Compare commits

..

268 Commits

Author SHA1 Message Date
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
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
63 changed files with 2328 additions and 749 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

@@ -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

View File

@@ -1,7 +1,14 @@
name: Update Wiki
on:
pull_request:
branches:
- master
paths:
- 'res/wiki/**'
push:
branches:
- master
paths:
- 'res/wiki/**'
@@ -20,14 +27,22 @@ jobs:
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
if git diff --name-only; then
git add .
git commit -m "Update wiki"
git push
fi
git add .
git commit -m "Update wiki"
git push

View File

@@ -26,7 +26,7 @@ jobs:
- 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 colorlog func_timeout dulwich Pillow CallingGPT tiktoken
- name: Copy Scripts
run: |

10
.gitignore vendored
View File

@@ -22,4 +22,12 @@ cmdpriv.json
tips.py
.venv
bin/
.vscode
.vscode
test_*
venv/
hugchat.json
qcapi
claude.json
bard.json
/*yaml
!/docker-compose.yaml

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 +1,14 @@
FROM python:3.9-slim
FROM python:3.10.13-alpine3.18
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 pip install -r requirements.txt
RUN pip install -U websockets==10.0
# 生成配置文件
RUN python main.py
CMD [ "python", "main.py" ]

185
README.md
View File

@@ -1,28 +1,59 @@
# QChatGPT🤖
<p align="center">
<img src="res/social.png" alt="QChatGPT" width="640" />
<img src="res/logo.png" alt="QChatGPT" width="120" />
</p>
[English](README_en.md) | 简体中文
<div align="center">
[![GitHub release (latest by date)](https://img.shields.io/github/v/release/RockChinQ/QChatGPT?style=flat-square)](https://github.com/RockChinQ/QChatGPT/releases/latest)
# QChatGPT
> 2023/4/24 支持使用go-cqhttp登录QQ请查看[此文档](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE)
> 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)
<!-- 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”
- 到[项目Wiki](https://github.com/RockChinQ/QChatGPT/wiki)可了解项目详细信息
- 官方交流、答疑群: 656285629
- **进群提问前请您`确保`已经找遍文档和issue均无法解决**
- 社区群(内有一键部署包、图形化界面等资源): 362515018
- 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)
[![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://lazyfree.top/2023/08/16/QChatGPT%E4%BD%BF%E7%94%A8%E6%89%8B%E5%86%8C/">
<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
@@ -32,6 +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
@@ -39,7 +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
@@ -48,14 +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>
@@ -82,30 +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>
@@ -149,16 +185,28 @@
<br/>
<img alt="New Bing" src="res/screenshots/person_newbing.png" width="400"/>
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>
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)
<details>
## 🔩部署
<summary>
**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**
## 🚀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
@@ -169,15 +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](res/docs/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
@@ -209,7 +260,7 @@
<details>
<summary>go-cqhttp</summary>
1. 按照[此文档](https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE)配置go-cqhttp
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`
@@ -227,7 +278,7 @@ cd QChatGPT
2. 安装依赖
```bash
pip3 install requests yiri-mirai openai colorlog func_timeout dulwich Pillow nakuru-project-idk
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
@@ -256,47 +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%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) - 支持通过指令切换使用的模型
- [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
@@ -304,6 +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>

View File

@@ -7,6 +7,7 @@
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
@@ -27,6 +28,7 @@ English | [简体中文](README.md)
- 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

View File

@@ -62,6 +62,9 @@ nakuru_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"
@@ -70,6 +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]
@@ -123,13 +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
@@ -172,16 +202,22 @@ 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
# 现已支持的模型有:
#
# 'gpt-4'
# 'gpt-4-0314'
# 'gpt-4-0613'
# 'gpt-4-32k'
# 'gpt-4-32k-0314'
# 'gpt-4-32k-0613'
# 'gpt-3.5-turbo'
# 'gpt-3.5-turbo-0301'
# 'gpt-3.5-turbo-16k'
# 'gpt-3.5-turbo-0613'
# 'gpt-3.5-turbo-16k-0613'
# 'text-davinci-003'
# 'text-davinci-002'
# 'code-davinci-002'
@@ -192,12 +228,12 @@ prompt_submit_length = 2048
