Compare commits

...

321 Commits

Author SHA1 Message Date
Junyan Qin
d7fc5283f7 chore: bump version 4.3.0b4 2025-08-28 14:43:45 +08:00
Junyan Qin
4bdd8a021c fix: tool call params in localagent 2025-08-28 14:38:10 +08:00
Junyan Qin
c0ccdaf91a fix: minor bugs 2025-08-28 14:02:56 +08:00
Junyan Qin
e7fe41810e fix: dark mode for plugins management page 2025-08-26 22:40:32 +08:00
Junyan Qin
56183867a7 fix: replace message_chain.has usage 2025-08-25 23:22:36 +08:00
Junyan Qin
ea6ce2f552 fix: set plugin enabled=true as default 2025-08-25 20:56:39 +08:00
Junyan Qin
55df728471 fix: wrong migration target version 2025-08-24 21:47:54 +08:00
Junyan Qin
8a370a260e fix: syntax errors 2025-08-24 21:46:20 +08:00
Junyan Qin
64764c412b Merge branch 'rc/new-plugin' into refactor/new-plugin-system 2025-08-24 21:40:02 +08:00
Junyan Qin
f2d5c21712 perf: inline code display style in markdown 2025-08-24 19:59:33 +08:00
Junyan Qin
6113c42014 fix: change tag of image to latest 2025-08-24 11:15:28 +08:00
Junyan Qin
fd9d1c4acc feat: update docker launch method 2025-08-24 11:10:05 +08:00
Junyan Qin
118ebddae6 fix: use --standalone-runtime 2025-08-23 23:03:32 +08:00
Junyan Qin
2742144e12 feat: change standalone runtime tag env 2025-08-23 22:57:46 +08:00
devin-ai-integration[bot]
83ff64698b feat: add ZIP file upload support for knowledge base (#1626)
* feat: add ZIP file upload support for knowledge base

- Add _parse_zip method to FileParser class using zipfile library
- Support extraction and processing of TXT, PDF, DOCX, MD, HTML files from ZIP
- Update FileUploadZone to accept .zip files
- Add ZIP format to supported formats in internationalization files
- Implement error handling for invalid ZIP files and unsupported content
- Follow existing async parsing patterns and error handling conventions

Co-Authored-By: Rock <rockchinq@gmail.com>

* refactor: modify ZIP processing to store each document as separate file

- Remove _parse_zip method from FileParser as ZIP handling now occurs at knowledge base level
- Add _store_zip_file method to RuntimeKnowledgeBase to extract and store each document separately
- Each document in ZIP is now stored as individual file entry in knowledge base
- Process ZIP files in memory using io.BytesIO to avoid filesystem writes
- Generate unique file names for extracted documents to prevent conflicts

Co-Authored-By: Rock <rockchinq@gmail.com>

* perf: delete temp files

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Rock <rockchinq@gmail.com>
2025-08-23 21:18:13 +08:00
How-Sean Xin
b5e22c6db8 Update package.json (#1627) 2025-08-23 20:22:25 +08:00
Junyan Qin
d3a147bbdd chore: bump version 4.3.0b3 2025-08-23 20:08:29 +08:00
Junyan Qin
8eb1b8759b chore: bump version to '4.3.0b2' 2025-08-23 20:06:19 +08:00
Junyan Qin
0155d3b0b9 fix: conflict in table plugin_settings 2025-08-23 20:05:24 +08:00
Junyan Qin
e47a5b4e0d chore: bump langbot_plugin version 2025-08-23 17:12:29 +08:00
Junyan Qin
87ecb4e519 feat: add note for remove_think & remove dify remove cot code 2025-08-21 21:38:58 +08:00
Ljzd_PRO
df524b8a7a Fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages (#1624)
* fix: update invoke_embedding to return only embeddings from client.embed

