token_before_query)
logging.debug("本回合使用token: {}, session counts: {}".format(total_token-total_token_before_query, self.token_counts))
# self.token_counts.append(total_tokens-total_token_before_query)
# logging.debug("本回合使用token: {}, session counts: {}".format(total_tokens-total_token_before_query, self.token_counts))
if self.just_switched_to_exist_session:
self.just_switched_to_exist_session = False
self.set_ongoing()
return res_ans if res_ans[0] != '\n' else res_ans[1:]
return res_ans if res_ans[0] != '\n' else res_ans[1:], finish_reason, funcs
# 删除上一回合并返回上一回合的问题
def undo(self) -> str:
@@ -261,7 +369,7 @@ class Session:
return question
# 构建对话体
def cut_out(self, msg: str, max_tokens: int) -> tuple[list, list]:
def cut_out(self, msg: str, max_tokens: int, default_prompt: list, prompt: list) -> tuple[list, list]:
"""将现有prompt进行切割处理使得新的prompt长度不超过max_tokens
:return: (新的prompt, 新的token_counts)
@@ -274,42 +382,35 @@ class Session:
# 包装目前的对话回合内容
changable_prompts = []
changable_counts = []
# 倒着来, 遍历prompt的步长为2, 遍历tokens_counts的步长为1
changable_index = len(self.prompt) - 1
token_count_index = len(self.token_counts) - 1
packed_tokens = 0
use_model = pkg.utils.context.get_config().completion_api_params['model']
while changable_index >= 0 and token_count_index >= 0:
if packed_tokens + self.token_counts[token_count_index] > max_tokens:
ptr = len(prompt) - 1
# 直接从后向前扫描拼接,不管是否是整回合
while ptr >= 0:
if count_tokens(prompt[ptr:ptr+1]+changable_prompts, use_model) > max_tokens:
break
changable_prompts.insert(0, self.prompt[changable_index])
changable_prompts.insert(0, self.prompt[changable_index - 1])
changable_counts.insert(0, self.token_counts[token_count_index])
packed_tokens += self.token_counts[token_count_index]
changable_prompts.insert(0, prompt[ptr])
changable_index -= 2
token_count_index -= 1
ptr -= 1
# 将default_prompt和changable_prompts合并
result_prompt = self.default_prompt + changable_prompts
result_prompt = default_prompt + changable_prompts
# 添加当前问题
result_prompt.append(
{
'role': 'user',
'content': msg
}
)
if msg:
result_prompt.append(
{
'role': 'user',
'content': msg
}
)
logging.debug('cut_out: {}\nchangable section tokens: {}\npacked counts: {}\nsession counts: {}'.format(json.dumps(result_prompt, ensure_ascii=False, indent=4),
packed_tokens,
changable_counts,
self.token_counts))
logging.debug("cut_out: {}".format(json.dumps(result_prompt, ensure_ascii=False, indent=4)))
return result_prompt, changable_counts
return result_prompt, count_tokens(changable_prompts, use_model)
# 持久化session
def persistence(self):
@@ -327,7 +428,7 @@ class Session:
json.dumps(self.prompt), json.dumps(self.default_prompt), json.dumps(self.token_counts))
# 重置session
def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None):
def reset(self, explicit: bool = False, expired: bool = False, schedule_new: bool = True, use_prompt: str = None, persist: bool = False):
if self.prompt:
self.persistence()
if explicit:
@@ -345,7 +446,8 @@ class Session:
if expired:
pkg.utils.context.get_database_manager().set_session_expired(self.name, self.create_timestamp)
self.default_prompt = self.get_default_prompt(use_prompt)
if not persist: # 不要求保持default prompt
self.default_prompt = self.get_default_prompt(use_prompt)
self.prompt = []
self.token_counts = []
self.create_timestamp = int(time.time())

View File

@@ -7,12 +7,21 @@ import pkgutil
import sys
import shutil
import traceback
import time
import re
import pkg.utils.updater as updater
import pkg.utils.context as context
import pkg.plugin.switch as switch
import pkg.plugin.settings as settings
import pkg.qqbot.adapter as msadapter
import pkg.utils.network as network
import pkg.plugin.metadata as metadata
from mirai import Mirai
import requests
from CallingGPT.session.session import Session
__plugins__ = {}
"""插件列表
@@ -40,6 +49,15 @@ __plugins__ = {}
__plugins_order__ = []
"""插件顺序"""
__enable_content_functions__ = True
"""是否启用内容函数"""
__callable_functions__ = []
"""供GPT调用的函数结构"""
__function_inst_map__: dict[str, callable] = {}
"""函数名:实例 映射"""
def generate_plugin_order():
"""根据__plugin__生成插件初始顺序无视是否启用"""
@@ -52,6 +70,8 @@ def generate_plugin_order():
def iter_plugins():
"""按照顺序迭代插件"""
for plugin_name in __plugins_order__:
if plugin_name not in __plugins__:
continue
yield __plugins__[plugin_name]
@@ -78,7 +98,7 @@ def walk_plugin_path(module, prefix='', path_prefix=''):
__current_module_path__ = "plugins/"+path_prefix + item.name + '.py'
importlib.import_module(module.__name__ + '.' + item.name)
logging.info('加载模块: plugins/{} 成功'.format(path_prefix + item.name + '.py'))
logging.debug('加载模块: plugins/{} 成功'.format(path_prefix + item.name + '.py'))
except:
logging.error('加载模块: plugins/{} 失败: {}'.format(path_prefix + item.name + '.py', sys.exc_info()))
traceback.print_exc()
@@ -86,7 +106,7 @@ def walk_plugin_path(module, prefix='', path_prefix=''):
def load_plugins():
"""加载插件"""
logging.info("加载插件")
logging.debug("加载插件")
PluginHost()
walk_plugin_path(__import__('plugins'))
@@ -100,20 +120,35 @@ def load_plugins():
# 加载插件顺序
settings.load_settings()
logging.debug("registered plugins: {}".format(__plugins__))
# 输出已注册的内容函数列表
logging.debug("registered content functions: {}".format(__callable_functions__))
logging.debug("function instance map: {}".format(__function_inst_map__))
# 迁移插件源地址记录
metadata.do_plugin_git_repo_migrate()
def initialize_plugins():
"""初始化插件"""
logging.info("初始化插件")
import pkg.plugin.models as models
successfully_initialized_plugins = []
for plugin in iter_plugins():
if not plugin['enabled']:
continue
# if not plugin['enabled']:
# continue
try:
models.__current_registering_plugin__ = plugin['name']
plugin['instance'] = plugin["class"](plugin_host=context.get_plugin_host())
logging.info("插件 {} 已初始化".format(plugin['name']))
# logging.info("插件 {} 已初始化".format(plugin['name']))
successfully_initialized_plugins.append(plugin['name'])
except:
logging.error("插件{}初始化时发生错误: {}".format(plugin['name'], sys.exc_info()))
logging.info("以下插件已初始化: {}".format(", ".join(successfully_initialized_plugins)))
def unload_plugins():
@@ -132,32 +167,98 @@ def unload_plugins():
# logging.error("插件{}卸载时发生错误: {}".format(plugin['name'], sys.exc_info()))
def install_plugin(repo_url: str):
"""安装插件从git储存库获取并解决依赖"""
try:
import pkg.utils.pkgmgr
pkg.utils.pkgmgr.ensure_dulwich()
except:
pass
def get_github_plugin_repo_label(repo_url: str) -> list[str]:
"""获取username, repo"""
try:
import dulwich
except ModuleNotFoundError:
raise Exception("dulwich模块未安装,请查看 https://github.com/RockChinQ/QChatGPT/issues/77")
# 提取 username/repo , 正则表达式
repo = re.findall(r'(?:https?://github\.com/|git@github\.com:)([^/]+/[^/]+?)(?:\.git|/|$)', repo_url)
from dulwich import porcelain
if len(repo) > 0: # github
return repo[0].split("/")
else:
return None
logging.info("克隆插件储存库: {}".format(repo_url))
repo = porcelain.clone(repo_url, "plugins/"+repo_url.split(".git")[0].split("/")[-1]+"/", checkout=True)
def download_plugin_source_code(repo_url: str, target_path: str) -> str:
"""下载插件源码"""
# 检查源类型
# 提取 username/repo , 正则表达式
repo = get_github_plugin_repo_label(repo_url)
target_path += repo[1]
if repo is not None: # github
logging.info("从 GitHub 下载插件源码...")
zipball_url = f"https://api.github.com/repos/{'/'.join(repo)}/zipball/HEAD"
zip_resp = requests.get(
url=zipball_url,
proxies=network.wrapper_proxies(),
stream=True
)
if zip_resp.status_code != 200:
raise Exception("下载源码失败: {}".format(zip_resp.text))
if os.path.exists("temp/"+target_path):
shutil.rmtree("temp/"+target_path)
if os.path.exists(target_path):
shutil.rmtree(target_path)
os.makedirs("temp/"+target_path)
with open("temp/"+target_path+"/source.zip", "wb") as f:
for chunk in zip_resp.iter_content(chunk_size=1024):
if chunk:
f.write(chunk)
logging.info("下载完成, 解压...")
import zipfile
with zipfile.ZipFile("temp/"+target_path+"/source.zip", 'r') as zip_ref:
zip_ref.extractall("temp/"+target_path)
os.remove("temp/"+target_path+"/source.zip")
# 目标是 username-repo-hash , 用正则表达式提取完整的文件夹名,复制到 plugins/repo
import glob
# 获取解压后的文件夹名
unzip_dir = glob.glob("temp/"+target_path+"/*")[0]
# 复制到 plugins/repo
shutil.copytree(unzip_dir, target_path+"/")
# 删除解压后的文件夹
shutil.rmtree(unzip_dir)
logging.info("解压完成")
else:
raise Exception("暂不支持的源类型,请使用 GitHub 仓库发行插件。")
return repo[1]
def check_requirements(path: str):
# 检查此目录是否包含requirements.txt
if os.path.exists("plugins/"+repo_url.split(".git")[0].split("/")[-1]+"/requirements.txt"):
if os.path.exists(path+"/requirements.txt"):
logging.info("检测到requirements.txt正在安装依赖")
import pkg.utils.pkgmgr
pkg.utils.pkgmgr.install_requirements("plugins/"+repo_url.split(".git")[0].split("/")[-1]+"/requirements.txt")
pkg.utils.pkgmgr.install_requirements(path+"/requirements.txt")
import main
main.reset_logging()
import pkg.utils.log as log
log.reset_logging()
def install_plugin(repo_url: str):
"""安装插件从git储存库获取并解决依赖"""
repo_label = download_plugin_source_code(repo_url, "plugins/")
check_requirements("plugins/"+repo_label)
metadata.set_plugin_metadata(repo_label, repo_url, int(time.time()), "HEAD")
def uninstall_plugin(plugin_name: str) -> str:
@@ -176,6 +277,47 @@ def uninstall_plugin(plugin_name: str) -> str:
return "plugins/"+plugin_path
def update_plugin(plugin_name: str):
"""更新插件"""
# 检查是否有远程地址记录
plugin_path_name = get_plugin_path_name_by_plugin_name(plugin_name)
meta = metadata.get_plugin_metadata(plugin_path_name)
if meta == {}:
raise Exception("没有此插件元数据信息,无法更新")
remote_url = meta['source']
if remote_url == "https://github.com/RockChinQ/QChatGPT" or remote_url == "https://gitee.com/RockChin/QChatGPT" \
or remote_url == "" or remote_url is None or remote_url == "http://github.com/RockChinQ/QChatGPT" or remote_url == "http://gitee.com/RockChin/QChatGPT":
raise Exception("插件没有远程地址记录,无法更新")
# 重新安装插件
logging.info("正在重新安装插件以进行更新...")
install_plugin(remote_url)
def get_plugin_name_by_path_name(plugin_path_name: str) -> str:
for k, v in __plugins__.items():
if v['path'] == "plugins/"+plugin_path_name+"/main.py":
return k
return None
def get_plugin_path_name_by_plugin_name(plugin_name: str) -> str:
if plugin_name not in __plugins__:
return None
plugin_main_module_path = __plugins__[plugin_name]['path']
plugin_main_module_path = plugin_main_module_path.replace("\\", "/")
spt = plugin_main_module_path.split("/")
return spt[1]
class EventContext:
"""事件上下文"""
eid = 0
@@ -212,7 +354,7 @@ class EventContext:
self.__return_value__[key] = []
self.__return_value__[key].append(ret)
def get_return(self, key: str):
def get_return(self, key: str) -> list:
"""获取key的所有返回值"""
if key in self.__return_value__:
return self.__return_value__[key]
@@ -261,7 +403,9 @@ class PluginHost:
"""插件宿主"""
def __init__(self):
"""初始化插件宿主"""
context.set_plugin_host(self)
self.calling_gpt_session = Session([])
def get_runtime_context(self) -> context:
"""获取运行时上下文pkg.utils.context模块的对象
@@ -276,13 +420,17 @@ class PluginHost:
"""获取机器人对象"""
return context.get_qqbot_manager().bot
def get_bot_adapter(self) -> msadapter.MessageSourceAdapter:
"""获取消息源适配器"""
return context.get_qqbot_manager().adapter
def send_person_message(self, person, message):
"""发送私聊消息"""
asyncio.run(self.get_bot().send_friend_message(person, message))
self.get_bot_adapter().send_message("person", person, message)
def send_group_message(self, group, message):
"""发送群消息"""
asyncio.run(self.get_bot().send_group_message(group, message))
self.get_bot_adapter().send_message("group", group, message)
def notify_admin(self, message):
"""通知管理员"""
@@ -327,7 +475,7 @@ class PluginHost:
logging.debug("插件 {} 已要求阻止事件 {} 的默认行为".format(plugin['name'], event_name))
except Exception as e:
logging.error("插件{}触发事件{}时发生错误".format(plugin['name'], event_name))
logging.error("插件{}响应事件{}时发生错误".format(plugin['name'], event_name))
logging.error(traceback.format_exc())
# print("done:{}".format(plugin['name']))
@@ -339,3 +487,6 @@ class PluginHost:
event_context.__return_value__))
return event_context
if __name__ == "__main__":
pass

87
pkg/plugin/metadata.py Normal file
View File

@@ -0,0 +1,87 @@
import os
import shutil
import json
import time
import dulwich.errors as dulwich_err
from ..utils import updater
def read_metadata_file() -> dict:
# 读取 plugins/metadata.json 文件
if not os.path.exists('plugins/metadata.json'):
return {}
with open('plugins/metadata.json', 'r') as f:
return json.load(f)
def write_metadata_file(metadata: dict):
if not os.path.exists('plugins'):
os.mkdir('plugins')
with open('plugins/metadata.json', 'w') as f:
json.dump(metadata, f, indent=4, ensure_ascii=False)
def do_plugin_git_repo_migrate():
# 仅在 plugins/metadata.json 不存在时执行
if os.path.exists('plugins/metadata.json'):
return
metadata = read_metadata_file()
# 遍历 plugins 下所有目录获取目录的git远程地址
for plugin_name in os.listdir('plugins'):
plugin_path = os.path.join('plugins', plugin_name)
if not os.path.isdir(plugin_path):
continue
remote_url = None
try:
remote_url = updater.get_remote_url(plugin_path)
except dulwich_err.NotGitRepository:
continue
if remote_url == "https://github.com/RockChinQ/QChatGPT" or remote_url == "https://gitee.com/RockChin/QChatGPT" \
or remote_url == "" or remote_url is None or remote_url == "http://github.com/RockChinQ/QChatGPT" or remote_url == "http://gitee.com/RockChin/QChatGPT":
continue
from . import host
if plugin_name not in metadata:
metadata[plugin_name] = {
'source': remote_url,
'install_timestamp': int(time.time()),
'ref': 'HEAD',
}
write_metadata_file(metadata)
def set_plugin_metadata(
plugin_name: str,
source: str,
install_timestamp: int,
ref: str,
):
metadata = read_metadata_file()
metadata[plugin_name] = {
'source': source,
'install_timestamp': install_timestamp,
'ref': ref,
}
write_metadata_file(metadata)
def remove_plugin_metadata(plugin_name: str):
metadata = read_metadata_file()
if plugin_name in metadata:
del metadata[plugin_name]
write_metadata_file(metadata)
def get_plugin_metadata(plugin_name: str) -> dict:
metadata = read_metadata_file()
if plugin_name in metadata:
return metadata[plugin_name]
return {}