#
# 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
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
@@ -206,18 +242,34 @@ 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
# 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

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

253
main.py
View File

@@ -47,9 +47,9 @@ def init_db():
def ensure_dependencies():
import pkg.utils.pkgmgr as pkgmgr
pkgmgr.run_pip(["install", "openai", "Pillow", "nakuru-project-idk", "--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
@@ -60,35 +60,42 @@ def override_config():
# 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]))
# 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("配置文件不完整您可以依据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
override_config()
if not is_integrity:
logging.warning("以上不存在的配置已被设为默认值将在3秒后继续启动... ")
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
@@ -97,6 +104,8 @@ def load_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')
@@ -104,10 +113,12 @@ def complete_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))
# 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)
@@ -134,127 +145,144 @@ 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.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 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.proxy = 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.proxy = 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.api_base = 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(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:
logging.info("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
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:
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:
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':
@@ -268,7 +296,7 @@ def start(first_time_init=False):
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,请查看 '
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']))
@@ -301,7 +329,8 @@ 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))

View File

@@ -21,21 +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": [
@@ -51,20 +54,24 @@
"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"
},
"trace_function_calls": false,
"quote_origin": true,
"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,

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 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={}&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
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

View File

@@ -0,0 +1,204 @@
import openai
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: dict = 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,
model: str,
messages: list[dict[str, str]],
**kwargs
):
self.model = model
self.messages = messages.copy()
self.kwargs = kwargs
self.req_func = openai.ChatCompletion.acreate
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}
resp = 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 'function_call' in choice0['message']:
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": choice0['message']['function_call']
},
"finish_reason": "function_call"
}
],
"usage": resp["usage"]
}
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": resp["usage"]
}
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 +1,111 @@
import openai
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,
model: str,
messages: list[dict[str, str]],
**kwargs
):
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 = openai.Completion.acreate
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 = self._req(
model=self.model,
prompt=self.prompt,
**self.kwargs
)
if resp["choices"][0]["finish_reason"] == "stop":
self.stopped = True
choice0 = 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": resp["usage"]
}
if __name__ == "__main__":
import os
openai.api_key = os.environ["OPENAI_API_KEY"]
for resp in CompletionRequest(
model="text-davinci-003",
messages=[
{
"role": "user",
"content": "Hello, who are you?"
}
]
):
print(resp)
if resp["choices"][0]["finish_reason"] == "stop":
break

62
pkg/openai/api/model.py Normal file
View File

@@ -0,0 +1,62 @@
# 定义不同接口请求的模型
import threading
import asyncio
import logging
import openai
class RequestBase:
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))