* fix: Fixed the incorrect extraction method of sender ID when converting aiocqhttp reply messages
2025-08-21 20:46:26 +08:00
Junyan Qin
8a7df423ab chore: update shengsuanyun url 2025-08-21 14:14:25 +08:00
Junyan Qin
cafd623c92 chore: update shengsuanyun 2025-08-21 12:03:04 +08:00
Junyan Qin
4df11ef064 chore: update for shengsuanyun 2025-08-21 11:47:40 +08:00
Junyan Qin
4012310d99 chore: bump version 4.3.0b1 2025-08-21 10:49:51 +08:00
Junyan Qin
9e9bc88473 chore: remove plugin reorder functionality 2025-08-21 10:47:53 +08:00
Junyan Qin
aa7c08ee00 chore: release v4.2.1 2025-08-21 10:15:05 +08:00
Junyan Qin
b98de29b07 feat: add shengsuanyun requester 2025-08-20 23:33:35 +08:00
Junyan Qin
53ade384eb feat: bump version of langbot-plugin 2025-08-20 23:26:32 +08:00
fdc310
c7c2eb4518 fix:in the gmini tool_calls no id The resulting call failure (#1622)
* fix:in the dify agent llm return message can not joint

* fix:in the gmini tool_calls no id The resulting call failure
2025-08-20 22:39:16 +08:00
Ljzd_PRO
37fa318258 fix: update invoke_embedding to return only embeddings from client.embed (#1619) 2025-08-20 10:25:33 +08:00
fdc310
ff7bebb782 fix:in the dify agent llm return message can not joint (#1617) 2025-08-19 23:23:00 +08:00
Junyan Qin
30bb26f898 doc(README): streaming output 2025-08-18 21:21:50 +08:00
Junyan Qin
9c1f4e1690 chore: release v4.2.0 2025-08-18 18:43:20 +08:00
dependabot[bot]
865ee2ca01 Merge pull request #1612 from langbot-app/dependabot/npm_and_yarn/web/form-data-4.0.4
chore(deps): bump form-data from 4.0.2 to 4.0.4 in /web
2025-08-18 16:10:56 +08:00
Junyan Qin (Chin)
c2264080bd Merge pull request #1442 from langbot-app/feat/streaming
feat: streaming output
2025-08-17 23:36:30 +08:00
Dong_master
67b622d5a6 fix:Some adjustments to the return types 2025-08-17 23:34:19 +08:00
Dong_master
a534c02d75 fix:remove print 2025-08-17 23:34:01 +08:00
Junyan Qin
da890d3074 chore: remove fix.MD 2025-08-17 21:20:32 +08:00
Junyan Qin
3049aa7a96 feat: add migration for pipeline remove-think 2025-08-17 21:18:41 +08:00
Junyan Qin
8b2480ad3b feat: setting plugin config 2025-08-17 21:01:43 +08:00
Junyan Qin
b176959836 feat: plugin deletion and upgrade 2025-08-17 18:07:51 +08:00
Junyan Qin
a0c42a5f6e feat: plugin operations 2025-08-17 16:51:44 +08:00
Junyan Qin (Chin)
e66f674968 Merge branch 'master' into feat/streaming 2025-08-17 14:30:22 +08:00
Junyan Qin (Chin)
dd0e0abdc4 Merge pull request #1571 from fdc310/streaming_feature
feat:add streaming output and pipeline stream
2025-08-17 14:27:39 +08:00
Junyan Qin (Chin)
13f6396eb4 Merge pull request #1610 from langbot-app/devin/1755399221-add-password-change-feature
feat: add password change functionality
2025-08-17 14:25:24 +08:00
Junyan Qin
7bbaa4fcad feat: perf ui & complete i18n 2025-08-17 14:09:28 +08:00
Junyan Qin
e931d5eb88 chore: remove print 2025-08-17 13:52:40 +08:00
Junyan Qin
4bbfa2f1d7 fix: telegram adapter gracefully stop 2025-08-17 13:52:02 +08:00
Junyan Qin
17d997c88e fix: i18n fallback 2025-08-17 11:43:38 +08:00
Devin AI
dd30d08c68 feat: add password change functionality
- Add password change button to sidebar account menu
- Create PasswordChangeDialog component with shadcn UI components
- Implement backend API endpoint /api/v1/user/change-password
- Add form validation with current password verification
- Include internationalization support for Chinese and English
- Add proper error handling and success notifications