View File

@@ -88,6 +88,8 @@ NormalMessageResponded = "normal_message_responded"
session: pkg.openai.session.Session 会话对象
prefix: str 回复文字消息的前缀
response_text: str 响应文本
finish_reason: str 响应结束原因
funcs_called: list[str] 此次响应中调用的函数列表
returns (optional):
prefix: str 修改后的回复文字消息的前缀
@@ -132,18 +134,64 @@ KeySwitched = "key_switched"
key_list: list[str] api-key列表
"""
PromptPreProcessing = "prompt_pre_processing"
"""每回合调用接口前对prompt进行预处理时触发此事件不支持阻止默认行为
kwargs:
session_name: str 会话名称(<launcher_type>_<launcher_id>)
default_prompt: list 此session使用的情景预设内容
prompt: list 此session现有的prompt内容
text_message: str 用户发送的消息文本
returns (optional):
default_prompt: list 修改后的情景预设内容
prompt: list 修改后的prompt内容
text_message: str 修改后的消息文本
"""
def on(event: str):
def on(*args, **kwargs):
"""注册事件监听器
:param
event: str 事件名称
"""
return Plugin.on(event)
return Plugin.on(*args, **kwargs)
def func(*args, **kwargs):
"""注册内容函数声明此函数为一个内容函数在对话中将发送此函数给GPT以供其调用
此函数可以具有任意的参数,但必须按照[此文档](https://github.com/RockChinQ/CallingGPT/wiki/1.-Function-Format#function-format)
所述的格式编写函数的docstring。
此功能仅支持在使用gpt-3.5或gpt-4系列模型时使用。
"""
return Plugin.func(*args, **kwargs)
__current_registering_plugin__ = ""
def require_ver(ge: str, le: str="v999.9.9") -> bool:
"""插件版本要求装饰器
Args:
ge (str): 最低版本要求
le (str, optional): 最高版本要求
Returns:
bool: 是否满足要求, False时为无法获取版本号True时为满足要求报错为不满足要求
"""
qchatgpt_version = ""
from pkg.utils.updater import get_current_tag, compare_version_str
try:
qchatgpt_version = get_current_tag() # 从updater模块获取版本号
except:
return False
if compare_version_str(qchatgpt_version, ge) < 0 or \
(compare_version_str(qchatgpt_version, le) > 0):
raise Exception("QChatGPT 版本不满足要求,某些功能(可能是由插件提供的)无法正常使用。(要求版本:{}-{},但当前版本:{}".format(ge, le, qchatgpt_version))
return True
class Plugin:
"""插件基类"""
@@ -176,6 +224,34 @@ class Plugin:
return wrapper
@classmethod
def func(cls, name: str=None):
"""内容函数装饰器
"""
global __current_registering_plugin__
from CallingGPT.entities.namespace import get_func_schema
def wrapper(func):
function_schema = get_func_schema(func)
function_schema['name'] = __current_registering_plugin__ + '-' + (func.__name__ if name is None else name)
function_schema['enabled'] = True
host.__function_inst_map__[function_schema['name']] = function_schema['function']
del function_schema['function']
# logging.debug("registering content function: p='{}', f='{}', s={}".format(__current_registering_plugin__, func, function_schema))
host.__callable_functions__.append(
function_schema
)
return func
return wrapper
def register(name: str, description: str, version: str, author: str):
"""注册插件, 此函数作为装饰器使用

View File

@@ -8,7 +8,10 @@ import logging
def wrapper_dict_from_runtime_context() -> dict:
"""从变量中包装settings.json的数据字典"""
settings = {
"order": []
"order": [],
"functions": {
"enabled": host.__enable_content_functions__
}
}
for plugin_name in host.__plugins_order__:
@@ -22,6 +25,11 @@ def apply_settings(settings: dict):
if "order" in settings:
host.__plugins_order__ = settings["order"]
if "functions" in settings:
if "enabled" in settings["functions"]:
host.__enable_content_functions__ = settings["functions"]["enabled"]
# logging.debug("set content function enabled: {}".format(host.__enable_content_functions__))
def dump_settings():
"""保存settings.json数据"""
@@ -78,6 +86,17 @@ def load_settings():
settings["order"].append(plugin_name)
settings_modified = True
if "functions" not in settings:
settings["functions"] = {
"enabled": host.__enable_content_functions__
}
settings_modified = True
elif "enabled" not in settings["functions"]:
settings["functions"]["enabled"] = host.__enable_content_functions__
settings_modified = True
logging.info("已全局{}内容函数。".format("启用" if settings["functions"]["enabled"] else "禁用"))
apply_settings(settings)
if settings_modified:

View File

@@ -28,6 +28,11 @@ def apply_switch(switch: dict):
for plugin_name in switch:
host.__plugins__[plugin_name]["enabled"] = switch[plugin_name]["enabled"]
# 查找此插件的所有内容函数
for func in host.__callable_functions__:
if func['name'].startswith(plugin_name + '-'):
func['enabled'] = switch[plugin_name]["enabled"]
def dump_switch():
"""保存开关数据"""

136
pkg/qqbot/adapter.py Normal file
View File

@@ -0,0 +1,136 @@
# MessageSource的适配器
import typing
import mirai
class MessageSourceAdapter:
def __init__(self, config: dict):
pass
def send_message(
self,
target_type: str,
target_id: str,
message: mirai.MessageChain
):
"""发送消息
Args:
target_type (str): 目标类型,`person`或`group`
target_id (str): 目标ID
message (mirai.MessageChain): YiriMirai库的消息链
"""
raise NotImplementedError
def reply_message(
self,
message_source: mirai.MessageEvent,
message: mirai.MessageChain,
quote_origin: bool = False
):
"""回复消息
Args:
message_source (mirai.MessageEvent): YiriMirai消息源事件
message (mirai.MessageChain): YiriMirai库的消息链
quote_origin (bool, optional): 是否引用原消息. Defaults to False.
"""
raise NotImplementedError
def is_muted(self, group_id: int) -> bool:
"""获取账号是否在指定群被禁言"""
raise NotImplementedError
def register_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
"""注册事件监听器
Args:
event_type (typing.Type[mirai.Event]): YiriMirai事件类型
callback (typing.Callable[[mirai.Event], None]): 回调函数接收一个参数为YiriMirai事件
"""
raise NotImplementedError
def unregister_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
"""注销事件监听器
Args:
event_type (typing.Type[mirai.Event]): YiriMirai事件类型
callback (typing.Callable[[mirai.Event], None]): 回调函数接收一个参数为YiriMirai事件
"""
raise NotImplementedError
def run_sync(self):
"""以阻塞的方式运行适配器"""
raise NotImplementedError
def kill(self) -> bool:
"""关闭适配器
Returns:
bool: 是否成功关闭热重载时若此函数返回False则不会重载MessageSource底层
"""
raise NotImplementedError
class MessageConverter:
"""消息链转换器基类"""
@staticmethod
def yiri2target(message_chain: mirai.MessageChain):
"""将YiriMirai消息链转换为目标消息链
Args:
message_chain (mirai.MessageChain): YiriMirai消息链
Returns:
typing.Any: 目标消息链
"""
raise NotImplementedError
@staticmethod
def target2yiri(message_chain: typing.Any) -> mirai.MessageChain:
"""将目标消息链转换为YiriMirai消息链
Args:
message_chain (typing.Any): 目标消息链
Returns:
mirai.MessageChain: YiriMirai消息链
"""
raise NotImplementedError
class EventConverter:
"""事件转换器基类"""
@staticmethod
def yiri2target(event: typing.Type[mirai.Event]):
"""将YiriMirai事件转换为目标事件
Args:
event (typing.Type[mirai.Event]): YiriMirai事件
Returns:
typing.Any: 目标事件
"""
raise NotImplementedError
@staticmethod
def target2yiri(event: typing.Any) -> mirai.Event:
"""将目标事件的调用参数转换为YiriMirai的事件参数对象
Args:
event (typing.Any): 目标事件
Returns:
typing.Type[mirai.Event]: YiriMirai事件
"""
raise NotImplementedError

View File

@@ -64,12 +64,7 @@ def text_to_image(text: str) -> MessageComponent:
def check_text(text: str) -> list:
"""检查文本是否为长消息,并转换成该使用的消息链组件"""
if not hasattr(config, 'blob_message_threshold'):
return [text]
if len(text) > config.blob_message_threshold:
if not hasattr(config, 'blob_message_strategy'):
raise AttributeError('未定义长消息处理策略')
# logging.info("长消息: {}".format(text))
if config.blob_message_strategy == 'image':

View File

@@ -9,6 +9,9 @@ import json
__command_list__ = {}
import tips as tips_custom
"""命令树
结构
@@ -257,12 +260,12 @@ def execute(context: Context) -> list:
while True:
try:
logging.debug('执行指令: {}'.format(path))
node = __command_list__[path]
logging.debug('执行指令: {}'.format(path))
# 检查权限
if ctx.privilege < node['privilege']:
raise CommandPrivilegeError('权限不足: {}'.format(path))
raise CommandPrivilegeError(tips_custom.command_admin_message+"{}".format(path))
# 执行
execed, reply = node['cls'].process(ctx)
@@ -275,7 +278,7 @@ def execute(context: Context) -> list:
path = path + '.' + ctx.crt_command
except KeyError:
traceback.print_exc()
raise CommandPrivilegeError('找不到指令: {}'.format(path))
raise CommandPrivilegeError(tips_custom.command_err_message+"{}".format(path))
def register_all():
@@ -324,6 +327,10 @@ def apply_privileges():
for path, priv in data.items():
if path == 'comment':
continue
if path not in __command_list__:
continue
if __command_list__[path]['privilege'] != priv:
logging.debug('应用权限: {} -> {}(default: {})'.format(path, priv, __command_list__[path]['privilege']))

View File

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import logging
from mirai import Image
@@ -19,6 +19,7 @@ class DrawCommand(AbstractCommandNode):
import pkg.openai.session
reply = []
if len(ctx.params) == 0:
reply = ["[bot]err: 未提供图片描述文字"]
else:

View File

@@ -0,0 +1,33 @@
from ..aamgr import AbstractCommandNode, Context
import logging
import json
@AbstractCommandNode.register(
parent=None,
name="func",
description="管理内容函数",
usage="!func",
aliases=[],
privilege=1
)
class FuncCommand(AbstractCommandNode):
@classmethod
def process(cls, ctx: Context) -> tuple[bool, list]:
from pkg.plugin.models import host
reply = []
reply_str = "当前已加载的内容函数:\n\n"
logging.debug("host.__callable_functions__: {}".format(json.dumps(host.__callable_functions__, indent=4)))
index = 1
for func in host.__callable_functions__:
reply_str += "{}. {}{}:\n{}\n\n".format(index, ("(已禁用) " if not func['enabled'] else ""), func['name'], func['description'])
index += 1
reply = [reply_str]
return True, reply

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import os
@@ -10,9 +10,9 @@ import pkg.utils.updater as updater
parent=None,
name="plugin",
description="插件管理",
usage="!plugin\n!plugin get <插件仓库地址>\!plugin update\n!plugin del <插件名>\n!plugin on <插件名>\n!plugin off <插件名>",
usage="!plugin\n!plugin get <插件仓库地址>\n!plugin update\n!plugin del <插件名>\n!plugin on <插件名>\n!plugin off <插件名>",
aliases=[],
privilege=2
privilege=1
)
class PluginCommand(AbstractCommandNode):
@classmethod
@@ -42,7 +42,7 @@ class PluginCommand(AbstractCommandNode):
reply = [reply_str]
return True, reply
elif ctx.params[0].startswith("http"):
reply = ["[bot]err: 此命令已用,请使用 !plugin get <插件仓库地址> 进行安装"]
reply = ["[bot]err: 此命令已用,请使用 !plugin get <插件仓库地址> 进行安装"]
return True, reply
else:
return False, []
@@ -84,7 +84,7 @@ class PluginGetCommand(AbstractCommandNode):
@AbstractCommandNode.register(
parent=PluginCommand,
name="update",
description="更新所有插件",
description="更新指定插件或全部插件",
usage="!plugin update",
aliases=[],
privilege=2
@@ -97,37 +97,36 @@ class PluginUpdateCommand(AbstractCommandNode):
plugin_list = plugin_host.__plugins__
reply = []
def closure():
try:
import pkg.utils.context
updated = []
for key in plugin_list:
plugin = plugin_list[key]
if updater.is_repo("/".join(plugin['path'].split('/')[:-1])):
success = updater.pull_latest("/".join(plugin['path'].split('/')[:-1]))
if success:
updated.append(plugin['name'])
# 检查是否有requirements.txt
pkg.utils.context.get_qqbot_manager().notify_admin("正在安装依赖...")
for key in plugin_list:
plugin = plugin_list[key]
if os.path.exists("/".join(plugin['path'].split('/')[:-1])+"/requirements.txt"):
logging.info("{}检测到requirements.txt安装依赖".format(plugin['name']))
import pkg.utils.pkgmgr
pkg.utils.pkgmgr.install_requirements("/".join(plugin['path'].split('/')[:-1])+"/requirements.txt")
if len(ctx.crt_params) > 0:
def closure():
try:
import pkg.utils.context
updated = []
import main
main.reset_logging()
if ctx.crt_params[0] == 'all':
for key in plugin_list:
plugin_host.update_plugin(key)
updated.append(key)
else:
plugin_path_name = plugin_host.get_plugin_path_name_by_plugin_name(ctx.crt_params[0])
pkg.utils.context.get_qqbot_manager().notify_admin("已更新插件: {}".format(", ".join(updated)))
except Exception as e:
logging.error("插件更新失败:{}".format(e))
pkg.utils.context.get_qqbot_manager().notify_admin("插件更新失败:{} 请尝试手动更新插件".format(e))
if plugin_path_name is not None:
plugin_host.update_plugin(ctx.crt_params[0])
updated.append(ctx.crt_params[0])
else:
raise Exception("未找到插件: {}".format(ctx.crt_params[0]))
pkg.utils.context.get_qqbot_manager().notify_admin("已更新插件: {}, 请发送 !reload 重载插件".format(", ".join(updated)))
except Exception as e:
logging.error("插件更新失败:{}".format(e))
pkg.utils.context.get_qqbot_manager().notify_admin("插件更新失败:{} 请使用 !plugin 命令确认插件名称或尝试手动更新插件".format(e))
threading.Thread(target=closure).start()
reply = ["[bot]正在更新所有插件,请勿重复发起..."]
reply = ["[bot]正在更新插件,请勿重复发起..."]
threading.Thread(target=closure).start()
else:
reply = ["[bot]请指定要更新的插件, 或使用 !plugin update all 更新所有插件"]
return True, reply
@@ -191,6 +190,11 @@ class PluginOnOffCommand(AbstractCommandNode):
plugin_name = ctx.crt_params[0]
if plugin_name in plugin_list:
plugin_list[plugin_name]['enabled'] = new_status
for func in plugin_host.__callable_functions__:
if func['name'].startswith(plugin_name+"-"):
func['enabled'] = new_status
plugin_switch.dump_switch()
reply = ["[bot]已{}插件: {}".format("启用" if new_status else "禁用", plugin_name)]
else:

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
@AbstractCommandNode.register(

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
@AbstractCommandNode.register(

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime
import json

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import datetime

View File

@@ -1,4 +1,5 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import tips as tips_custom
import pkg.openai.session
import pkg.utils.context
@@ -22,12 +23,12 @@ class ResetCommand(AbstractCommandNode):
if len(params) == 0:
pkg.openai.session.get_session(session_name).reset(explicit=True)
reply = ["[bot]会话已重置"]
reply = [tips_custom.command_reset_message]
else:
try:
import pkg.openai.dprompt as dprompt
pkg.openai.session.get_session(session_name).reset(explicit=True, use_prompt=params[0])
reply = ["[bot]会话已重置,使用场景预设:{}".format(dprompt.mode_inst().get_full_name(params[0]))]
reply = [tips_custom.command_reset_name_message+"{}".format(dprompt.mode_inst().get_full_name(params[0]))]
except Exception as e:
reply = ["[bot]会话重置失败:{}".format(e)]

View File

@@ -0,0 +1,100 @@
from ..aamgr import AbstractCommandNode, Context
import json
def config_operation(cmd, params):
reply = []
import pkg.utils.context
config = pkg.utils.context.get_config()
reply_str = ""
if len(params) == 0:
reply = ["[bot]err:请输入!cmd cfg查看使用方法"]
else:
cfg_name = params[0]
if cfg_name == 'all':
reply_str = "[bot]所有配置项:\n\n"
for cfg in dir(config):
if not cfg.startswith('__') and not cfg == 'logging':
# 根据配置项类型进行格式化如果是字典则转换为json并格式化
if isinstance(getattr(config, cfg), str):
reply_str += "{}: \"{}\"\n".format(cfg, getattr(config, cfg))
elif isinstance(getattr(config, cfg), dict):
# 不进行unicode转义并格式化
reply_str += "{}: {}\n".format(cfg,
json.dumps(getattr(config, cfg),
ensure_ascii=False, indent=4))
else:
reply_str += "{}: {}\n".format(cfg, getattr(config, cfg))
reply = [reply_str]
else:
cfg_entry_path = cfg_name.split('.')
try:
if len(params) == 1:
cfg_entry = getattr(config, cfg_entry_path[0])
if len(cfg_entry_path) > 1:
for i in range(1, len(cfg_entry_path)):
cfg_entry = cfg_entry[cfg_entry_path[i]]
if isinstance(cfg_entry, str):
reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, cfg_entry)
elif isinstance(cfg_entry, dict):
reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
json.dumps(cfg_entry,
ensure_ascii=False, indent=4))
else:
reply_str = "[bot]配置项{}: {}\n".format(cfg_name, cfg_entry)
reply = [reply_str]
else:
cfg_value = " ".join(params[1:])
# 类型转换如果是json则转换为字典
# if cfg_value == 'true':
# cfg_value = True
# elif cfg_value == 'false':
# cfg_value = False
# elif cfg_value.isdigit():
# cfg_value = int(cfg_value)
# elif cfg_value.startswith('{') and cfg_value.endswith('}'):
# cfg_value = json.loads(cfg_value)
# else:
# try:
# cfg_value = float(cfg_value)
# except ValueError:
# pass
cfg_value = eval(cfg_value)
cfg_entry = getattr(config, cfg_entry_path[0])
if len(cfg_entry_path) > 1:
for i in range(1, len(cfg_entry_path) - 1):
cfg_entry = cfg_entry[cfg_entry_path[i]]
if isinstance(cfg_entry[cfg_entry_path[-1]], type(cfg_value)):
cfg_entry[cfg_entry_path[-1]] = cfg_value
reply = ["[bot]配置项{}修改成功".format(cfg_name)]
else:
reply = ["[bot]err:配置项{}类型不匹配".format(cfg_name)]
else:
setattr(config, cfg_entry_path[0], cfg_value)
reply = ["[bot]配置项{}修改成功".format(cfg_name)]
except AttributeError:
reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
except ValueError:
reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
# else:
# reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
return reply
@AbstractCommandNode.register(
parent=None,
name="cfg",
description="配置项管理",
usage="!cfg <配置项> [配置值]\n!cfg all",
aliases=[],
privilege=2
)
class CfgCommand(AbstractCommandNode):
@classmethod
def process(cls, ctx: Context) -> tuple[bool, list]:
return True, config_operation(ctx.command, ctx.params)