openai.api_key = context.get_openai_manager().key_mgr.get_using_key()
def _req(self, **kwargs):
"""处理代理问题"""
import config
ret: dict = {}
exception: Exception = None
async def awrapper(**kwargs):
nonlocal ret, exception
try:
ret = await 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
except Exception as e:
exception = e
loop = asyncio.new_event_loop()
thr = threading.Thread(
target=loop.run_until_complete,
args=(awrapper(**kwargs),)
)
thr.start()
thr.join()
if exception is not None:
raise exception
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:
@@ -27,51 +29,37 @@ class OpenAIInteract:
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()
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(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

View File

@@ -7,6 +7,11 @@ Completion - text-davinci-003 等模型
"""
import openai, logging, threading, asyncio
import openai.error as aiE
import tiktoken
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',
@@ -20,11 +25,23 @@ COMPLETION_MODELS = {
CHAT_COMPLETION_MODELS = {
'gpt-3.5-turbo',
'gpt-3.5-turbo-0301',
'gpt-3.5-turbo-16k',
'gpt-3.5-turbo-0613',
'gpt-3.5-turbo-16k-0613',
# 'gpt-3.5-turbo-0301',
'gpt-4',
'gpt-4-0314',
'gpt-4-0613',
'gpt-4-32k',
'gpt-4-32k-0314'
'gpt-4-32k-0613',
# 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 +53,85 @@ 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 type(e)(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(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(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(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
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'] + "\n"
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

@@ -8,6 +8,7 @@ import sys
import shutil
import traceback
import pkg.utils.updater as updater
import pkg.utils.context as context
import pkg.plugin.switch as switch
import pkg.plugin.settings as settings
@@ -15,6 +16,8 @@ import pkg.qqbot.adapter as msadapter
from mirai import Mirai
from CallingGPT.session.session import Session
__plugins__ = {}
"""插件列表
@@ -41,6 +44,15 @@ __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"""
@@ -79,7 +91,7 @@ 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()
@@ -87,7 +99,7 @@ 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'))
@@ -101,20 +113,30 @@ def load_plugins():
# 加载插件顺序
settings.load_settings()
# 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__))
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
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():
@@ -177,6 +199,43 @@ 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
target_plugin_dir = "plugins/" + __plugins__[plugin_name]['path'].replace("\\", "/").split("plugins/")[1].split("/")[0]
remote_url = updater.get_remote_url(target_plugin_dir)
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")
# 把远程clone到temp/plugins/update/插件名
logging.info("克隆插件储存库: {}".format(remote_url))
from dulwich import porcelain
clone_target_dir = "temp/plugins/update/"+target_plugin_dir.split("/")[-1]+"/"
if os.path.exists(clone_target_dir):
shutil.rmtree(clone_target_dir)
if not os.path.exists(clone_target_dir):
os.makedirs(clone_target_dir)
repo = porcelain.clone(remote_url, clone_target_dir, checkout=True)
# 检查此目录是否包含requirements.txt
if os.path.exists(clone_target_dir+"requirements.txt"):
logging.info("检测到requirements.txt正在安装依赖")
import pkg.utils.pkgmgr
pkg.utils.pkgmgr.install_requirements(clone_target_dir+"requirements.txt")
import pkg.utils.log as log
log.reset_logging()
# 将temp/plugins/update/插件名 覆盖到 plugins/插件名
shutil.rmtree(target_plugin_dir)
shutil.copytree(clone_target_dir, target_plugin_dir)
class EventContext:
"""事件上下文"""
eid = 0
@@ -213,7 +272,7 @@ 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]
@@ -262,7 +321,9 @@ 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
@@ -283,11 +344,11 @@ class PluginHost:
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"""
@@ -332,7 +393,7 @@ 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']))
@@ -344,3 +405,6 @@ class PluginHost:
event_context.__return_value__))
return event_context
if __name__ == "__main__":
pass

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"""

View File

@@ -260,8 +260,8 @@ 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']:
@@ -327,6 +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

@@ -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