Co-Authored-By: Rock <rockchinq@gmail.com>
2025-08-17 03:03:36 +00:00
Junyan Qin
0ea7609ff1 perf: frontend 2025-08-16 23:23:24 +08:00
Junyan Qin
28d4b1dd61 feat: marketplace page 2025-08-16 18:05:33 +08:00
Junyan Qin
5179b3e53a feat: trace plugin installation 2025-08-16 15:42:49 +08:00
Dong_master
8ccda10045 fix: in the dashscopeapi.py workflow stream bug 2025-08-16 12:11:00 +08:00
Dong_master
46fbfbefea fix: in the dashscopeapi.py stream and non-stream remove_think logic 2025-08-16 02:13:45 +08:00
Junyan Qin
288b294148 feat: plugin installation webui 2025-08-15 22:05:39 +08:00
Junyan Qin
b464d238c5 feat: plugin installation 2025-08-15 21:30:26 +08:00
Junyan Qin
e1a78e8ff9 feat: tag debugging plugins in webui 2025-08-15 19:11:49 +08:00
Junyan Qin
2b8eb5f01c fix: bot switching 2025-08-15 17:02:00 +08:00
Dong_master
8f863cf530 fix: remove_think bug 2025-08-15 00:55:39 +08:00
Dong_master
2351193c51 fix: in the difysvapi.py add stream , and remove_think on chunk 2025-08-15 00:50:32 +08:00
Junyan Qin
bf2bc70794 feat: refactor webui httpclient 2025-08-14 23:55:14 +08:00
Junyan Qin
ebe0b68e8f feat: set cloud_service_url 2025-08-14 23:42:57 +08:00
Dong_master
8c87a47f5a fix: in the ollamachat.py func _closure add remove_think agr 2025-08-14 22:35:30 +08:00
Dong_master
b8b9a37825 fix: in the dify non-stream remove_think lgic 2025-08-14 22:32:22 +08:00
Dong_master
13dd6fcee3 fix: in the webchat non-stream not save resp_message in message_lists 2025-08-14 22:29:42 +08:00
Junyan Qin
39c50d3c12 feat: get_bot_info api 2025-08-13 20:54:43 +08:00
Junyan Qin
29f0075bd8 perf: zh-Hant specs 2025-08-13 17:49:54 +08:00
Junyan Qin
8a96ffbcc0 chore: complete zh-Hant specs for top_k 2025-08-13 17:33:47 +08:00
Junyan Qin (Chin)
67f68d8101 Merge pull request #1606 from langbot-app/feat/topk_splitter
Feat/topk splitter
2025-08-13 17:31:11 +08:00
Junyan Qin
ad59d92cef perf: i18n 2025-08-13 17:28:00 +08:00
Dong_master
85f97860c5 fix: Fixed the errors in modelscopechatcmpl.py when in pseudo-non-streaming mode, regarding the display of main content and tool calls. 2025-08-13 01:55:06 +08:00
Dong_master
8fd21e76f2 fix: Only when messagechunk is present, will msg_sequence be assigned to the subsequent tool calls. 2025-08-13 00:00:10 +08:00
Dong_master
cc83ddbe21 fix: del print 2025-08-12 23:29:32 +08:00
Dong_master
99fcde1586 fix: in the MessageChunk add msg_sequence ,And obtain the usage in the adapter. 2025-08-12 23:20:41 +08:00
WangCham
eab08dfbf3 fix: format the code 2025-08-12 23:13:00 +08:00
Dong_master
dbf0200cca feat:add More attractive card templates 2025-08-12 22:36:42 +08:00
Junyan Qin
ac44f35299 chore: remove comments 2025-08-12 21:07:23 +08:00
Junyan Qin
d6a5fdd911 perf: complete sidebar menu 2025-08-12 21:02:40 +08:00
Dong_master
4668db716a fix: fix command reply_message error bug,del some print 2025-08-12 20:54:47 +08:00
Junyan Qin
f7cd6b76f2 feat: refactor account menu 2025-08-12 20:13:18 +08:00
Junyan Qin
b6d47187f5 perf: prettier 2025-08-12 19:39:41 +08:00