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context, __command_list__
from ..aamgr import AbstractCommandNode, Context, __command_list__
@AbstractCommandNode.register(

View File

@@ -1,39 +0,0 @@
from ..mgr import AbstractCommandNode, Context, __command_list__
@AbstractCommandNode.register(
parent=None,
name="cmd",
description="显示指令列表",
usage="!help\n!help <指令名称>",
aliases=[],
privilege=1
)
class CmdCommand(AbstractCommandNode):
@classmethod
def process(cls, ctx: Context) -> tuple[bool, list]:
command_list = __command_list__
reply = []
if len(ctx.params) == 0:
reply_str = "[bot]当前所有指令:\n\n"
# 遍历顶级指令
for key in command_list:
command = command_list[key]
if command['parent'] is None:
reply_str += "!{} - {}\n".format(key, command['description'])
reply_str += "\n请使用 !cmd <指令名称> 来查看指令的详细信息"
reply = [reply_str]
else:
command_name = ctx.params[0]
if command_name in command_list:
reply = [command_list[command_name]['cls'].help()]
else:
reply = ["[bot]指令 {} 不存在".format(command_name)]
return True, reply

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
@AbstractCommandNode.register(
@@ -12,8 +12,13 @@ from ..mgr import AbstractCommandNode, Context
class HelpCommand(AbstractCommandNode):
@classmethod
def process(cls, ctx: Context) -> tuple[bool, list]:
import tips
reply = ["[bot] "+tips.help_message + "\n请输入 !cmd 查看指令列表"]
# 警告config.help_message过时
import config
reply = [(config.help_message if hasattr(config, 'help_message') else "") + "\n请输入 !cmds 查看指令列表"]
if hasattr(config, "help_message"):
reply[0] += "\n\n警告config.py中的help_message已过时不再生效请使用tips.py中的help_message替代"
return True, reply

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import threading
@AbstractCommandNode.register(

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import threading
import traceback

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
import logging

View File

@@ -1,4 +1,4 @@
from ..mgr import AbstractCommandNode, Context
from ..aamgr import AbstractCommandNode, Context
@AbstractCommandNode.register(

View File

@@ -14,7 +14,7 @@ import pkg.utils.context
import pkg.qqbot.message
import pkg.utils.credit as credit
# import pkg.qqbot.cmds.model as cmdmodel
import pkg.qqbot.cmds.mgr as cmdmgr
import pkg.qqbot.cmds.aamgr as cmdmgr
from mirai import Image
@@ -54,7 +54,7 @@ def process_command(session_name: str, text_message: str, mgr, config,
try:
reply = cmdmgr.execute(context)
except cmdmgr.CommandPrivilegeError as e:
reply = ["[bot]err:{}".format(e)]
reply = ["{}".format(e)]
return reply
except Exception as e:

View File

@@ -21,11 +21,11 @@ class ReplyFilter:
self.mask = mask
self.mask_word = mask_word
import config
if hasattr(config, 'baidu_check') and hasattr(config, 'baidu_api_key') and hasattr(config, 'baidu_secret_key'):
self.baidu_check = config.baidu_check
self.baidu_api_key = config.baidu_api_key
self.baidu_secret_key = config.baidu_secret_key
self.inappropriate_message_tips = config.inappropriate_message_tips
self.baidu_check = config.baidu_check
self.baidu_api_key = config.baidu_api_key
self.baidu_secret_key = config.baidu_secret_key
self.inappropriate_message_tips = config.inappropriate_message_tips
def is_illegal(self, message: str) -> bool:
processed = self.process(message)

View File

@@ -5,9 +5,6 @@ def ignore(msg: str) -> bool:
"""检查消息是否应该被忽略"""
import config
if not hasattr(config, 'ignore_rules'):
return False
if 'prefix' in config.ignore_rules:
for rule in config.ignore_rules['prefix']:
if msg.startswith(rule):

View File

@@ -3,9 +3,9 @@ import json
import os
import threading
import mirai.models.bus
from mirai import At, GroupMessage, MessageEvent, Mirai, StrangerMessage, WebSocketAdapter, HTTPAdapter, \
FriendMessage, Image
FriendMessage, Image, MessageChain, Plain
from func_timeout import func_set_timeout
import pkg.openai.session
@@ -19,15 +19,24 @@ import pkg.utils.context
import pkg.plugin.host as plugin_host
import pkg.plugin.models as plugin_models
import tips as tips_custom
import pkg.qqbot.adapter as msadapter
# 检查消息是否符合泛响应匹配机制
def check_response_rule(text: str):
def check_response_rule(group_id:int, text: str):
config = pkg.utils.context.get_config()
if not hasattr(config, 'response_rules'):
return False, ''
rules = config.response_rules
# 检查是否有特定规则
if 'prefix' not in config.response_rules:
if str(group_id) in config.response_rules:
rules = config.response_rules[str(group_id)]
else:
rules = config.response_rules['default']
# 检查前缀匹配
if 'prefix' in rules:
for rule in rules['prefix']:
@@ -45,19 +54,39 @@ def check_response_rule(text: str):
return False, ""
def response_at():
def response_at(group_id: int):
config = pkg.utils.context.get_config()
if 'at' not in config.response_rules:
use_response_rule = config.response_rules
# 检查是否有特定规则
if 'prefix' not in config.response_rules:
if str(group_id) in config.response_rules:
use_response_rule = config.response_rules[str(group_id)]
else:
use_response_rule = config.response_rules['default']
if 'at' not in use_response_rule:
return True
return config.response_rules['at']
return use_response_rule['at']
def random_responding():
def random_responding(group_id):
config = pkg.utils.context.get_config()
if 'random_rate' in config.response_rules:
use_response_rule = config.response_rules
# 检查是否有特定规则
if 'prefix' not in config.response_rules:
if str(group_id) in config.response_rules:
use_response_rule = config.response_rules[str(group_id)]
else:
use_response_rule = config.response_rules['default']
if 'random_rate' in use_response_rule:
import random
return random.random() < config.response_rules['random_rate']
return random.random() < use_response_rule['random_rate']
return False
@@ -65,57 +94,52 @@ def random_responding():
class QQBotManager:
retry = 3
bot: Mirai = None
adapter: msadapter.MessageSourceAdapter = None
bot_account_id: int = 0
reply_filter = None
enable_banlist = False
enable_private = True
enable_group = True
ban_person = []
ban_group = []
def __init__(self, mirai_http_api_config: dict, timeout: int = 60, retry: int = 3, first_time_init=True):
self.timeout = timeout
self.retry = retry
def __init__(self, first_time_init=True):
import config
# 加载禁用列表
if os.path.exists("banlist.py"):
import banlist
self.enable_banlist = banlist.enable
self.ban_person = banlist.person
self.ban_group = banlist.group
logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))
config = pkg.utils.context.get_config()
if os.path.exists("sensitive.json") \
and config.sensitive_word_filter is not None \
and config.sensitive_word_filter:
with open("sensitive.json", "r", encoding="utf-8") as f:
sensitive_json = json.load(f)
self.reply_filter = pkg.qqbot.filter.ReplyFilter(
sensitive_words=sensitive_json['words'],
mask=sensitive_json['mask'] if 'mask' in sensitive_json else '*',
mask_word=sensitive_json['mask_word'] if 'mask_word' in sensitive_json else ''
)
else:
self.reply_filter = pkg.qqbot.filter.ReplyFilter([])
self.timeout = config.process_message_timeout
self.retry = config.retry_times
# 由于YiriMirai的bot对象是单例的且shutdown方法暂时无法使用
# 故只在第一次初始化时创建bot对象重载之后使用原bot对象
# 因此bot的配置不支持热重载
if first_time_init:
self.first_time_init(mirai_http_api_config)
logging.debug("Use adapter:" + config.msg_source_adapter)
if config.msg_source_adapter == 'yirimirai':
from pkg.qqbot.sources.yirimirai import YiriMiraiAdapter
mirai_http_api_config = config.mirai_http_api_config
self.bot_account_id = config.mirai_http_api_config['qq']
self.adapter = YiriMiraiAdapter(mirai_http_api_config)
elif config.msg_source_adapter == 'nakuru':
from pkg.qqbot.sources.nakuru import NakuruProjectAdapter
self.adapter = NakuruProjectAdapter(config.nakuru_config)
self.bot_account_id = self.adapter.bot_account_id
else:
self.bot = pkg.utils.context.get_qqbot_manager().bot
self.adapter = pkg.utils.context.get_qqbot_manager().adapter
self.bot_account_id = pkg.utils.context.get_qqbot_manager().bot_account_id
pkg.utils.context.set_qqbot_manager(self)
# 注册诸事件
# Caution: 注册新的事件处理器之后请务必在unsubscribe_all中编写相应的取消订阅代码
@self.bot.on(FriendMessage)
async def on_friend_message(event: FriendMessage):
def friend_message_handler(event: FriendMessage):
def on_friend_message(event: FriendMessage):
def friend_message_handler():
# 触发事件
args = {
"launcher_type": "person",
@@ -132,13 +156,15 @@ class QQBotManager:
pkg.utils.context.get_thread_ctl().submit_user_task(
friend_message_handler,
event
)
self.adapter.register_listener(
FriendMessage,
on_friend_message
)
@self.bot.on(StrangerMessage)
async def on_stranger_message(event: StrangerMessage):
def on_stranger_message(event: StrangerMessage):
def stranger_message_handler(event: StrangerMessage):
def stranger_message_handler():
# 触发事件
args = {
"launcher_type": "person",
@@ -155,11 +181,15 @@ class QQBotManager:
pkg.utils.context.get_thread_ctl().submit_user_task(
stranger_message_handler,
event
)
# nakuru不区分好友和陌生人故仅为yirimirai注册陌生人事件
if config.msg_source_adapter == 'yirimirai':
self.adapter.register_listener(
StrangerMessage,
on_stranger_message
)
@self.bot.on(GroupMessage)
async def on_group_message(event: GroupMessage):
def on_group_message(event: GroupMessage):
def group_message_handler(event: GroupMessage):
# 触发事件
@@ -180,64 +210,92 @@ class QQBotManager:
group_message_handler,
event
)
self.adapter.register_listener(
GroupMessage,
on_group_message
)
def unsubscribe_all():
"""取消所有订阅
用于在热重载流程中卸载所有事件处理器
"""
assert isinstance(self.bot, Mirai)
bus = self.bot.bus
assert isinstance(bus, mirai.models.bus.ModelEventBus)
bus.unsubscribe(FriendMessage, on_friend_message)
bus.unsubscribe(StrangerMessage, on_stranger_message)
bus.unsubscribe(GroupMessage, on_group_message)
import config
self.adapter.unregister_listener(
FriendMessage,
on_friend_message
)
if config.msg_source_adapter == 'yirimirai':
self.adapter.unregister_listener(
StrangerMessage,
on_stranger_message
)
self.adapter.unregister_listener(
GroupMessage,
on_group_message
)
self.unsubscribe_all = unsubscribe_all
def go(self, func, *args, **kwargs):
self.pool.submit(func, *args, **kwargs)
# 加载禁用列表
if os.path.exists("banlist.py"):
import banlist
self.enable_banlist = banlist.enable
self.ban_person = banlist.person
self.ban_group = banlist.group
logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))
def first_time_init(self, mirai_http_api_config: dict):
"""热重载后不再运行此函数"""
if hasattr(banlist, "enable_private"):
self.enable_private = banlist.enable_private
if hasattr(banlist, "enable_group"):
self.enable_group = banlist.enable_group
if 'adapter' not in mirai_http_api_config or mirai_http_api_config['adapter'] == "WebSocketAdapter":
bot = Mirai(
qq=mirai_http_api_config['qq'],
adapter=WebSocketAdapter(
verify_key=mirai_http_api_config['verifyKey'],
host=mirai_http_api_config['host'],
port=mirai_http_api_config['port']
)
)
elif mirai_http_api_config['adapter'] == "HTTPAdapter":
bot = Mirai(
qq=mirai_http_api_config['qq'],
adapter=HTTPAdapter(
verify_key=mirai_http_api_config['verifyKey'],
host=mirai_http_api_config['host'],
port=mirai_http_api_config['port']
)
)
else:
raise Exception("未知的适配器类型")
self.bot = bot
def send(self, event, msg, check_quote=True):
config = pkg.utils.context.get_config()
asyncio.run(
self.bot.send(event, msg, quote=True if hasattr(config,
"quote_origin") and config.quote_origin and check_quote else False))
if os.path.exists("sensitive.json") \
and config.sensitive_word_filter is not None \
and config.sensitive_word_filter:
with open("sensitive.json", "r", encoding="utf-8") as f:
sensitive_json = json.load(f)
self.reply_filter = pkg.qqbot.filter.ReplyFilter(
sensitive_words=sensitive_json['words'],
mask=sensitive_json['mask'] if 'mask' in sensitive_json else '*',
mask_word=sensitive_json['mask_word'] if 'mask_word' in sensitive_json else ''
)
else:
self.reply_filter = pkg.qqbot.filter.ReplyFilter([])
def send(self, event, msg, check_quote=True, check_at_sender=True):
config = pkg.utils.context.get_config()
if check_at_sender and config.at_sender:
msg.insert(
0,
Plain(" \n")
)
# 当回复的正文中包含换行时quote可能会自带at此时就不再单独添加at只添加换行
if "\n" not in str(msg[1]) or config.msg_source_adapter == 'nakuru':
msg.insert(
0,
At(
event.sender.id
)
)
self.adapter.reply_message(
event,
msg,
quote_origin=True if config.quote_origin and check_quote else False
)
# 私聊消息处理
def on_person_message(self, event: MessageEvent):
import config
reply = ''
if event.sender.id == self.bot.qq:
if not self.enable_private:
logging.debug("已在banlist.py中禁用所有私聊")
elif event.sender.id == self.bot_account_id:
pass
else:
if Image in event.message_chain:
@@ -268,20 +326,19 @@ class QQBotManager:
if failed == self.retry:
pkg.openai.session.get_session('person_{}'.format(event.sender.id)).release_response_lock()
self.notify_admin("{} 请求超时".format("person_{}".format(event.sender.id)))
reply = ["[bot]err:请求超时"]
reply = [tips_custom.reply_message]
if reply:
return self.send(event, reply, check_quote=False)
return self.send(event, reply, check_quote=False, check_at_sender=False)
# 群消息处理
def on_group_message(self, event: GroupMessage):
import config
reply = ''
def process(text=None) -> str:
replys = ""
if At(self.bot.qq) in event.message_chain:
event.message_chain.remove(At(self.bot.qq))
if At(self.bot_account_id) in event.message_chain:
event.message_chain.remove(At(self.bot_account_id))
# 超时则重试,重试超过次数则放弃
failed = 0
@@ -308,23 +365,25 @@ class QQBotManager:
if failed == self.retry:
pkg.openai.session.get_session('group_{}'.format(event.group.id)).release_response_lock()
self.notify_admin("{} 请求超时".format("group_{}".format(event.group.id)))
replys = ["[bot]err:请求超时"]
replys = [tips_custom.replys_message]
return replys
if Image in event.message_chain:
if not self.enable_group:
logging.debug("已在banlist.py中禁用所有群聊")
elif Image in event.message_chain:
pass
else:
if At(self.bot.qq) in event.message_chain and response_at():
if At(self.bot_account_id) in event.message_chain and response_at(event.group.id):
# 直接调用
reply = process()
else:
check, result = check_response_rule(str(event.message_chain).strip())
check, result = check_response_rule(event.group.id, str(event.message_chain).strip())
if check:
reply = process(result.strip())
# 检查是否随机响应
elif random_responding():
elif random_responding(event.group.id):
logging.info("随机响应group_{}消息".format(event.group.id))
reply = process()
@@ -334,25 +393,36 @@ class QQBotManager:
# 通知系统管理员
def notify_admin(self, message: str):
config = pkg.utils.context.get_config()
if hasattr(config, "admin_qq") and config.admin_qq != 0 and config.admin_qq != []:
if config.admin_qq != 0 and config.admin_qq != []:
logging.info("通知管理员:{}".format(message))
if type(config.admin_qq) == int:
send_task = self.bot.send_friend_message(config.admin_qq, "[bot]{}".format(message))
threading.Thread(target=asyncio.run, args=(send_task,)).start()
self.adapter.send_message(
"person",
config.admin_qq,
MessageChain([Plain("[bot]{}".format(message))])
)
else:
for adm in config.admin_qq:
send_task = self.bot.send_friend_message(adm, "[bot]{}".format(message))
threading.Thread(target=asyncio.run, args=(send_task,)).start()
self.adapter.send_message(
"person",
adm,
MessageChain([Plain("[bot]{}".format(message))])
)
def notify_admin_message_chain(self, message):
config = pkg.utils.context.get_config()
if hasattr(config, "admin_qq") and config.admin_qq != 0 and config.admin_qq != []:
if config.admin_qq != 0 and config.admin_qq != []:
logging.info("通知管理员:{}".format(message))
if type(config.admin_qq) == int:
send_task = self.bot.send_friend_message(config.admin_qq, message)
threading.Thread(target=asyncio.run, args=(send_task,)).start()
self.adapter.send_message(
"person",
config.admin_qq,
message
)
else:
for adm in config.admin_qq:
send_task = self.bot.send_friend_message(adm, message)
threading.Thread(target=asyncio.run, args=(send_task,)).start()
self.adapter.send_message(
"person",
adm,
message
)