@@ -12,7 +12,7 @@ import pkg.utils.updater as updater
description="插件管理",
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
@@ -97,37 +97,34 @@ 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 pkg.utils.log as log
log.reset_logging()
if ctx.crt_params[0] == 'all':
for key in plugin_list:
plugin_host.update_plugin(key)
updated.append(key)
else:
if ctx.crt_params[0] in plugin_list:
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: {}".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))
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 +188,11 @@ 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

@@ -8,7 +8,7 @@ def config_operation(cmd, params):
config = pkg.utils.context.get_config()
reply_str = ""
if len(params) == 0:
reply = ["[bot]err:请输入配置项"]
reply = ["[bot]err:请输入!cmd cfg查看使用方法"]
else:
cfg_name = params[0]
if cfg_name == 'all':
@@ -26,45 +26,61 @@ def config_operation(cmd, params):
else:
reply_str += "{}: {}\n".format(cfg, getattr(config, cfg))
reply = [reply_str]
elif cfg_name in dir(config):
if len(params) == 1:
# 按照配置项类型进行格式化
if isinstance(getattr(config, cfg_name), str):
reply_str = "[bot]配置项{}: \"{}\"\n".format(cfg_name, getattr(config, cfg_name))
elif isinstance(getattr(config, cfg_name), dict):
reply_str = "[bot]配置项{}: {}\n".format(cfg_name,
json.dumps(getattr(config, cfg_name),
ensure_ascii=False, indent=4))
else:
reply_str = "[bot]配置项{}: {}\n".format(cfg_name, getattr(config, cfg_name))
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
# 检查类型是否匹配
if isinstance(getattr(config, cfg_name), type(cfg_value)):
setattr(config, cfg_name, cfg_value)
pkg.utils.context.set_config(config)
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:
reply = ["[bot]err:未找到配置项 {}".format(cfg_name)]
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

View File

@@ -25,10 +25,18 @@ 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()
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']:
@@ -46,19 +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
@@ -74,6 +102,9 @@ class QQBotManager:
enable_banlist = False
enable_private = True
enable_group = True
ban_person = []
ban_group = []
@@ -87,7 +118,7 @@ class QQBotManager:
# 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:
logging.info("Use adapter:" + config.msg_source_adapter)
logging.debug("Use adapter:" + config.msg_source_adapter)
if config.msg_source_adapter == 'yirimirai':
from pkg.qqbot.sources.yirimirai import YiriMiraiAdapter
@@ -100,6 +131,7 @@ class QQBotManager:
self.bot_account_id = self.adapter.bot_account_id
else:
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)
@@ -213,6 +245,11 @@ class QQBotManager:
self.ban_group = banlist.group
logging.info("加载禁用列表: person: {}, group: {}".format(self.ban_person, self.ban_group))
if hasattr(banlist, "enable_private"):
self.enable_private = banlist.enable_private
if hasattr(banlist, "enable_group"):
self.enable_group = banlist.enable_group
config = pkg.utils.context.get_config()
if os.path.exists("sensitive.json") \
and config.sensitive_word_filter is not None \
@@ -227,8 +264,24 @@ class QQBotManager:
else:
self.reply_filter = pkg.qqbot.filter.ReplyFilter([])
def send(self, event, msg, check_quote=True):
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,
@@ -240,7 +293,9 @@ class QQBotManager:
import config
reply = ''
if event.sender.id == self.bot_account_id:
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:
@@ -274,7 +329,7 @@ class QQBotManager:
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):
@@ -313,20 +368,22 @@ class QQBotManager:
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_account_id) 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()

View File

@@ -40,7 +40,7 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
try:
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 = {
@@ -49,7 +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)
@@ -62,10 +64,11 @@ 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:
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")
@@ -114,8 +117,12 @@ def process_normal_message(text_message: str, mgr, config, launcher_type: str,
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")
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.error.ServiceUnavailableError 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:

View File

@@ -74,12 +74,16 @@ def process_message(launcher_type: str, launcher_id: int, text_message: str, mes