Junyan Qin
051fffd41e fix: stash 2025-08-12 19:18:49 +08:00
Junyan Qin
c5480078b3 perf: make prompt editor textarea 2025-08-12 11:30:42 +08:00
Dong_master
e744e9c4ef fix: in the localagent.py yield MessageChunk add agr tool_calls,and After calling the "tool_calls", the first returned body data will be concatenated. 2025-08-12 11:25:37 +08:00
Dong_master
9f22b8b585 fix: be adapter.py func reply_message_chunk agr message_id alter bot_message,and in pipelinemgr.py respback.py agr alter 2025-08-12 11:21:08 +08:00
Dong_master
27cee0a4e1 fix: in the adapter.py func reply_message_chunk agr message_id alter bot_message,and in dingtalk.py lark.py telegram.py webchat.py agr alter 2025-08-12 11:19:27 +08:00
Dong_master
6d35fc408c fix: some time in the anthropicmsgs.py mesg_dcit["content"] is str can not append 2025-08-12 11:15:17 +08:00
Dong_master
0607a0fa5c fix: in the modelscopechatcmpl.py stream tool_calls arguments bug, 2025-08-12 00:04:21 +08:00
Dong_master
ed57d2fafa del localagent.py print 2025-08-11 23:49:19 +08:00
Junyan Qin
39ef92676b doc: add back wechat 2025-08-11 23:38:41 +08:00
Dong_master
7301476228 fix:Because the message_id was popped out, it caused the issue where the tool couldn't find the message_id after being invoked. 2025-08-11 23:36:01 +08:00
WangCham
457cc3eecd fix: wrong definition of topk 2025-08-11 23:22:36 +08:00
Dong_master
a381069bcc fix:fix tool_result argument bug 2025-08-11 23:05:47 +08:00
WangCham
146c38e64c fix: wrong positions 2025-08-11 22:58:48 +08:00
Junyan Qin (Chin)
763c41729e Merge pull request #1605 from TwperBody/master
feat: dark mode supports for webui
2025-08-11 20:51:58 +08:00
Junyan Qin
0021efebd7 perf: minor fix 2025-08-11 20:50:39 +08:00
Junyan Qin
5f18a1b13a chore: prettier 2025-08-11 20:46:08 +08:00
Junyan Qin
0124448479 perf: card shadowbox 2025-08-11 20:41:57 +08:00
Junyan Qin
621f1301b3 fix: message chain init 2025-08-11 17:24:57 +08:00
WangCham
e76bc80e51 Merge branch 'feat/topk_splitter' of github.com:RockChinQ/LangBot into feat/topk_splitter 2025-08-11 00:20:13 +08:00
WangCham
a27560e804 fix: page bug 2025-08-11 00:12:06 +08:00
Dong_master
46452de7b5 fix:The handling of the streaming tool calls has been fixed, but there are still bugs in the model's reply messages with thoughtfulness. 2025-08-10 23:14:57 +08:00
TwperBody
2aef139577 dark mode 2025-08-10 22:17:06 +08:00
Dong_master
03b11481ed fix:fix remove_think logic, and end<think> fix </think> 2025-08-10 00:28:55 +08:00
Dong_master
8c5cb71812 fix:del the chatcmpl.py useless logic,and in the modelscopechatcmpl.py Non-streaming add and del <think> logic,and fix the ppiochatcmpl.py stream logic and the giteeaichatcmpl.py inherit ppiochatcmpl.py 2025-08-10 00:16:13 +08:00
Dong_master
7c59bc1ce5 feat:add anthropic stream ouput 2025-08-10 00:09:19 +08:00
Junyan Qin
0b60ef0d06 chore: bump langbot-plugin version to 0.1.1a1 2025-08-09 21:06:31 +08:00
Dong_master