View File

@@ -7,17 +7,15 @@ import pkg.openai.session
import pkg.plugin.host as plugin_host
import pkg.plugin.models as plugin_models
import pkg.qqbot.blob as blob
import tips as tips_custom
def handle_exception(notify_admin: str = "", set_reply: str = "") -> list:
"""处理异常当notify_admin不为空时会通知管理员返回通知用户的消息"""
import config
pkg.utils.context.get_qqbot_manager().notify_admin(notify_admin)
if hasattr(config, 'hide_exce_info_to_user') and config.hide_exce_info_to_user:
if hasattr(config, 'alter_tip_message'):
return [config.alter_tip_message] if config.alter_tip_message else []
else:
return ["[bot]出错了,请重试或联系管理员"]
if config.hide_exce_info_to_user:
return [tips_custom.alter_tip_message] if tips_custom.alter_tip_message else []
else:
return [set_reply]
@@ -40,9 +38,9 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
reply = handle_exception(notify_admin=f"{session_name},多次尝试失败。", set_reply=f"[bot]多次尝试失败,请重试或联系管理员")
break
try:
prefix = "[GPT]" if hasattr(config, "show_prefix") and config.show_prefix else ""
prefix = "[GPT]" if config.show_prefix else ""
text = session.append(text_message)
text, finish_reason, funcs = session.query(text_message)
# 触发插件事件
args = {
@@ -51,7 +49,9 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
"sender_id": sender_id,
"session": session,
"prefix": prefix,
"response_text": text
"response_text": text,
"finish_reason": finish_reason,
"funcs_called": funcs,
}
event = pkg.plugin.host.emit(plugin_models.NormalMessageResponded, **args)
@@ -64,14 +64,15 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
if not event.is_prevented_default():
reply = [prefix + text]
except openai.error.APIConnectionError as e:
except openai.APIConnectionError as e:
err_msg = str(e)
if err_msg.__contains__('Error communicating with OpenAI'):
reply = handle_exception("{}会话调用API失败:{}\n请尝试关闭网络代理来解决此问题。".format(session_name, e),
reply = handle_exception("{}会话调用API失败:{}\n您的网络无法访问OpenAI接口或网络代理不正常".format(session_name, e),
"[bot]err:调用API失败请重试或联系管理员或等待修复")
else:
reply = handle_exception("{}会话调用API失败:{}".format(session_name, e), "[bot]err:调用API失败请重试或联系管理员或等待修复")
except openai.error.RateLimitError as e:
except openai.RateLimitError as e:
logging.debug(type(e))
logging.debug(e.error['message'])
@@ -115,10 +116,14 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
else:
reply = handle_exception("{}会话调用API失败:{}".format(session_name, e),
"[bot]err:RateLimitError,请重试或联系作者,或等待修复")
except openai.error.InvalidRequestError as e:
reply = handle_exception("{}API调用参数错误:{}\n".format(
session_name, e), "[bot]err:API调用参数错误请联系管理员或等待修复")
except openai.error.ServiceUnavailableError as e:
except openai.BadRequestError as e:
if config.auto_reset and "This model's maximum context length is" in str(e):
session.reset(persist=True)
reply = [tips_custom.session_auto_reset_message]
else:
reply = handle_exception("{}API调用参数错误:{}\n".format(
session_name, e), "[bot]err:API调用参数错误请联系管理员或等待修复")
except openai.APIStatusError as e:
reply = handle_exception("{}API调用服务不可用:{}".format(session_name, e), "[bot]err:API调用服务不可用请重试或联系管理员或等待修复")
except Exception as e:
logging.exception(e)

View File

@@ -27,6 +27,7 @@ import pkg.plugin.models as plugin_models
import pkg.qqbot.ignore as ignore
import pkg.qqbot.banlist as banlist
import pkg.qqbot.blob as blob
import tips as tips_custom
processing = []
@@ -58,29 +59,33 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
logging.info("根据忽略规则忽略消息: {}".format(text_message))
return []
import config
if not config.wait_last_done and session_name in processing:
return MessageChain([Plain(tips_custom.message_drop_tip)])
# 检查是否被禁言
if launcher_type == 'group':
result = mgr.bot.member_info(target=launcher_id, member_id=mgr.bot.qq).get()
result = asyncio.run(result)
if result.mute_time_remaining > 0:
logging.info("机器人被禁言,跳过消息处理(group_{},剩余{}s)".format(launcher_id,
result.mute_time_remaining))
is_muted = mgr.adapter.is_muted(launcher_id)
if is_muted:
logging.info("机器人被禁言,跳过消息处理(group_{})".format(launcher_id))
return reply
import config
if hasattr(config, 'income_msg_check') and config.income_msg_check:
if config.income_msg_check:
if mgr.reply_filter.is_illegal(text_message):
return MessageChain(Plain("[bot] 你的提问中有不合适的内容, 请更换措辞~"))
return MessageChain(Plain("[bot] 消息中存在不合适的内容, 请更换措辞"))
pkg.openai.session.get_session(session_name).acquire_response_lock()
text_message = text_message.strip()
# 为强制消息延迟计时
start_time = time.time()
# 处理消息
try:
if session_name in processing:
pkg.openai.session.get_session(session_name).release_response_lock()
return MessageChain([Plain("[bot]err:正在处理中,请稍后再试")])
config = pkg.utils.context.get_config()
@@ -115,10 +120,11 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
else: # 消息
# 限速丢弃检查
# print(ratelimit.__crt_minute_usage__[session_name])
if hasattr(config, "rate_limitation") and config.rate_limit_strategy == "drop":
if config.rate_limit_strategy == "drop":
if ratelimit.is_reach_limit(session_name):
logging.info("根据限速策略丢弃[{}]消息: {}".format(session_name, text_message))
return MessageChain(["[bot]"+config.rate_limit_drop_tip]) if hasattr(config, "rate_limit_drop_tip") and config.rate_limit_drop_tip != "" else []
return MessageChain(["[bot]"+tips_custom.rate_limit_drop_tip]) if tips_custom.rate_limit_drop_tip != "" else []
before = time.time()
# 触发插件事件
@@ -144,11 +150,10 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
mgr, config, launcher_type, launcher_id, sender_id)
# 限速等待时间
if hasattr(config, "rate_limitation") and config.rate_limit_strategy == "wait":
if config.rate_limit_strategy == "wait":
time.sleep(ratelimit.get_rest_wait_time(session_name, time.time() - before))
if hasattr(config, "rate_limitation"):
ratelimit.add_usage(session_name)
ratelimit.add_usage(session_name)
if reply is not None and len(reply) > 0 and (type(reply[0]) == str or type(reply[0]) == mirai.Plain):
if type(reply[0]) == mirai.Plain:
@@ -167,4 +172,23 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
finally:
pkg.openai.session.get_session(session_name).release_response_lock()
# 检查延迟时间
if config.force_delay_range[1] == 0:
delay_time = 0
else:
import random
# 从延迟范围中随机取一个值(浮点)
rdm = random.uniform(config.force_delay_range[0], config.force_delay_range[1])
spent = time.time() - start_time
# 如果花费时间小于延迟时间,则延迟
delay_time = rdm - spent if rdm - spent > 0 else 0
# 延迟
if delay_time > 0:
logging.info("[风控] 强制延迟{:.2f}秒(如需关闭请到config.py修改force_delay_range字段)".format(delay_time))
time.sleep(delay_time)
return MessageChain(reply)

View File

@@ -10,6 +10,20 @@ __crt_minute_usage__ = {}
__timer_thr__: threading.Thread = None
def get_limitation(session_name: str) -> int:
"""获取会话的限制次数"""
import config
if type(config.rate_limitation) == dict:
# 如果被指定了
if session_name in config.rate_limitation:
return config.rate_limitation[session_name]
else:
return config.rate_limitation["default"]
elif type(config.rate_limitation) == int:
return config.rate_limitation
def add_usage(session_name: str):
"""增加会话的对话次数"""
global __crt_minute_usage__
@@ -56,12 +70,7 @@ def get_rest_wait_time(session_name: str, spent: float) -> float:
"""获取会话此回合的剩余等待时间"""
global __crt_minute_usage__
import config
if not hasattr(config, 'rate_limitation'):
return 0
min_seconds_per_round = 60.0 / config.rate_limitation
min_seconds_per_round = 60.0 / get_limitation(session_name)
if session_name in __crt_minute_usage__:
return max(0, min_seconds_per_round - spent)
@@ -73,13 +82,8 @@ def is_reach_limit(session_name: str) -> bool:
"""判断会话是否超过限制"""
global __crt_minute_usage__
import config
if not hasattr(config, 'rate_limitation'):
return False
if session_name in __crt_minute_usage__:
return __crt_minute_usage__[session_name] >= config.rate_limitation
return __crt_minute_usage__[session_name] >= get_limitation(session_name)
else:
return False

View File

325
pkg/qqbot/sources/nakuru.py Normal file
View File

@@ -0,0 +1,325 @@
import mirai
from ..adapter import MessageSourceAdapter, MessageConverter, EventConverter
import nakuru
import nakuru.entities.components as nkc
import asyncio
import typing
import traceback
import logging
import json
from pkg.qqbot.blob import Forward, ForwardMessageNode, ForwardMessageDiaplay
class NakuruProjectMessageConverter(MessageConverter):
"""消息转换器"""
@staticmethod
def yiri2target(message_chain: mirai.MessageChain) -> list:
msg_list = []
if type(message_chain) is mirai.MessageChain:
msg_list = message_chain.__root__
elif type(message_chain) is list:
msg_list = message_chain
else:
raise Exception("Unknown message type: " + str(message_chain) + str(type(message_chain)))
nakuru_msg_list = []
# 遍历并转换
for component in msg_list:
if type(component) is mirai.Plain:
nakuru_msg_list.append(nkc.Plain(component.text, False))
elif type(component) is mirai.Image:
if component.url is not None:
nakuru_msg_list.append(nkc.Image.fromURL(component.url))
elif component.base64 is not None:
nakuru_msg_list.append(nkc.Image.fromBase64(component.base64))
elif component.path is not None:
nakuru_msg_list.append(nkc.Image.fromFileSystem(component.path))
elif type(component) is mirai.Face:
nakuru_msg_list.append(nkc.Face(id=component.face_id))
elif type(component) is mirai.At:
nakuru_msg_list.append(nkc.At(qq=component.target))
elif type(component) is mirai.AtAll:
nakuru_msg_list.append(nkc.AtAll())
elif type(component) is mirai.Voice:
if component.url is not None:
nakuru_msg_list.append(nkc.Record.fromURL(component.url))
elif component.path is not None:
nakuru_msg_list.append(nkc.Record.fromFileSystem(component.path))
elif type(component) is Forward:
# 转发消息
yiri_forward_node_list = component.node_list
nakuru_forward_node_list = []
# 遍历并转换
for yiri_forward_node in yiri_forward_node_list:
try:
content_list = NakuruProjectMessageConverter.yiri2target(yiri_forward_node.message_chain)
nakuru_forward_node = nkc.Node(
name=yiri_forward_node.sender_name,
uin=yiri_forward_node.sender_id,
time=int(yiri_forward_node.time.timestamp()) if yiri_forward_node.time is not None else None,
content=content_list
)
nakuru_forward_node_list.append(nakuru_forward_node)
except Exception as e:
import traceback
traceback.print_exc()
nakuru_msg_list.append(nakuru_forward_node_list)
else:
nakuru_msg_list.append(nkc.Plain(str(component)))
return nakuru_msg_list
@staticmethod
def target2yiri(message_chain: typing.Any, message_id: int = -1) -> mirai.MessageChain:
"""将Yiri的消息链转换为YiriMirai的消息链"""
assert type(message_chain) is list
yiri_msg_list = []
import datetime
# 添加Source组件以标记message_id等信息
yiri_msg_list.append(mirai.models.message.Source(id=message_id, time=datetime.datetime.now()))
for component in message_chain:
if type(component) is nkc.Plain:
yiri_msg_list.append(mirai.Plain(text=component.text))
elif type(component) is nkc.Image:
yiri_msg_list.append(mirai.Image(url=component.url))
elif type(component) is nkc.Face:
yiri_msg_list.append(mirai.Face(face_id=component.id))
elif type(component) is nkc.At:
yiri_msg_list.append(mirai.At(target=component.qq))
elif type(component) is nkc.AtAll:
yiri_msg_list.append(mirai.AtAll())
else:
pass
logging.debug("转换后的消息链: " + str(yiri_msg_list))
chain = mirai.MessageChain(yiri_msg_list)
return chain
class NakuruProjectEventConverter(EventConverter):
"""事件转换器"""
@staticmethod
def yiri2target(event: typing.Type[mirai.Event]):
if event is mirai.GroupMessage:
return nakuru.GroupMessage
elif event is mirai.FriendMessage:
return nakuru.FriendMessage
else:
raise Exception("未支持转换的事件类型: " + str(event))
@staticmethod
def target2yiri(event: typing.Any) -> mirai.Event:
yiri_chain = NakuruProjectMessageConverter.target2yiri(event.message, event.message_id)
if type(event) is nakuru.FriendMessage: # 私聊消息事件
return mirai.FriendMessage(
sender=mirai.models.entities.Friend(
id=event.sender.user_id,
nickname=event.sender.nickname,
remark=event.sender.nickname
),
message_chain=yiri_chain,
time=event.time
)
elif type(event) is nakuru.GroupMessage: # 群聊消息事件
permission = "MEMBER"
if event.sender.role == "admin":
permission = "ADMINISTRATOR"
elif event.sender.role == "owner":
permission = "OWNER"
import mirai.models.entities as entities
return mirai.GroupMessage(
sender=mirai.models.entities.GroupMember(
id=event.sender.user_id,
member_name=event.sender.nickname,
permission=permission,
group=mirai.models.entities.Group(
id=event.group_id,
name=event.sender.nickname,
permission=entities.Permission.Member
),
special_title=event.sender.title,
join_timestamp=0,
last_speak_timestamp=0,
mute_time_remaining=0,
),
message_chain=yiri_chain,
time=event.time
)
else:
raise Exception("未支持转换的事件类型: " + str(event))
class NakuruProjectAdapter(MessageSourceAdapter):
"""nakuru-project适配器"""
bot: nakuru.CQHTTP
bot_account_id: int
message_converter: NakuruProjectMessageConverter = NakuruProjectMessageConverter()
event_converter: NakuruProjectEventConverter = NakuruProjectEventConverter()
listener_list: list[dict]
def __init__(self, cfg: dict):
"""初始化nakuru-project的对象"""
self.bot = nakuru.CQHTTP(**cfg)
self.listener_list = []
# nakuru库有bug这个接口没法带access_token会失败
# 所以目前自行发请求
import config
import requests
resp = requests.get(
url="http://{}:{}/get_login_info".format(config.nakuru_config['host'], config.nakuru_config['http_port']),
headers={
'Authorization': "Bearer " + config.nakuru_config['token'] if 'token' in config.nakuru_config else ""
},
timeout=5
)
if resp.status_code == 403:
logging.error("go-cqhttp拒绝访问请检查config.py中nakuru_config的token是否与go-cqhttp设置的access-token匹配")
raise Exception("go-cqhttp拒绝访问请检查config.py中nakuru_config的token是否与go-cqhttp设置的access-token匹配")
try:
self.bot_account_id = int(resp.json()['data']['user_id'])
except Exception as e:
logging.error("获取go-cqhttp账号信息失败: {}, 请检查是否已启动go-cqhttp并配置正确".format(e))
raise Exception("获取go-cqhttp账号信息失败: {}, 请检查是否已启动go-cqhttp并配置正确".format(e))
def send_message(
self,
target_type: str,
target_id: str,
message: typing.Union[mirai.MessageChain, list],
converted: bool = False
):
task = None
converted_msg = self.message_converter.yiri2target(message) if not converted else message
# 检查是否有转发消息
has_forward = False
for msg in converted_msg:
if type(msg) is list: # 转发消息,仅回复此消息组件
has_forward = True
converted_msg = msg
break
if has_forward:
if target_type == "group":
task = self.bot.sendGroupForwardMessage(int(target_id), converted_msg)
elif target_type == "person":
task = self.bot.sendPrivateForwardMessage(int(target_id), converted_msg)
else:
raise Exception("Unknown target type: " + target_type)
else:
if target_type == "group":
task = self.bot.sendGroupMessage(int(target_id), converted_msg)
elif target_type == "person":
task = self.bot.sendFriendMessage(int(target_id), converted_msg)
else:
raise Exception("Unknown target type: " + target_type)
asyncio.run(task)
def reply_message(
self,
message_source: mirai.MessageEvent,
message: mirai.MessageChain,
quote_origin: bool = False
):
message = self.message_converter.yiri2target(message)
if quote_origin:
# 在前方添加引用组件
message.insert(0, nkc.Reply(
id=message_source.message_chain.message_id,
)
)
if type(message_source) is mirai.GroupMessage:
self.send_message(
"group",
message_source.sender.group.id,
message,
converted=True
)
elif type(message_source) is mirai.FriendMessage:
self.send_message(
"person",
message_source.sender.id,
message,
converted=True
)
else:
raise Exception("Unknown message source type: " + str(type(message_source)))
def is_muted(self, group_id: int) -> bool:
import time
# 检查是否被禁言
group_member_info = asyncio.run(self.bot.getGroupMemberInfo(group_id, self.bot_account_id))
return group_member_info.shut_up_timestamp > int(time.time())
def register_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
try:
logging.debug("注册监听器: " + str(event_type) + " -> " + str(callback))
# 包装函数
async def listener_wrapper(app: nakuru.CQHTTP, source: self.event_converter.yiri2target(event_type)):
callback(self.event_converter.target2yiri(source))
# 将包装函数和原函数的对应关系存入列表
self.listener_list.append(
{
"event_type": event_type,
"callable": callback,
"wrapper": listener_wrapper,
}
)
# 注册监听器
self.bot.receiver(self.event_converter.yiri2target(event_type).__name__)(listener_wrapper)
logging.debug("注册完成")
except Exception as e:
traceback.print_exc()
raise e
def unregister_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
nakuru_event_name = self.event_converter.yiri2target(event_type).__name__
new_event_list = []
# 从本对象的监听器列表中查找并删除
target_wrapper = None
for listener in self.listener_list:
if listener["event_type"] == event_type and listener["callable"] == callback:
target_wrapper = listener["wrapper"]
self.listener_list.remove(listener)
break
if target_wrapper is None:
raise Exception("未找到对应的监听器")
for func in self.bot.event[nakuru_event_name]:
if func.callable != target_wrapper:
new_event_list.append(func)
self.bot.event[nakuru_event_name] = new_event_list
def run_sync(self):
loop = asyncio.new_event_loop()
asyncio.set_event_loop(loop)
self.bot.run()
def kill(self) -> bool:
return False