import config
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:
@@ -168,4 +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

@@ -23,7 +23,7 @@ class NakuruProjectMessageConverter(MessageConverter):
elif type(message_chain) is list:
msg_list = message_chain
else:
raise Exception("Unknown message type: " + str(message_chain) + type(message_chain))
raise Exception("Unknown message type: " + str(message_chain) + str(type(message_chain)))
nakuru_msg_list = []
@@ -157,7 +157,6 @@ class NakuruProjectEventConverter(EventConverter):
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
@@ -183,6 +182,9 @@ class NakuruProjectAdapter(MessageSourceAdapter):
},
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")
self.bot_account_id = int(resp.json()['data']['user_id'])
def send_message(

View File

@@ -1,6 +1,7 @@
from ..adapter import MessageSourceAdapter
import mirai
import mirai.models.bus
from mirai.bot import MiraiRunner
import asyncio
import typing
@@ -110,7 +111,12 @@ class YiriMiraiAdapter(MessageSourceAdapter):
bus.unsubscribe(event_type, callback)
def run_sync(self):
self.bot.run()
"""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

File diff suppressed because one or more lines are too long

View File

@@ -8,7 +8,8 @@ def install(package):
log.reset_logging()
def install_upgrade(package):
pipmain(['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()
@@ -18,7 +19,8 @@ def run_pip(params: list):
def install_requirements(file):
pipmain(['install', '-r', file, "--upgrade"])
pipmain(['install', '-r', file, "--upgrade", "-i", "https://pypi.tuna.tsinghua.edu.cn/simple",
"--trusted-host", "pypi.tuna.tsinghua.edu.cn"])
log.reset_logging()

View File

@@ -34,13 +34,18 @@ def pull_latest(repo_path: str) -> bool:
return True
def is_newer_ignored_bugfix_ver(new_tag: str, old_tag: str):
"""判断版本是否更新,忽略第四位版本"""
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
@@ -73,6 +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()
@@ -97,7 +130,7 @@ def update_all(cli: bool = False) -> bool:
else:
print("更新日志: {}".format(rls_notes))
if latest_rls == {} and not is_newer_ignored_bugfix_ver(latest_tag_name, current_tag): # 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
@@ -254,7 +287,7 @@ def is_new_version_available() -> bool:
latest_tag_name = rls['tag_name']
break
return is_newer_ignored_bugfix_ver(latest_tag_name, current_tag)
return is_newer(latest_tag_name, current_tag)
def get_rls_notes() -> list:

View File

@@ -1,10 +1,13 @@
requests~=2.28.1
openai~=0.27.4
dulwich~=0.21.3
requests
openai~=0.28.0
dulwich~=0.21.6
colorlog~=6.6.0
yiri-mirai~=0.2.6.1
yiri-mirai
websockets
urllib3~=1.26.10
urllib3
func_timeout~=4.3.5
Pillow
nakuru-project-idk
nakuru-project-idk
CallingGPT
tiktoken
PyYaml

View File

@@ -1,8 +1,8 @@
[
{
"id": 0,
"time": "2023-04-24 16:05:20",
"timestamp": 1682323520,
"content": "现已支持使用go-cqhttp替换mirai作为QQ登录框架, 请更新并查看 https://github.com/RockChinQ/QChatGPT/wiki/go-cqhttp%E9%85%8D%E7%BD%AE"
"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"
}
]

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。

Binary file not shown.

Before

Width:  |  Height:  |  Size: 203 KiB

After

Width:  |  Height:  |  Size: 35 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 22 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,

BIN
res/webwlkr-demo.gif Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 879 KiB

View File

@@ -48,12 +48,12 @@
</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>`令加载
- 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%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>`令加载
</details>
<details>
@@ -61,25 +61,25 @@
- 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`令管理会话
- 运行期间可使用`!reset` `!list` `!last` `!next` `!prompt`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`!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)
- 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>
@@ -153,14 +153,14 @@
<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
### 机器人
目前支持的
目前支持的
> `<>` 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
#### 用户级别
> 可以使用`!help`命令来查看命令说明
@@ -174,7 +174,7 @@
!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令查看可用的)
!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
@@ -184,7 +184,7 @@
!default 查看可用的情景预设值
```
#### 管理员
#### 管理员
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
@@ -197,9 +197,9 @@
!delhst all 删除所有会话的所有历史记录
```
<details>