eede354d3b fix:chatcmpl.py del content <think>,in the ppiochatcmpl.py and modelsopechatcmpl.py fun _closure_stream stream logic 2025-08-09 02:46:13 +08:00
Junyan Qin
eb7b5dcc25 chore: rename zh_Hans label of deepseek requester 2025-08-08 17:31:24 +08:00
WangCham
47e9ce96fc feat: add topk 2025-08-07 18:10:33 +08:00
WangCham
4e95bc542c fix: kb form 2025-08-07 18:10:33 +08:00
WangCham
e4f321ea7a feat: add description for topk 2025-08-07 18:10:33 +08:00
WangCham
246eb71b75 feat: add topk 2025-08-07 18:10:33 +08:00
Junyan Qin
261f50b8ec feat: refactor with cursor max mode claude 4.1 opus 2025-08-07 15:47:57 +08:00
Junyan Qin
9736d0708a fix: missing deps 2025-08-07 10:15:09 +08:00
Junyan Qin
02dbe80d2f perf: model testing 2025-08-07 10:01:04 +08:00
Dong_master
0f239ace17 Merge remote-tracking branch 'origin/streaming_feature' into streaming_feature 2025-08-06 23:02:35 +08:00
Dong_master
3a82ae8da5 fix: the bug in the "remove_think" function. 2025-08-06 23:00:57 +08:00
Junyan Qin
c33c9eaab0 chore: remove remove_think param in trigger.yaml 2025-08-06 15:45:35 +08:00
Junyan Qin
87f626f3cc doc(README): add HelloGitHub badge 2025-08-05 17:40:27 +08:00
Dong_master
e88302f1b4 fix:The handling logic of remove_think in the connector and Temporarily blocked the processing of streaming tool calls in the runner. 2025-08-05 04:24:03 +08:00
Dong_master
5597dffaeb Merge remote-tracking branch 'origin/streaming_feature' into streaming_feature
# Conflicts:
#	pkg/api/http/controller/groups/pipelines/webchat.py
#	pkg/pipeline/process/handlers/chat.py
#	pkg/platform/sources/aiocqhttp.py
#	pkg/platform/sources/dingtalk.py
#	pkg/platform/sources/discord.py
#	pkg/platform/sources/lark.py
#	pkg/platform/sources/telegram.py
#	pkg/platform/sources/wechatpad.py
#	pkg/provider/modelmgr/requester.py
#	pkg/provider/modelmgr/requesters/chatcmpl.py
#	pkg/provider/modelmgr/requesters/deepseekchatcmpl.py
#	pkg/provider/modelmgr/requesters/giteeaichatcmpl.py
#	pkg/provider/modelmgr/requesters/modelscopechatcmpl.py
#	pkg/provider/modelmgr/requesters/ppiochatcmpl.py
#	pkg/provider/runners/dashscopeapi.py
#	pkg/provider/runners/difysvapi.py
#	pkg/provider/runners/localagent.py
2025-08-04 23:17:36 +08:00
Junyan Qin
7f25d61531 fix: minor fix 2025-08-04 23:00:54 +08:00
Junyan Qin
15e524c6e6 perf: move remove-think to output tab 2025-08-04 19:26:19 +08:00
fdc
4a1d033ee9 fix: Reduce chunk returns in dify and Hundred Refining Runner to every 8 chunks 2025-08-04 19:26:19 +08:00
fdc
8adc88a8c0 fix:Modify the remove_think that directly retrieves the configuration file from the requester, retrieves it from the runner, and passes it to the required function 2025-08-04 19:26:18 +08:00
fdc
a62b38eda7 fix: In the reply_message_chunk of the adapter, the message is only streamed into the card or edited at the end of the 8th chunk return or streaming 2025-08-04 19:26:18 +08:00
Dong_master
fcef784180 fix: In the runner, every 8 tokens yield 2025-08-04 19:26:18 +08:00
Junyan Qin
c3ed4ef6a1 feat: no longer use typewriter in debug dialog 2025-08-04 19:26:18 +08:00