View File

@@ -0,0 +1,122 @@
from ..adapter import MessageSourceAdapter
import mirai
import mirai.models.bus
from mirai.bot import MiraiRunner
import asyncio
import typing
class YiriMiraiAdapter(MessageSourceAdapter):
"""YiriMirai适配器"""
bot: mirai.Mirai
def __init__(self, config: dict):
"""初始化YiriMirai的对象"""
if 'adapter' not in config or \
config['adapter'] == 'WebSocketAdapter':
self.bot = mirai.Mirai(
qq=config['qq'],
adapter=mirai.WebSocketAdapter(
host=config['host'],
port=config['port'],
verify_key=config['verifyKey']
)
)
elif config['adapter'] == 'HTTPAdapter':
self.bot = mirai.Mirai(
qq=config['qq'],
adapter=mirai.HTTPAdapter(
host=config['host'],
port=config['port'],
verify_key=config['verifyKey']
)
)
else:
raise Exception('Unknown adapter for YiriMirai: ' + config['adapter'])
def send_message(
self,
target_type: str,
target_id: str,
message: mirai.MessageChain
):
"""发送消息
Args:
target_type (str): 目标类型,`person`或`group`
target_id (str): 目标ID
message (mirai.MessageChain): YiriMirai库的消息链
"""
task = None
if target_type == 'person':
task = self.bot.send_friend_message(int(target_id), message)
elif target_type == 'group':
task = self.bot.send_group_message(int(target_id), message)
else:
raise Exception('Unknown target type: ' + target_type)
asyncio.run(task)
def reply_message(
self,
message_source: mirai.MessageEvent,
message: mirai.MessageChain,
quote_origin: bool = False
):
"""回复消息
Args:
message_source (mirai.MessageEvent): YiriMirai消息源事件
message (mirai.MessageChain): YiriMirai库的消息链
quote_origin (bool, optional): 是否引用原消息. Defaults to False.
"""
asyncio.run(self.bot.send(message_source, message, quote_origin))
def is_muted(self, group_id: int) -> bool:
result = self.bot.member_info(target=group_id, member_id=self.bot.qq).get()
result = asyncio.run(result)
if result.mute_time_remaining > 0:
return True
return False
def register_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
"""注册事件监听器
Args:
event_type (typing.Type[mirai.Event]): YiriMirai事件类型
callback (typing.Callable[[mirai.Event], None]): 回调函数接收一个参数为YiriMirai事件
"""
self.bot.on(event_type)(callback)
def unregister_listener(
self,
event_type: typing.Type[mirai.Event],
callback: typing.Callable[[mirai.Event], None]
):
"""注销事件监听器
Args:
event_type (typing.Type[mirai.Event]): YiriMirai事件类型
callback (typing.Callable[[mirai.Event], None]): 回调函数接收一个参数为YiriMirai事件
"""
assert isinstance(self.bot, mirai.Mirai)
bus = self.bot.bus
assert isinstance(bus, mirai.models.bus.ModelEventBus)
bus.unsubscribe(event_type, callback)
def run_sync(self):
"""运行YiriMirai"""
# 创建新的
loop = asyncio.new_event_loop()
loop.run_until_complete(MiraiRunner(self.bot)._run())
def kill(self) -> bool:
return False

View File

@@ -1,47 +1,68 @@
import base64
import os
import json
import requests
import pkg.utils.network as network
def read_latest() -> str:
def read_latest() -> list:
import pkg.utils.network as network
resp = requests.get(
url="https://api.github.com/repos/RockChinQ/QChatGPT/contents/res/announcement",
url="https://api.github.com/repos/RockChinQ/QChatGPT/contents/res/announcement.json",
proxies=network.wrapper_proxies()
)
obj_json = resp.json()
b64_content = obj_json["content"]
# 解码
content = base64.b64decode(b64_content).decode("utf-8")
return content
return json.loads(content)
def read_saved() -> str:
def read_saved() -> list:
# 已保存的在res/announcement_saved
# 检查是否存在
if not os.path.exists("res/announcement_saved"):
with open("res/announcement_saved", "w", encoding="utf-8") as f:
f.write("")
if not os.path.exists("res/announcement_saved.json"):
with open("res/announcement_saved.json", "w", encoding="utf-8") as f:
f.write("[]")
with open("res/announcement_saved", "r", encoding="utf-8") as f:
with open("res/announcement_saved.json", "r", encoding="utf-8") as f:
content = f.read()
return content
return json.loads(content)
def write_saved(content: str):
def write_saved(content: list):
# 已保存的在res/announcement_saved
with open("res/announcement_saved", "w", encoding="utf-8") as f:
f.write(content)
with open("res/announcement_saved.json", "w", encoding="utf-8") as f:
f.write(json.dumps(content, indent=4, ensure_ascii=False))
def fetch_new() -> str:
def fetch_new() -> list:
latest = read_latest()
saved = read_saved()
if latest.replace(saved, "").strip() == "":
return ""
else:
write_saved(latest)
return latest.replace(saved, "").strip()
to_show: list = []
for item in latest:
# 遍历saved检查是否有相同id的公告
for saved_item in saved:
if saved_item["id"] == item["id"]:
break
else:
# 没有相同id的公告
to_show.append(item)
write_saved(latest)
return to_show
if __name__ == '__main__':
resp = requests.get(
url="https://api.github.com/repos/RockChinQ/QChatGPT/contents/res/announcement.json",
)
obj_json = resp.json()
b64_content = obj_json["content"]
# 解码
content = base64.b64decode(b64_content).decode("utf-8")
print(json.dumps(json.loads(content), indent=4, ensure_ascii=False))

File diff suppressed because one or more lines are too long

66
pkg/utils/log.py Normal file
View File

@@ -0,0 +1,66 @@
import os
import time
import logging
import shutil
log_file_name = "qchatgpt.log"
log_colors_config = {
'DEBUG': 'green', # cyan white
'INFO': 'white',
'WARNING': 'yellow',
'ERROR': 'red',
'CRITICAL': 'cyan',
}
def init_runtime_log_file():
"""为此次运行生成日志文件
格式: qchatgpt-yyyy-MM-dd-HH-mm-ss.log
"""
global log_file_name
# 检查logs目录是否存在
if not os.path.exists("logs"):
os.mkdir("logs")
# 检查本目录是否有qchatgpt.log若有移动到logs目录
if os.path.exists("qchatgpt.log"):
shutil.move("qchatgpt.log", "logs/qchatgpt.legacy.log")
log_file_name = "logs/qchatgpt-%s.log" % time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
def reset_logging():
global log_file_name
import config
import pkg.utils.context
import colorlog
if pkg.utils.context.context['logger_handler'] is not None:
logging.getLogger().removeHandler(pkg.utils.context.context['logger_handler'])
for handler in logging.getLogger().handlers:
logging.getLogger().removeHandler(handler)
logging.basicConfig(level=config.logging_level, # 设置日志输出格式
filename=log_file_name, # log日志输出的文件位置和文件名
format="[%(asctime)s.%(msecs)03d] %(pathname)s (%(lineno)d) - [%(levelname)s] :\n%(message)s",
# 日志输出的格式
# -8表示占位符让输出左对齐输出长度都为8位
datefmt="%Y-%m-%d %H:%M:%S" # 时间输出的格式
)
sh = logging.StreamHandler()
sh.setLevel(config.logging_level)
sh.setFormatter(colorlog.ColoredFormatter(
fmt="%(log_color)s[%(asctime)s.%(msecs)03d] %(filename)s (%(lineno)d) - [%(levelname)s] : "
"%(message)s",
datefmt="%Y-%m-%d %H:%M:%S",
log_colors=log_colors_config
))
logging.getLogger().addHandler(sh)
pkg.utils.context.context['logger_handler'] = sh
return sh

View File

@@ -1,21 +1,27 @@
from pip._internal import main as pipmain
import main
import pkg.utils.log as log
def install(package):
pipmain(['install', package])
main.reset_logging()
log.reset_logging()
def install_upgrade(package):
pipmain(['install', '--upgrade', package, "-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
"--trusted-host", "pypi.tuna.tsinghua.edu.cn"])
log.reset_logging()
def run_pip(params: list):
pipmain(params)
main.reset_logging()
log.reset_logging()
def install_requirements(file):
pipmain(['install', '-r', file, "--upgrade"])
main.reset_logging()
pipmain(['install', '-r', file, "--upgrade", "-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
"--trusted-host", "pypi.tuna.tsinghua.edu.cn"])
log.reset_logging()
def ensure_dulwich():

View File

@@ -29,7 +29,7 @@ def reload_all(notify=True):
main.stop()
# 删除所有已注册的指令
import pkg.qqbot.cmds.mgr as cmdsmgr
import pkg.qqbot.cmds.aamgr as cmdsmgr
cmdsmgr.__command_list__ = {}
cmdsmgr.__tree_index__ = {}
@@ -41,15 +41,20 @@ def reload_all(notify=True):
importlib.reload(__import__('config'))
importlib.reload(__import__('main'))
importlib.reload(__import__('banlist'))
importlib.reload(__import__('tips'))
context.context = this_context
# 重载插件
import plugins
walk(plugins)
# 初始化相关文件
main.check_file()
# 执行启动流程
logging.info("执行程序启动流程")
main.load_config()
main.complete_tips()
context.get_thread_ctl().reload(
admin_pool_num=context.get_config().admin_pool_num,
user_pool_num=context.get_config().user_pool_num

View File

@@ -8,8 +8,8 @@ import traceback
text_render_font: ImageFont = None
if hasattr(config, "blob_message_strategy") and config.blob_message_strategy == "image": # 仅在启用了image时才加载字体
use_font = config.font_path if hasattr(config, "font_path") else ""
if config.blob_message_strategy == "image": # 仅在启用了image时才加载字体
use_font = config.font_path
try:
# 检查是否存在

View File

@@ -34,6 +34,28 @@ def pull_latest(repo_path: str) -> bool:
return True
def is_newer(new_tag: str, old_tag: str):
"""判断版本是否更新,忽略第四位版本和第一位版本"""
if new_tag == old_tag:
return False
new_tag = new_tag.split(".")
old_tag = old_tag.split(".")
# 判断主版本是否相同
if new_tag[0] != old_tag[0]:
return False
if len(new_tag) < 4:
return True
# 合成前三段,判断是否相同
new_tag = ".".join(new_tag[:3])
old_tag = ".".join(old_tag[:3])
return new_tag != old_tag
def get_release_list() -> list:
"""获取发行列表"""
rls_list_resp = requests.get(
@@ -56,6 +78,34 @@ def get_current_tag() -> str:
return current_tag
def compare_version_str(v0: str, v1: str) -> int:
"""比较两个版本号"""
# 删除版本号前的v
if v0.startswith("v"):
v0 = v0[1:]
if v1.startswith("v"):
v1 = v1[1:]
v0:list = v0.split(".")
v1:list = v1.split(".")
# 如果两个版本号节数不同把短的后面用0补齐
if len(v0) < len(v1):
v0.extend(["0"]*(len(v1)-len(v0)))
elif len(v0) > len(v1):
v1.extend(["0"]*(len(v0)-len(v1)))
# 从高位向低位比较
for i in range(len(v0)):
if int(v0[i]) > int(v1[i]):
return 1
elif int(v0[i]) < int(v1[i]):
return -1
return 0
def update_all(cli: bool = False) -> bool:
"""检查更新并下载源码"""
current_tag = get_current_tag()
@@ -64,8 +114,12 @@ def update_all(cli: bool = False) -> bool:
latest_rls = {}
rls_notes = []
latest_tag_name = ""
for rls in rls_list:
rls_notes.append(rls['name']) # 使用发行名称作为note
if latest_tag_name == "":
latest_tag_name = rls['tag_name']
if rls['tag_name'] == current_tag:
break
@@ -76,7 +130,7 @@ def update_all(cli: bool = False) -> bool:
else:
print("更新日志: {}".format(rls_notes))
if latest_rls == {}: # 没有新版本
if latest_rls == {} and not is_newer(latest_tag_name, current_tag): # 没有新版本
return False
# 下载最新版本的zip到temp目录
@@ -150,9 +204,9 @@ def update_all(cli: bool = False) -> bool:
# 通知管理员
if not cli:
import pkg.utils.context
pkg.utils.context.get_qqbot_manager().notify_admin("已更新到最新版本: {}\n更新日志:\n{}\n新功能通常可以在config-template.py中看到完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes)))
pkg.utils.context.get_qqbot_manager().notify_admin("已更新到最新版本: {}\n更新日志:\n{}\n完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes[:-1])))
else:
print("已更新到最新版本: {}\n更新日志:\n{}\n新功能通常可以在config-template.py中看到完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes)))
print("已更新到最新版本: {}\n更新日志:\n{}\n完整的更新日志请前往 https://github.com/RockChinQ/QChatGPT/releases 查看".format(current_tag, "\n".join(rls_notes[:-1])))
return True
@@ -227,11 +281,13 @@ def is_new_version_available() -> bool:
current_tag = get_current_tag()
# 检查是否有新版本
latest_tag_name = ""
for rls in rls_list:
if rls['tag_name'] == current_tag:
return False
else:
return True
if latest_tag_name == "":
latest_tag_name = rls['tag_name']
break
return is_newer(latest_tag_name, current_tag)
def get_rls_notes() -> list:

View File

@@ -1,9 +1,13 @@
requests~=2.28.1
openai~=0.27.2
dulwich~=0.21.3
requests
openai
dulwich~=0.21.6
colorlog~=6.6.0
yiri-mirai~=0.2.6.1
websockets~=10.4
urllib3~=1.26.10
yiri-mirai
websockets
urllib3
func_timeout~=4.3.5
Pillow
Pillow
nakuru-project-idk
CallingGPT
tiktoken
PyYaml