<summary>⚙ !cfg 令及其简化形式详解</summary>
<summary>⚙ !cfg 令及其简化形式详解</summary>
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**。
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
@@ -225,7 +225,7 @@
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
!cfg default_prompt "我是Rock Chin"
```
输出示例
@@ -239,11 +239,19 @@
格式:`!~<配置项名称>`
其中`!~`等价于`!cfg `
则前述三个令分别可以简化为:
则前述三个令分别可以简化为:
```
!~all
!~default_prompt
!~default_prompt 我是Rock Chin
!~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>
@@ -282,11 +290,11 @@ sensitive_word_filter = True
### 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>`令加载,或使用`!default <文件名>`令将其设为默认
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>`令加载,或使用`!default <文件名>`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>`令加载,或使用`!default <文件名>`令将其设为默认.
将JSON情景写入到`scenario/`目录下,运行期间即可使用`!reset <文件名>`令加载,或使用`!default <文件名>`令将其设为默认.
JSON情景模板参考`scenario/default_template.json`
@@ -359,7 +367,7 @@ prompt_submit_length = <模型单次请求token数上限> - 情景预设中token
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`管理员令`段落
详见前述`管理员令`段落
### 群内无需@响应规则
@@ -367,4 +375,5 @@ prompt_submit_length = <模型单次请求token数上限> - 情景预设中token
### 加入黑名单
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
- 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

@@ -4,7 +4,7 @@
#### 自动更新
由管理员QQ私聊机器人QQ发送`!update`
由管理员QQ私聊机器人QQ发送`!update`
#### 手动更新

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!!

View File

@@ -1,7 +1,7 @@
QChatGPT 插件开发Wiki
> 请先阅读[插件使用页](https://github.com/RockChinQ/QChatGPT/wiki/%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/%E6%8A%80%E6%9C%AF%E4%BF%A1%E6%81%AF)
> 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
@@ -113,6 +113,199 @@ class HelloPlugin(Plugin):
- 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>!"或"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>!"或"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
@@ -161,18 +354,18 @@ PersonNormalMessageReceived = "person_normal_message_received"
"""
PersonCommandSent = "person_command_sent"
"""判断为应该处理的私聊令时触发
"""判断为应该处理的私聊令时触发
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
command: str
params: list[str] 参数列表
text_message: str 完整令文本
text_message: str 完整令文本
is_admin: bool 是否为管理员
returns (optional):
alter: str 修改后的完整令文本
alter: str 修改后的完整令文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
@@ -190,18 +383,18 @@ GroupNormalMessageReceived = "group_normal_message_received"
"""
GroupCommandSent = "group_command_sent"
"""判断为应该处理的群聊令时触发
"""判断为应该处理的群聊令时触发
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
command: str
params: list[str] 参数列表
text_message: str 完整令文本
text_message: str 完整令文本
is_admin: bool 是否为管理员
returns (optional):
alter: str 修改后的完整令文本
alter: str 修改后的完整令文本
reply: list 回复消息组件列表元素为YiriMirai支持的消息组件
"""
@@ -214,10 +407,11 @@ 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
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元素为YiriMirai支持的消息组件
reply: list 替换回复消息组件列表
"""
SessionFirstMessageReceived = "session_first_message_received"
@@ -257,6 +451,20 @@ KeySwitched = "key_switched"
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

View File

@@ -5,24 +5,27 @@
## 步骤
1. 从[go-cqhttp的Release](https://github.com/Mrs4s/go-cqhttp/releases/latest)下载最新的go-cqhttp可执行文件建议直接下载可执行文件压缩包而不是安装器
2. 解压并运行,首次运行会询问需要开放的网络协议,**请填入`02`并回车**
2. 解压并运行,首次运行会询问需要开放的网络协议,**请填入`02`并回车,必须输入`02`❗❗❗❗❗❗❗**
```
C:\Softwares\go-cqhttp.old> .\go-cqhttp.exe
未找到配置文件,正在为您生成配置文件中!
请选择你需要的通信方式:
> 0: HTTP通信
> 1: 云函数服务
> 2: 正向 Websocket 通信
> 3: 反向 Websocket 通信
请输入你需要的编号(0-9),可输入多个,同一编号也可输入多个(如: 233)
您的选择是:02
```
提示已生成`config.yml`文件关闭go-cqhttp。
<h1> 你这里必须得输入`02`,你懂么,`0`必须得输入,看好了,看好下面输入什么了吗?别他妈的搁那就输个`2`完了启动连不上还跑群里问,问一个我踢一个。 </h1>
```
C:\Softwares\go-cqhttp.old> .\go-cqhttp.exe
未找到配置文件,正在为您生成配置文件中!
请选择你需要的通信方式:
> 0: HTTP通信
> 1: 云函数服务
> 2: 正向 Websocket 通信
> 3: 反向 Websocket 通信
请输入你需要的编号(0-9),可输入多个,同一编号也可输入多个(如: 233)
您的选择是:02
```
提示已生成`config.yml`文件关闭go-cqhttp。
3. 打开go-cqhttp同目录的`config.yml`
1. 编辑账号登录信息(可选)
1. 编辑账号登录信息
只需要修改下方`uin``password`为你要登录的机器人账号的QQ号和密码即可。
**若您不填写,将会在启动时请求扫码登录。**
@@ -39,7 +42,7 @@
max-times: 0 # 最大重连次数, 0为无限制
```
2. 修改websocket端口(必需)
2. 修改websocket端口
`config.yml`下方找到以下内容
@@ -64,4 +67,4 @@
4. 配置完成重新启动go-cqhttp
> 若启动后登录不成功,请尝试根据[此文档](https://docs.go-cqhttp.org/guide/config.html#%E8%AE%BE%E5%A4%87%E4%BF%A1%E6%81%AF)修改`device.json`的协议编号。
> 若启动后登录不成功,请尝试根据[此文档](https://docs.go-cqhttp.org/guide/config.html#%E8%AE%BE%E5%A4%87%E4%BF%A1%E6%81%AF)修改`device.json`的协议编号。