Junyan Qin
b9f768af25 perf: minor fixes 2025-08-04 19:26:18 +08:00
Junyan Qin
47ff883fc7 perf: ruff format & remove stream params in requester 2025-08-04 19:26:18 +08:00
Dong_master
68906c43ff feat: add webchat Word-by-word output
fix:webchat on message stream bug
2025-08-04 19:26:18 +08:00
Dong_master
c6deed4e6e feat: webchat stream is ok 2025-08-04 19:26:18 +08:00
Dong_master
b45cc59322 fix:webchat stream judge bug and frontend bug 2025-08-04 19:26:17 +08:00
fdc
c33a96823b fix: frontend bug 2025-08-04 19:26:17 +08:00
fdc
d3ab16761d fix:lsome bug 2025-08-04 19:26:17 +08:00
fdc
70f23f24b0 fix: is_stream_output_supperted in webchat return 2025-08-04 19:26:17 +08:00
fdc
00a8410c94 feat:webchat frontend stream 2025-08-04 19:26:17 +08:00
fdc
2a17e89a99 feat: add webchat stream but only some 2025-08-04 19:26:17 +08:00
fdc
8fe0992c15 fix:in chat judge create_message_card telegram reply_message_chunk no message 2025-08-04 19:26:17 +08:00
Dong_master
a9776b7b53 fix:del some print ,and amend respback on stream judge ,and del in dingtalk this is_stream_output_supported() use 2025-08-04 19:26:16 +08:00
Dong_master
074d359c8e feat:add dashscopeapi stream
fix:dify 64chunk yield
2025-08-04 19:26:16 +08:00
Dong_master
7728b4262b fix:lark message_id and dingtalk incoming_message 2025-08-04 19:26:16 +08:00
Dong_master
4905b5a738 feat:add dingtalk stream
fix:adapter is_stream_output_supported bug
fix:stream message reply chunk in message_id
2025-08-04 19:26:16 +08:00
Dong_master
43a259a1ae feat:add dingtalk stream 2025-08-04 19:26:16 +08:00
Dong_master
cffe493db0 feat:add telegram stream 2025-08-04 19:26:16 +08:00
Dong_master
0042629bf0 feat:add ppio and openrouter llm stream,and ppio think in content remove_think.
fix: giteeai stream no remove_think content add char"<think>"
2025-08-04 19:26:16 +08:00
Dong_master
a7d638cc9a feat:add deepseek and modelscope llm stream,and giteeai think in content remove_think 2025-08-04 19:26:16 +08:00
Dong_master
f84a79bf74 perf:del dify stream in ai.yaml config.and enbale stream in lark.yaml.
fix:localagent remove_think bug
2025-08-04 19:26:15 +08:00
Dong_master
f5a0cb9175 feat:add dify _agent_chat_message streaming 2025-08-04 19:26:15 +08:00
Dong_master
f9a5507029 fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大,以及有思考的think处理
feat:增加带有深度思考模型的think的去think操作
feat:dify中聊天机器人,chatflow对流式的支持
2025-08-04 19:26:15 +08:00
Dong_master
5ce32d2f04 fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大,以及带有深度思考模型的think增加 2025-08-04 19:26:15 +08:00
Dong_master
4908996cac 流式基本流程已通过修改了yield和return的冲突导致的问题 2025-08-04 19:26:15 +08:00
fdc
ee545a163f 增加了飞书中的流式但是好像还有问题 2025-08-04 19:26:15 +08:00
fdc
6e0e5802cc fix:修改手误message_id写进reply_message中 2025-08-04 19:26:15 +08:00
fdc
0d53843230 chat中的流式修改 2025-08-04 19:26:14 +08:00
fdc
b65670cd1a feat: 实现流式消息处理支持 2025-08-04 19:26:14 +08:00
zejiewang
ba4b5255a2 feat:support dify message streaming output (#1437)
* fix:lark adapter listeners init problem