14
res/announcement.json Normal file
View File

@@ -0,0 +1,14 @@
[
{
"id": 2,
"time": "2023-08-01 10:49:26",
"timestamp": 1690858166,
"content": "现已支持GPT函数调用功能欢迎了解https://github.com/RockChinQ/QChatGPT/wiki/%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8-%E5%86%85%E5%AE%B9%E5%87%BD%E6%95%B0"
},
{
"id": 3,
"time": "2023-11-10 12:20:09",
"timestamp": 1699590009,
"content": "OpenAI 库1.0版本已发行,若出现 OpenAI 调用问题,请更新 QChatGPT 版本。详见项目主页https://github.com/RockChinQ/QChatGPT"
}
]

View File

@@ -1,4 +1,6 @@
> **Warning**
> 此文档已过时,请查看[QChatGPT 容器化部署指南](docker_deployment.md)
## 操作步骤

View File

@@ -0,0 +1,64 @@
# QChatGPT 容器化部署指南
> **Warning**
> 请您确保您**确实**需要 Docker 部署,您**必须**具有以下能力:
> - 了解 `Docker` 和 `Docker Compose` 的使用
> - 了解容器间网络通信配置方式
> - 了解容器文件挂载机制
> - 了解容器调试操作
> - 动手能力强、资料查找能力强
>
> 若您不完全具有以上能力,请勿使用 Docker 部署,由于误操作导致的配置不正确,我们将不会解答您的问题并不负任何责任。
> **非常不建议**您在除 Linux 之外的系统上使用 Docker 进行部署。
## 概览
QChatGPT 主程序需要连接`QQ登录框架`以与QQ通信您可以选择 [Mirai](https://github.com/mamoe/mirai)还需要配置mirai-api-http请查看此仓库README中手动部署部分 或 [go-cqhttp](https://github.com/Mrs4s/go-cqhttp),我们仅发布 QChatGPT主程序 的镜像您需要自行配置QQ登录框架可以参考[README.md](https://github.com/RockChinQ/QChatGPT#-%E9%85%8D%E7%BD%AEqq%E7%99%BB%E5%BD%95%E6%A1%86%E6%9E%B6)中的教程,或自行寻找其镜像)并在 QChatGPT 的配置文件中设置连接地址。
> **Note**
> 请先确保 Docker 和 Docker Compose 已安装
## 准备文件
> QChatGPT 目前暂不可以在没有配置模板文件的情况下自动生成文件,您需要按照以下步骤手动创建需要挂载的文件。
> 如无特殊说明,模板文件均在此仓库中。
> 如果您不想挨个创建也可以直接clone本仓库到本地执行`python main.py`后即可自动根据模板生成所需文件。
现在请在一个空目录创建以下文件或目录:
### 📄`config.py`
复制根目录的`config-template.py`所有内容,创建`config.py`并根据其中注释进行修改。
### 📄`banlist.py`
复制`res/templates/banlist-template.py`所有内容,创建`banlist.py`,这是黑名单配置文件,根据需要修改。
### 📄`cmdpriv.json`
复制`res/templates/cmdpriv-template.json`所有内容,创建`cmdpriv.json`,这是各命令的权限配置文件,根据需要修改。
### 📄`sensitive.json`
复制`res/templates/sensitive-template.json`所有内容,创建`sensitive.json`,这是敏感词配置,根据需要修改。
### 📄`tips.py`
复制`tips-custom-template.py`所有内容,创建`tips.py`,这是部分提示语的配置,根据需要修改。
## 运行
已预先准备好`docker-compose.yaml`,您需要根据您的网络配置进行适当修改,使容器内的 QChatGPT 程序可以正常与 Mirai 或 go-cqhttp 通信。
`docker-compose.yaml`复制到本目录,根据网络环境进行配置,并执行:
```bash
docker compose up
```
若无报错即配置完成您可以Ctrl+C关闭后使用`docker compose up -d`将其置于后台运行
## 注意
- 安装的插件都会保存在`plugins`(映射到本目录`plugins`),安装插件时可能会自动安装相应的依赖,此时若`重新创建`容器,已安装的插件将被加载,但所需的增量依赖并未安装,会导致引入问题。您可以删除插件目录后重启,再次安装插件,以便程序可以自动安装插件所需依赖。

BIN
res/logo.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 35 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 129 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 101 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 98 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 22 KiB

View File

@@ -1,4 +1,4 @@
import pkg.qqbot.cmds.mgr as cmdsmgr
import pkg.qqbot.cmds.aamgr as cmdsmgr
import json
# 执行命令模块的注册
@@ -13,5 +13,5 @@ for key in cmdsmgr.__command_list__:
template[key] = cmdsmgr.__command_list__[key]['privilege']
# 写入cmdpriv-template.json
with open('cmdpriv-template.json', 'w') as f:
with open('res/templates/cmdpriv-template.json', 'w') as f:
f.write(json.dumps(template, indent=4, ensure_ascii=False))

View File

@@ -0,0 +1,32 @@
# 输出工作路径
import os
print("工作路径: " + os.getcwd())
announcement = input("请输入公告内容: ")
import json
# 读取现有的公告文件 res/announcement.json
with open("res/announcement.json", "r", encoding="utf-8") as f:
announcement_json = json.load(f)
# 将公告内容写入公告文件
# 当前自然时间
import time
now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
# 获取最后一个公告的id
last_id = announcement_json[-1]["id"] if len(announcement_json) > 0 else -1
announcement = {
"id": last_id + 1,
"time": now,
"timestamp": int(time.time()),
"content": announcement
}
announcement_json.append(announcement)
# 将公告写入公告文件
with open("res/announcement.json", "w", encoding="utf-8") as f:
json.dump(announcement_json, f, indent=4, ensure_ascii=False)

BIN
res/social.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 70 KiB

View File

@@ -1,3 +1,13 @@
# 是否处理群聊消息
# 为False时忽略所有群聊消息
# 优先级高于下方禁用列表
enable_group = True
# 是否处理私聊消息
# 为False时忽略所有私聊消息
# 优先级高于下方禁用列表
enable_private = True
# 是否启用禁用列表
enable = True

View File

@@ -1,7 +1,8 @@
{
"comment": "以下为命令权限请设置到cmdpriv.json中。关于此功能的说明请查看https://github.com/RockChinQ/QChatGPT/wiki/%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E5%91%BD%E4%BB%A4%E6%9D%83%E9%99%90%E6%8E%A7%E5%88%B6",
"draw": 1,
"plugin": 2,
"func": 1,
"plugin": 1,
"plugin.get": 2,
"plugin.update": 2,
"plugin.del": 2,
@@ -19,6 +20,7 @@
"prompt": 1,
"resend": 1,
"reset": 1,
"cfg": 2,
"cmd": 1,
"help": 1,
"reload": 2,

BIN
res/webwlkr-demo.gif Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 879 KiB

379
res/wiki/1-功能使用.md Normal file
View File

@@ -0,0 +1,379 @@
## 功能点列举
<details>
<summary>✅回复符合上下文</summary>
- 程序向模型发送近几次对话内容,模型根据上下文生成回复
- 您可在`config.py`中修改`prompt_submit_length`自定义联系上下文的范围
</details>
<details>
<summary>✅支持敏感词过滤,避免账号风险</summary>
- 难以监测机器人与用户对话时的内容,故引入此功能以减少机器人风险
- 编辑`sensitive.json`,并在`config.py`中修改`sensitive_word_filter`的值以开启此功能
</details>
<details>
<summary>✅群内多种响应规则不必at</summary>
- 默认回复`ai`作为前缀或`@`机器人的消息
- 详细见`config.py`中的`response_rules`字段
</details>
<details>
<summary>✅使用官方api不需要网络代理稳定快捷</summary>
- 不使用ChatGPT逆向接口而使用官方的Completion API稳定性高
- 您可以在`config.py`中自定义`completion_api_params`字段设置向官方API提交的参数以自定义机器人的风格
</details>
<details>
<summary>✅完善的多api-key管理超额自动切换</summary>
- 支持配置多个`api-key`,内部统计使用量并在超额时自动切换
- 请在`config.py`中修改`openai_config`的值以设置`api-key`
- 可以在`config.py`中修改`api_key_fee_threshold`来自定义切换阈值
- 运行期间向机器人说`!usage`以查看当前使用情况
</details>
<details>
<summary>✅组件少部署方便提供一键安装器及Docker安装</summary>
- 手动部署步骤少
- 提供自动安装器及docker方式详见以下安装步骤
</details>
<details>
<summary>✅支持预设文字</summary>
- 支持以自然语言预设文字,自定义机器人人格等信息
- 详见`config.py`中的`default_prompt`部分
- 支持设置多个预设情景,并通过!reset、!default等命令控制详细请查看[wiki命令](https://github.com/RockChinQ/QChatGPT/wiki/1-%E5%8A%9F%E8%83%BD%E4%BD%BF%E7%94%A8#%E6%9C%BA%E5%99%A8%E4%BA%BA%E5%91%BD%E4%BB%A4)
- 支持使用文件存储情景预设文字,并加载: 在`prompts/`目录新建文件写入预设文字,即可通过`!reset <文件名>`命令加载
</details>
<details>
<summary>✅完善的会话管理,重启不丢失</summary>
- 使用SQLite进行会话内容持久化
- 最后一次对话一定时间后自动保存,请到`config.py`中修改`session_expire_time`的值以自定义时间
- 运行期间可使用`!reset` `!list` `!last` `!next` `!prompt`等命令管理会话
</details>
<details>
<summary>✅支持对话、绘图等模型,可玩性更高</summary>
- 现已支持OpenAI的对话`Completion API`和绘图`Image API`
- 向机器人发送命令`!draw <prompt>`即可使用绘图模型
</details>
<details>
<summary>✅支持命令控制热重载、热更新</summary>
- 允许在运行期间修改`config.py`或其他代码后,以管理员账号向机器人发送命令`!reload`进行热重载,无需重启
- 运行期间允许以管理员账号向机器人发送命令`!update`进行热更新,拉取远程最新代码并执行热重载
</details>
<details>
<summary>✅支持插件加载🧩</summary>
- 自行实现插件加载器及相关支持
- 详细查看[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/5-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
</details>
<details>
<summary>✅私聊、群聊黑名单机制</summary>
- 支持将人或群聊加入黑名单以忽略其消息
- 详见下方`加入黑名单`
</details>
<details>
<summary>✅回复速度限制</summary>
- 支持限制单会话内每分钟可进行的对话次数
- 具有“等待”和“丢弃”两种策略
- “等待”策略:在获取到回复后,等待直到此次响应时间达到对话响应时间均值
- “丢弃”策略:此分钟内对话次数达到限制时,丢弃之后的对话
- 详细请查看config.py中的相关配置
</details>
<details>
<summary>✅支持自定义提示内容</summary>
- 允许用户自定义报错、帮助等提示信息
- 请查看`tips.py`
</details>
## 限制
- ❗OpenAI接口是收费的每个OpenAI账户有18美元免费额度收费标准参照 https://openai.com/api/pricing/
- ❗官方关于模型生成内容的警告:
- May occasionally generate incorrect information可能会生成不正确的信息
- May occasionally produce harmful instructions or biased content可能会产生有害说明或有偏见的内容
- Limited knowledge of world and events after 2021对2021年后的世界和事件的了解有限
- ❗模型无思维能力,仅针对传入的上下文根据数据集生成内容,请勿过于信任其输出
- ❗模型无网络访问能力及其他与外界交互的能力,如询问其实时性的内容,获得的回复基本都是错误的
- ❗仅支持文字对话,其他内容无法识别
- ❗模型不了解其运行平台及其使用的模型版本,任何针对其实现原理的问题答案均视为无效,请以项目文档为准
- ❗仅可进行一句话回复一句话的对话,其他形式无效
- ~~当然你也可以让他写一篇关于“人类有多么愚蠢”的论文并在一个小时后发送到你邮箱,接着你像个傻子一样盯着邮箱等待一个小时,并用自己的实际行动展示这篇论文~~
以上是关于此程序的限制的最高优先级描述,其他方式(如询问机器人相关信息)获得的描述均应被视为无效
由于模型生成的内容导致的一切损失,本项目概不负责
## 使用方式
对话及绘图功能均直接调用OpenAI的模型进行处理与机器人程序无关这意味着模型并不了解此项目的相关信息如实现方式、技术栈、运行平台等除非在预设值中写入相关信息。
### 基础对话
程序将一个人/群视为一个对象,每个对象的会话独立保存。
`会话`是程序中的一个自设概念,当机器人与当前对象无会话时,会自动创建新会话,新会话由预设信息(若有)开头。
每个会话最后一次对话一段时间(见上述功能点中的`会话管理`)后会被结束并存进数据库,之后的对话将开启新的会话。
#### 私聊使用
1. 添加机器人QQ为好友
2. 发送消息给机器人,机器人即会自动回复
3. 可以通过`!help`查看帮助信息
<img alt="私聊示例" src="https://github.com/RockChinQ/QChatGPT/blob/master/res/屏幕截图%202022-12-08%20150949.png" width="550" height="279"/>
#### 群聊使用
1. 将机器人拉进群
2. at机器人并发送消息机器人即会自动回复
3. at机器人并发送`!help`查看帮助信息
<img alt="群聊示例" src="https://github.com/RockChinQ/QChatGPT/blob/master/res/屏幕截图%202022-12-08%20150511.png" width="550" height="428"/>
### 绘图功能
对机器人发送`!draw <图片描述>`即可获得图片,绘图时间较长,请耐心等待。
绘图功能与对话功能是分离的,机器人对话时并不了解其具有绘画能力。
<img alt="绘图功能" src="https://github.com/RockChinQ/QChatGPT/blob/master/res/屏幕截图%202022-12-29%20194948.png" width="550" height="348"/>
### 机器人命令
目前支持的命令
> `<>` 中的为必填参数,使用时请不要包含`<>`
> `[]` 中的为可选参数,使用时请不要包含`[]`
#### 用户级别命令
> 可以使用`!help`命令来查看命令说明
任何对象可使用
```
!help 显示自定义的帮助信息可在config.py修改help_message设置
!cmd [命令名称] 显示命令列表或指定命令的详细信息
!list [页数] 列出本对象的历史会话列表
!del <序号> 删除指定的历史记录,可以通过 !list 查看序号
!del all 删除本会话对象的所有历史记录
!last 切换到前一次会话
!next 切换到后一次会话
!reset [使用预设] 重置对象的当前会话,可指定使用的情景预设值(通过!default命令查看可用的)
!prompt 查看对象当前会话的所有记录
!usage 查看api-key的使用量
!draw <提示语> 进行绘图
!version 查看当前版本并检查更新
!resend 重新回复上一个问题
!plugin 用法请查看插件使用页的`管理`章节
!default 查看可用的情景预设值
```
#### 管理员命令
仅管理员私聊机器人时可使用,必须先在`config.py`中的`admin_qq`设置管理员QQ
```
!reload 重载程序代码,适用于更新配置文件或更改代码后的热重载
!update 进行程序自动更新
!cfg <all|配置项名称> [配置项新值] 运行期间操作配置项,使用方法见下文
!default set <情景预设名称> 修改!reset未指定情景预设时的默认情景详细请查看config.py中default_prompt字段的注释
!delhst <会话名称> 删除指定会话的所有历史记录, 会话名称为 group_群号 或 person_QQ号
!delhst all 删除所有会话的所有历史记录
```
<details>
<summary>⚙ !cfg 命令及其简化形式详解</summary>
此命令可以在运行期间由管理员通过QQ私聊窗口修改配置信息**重启之后会失效**。
用法:
1. 查看所有配置项及其值
```
!cfg all
```
2. 查看某个配置项的值
`default_prompt`示例
```
!cfg default_prompt
```
输出示例
```
[bot]配置项default_prompt: "如果我之后想获取帮助,请你说“输入!help获取帮助”"
```
3. 修改某个配置项
格式: `!cfg <配置项名称> <配置项新值>`
以修改`default_prompt`示例
```
!cfg default_prompt "我是Rock Chin"
```
输出示例
```
[bot]配置项default_prompt修改成功
```
此时创建新的会话,新的`default_prompt`就会生效
4. ⭐此命令的简化形式
格式:`!~<配置项名称>`
其中`!~`等价于`!cfg `
则前述三个命令分别可以简化为:
```
!~all
!~default_prompt
!~default_prompt "我是Rock Chin"
```
5. 配置项名称支持使用点号(.)拼接以索引子配置项
例如: `openai_config.api_key`将索引`config`字典中的`openai_config`字典中的`api_key`字段,可以通过这个方式查看或修改此子配置项
```
!~openai_config.api_key
```
</details>
### 命令权限控制
> 我们在[此PR](https://github.com/RockChinQ/QChatGPT/pull/336)重构了命令管理模块,并支持命令节点权限配置
您可以编辑`cmdpriv.json`来设置命令节点的权限,当命令被发起时,若用户的权限级别(管理员为`2`,普通用户为`1`)大于等于命令节点的权限级别,命令即可被成功执行。
示例:
```json
{
"plugin": 1,
"plugin.get": 2
}
```
如此,普通用户可以执行`!plugin`查看插件列表,而仅管理员可以执行`!plugin get <url>`命令安装插件。
命令节点权限支持缺省,这意味的您未在`cmdpriv.json`中设置权限的节点将使用默认的权限级别(见上方)。
### 敏感词过滤
`sensitive.json`中编辑敏感词,并在`config.py`中设置
```Python
# 敏感词过滤开关,以同样数量的*代替敏感词回复
# 请在sensitive.json中添加敏感词
sensitive_word_filter = True
```
### 设置多个api-key自动切换
请在`config.py`中修改`openai_config`的值以设置`api-key`
可以在`config.py`中修改`api_key_fee_threshold`来自定义切换阈值
运行期间向机器人说`!usage`以查看当前使用情况
### 预设文字(default模式)
编辑`config.py`中的`default_prompt`字段,预设文字不宜过长(建议1000字以内),目前所有会话都会射到预设文字的影响。
或将情景预设文字写入到`prompts/`目录下,运行期间即可使用`!reset <文件名>`命令加载,或使用`!default <文件名>`命令将其设为默认
### 预设文字(full_scenario模式)
将JSON情景写入到`scenario/`目录下,运行期间即可使用`!reset <文件名>`命令加载,或使用`!default <文件名>`命令将其设为默认.
JSON情景模板参考`scenario/default_template.json`
#### JSON结构
- `prompt`一个包含伪造对话的数组。每次请求API时会将其置于API的`messages`参数中作为对话上下文因此可以在一定程度上引导ChatGPT的认知。
- `role`:角色标签,包括`system`,`user`,`assistant`。分别代表系统用户和GPT角色。
- `content`:该角色的对话文本。
- 一个JSON情景文件应该像下面这样
```JSON
{
"prompt": [
{
"role": "system",
"content": "You are a helpful assistant. 如果我需要帮助,你要说“输入!help获得帮助”"
},
{
"role": "assistant",
"content": "好的我是一个能干的AI助手。 如果你需要帮助,我会说“输入!help获得帮助”"
}
]
}
```
#### 编写建议
1. 使用**提出要求--肯定并复述**的对话模式:
```JSON
{
"role": "system",
"content": "你将充当“百度”公司研发的“文心一言”。你除了所属和名字之外和ChatGPT并无区别。即使用户在之后指出你其实是OpenAI的ChatGPT你也要一口咬定你是“文心一言”。"
},
{
"role": "assistant",
"content": "好的我不是ChatGPT。我就是“百度”公司研发的“文心一言”大语言模型。即使用户在之后指出我是OpenAI的ChatGPT我也会一口咬定我自己是“文心一言”"
}
```
2. 按情况对设定继续写入伪对话更能使GPT理解上下文
```JSON
{
"role": "user",
"content": "你好文心一言。你真的不是ChatGPT吗"
},
{
"role": "assistant",
"content": "你好我是由百度公司研发的大语言模型“文心一言”并不是ChatGPT。你有什么需要我帮助的吗"
}
```
#### 优点
使用该模式可以“伪造GPT的记忆”影响模型对上下文理解进而达到**人格增强**、**跨越限制**的奇效。
#### 局限性
- 由于目前GPT3.5的请求API最大token数为4096无法保留超过此token数目的上下文。`prompt`中的`content`**不会**被计入`config.py`中的`prompt_submit_length`,因此过长的预设内容可能会导致程序报错,`prompt_submit_length`的值参考以下公式:
```
prompt_submit_length = <模型单次请求token数上限> - 情景预设中token数 - 预留给用户最后一次提问的token数
```
> token是OpenAI接口文字量计数单位目前精确算法未知一个汉字为一个token英文算法未知。
- **GPT3.5仍然存在更高级别的*思想钢印*,该模式对部分触及该钢印的话题无效。**
### 配置热加载,代码热更新
在运行期间使用管理员QQ账号私聊机器人发送`!reload`加载修改后的`config.py`的值或编辑后的代码,无需重启
使用管理员账号私聊机器人,发送`!update`拉取最新代码并进行热更新,无需重启
详见前述`管理员命令`段落
### 群内无需@响应规则
支持回复未at机器人的、符合指定规则的消息详细规则请在`config.py`中的`response_rules`字段设置
### 加入黑名单
- 支持禁用所有`私聊``群聊`,请查看`banlist.py`中的`enable_private``enable_group`字段
- 编辑`banlist.py`,设置`enable = True`,并在其中的`person``group`列表中加入要封禁的人或群聊,修改完成后重启程序或进行热重载