View File

@@ -1,44 +0,0 @@
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
## 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 指令
```
!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 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 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)
```
### 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

42
tests/bs_test/bs_test.py Normal file
View File

@@ -0,0 +1,42 @@
import requests
from bs4 import BeautifulSoup
import os
import random
import sys
user_agents = [
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:89.0) Gecko/20100101 Firefox/89.0',
'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.131 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1.2 Safari/537.36',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Version/14.1 Safari/537.36',
'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0',
'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:88.0) Gecko/20100101 Firefox/88.0'
]
r = requests.get(
sys.argv[1],
headers={
"User-Agent": random.choice(user_agents)
}
)
soup = BeautifulSoup(r.text, 'html.parser')
# print(soup.get_text())
raw = soup.get_text()
import re
# strip每一行
# raw = '\n'.join([line.strip() for line in raw.split('\n')])
# # 删除所有空行或只有空格的行
# raw = re.sub(r'\n\s*\n', '\n', raw)
print(raw)

View File

@@ -0,0 +1,57 @@
import os
import sys
import paramiko
import time
import select
class sshClient:
#创建一个ssh客户端和服务器连接上准备发消息
def __init__(self,host,port,user,password):
self.trans = paramiko.Transport((host, port))
self.trans.start_client()
self.trans.auth_password(username=user, password=password)
self.channel = self.trans.open_session()
self.channel.get_pty()
self.channel.invoke_shell()
#给服务器发送一个命令
def sendCmd(self,cmd):
self.channel.sendall(cmd)
#接收的时候,有时候服务器处理的比较慢,需要设置一个延时等待一下。
def recvResponse(self,timeout):
data=b''
while True:
try:
#使用select不断的读取数据直到没有多余的数据了超时返回。
readable,w,e= select.select([self.channel],[],[],timeout)
if self.channel in readable:
data = self.channel.recv(1024)
else:
sys.stdout.write(data.decode())
sys.stdout.flush()
return data.decode()
except TimeoutError:
sys.stdout.write(data.decode())
sys.stdout.flush()
return data.decode
#关闭客户端
def close(self):
self.channel.close()
self.trans.close()
host='host'
port=22#your port
user='root'
pwd='pass'
ssh = sshClient(host,port,user,pwd)
response = ssh.recvResponse(1)
response = ssh.sendCmd("ls\n")
ssh.sendCmd("cd /home\n")
response = ssh.recvResponse(1)
ssh.sendCmd("ls\n")
response = ssh.recvResponse(1)
ssh.close()

View File

@@ -0,0 +1,124 @@
import tiktoken
import openai
import json
import os
openai.api_key = os.getenv("OPENAI_API_KEY")
def encode(text: str, model: str):
import tiktoken
enc = tiktoken.get_encoding("cl100k_base")
assert enc.decode(enc.encode("hello world")) == "hello world"
# To get the tokeniser corresponding to a specific model in the OpenAI API:
enc = tiktoken.encoding_for_model(model)
return enc.encode(text)
# def ask(prompt: str, model: str = "gpt-3.5-turbo"):
# # To get the tokeniser corresponding to a specific model in the OpenAI API:
# enc = tiktoken.encoding_for_model(model)
# resp = openai.ChatCompletion.create(
# model=model,
# messages=[
# {
# "role": "user",
# "content": prompt
# }
# ]
# )
# return enc.encode(prompt), enc.encode(resp['choices'][0]['message']['content']), resp
def ask(
messages: list,
model: str = "gpt-3.5-turbo"
):
enc = tiktoken.encoding_for_model(model)
resp = openai.ChatCompletion.create(
model=model,
messages=messages
)
txt = ""
for r in messages:
txt += r['role'] + r['content'] + "\n"
txt += "assistant: "
return enc.encode(txt), enc.encode(resp['choices'][0]['message']['content']), resp
def num_tokens_from_messages(messages, model="gpt-3.5-turbo-0613"):
"""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",
}:
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 num_tokens_from_messages(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 num_tokens_from_messages(messages, model="gpt-4-0613")
else:
raise NotImplementedError(
f"""num_tokens_from_messages() 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
messages = [
{
"role": "user",
"content": "你叫什么名字?"
},{
"role": "assistant",
"content": "我是AI助手没有具体的名字。你可以叫我GPT-3。有什么可以帮到你的吗"
},{
"role": "user",
"content": "你是由谁开发的?"
},{
"role": "assistant",
"content": "我是由OpenAI开发的一家人工智能研究实验室。OpenAI的使命是促进人工智能的发展使其为全人类带来积极影响。我是由OpenAI团队使用GPT-3模型训练而成的。"
},{
"role": "user",
"content": "很高兴见到你。"
}
]
pro, rep, resp=ask(messages)
print(len(pro), len(rep))
print(resp)
print(resp['choices'][0]['message']['content'])
print(num_tokens_from_messages(messages, model="gpt-3.5-turbo"))

View File

@@ -27,8 +27,11 @@ replys_message = "[bot]err:请求超时"
# 指令权限不足提示
command_admin_message = "[bot]err:权限不足: "
# 指令无效提示
command_err_message = "[bot]err:指令执行出错"
command_err_message = "[bot]err:指令不存在"
# 会话重置提示
command_reset_message = "[bot]:会话已重置"
command_reset_name_message = "[bot]:会话已重置,使用场景预设:"
command_reset_message = "[bot]会话已重置"
command_reset_name_message = "[bot]会话已重置,使用场景预设:"
# 会话自动重置时的提示
session_auto_reset_message = "[bot]会话token超限已自动重置请重新发送消息"