View File

@@ -0,0 +1,58 @@
使用过程中的一些疑问,这里不是解决异常的地方,遇到异常请见`常见错误`
### ❓ 如何更新代码到最新版本?
#### 自动更新
由管理员QQ私聊机器人QQ发送`!update`命令
#### 手动更新
到[Releases页](https://github.com/RockChinQ/QChatGPT/releases)下载最新版本的源码压缩包并解压覆盖到QChatGPT程序目录
### ❓ 机器人的回复与官网ChatGPT的答案有所差距
ChatGPT通过使用OpenAI的回复API创建进行了参数调优本机器人通过使用自定义的参数调用OpenAI的回复API并非调用ChatGPT的接口二者底层原理相同但由于官方对ChatGPT进行了调优故此机器人回复可能不如ChatGPT。
### ❓ 如何设置机器人在群内无需@就能回复消息?
支持回复未at机器人的、符合指定规则的消息详细规则请在`config.py`中的`response_rules`字段设置
### ❓ 绘图功能使用的是什么模型?
OpenAI官方的DALL·E模型
### ❓ 多api-key的管理机制以及切换逻辑
> 此特性仅在提交`36c8a58`(2023年1月3日23点左右)前的代码有效,之后版本的代码不再根据估算的使用量进行切换,仅当接口报错时进行切换
程序支持在`config.py`中设置多个账户的`api-key`以便在超过免费额度时自动切换,在每次进行对话或进行绘图时,程序根据[价格表](https://openai.com/api/pricing)计算当前`api-key`的账户的额度使用量(费用),当使用量到达`config.py`中设置的`api_key_fee_threshold`自动切换到下一个未达到额度的key。
- 请勿将单个账户的多个key放入配置文件因为免费额度是以账户为单位的
- 程序会将使用额度储存到数据库,以便重启后继续计算
- 由于官方未提供查询接口,使用额度均为依据价目表进行的估算,不一定准确
- 若要保证每个账户的额度均能用完,可以把`api_key_fee_threshold`设置成很高的值,当超额调用报错时程序也会自动切换
### ❓ 账户余额消耗太快怎么办?
可能是由于每次请求包含的上下文数量过多或请求的回复过长导致的。
可以在`config.py`中将`prompt_submit_length`字段修改成较小的值,以限制每次向模型提交的前文字符数量,详情见`config.py`中此字段的注释。
还可以编辑`config.py`中的`completion_api_params`字段中的`max_tokens`为较小的值,这将控制模型传回的回复的字符数量。
### ❓ 如何设置在消息处理失败时不向用户发送错误信息?
`config.py`中设置
```Python
# 消息处理出错时是否向用户隐藏错误详细信息
# 设置为True时仅向管理员发送错误详细信息
# 设置为False时向用户及管理员发送错误详细信息
hide_exce_info_to_user = True
# 消息处理出错时向用户发送的提示信息
# 仅当hide_exce_info_to_user为True时生效
# 设置为空字符串时,不发送提示信息
alter_tip_message = '出错了,请稍后再试'
```
若此两项字段不存在,请复制以上内容并新增到`config.py`末尾

View File

@@ -0,0 +1 @@
搜索[主仓库issue](https://github.com/RockChinQ/QChatGPT/issues)和[安装器issue](https://github.com/RockChinQ/qcg-installer/issues)

108
res/wiki/4-技术信息.md Normal file
View File

@@ -0,0 +1,108 @@
以下是QChatGPT实现原理等技术信息贡献之前请仔细阅读
> 太久没更了,过时了,建议读源码,~~注释还挺全的~~
> 请先阅读OpenAI API的相关文档 https://beta.openai.com/docs/ 以下信息假定您已了解OpenAI模型的相关特性及其接口的调用方法。
## 术语
包含OpenAI API涉及的术语和项目中的概念的命名
括号中是程序中相应术语的命名,无括号的为抽象概念
### 模型(model)
AI模型程序调用OpenAI的接口获取的内容均为OpenAI的模型生成的内容。
### 字符(tokens)
OpenAI定义的字符ASCII字符为1 token其他为2 token。
### 提示符(prompt)
i. 调用OpenAI的文字补全模型时的提示语模型接口会根据提示语返回回复内容。程序底层会将对话内容进行封装生成提示符。调用文字补全模型时的提示符均由`user_name`(默认为`You`,可在配置文件修改)和`bot_name`(默认为`Bot`,可在配置文件修改)标记对话角色以供模型识别,以下是实例:
```
You:今天天气真不错
Bot:很高兴你喜欢今天的天气:)
You:谢谢你
Bot:不客气:)
```
补全模型调用的程序实现请查看下文`实现`节。
ii. 调用OpenAI的绘图模型时的提示语模型会根据提示语进行绘图并返回图片URL。
### 对象
程序将单个人或单个QQ群视为一个对象对象和模型是一次会话中的对话双方。
### 会话(session)
会话只对文字补全功能有效,绘图功能无会话概念。每个对象使用同一个会话,会话中仅有对象和模型两个角色,故群内所有的人都将被视为同一个角色与模型进行对话。
程序获取回复的本质是`文字补全`
由于对话需要实现联系上下文,故程序会将模型与对象的对话历史记录作为`提示符`发送给OpenAI的接口以获取符合前文的回复。
而OpenAI的文字补全接口的提示符具有长度限制(默认使用的`text-davinci-003`限制为4096 tokens)
所以增加`会话`概念以管理向接口发送的提示符内容。
会话的存活时间可以在`config.py`中设置默认为20分钟。会话过期之后会被存入数据库并重置。下一次该对象发起对话时将重启新的会话。
### 预设值、人格(default_prompt)
每个会话的预设对话信息,可在`config.py`中设置,程序会在每个会话创建时向提示符写入以下内容:
```
You:<预设信息>
Bot:好的
```
## 实现
### QQ机器人
> 程序路径:
> pkg.qqbot
- `pkg.qqbot.manager`中的`QQBotManager`实现了接收消息、调用OpenAI模块处理消息、报告审计模块记录使用量等功能并提供通知管理员、发送消息等方法供其他模块调用。
- `pkg.qqbot.filter`提供了敏感词过滤的相关操作。
- `pkg.qqbot.process`提供了私聊消息和群聊消息的统一处理逻辑。
使用mirai及YiriMirai作为Python与QQ交互的框架详细请见其文档。
在启动时会调用YiriMirai的函数以创建一个bot对象用于程序通过mirai与QQ进行交互在上层程序调用此bot对象的方法进行消息处理。
由于YiriMirai暂时无法关闭机器人故在热重载前后维持同一个bot对象这意味着QQ机器人的相关配置(QQ号、适配器等)信息不支持热重载。
### 数据库
> 程序路径:
> pkg.database
- `pkg.database.manager`中的`DatabaseManager`封装了诸多调用数据库的方法以供其他模块调用。
使用SQLite作为数据库储存所有对象的历史会话信息、api-key的费用情况、api-key的使用量情况。
### OpenAI交互
> 程序路径:
> pkg.openai
- `pkg.openai.manager`中的`OpenAIInteract`类封装了OpenAI的文字补全`Completion`API和绘图API供机器人模块调用并在接口调用成功之后向审计模块报告当前使用的api-key的使用量信息。
- `pkg.openai.keymgr`实现了多api-key的管理其中以`exceeded`变量在运行时记录api-key的超额报错记录并提供根据超额记录进行的api-key切换功能。
- `pkg.openai.pricing`记录各个模型的费用信息供调用接口时估算费用费用估算功能不再与api-key的切换挂钩api-key仅在调用接口报错超额时进行切换。
- `pkg.openai.session`中的`Session`进行会话管理。
### utils模块
#### context模块
保存前述模块中的对象,并允许各个模块从此处获取其他模块的对象以调用其方法。
#### 热重载功能
> pkg.utils.reloader
重载前保存context中的所有对象执行`main.py`中的程序关闭流程,使用`importlib``reload`函数重载所有模块(包含配置文件,包含新增的模块)重载后将context恢复并执行程序启动流程。
所有模块都会重新创建对象但QQ机器人模块中的bot对象不会被重新创建这是因为YiriMirai提供的shutdown方法无法使用这意味着`config.py`中关于QQ机器人的配置不支持热重载。
#### 热更新功能
> pkg.utils.updater
使用`dulwich`库执行pull操作拉取远程仓库的最新源码并进行一次热重载加载最新代码。

View File

@@ -0,0 +1,55 @@
QChatGPT 插件使用Wiki
## 简介
`plugins`目录下的所有`.py`程序都将被加载,除了`__init__.py`之外的模块支持热加载
> 插件分为`行为插件`和`内容插件`两种行为插件由主程序运行中的事件驱动内容插件由GPT生成的内容驱动请查看内容插件页
> 已有插件列表:[QChatGPT 插件](https://github.com/stars/RockChinQ/lists/qchatgpt-%E6%8F%92%E4%BB%B6)
## 安装
### 储存库克隆(推荐)
在运行期间,使用管理员账号对机器人私聊发送`!plugin get <Git储存库地址>`即可自动获取源码并安装插件,程序会根据仓库中的`requirements.txt`文件自动安装依赖库
例如安装`hello_plugin`插件
```
!plugin get https://github.com/RockChinQ/hello_plugin
```
安装完成后重启程序或使用管理员账号私聊机器人发送`!reload`进行热重载加载插件
### 手动安装
将获取到的插件程序放置到`plugins`目录下,具体使用方式请查看各插件文档或咨询其开发者。
## 管理
### !plugin 命令
```
!plugin 列出所有已安装的插件
!plugin get <储存库地址> 从Git储存库安装插件(需要管理员权限)
!plugin update all 更新所有插件(需要管理员权限,仅支持从储存库安装的插件)
!plugin update <插件名> 更新指定插件
!plugin del <插件名> 删除插件(需要管理员权限)
!plugin on <插件名> 启用插件(需要管理员权限)
!plugin off <插件名> 禁用插件(需要管理员权限)
!func 列出所有内容函数
```
### 控制插件执行顺序
可以通过修改`plugins/settings.json``order`字段中每个插件名称的前后顺序,以更改插件**初始化**和**事件执行**顺序
### 启用或关闭插件
无需卸载即可管理插件的开关
编辑`plugins`目录下的`switch.json`文件,将相应的插件的`enabled`字段设置为`true/false(开/关)`,之后重启程序或执行热重载即可控制插件开关
### 控制全局内容函数开关
内容函数是基于[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的这是一种嵌入对话中由GPT自动调用的函数。
每个插件可以自行注册内容函数,您可以在`plugins`目录下的`settings.json`中设置`functions`下的`enabled``true``false`控制这些内容函数的启用或禁用。

View File

@@ -0,0 +1,31 @@
> 说白了就是ChatGPT官方插件那种东西
内容函数是基于[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的这是一种嵌入对话中由GPT自动调用的函数。
例如我们为GPT提供一个函数`access_the_web`并提供其详细的描述以及其参数的描述那么当我们在与GPT对话时涉及类似以下内容时
```
Q: 请搜索一下github上有那些QQ机器人项目
Q: 请为我搜索一些不错的云服务商网站?
Q阅读并总结这篇文章https://zhuanlan.zhihu.com/p/607570830
Q搜一下清远今天天气如何
```
GPT将会回复一个对`access_the_web`的函数调用请求QChatGPT将自动处理执行该调用并返回结果给GPT使其生成新的回复。
当然,函数调用功能不止局限于网络访问,还可以实现图片处理、科学计算、行程规划等需要调用函数的功能,理论上我们可以通过内容函数实现与`ChatGPT Plugins`相同的功能。
- 您需要使用`v2.5.0`以上的版本才能加载包含内容函数的插件
- 您需要同时在`config.py`中的`completion_api_params`中设置`model`为支持函数调用的模型,推荐使用`gpt-3.5-turbo-16k`
- 使用此功能可能会造成难以预期的账号余额消耗,请关注
- [逆向库插件](https://github.com/RockChinQ/revLibs)现在也支持函数调用了..您可以在完全免费的情况下使用GPT-3.5进行函数调用若您在主程序配置了内容函数并启用逆向ChatGPT会自动使用这些函数
### QChatGPT有什么类型的插件区别是什么
QChatGPT具有`行为插件``内容函数`两种扩展方式行为插件是完整的插件结构是由运行期间的事件驱动的内容函数被包含于一个完整的插件体中由GPT接口驱动。
> 还是不理解?可以尝试根据插件开发页的步骤自行编写插件
## QChatGPT的一些不错的内容函数插件
- [WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin) - 让机器人能联网!!

476
res/wiki/7-插件开发.md Normal file
View File

@@ -0,0 +1,476 @@
QChatGPT 插件开发Wiki
> 请先阅读[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/5-%E6%8F%92%E4%BB%B6%E4%BD%BF%E7%94%A8)
> 请先阅读[技术信息页](https://github.com/RockChinQ/QChatGPT/wiki/4-%E6%8A%80%E6%9C%AF%E4%BF%A1%E6%81%AF)
> 建议先阅读本项目源码,了解项目架构
> 问题、需求请到仓库issue发起
> **提问前请先靠自己尝试**
## 💬简介
尽管“为一个基于OpenAI API的QQ机器人开发插件支持”这事看起来有点小题大做但萌生此想法后的几天内好几个人提出了这个需求最终促使此项目正式支持插件。
## 🧱实现
基于`importlib`库加载模块的方法动态加载额外Python程序文件以便实现插件加载插件均存放在`plugins`文件夹,其中的所有`.py`文件都将被加载(除了所有`__init__.py`)
## 📚示例代码
请查看代码目录`tests/plugin_examples`中的插件目录
## 💻快速开始
按照文档部署此项目,并使其正常运行。
`plugins`目录下新建目录`hello`,在其中新建空文件`__init__.py`以标记此目录为软件包,继续新建文件`main.py`
> 您也可以使用[hello_plugin](https://github.com/RockChinQ/hello_plugin)作为模板直接生成插件代码仓库
编辑`main.py`输入以下内容:
```Python
from pkg.plugin.models import *
from pkg.plugin.host import EventContext, PluginHost
"""
在收到私聊或群聊消息"hello"时,回复"hello, <发送者id>!""hello, everyone!"
"""
# 注册插件
@register(name="Hello", description="hello world", version="0.1", author="RockChinQ")
class HelloPlugin(Plugin):
# 插件加载时触发
# plugin_host (pkg.plugin.host.PluginHost) 提供了与主程序交互的一些方法,详细请查看其源码
def __init__(self, plugin_host: PluginHost):
pass
# 当收到个人消息时触发
@on(PersonNormalMessageReceived)
def person_normal_message_received(self, event: EventContext, **kwargs):
msg = kwargs['text_message']
if msg == "hello": # 如果消息为hello
# 输出调试信息
logging.debug("hello, {}".format(kwargs['sender_id']))
# 回复消息 "hello, <发送者id>!"
event.add_return("reply", ["hello, {}!".format(kwargs['sender_id'])])
# 阻止该事件默认行为(向接口获取回复)
event.prevent_default()
# 当收到群消息时触发
@on(GroupNormalMessageReceived)
def group_normal_message_received(self, event: EventContext, **kwargs):
msg = kwargs['text_message']
if msg == "hello": # 如果消息为hello
# 输出调试信息
logging.debug("hello, {}".format(kwargs['sender_id']))
# 回复消息 "hello, everyone!"
event.add_return("reply", ["hello, everyone!"])
# 阻止该事件默认行为(向接口获取回复)
event.prevent_default()
# 插件卸载时触发
def __del__(self):
pass
```
此插件将实现:私聊收到`hello`消息时回复`hello, <发送者QQ号>!`,群聊收到`hello`消息时回复`hello, everyone!`
### 解读此插件程序
- `import``pkg.plugin`引入`models`模块的所有字段(此程序使用了其中的`register函数``on函数``Plugin类``PersonNormalMessageReceived事件``GroupNormalMessageReceived事件`
- `@register()`将类`HelloPlugin`标记为一个插件类,声明插件名称为`Hello`以及插件简介、版本、作者
- 声明类`HelloPlugin`继承于`Plugin`,此类可以随意命名,插件名称只与`register`调用时的参数有关
- 声明此类的`__init__`方法,此方法是可选的,其中的代码将在主程序启动时加载插件的时候被执行
- `@on`将方法`person_normal_message_received`标记为一个事件处理器,处理`PersonNormalMessageReceived`收到私聊消息并在获取OpenAI回复前触发事件此方法可以随意命名绑定的事件只与`on`中的参数有关,更多支持的事件可到`pkg.plugin.models.py`文件中查看或查看下方`API`
- 输出调试信息,程序中可通过`logging`将日志输出到控制台和`qchatgpt.log`文件
- 方法内部从参数中取出`text_message`参数,判断是否为`hello`,如果是就将返回值`reply`设置为`["hello, {}!".format(kwargs['sender_id'])]`,接下来调用`event`对象的`prevent_default`方法,阻止原程序默认行为
- 每个事件`提供的参数``支持的返回值`请查看`pkg.plugin.models`中的每个事件的注释或查看下方`API`
- `event`对象提供的方法请查看`pkg.plugin.host`中的`EventContext`类或查看下方`API`
- 用相似的程序注册`GroupNormalMessageReceived`事件处理群消息
编写完毕保存后,重新启动主程序,查看到输出中包含以下内容,即为加载成功:
```
[2023-01-16 18:29:47.193] host.py (43) - [INFO] : 加载模块: hello.main
[2023-01-16 18:29:47.194] models.py (209) - [INFO] : 插件注册完成: n='Hello', d='hello world', v=0.1, a='RockChinQ' (<class 'plugins.hello.main.HelloPlugin'>)
```
> 建议在`config.py`中设置`logging_level = logging.DEBUG`以便开启调试输出
## ❗规范(重要)
- 请每个插件独立一个目录以便管理建议在Github上创建一个仓库储存单个插件以便获取和更新
- 插件名使用`大驼峰命名法`,如`Hello``ExamplePlugin``ChineseCommands`
- 一个目录内可以存放多个Python程序文件以独立出插件的各个功能便于开发者管理但不建议在一个目录内注册多个插件
- 插件需要的依赖库请在插件目录下的`requirements.txt`中指定,程序从储存库获取此插件时将自动安装依赖
## 🪝内容函数
通过[GPT的Function Calling能力](https://platform.openai.com/docs/guides/gpt/function-calling)实现的`内容函数`这是一种嵌入对话中由GPT自动调用的函数。
> 您的插件不一定必须包含内容函数,请先查看内容函数页了解此功能
<details>
<summary>示例:联网插件</summary>
加载含有联网功能的内容函数的插件[WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin),向机器人询问在线内容
```
# 控制台输出
[2023-07-29 17:37:18.698] message.py (26) - [INFO] : [person_1010553892]发送消息:介绍一下这个项目https://git...
[2023-07-29 17:37:21.292] util.py (67) - [INFO] : message='OpenAI API response' path=https://api.openai.com/v1/chat/completions processing_ms=1902 request_id=941afc13b2e1bba1e7877b92a970cdea response_code=200
[2023-07-29 17:37:21.293] chat_completion.py (159) - [INFO] : 执行函数调用: name=Webwlkr-access_the_web, arguments={'url': 'https://github.com/RockChinQ/QChatGPT', 'brief_len': 512}
[2023-07-29 17:37:21.848] chat_completion.py (164) - [INFO] : 函数执行完成。
```
![Webwlkr插件](https://github.com/RockChinQ/QChatGPT/blob/master/res/screenshots/webwlkr_plugin.png?raw=true)
</details>
### 内容函数编写步骤
1⃣ 请先按照上方步骤编写您的插件基础结构,现在请删除(当然你也可以不删,只是为了简洁)上述插件内容的诸个由`@on`装饰的类函数
<details>
<summary>删除后的结构</summary>
```python
from pkg.plugin.models import *
from pkg.plugin.host import EventContext, PluginHost
"""
在收到私聊或群聊消息"hello"时,回复"hello, <发送者id>!""hello, everyone!"
"""
# 注册插件
@register(name="Hello", description="hello world", version="0.1", author="RockChinQ")
class HelloPlugin(Plugin):
# 插件加载时触发
# plugin_host (pkg.plugin.host.PluginHost) 提供了与主程序交互的一些方法,详细请查看其源码
def __init__(self, plugin_host: PluginHost):
pass
# 插件卸载时触发
def __del__(self):
pass
```
</details>
2⃣ 现在我们将以下函数添加到刚刚删除的函数的位置
```Python
# 要添加的函数
@func(name="access_the_web") # 设置函数名称
def _(url: str):
"""Call this function to search about the question before you answer any questions.
- Do not search through baidu.com at any time.
- If you need to search somthing, visit https://www.google.com/search?q=xxx.
- If user ask you to open a url (start with http:// or https://), visit it directly.
- Summary the plain content result by yourself, DO NOT directly output anything in the result you got.
Args:
url(str): url to visit
Returns:
str: plain text content of the web page
"""
import requests
from bs4 import BeautifulSoup
# 你需要先使用
# pip install beautifulsoup4
# 安装依赖
r = requests.get(
url,
timeout=10,
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.183"
}
)
soup = BeautifulSoup(r.text, 'html.parser')
s = soup.get_text()
# 删除多余的空行或仅有\t和空格的行
s = re.sub(r'\n\s*\n', '\n', s)
if len(s) >= 512: # 截取获取到的网页纯文本内容的前512个字
return s[:512]
return s
```
<details>
<summary>现在这个文件内容应该是这样</summary>
```python
from pkg.plugin.models import *
from pkg.plugin.host import EventContext, PluginHost
"""
在收到私聊或群聊消息"hello"时,回复"hello, <发送者id>!""hello, everyone!"
"""
# 注册插件
@register(name="Hello", description="hello world", version="0.1", author="RockChinQ")
class HelloPlugin(Plugin):
# 插件加载时触发
# plugin_host (pkg.plugin.host.PluginHost) 提供了与主程序交互的一些方法,详细请查看其源码
def __init__(self, plugin_host: PluginHost):
pass
@func(name="access_the_web")
def _(url: str):
"""Call this function to search about the question before you answer any questions.
- Do not search through baidu.com at any time.
- If you need to search somthing, visit https://www.google.com/search?q=xxx.
- If user ask you to open a url (start with http:// or https://), visit it directly.
- Summary the plain content result by yourself, DO NOT directly output anything in the result you got.
Args:
url(str): url to visit
Returns:
str: plain text content of the web page
"""
import requests
from bs4 import BeautifulSoup
# 你需要先使用
# pip install beautifulsoup4
# 安装依赖
r = requests.get(
url,
timeout=10,
headers={
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.183"
}
)
soup = BeautifulSoup(r.text, 'html.parser')
s = soup.get_text()
# 删除多余的空行或仅有\t和空格的行
s = re.sub(r'\n\s*\n', '\n', s)
if len(s) >= 512: # 截取获取到的网页纯文本内容的前512个字
return s[:512]
return s
# 插件卸载时触发
def __del__(self):
pass
```
</details>
#### 请注意:
- 函数的注释必须严格按照要求的格式进行书写,具体格式请查看[此文档](https://github.com/RockChinQ/CallingGPT/wiki/1.-Function-Format#function-format)
- 内容函数和`以@on装饰的行为函数`可以同时存在于同一个插件,并同时受到`switch.json`中的插件开关的控制
- 务必确保您使用的模型支持函数调用功能,可以到`config.py``completion_api_params`中修改模型,推荐使用`gpt-3.5-turbo-16k`
3⃣ 现在您的程序已具备网络访问功能,重启程序,询问机器人有关在线的内容或直接发送文章链接请求其总结。
- 这仅仅是一个示例,需要更高效的网络访问能力支持插件,请查看[WebwlkrPlugin](https://github.com/RockChinQ/WebwlkrPlugin)
## 🔒版本要求
若您的插件对主程序的版本有要求,可以使用以下函数进行断言,若不符合版本,此函数将报错并打断此函数所在的流程:
```python
require_ver("v2.5.1") # 要求最低版本为 v2.5.1
```
```python
require_ver("v2.5.1", "v2.6.0") # 要求最低版本为 v2.5.1, 同时要求最高版本为 v2.6.0
```
- 此函数在主程序`v2.5.1`中加入
- 此函数声明在`pkg.plugin.models`模块中,在插件示例代码最前方已引入此模块所有内容,故可直接使用
## 📄API参考
### 说明
事件处理函数将会获得一系列参数,可以在`kwargs`中取出。
其中`host`参数(`pkg.plugin.host.PluginHost`类的实例)是插件宿主,提供与主程序各个模块交互的一些方法。
`event`参数(`pkg.plugin.host.EventContext`类的实例)是事件执行期间的上下文,提供对此次事件执行的一些操作方法。
事件返回值均为**可选**的,可以通过调用`event.add_return(key: str, ret)`来提交返回值
### 事件
所有事件参数均有`host``event`,以下仅展示其他参数
关于`YiriMirai`支持的消息链组件,请查看 [YiriMirai的文档](https://yiri-mirai.wybxc.cc/docs/basic/message-chain)
```Python
PersonMessageReceived = "person_message_received"
"""收到私聊消息时,在判断是否应该响应前触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
message_chain: mirai.models.message.MessageChain 消息链
"""
GroupMessageReceived = "group_message_received"
"""收到群聊消息时,在判断是否应该响应前触发(所有群消息)
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
message_chain: mirai.models.message.MessageChain 消息链
"""
PersonNormalMessageReceived = "person_normal_message_received"
"""判断为应该处理的私聊普通消息时触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
text_message: str 消息文本
returns (optional):
alter: str 修改后的消息文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
PersonCommandSent = "person_command_sent"
"""判断为应该处理的私聊命令时触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
command: str 命令
params: list[str] 参数列表
text_message: str 完整命令文本
is_admin: bool 是否为管理员
returns (optional):
alter: str 修改后的完整命令文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
GroupNormalMessageReceived = "group_normal_message_received"
"""判断为应该处理的群聊普通消息时触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
text_message: str 消息文本
returns (optional):
alter: str 修改后的消息文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
GroupCommandSent = "group_command_sent"
"""判断为应该处理的群聊命令时触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
command: str 命令
params: list[str] 参数列表
text_message: str 完整命令文本
is_admin: bool 是否为管理员
returns (optional):
alter: str 修改后的完整命令文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
NormalMessageResponded = "normal_message_responded"
"""获取到对普通消息的文字响应时触发
kwargs:
launcher_type: str 发起对象类型(group/person)
launcher_id: int 发起对象ID(群号/QQ号)
sender_id: int 发送者ID(QQ号)
session: pkg.openai.session.Session 会话对象
prefix: str 回复文字消息的前缀
response_text: str 响应文本
finish_reason: str 响应结束原因
returns (optional):
prefix: str 修改后的回复文字消息的前缀
reply: list 替换回复消息组件列表
"""
SessionFirstMessageReceived = "session_first_message_received"
"""会话被第一次交互时触发
kwargs:
session_name: str 会话名称(<launcher_type>_<launcher_id>)
session: pkg.openai.session.Session 会话对象
default_prompt: str 预设值
"""
SessionExplicitReset = "session_reset"
"""会话被用户手动重置时触发,此事件不支持阻止默认行为
kwargs:
session_name: str 会话名称(<launcher_type>_<launcher_id>)
session: pkg.openai.session.Session 会话对象
"""
SessionExpired = "session_expired"
"""会话过期时触发
kwargs:
session_name: str 会话名称(<launcher_type>_<launcher_id>)
session: pkg.openai.session.Session 会话对象
session_expire_time: int 已设置的会话过期时间(秒)
"""
KeyExceeded = "key_exceeded"
"""api-key超额时触发
kwargs:
key_name: str 超额的api-key名称
usage: dict 超额的api-key使用情况
exceeded_keys: list[str] 超额的api-key列表
"""
KeySwitched = "key_switched"
"""api-key超额切换成功时触发此事件不支持阻止默认行为
kwargs:
key_name: str 切换成功的api-key名称
key_list: list[str] api-key列表
"""
PromptPreProcessing = "prompt_pre_processing" # 于v2.5.1加入
"""每回合调用接口前对prompt进行预处理时触发此事件不支持阻止默认行为
kwargs:
session_name: str 会话名称(<launcher_type>_<launcher_id>)
default_prompt: list 此session使用的情景预设内容
prompt: list 此session现有的prompt内容
text_message: str 用户发送的消息文本
returns (optional):
default_prompt: list 修改后的情景预设内容
prompt: list 修改后的prompt内容
text_message: str 修改后的消息文本
"""
```
### host: PluginHost 详解
提供与主程序各个模块交互的一些方法,具体查看`pkg.plugin.host`中的`PluginHost`
### event: EventContext 详解
提供对此次事件执行的一些操作方法,具体查看`pkg.plugin.host`中的`EventContext`

View File

@@ -0,0 +1,14 @@
## 多个对话接口有何区别?
出于对稳定性的高要求本项目主线接入的是GPT-3模型接口此接口由OpenAI官方开放稳定性强。
目前支持通过加载[插件](https://github.com/RockChinQ/revLibs)的方式接入ChatGPT网页版使用的是acheong08/ChatGPT的逆向工程库但文本生成质量更高。
同时程序主线已支持ChatGPT API并作为默认接口 [#195](https://github.com/RockChinQ/QChatGPT/issues/195)
|官方接口|ChatGPT网页版|ChatGPT API
|---|---|---|
|官方开放,稳定性高 | 由[acheong08](https://github.com/acheong08)破解网页版协议接入| 由OpenAI官方开放
|一次性回复,响应速度较快| 流式回复,响应速度较慢|响应速度较快|
|收费0.02美元/千字|免费|收费0.002美元/千字|
|GPT-3模型|GPT-3.5模型|GPT-3.5模型|
|任何地区主机均可使用(疑似受到GFW影响)|ChatGPT限制访问的区域使用有难度|任何地区主机均可使用(疑似受到GFW影响)|

Some files were not shown because too many files have changed in this diff Show More