* feat:support dify streaming mode

* feat:remove some log

* fix(bot form): field desc missing

* fix: not compatible with chatflow

---------

Co-authored-by: wangzejie <wangzejie@meicai.cn>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-08-04 18:45:52 +08:00
Junyan Qin (Chin)
d60af2b451 fix(pipeline dialog): config reset between tabs switching (#1597) 2025-08-04 00:05:55 +08:00
Dong_master
44ac8b2b63 fix: In the runner, every 8 tokens yield 2025-08-03 23:23:51 +08:00
Junyan Qin
b70001c579 chore: release v4.1.2 2025-08-03 22:52:47 +08:00
Junyan Qin (Chin)
4a8f5516f6 feat: add new api requester (#1596) 2025-08-03 22:30:52 +08:00
Junyan Qin
48d11540ae feat: no longer use typewriter in debug dialog 2025-08-03 17:18:44 +08:00
Junyan Qin
84129e3339 perf: minor fixes 2025-08-03 15:30:11 +08:00
Junyan Qin
377d455ec1 perf: ruff format & remove stream params in requester 2025-08-03 13:08:51 +08:00
Junyan Qin
41650b585a perf: dispose process 2025-08-02 23:54:06 +08:00
Dong_master
52280d7a05 feat: add webchat Word-by-word output
fix:webchat on message stream bug
2025-08-02 01:42:22 +08:00
Dong_master
0ce81a2df2 feat: webchat stream is ok 2025-08-01 11:33:16 +08:00
Dong_master
d9a2bb9a06 fix:webchat stream judge bug and frontend bug 2025-07-31 14:49:12 +08:00
fdc
cb88da7f02 fix: frontend bug 2025-07-31 10:34:36 +08:00
fdc
5560a4f52d fix:lsome bug 2025-07-31 10:28:43 +08:00
fdc
e4d951b174 fix: is_stream_output_supperted in webchat return 2025-07-31 10:01:47 +08:00
fdc
6e08bf71c9 feat:webchat frontend stream 2025-07-31 09:51:25 +08:00
fdc
daaf4b54ef feat: add webchat stream but only some 2025-07-30 17:06:14 +08:00
fdc
3291266f5d fix:in chat judge create_message_card telegram reply_message_chunk no message 2025-07-30 15:21:59 +08:00
Dong_master
307f6acd8c fix:del some print ,and amend respback on stream judge ,and del in dingtalk this is_stream_output_supported() use 2025-07-29 23:09:02 +08:00
Junyan Qin
f1ac9c77e6 doc: update README_TW 2025-07-28 15:50:00 +08:00
Junyan Qin
b434a4e3d7 doc: add README_TW 2025-07-28 15:47:50 +08:00
Junyan Qin
2f209cd59f chore(i18n): add zh-Hant 2025-07-28 15:11:41 +08:00
Junyan Qin
0f585fd5ef fix(moonshot): make api.moonshot.ai the default api base url 2025-07-26 22:23:33 +08:00
Junyan Qin
a152dece9a chore: switch to pnpm 2025-07-26 19:45:38 +08:00
Junyan Qin
d3b31f7027 chore: release v4.1.1 2025-07-26 19:28:34 +08:00
How-Sean Xin
c00f05fca4 Add GitHub link redirection for front-end plugin cards (#1579)
* Update package.json

* Update PluginMarketComponent.tsx

* Update PluginMarketComponent.tsx

* Update package.json

* Update PluginCardComponent.tsx

* perf: no display github button when plugin has no github url

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-07-26 19:22:00 +08:00
Junyan Qin
92c3a86356 feat: add qhaigc 2025-07-24 22:42:26 +08:00
Junyan Qin
341fdc409d perf: embedding model ui 2025-07-24 22:29:25 +08:00
Junyan Qin
ebd542f592 feat: 302.AI embeddings 2025-07-24 22:05:15 +08:00
Junyan Qin
194b2d9814 feat: supports more embedding providers 2025-07-24 22:03:20 +08:00
Junyan Qin
7aed5cf1ed feat: ollama embeddings models 2025-07-24 10:36:32 +08:00
Junyan Qin
abc88c4979 doc: update README 2025-07-23 18:53:15 +08:00
WangCham
3fa38f71f1 feat: add topk 2025-07-23 17:29:36 +08:00
WangCham
d651d956d6 Merge branch 'master' into feat/topk_splitter 2025-07-23 16:37:27 +08:00
gaord
6754666845 feat(wechatpad): 添加对@所有人的支持并统一处理消息派发 (#1588)
在消息转换器中添加对AtAll组件的支持,将@所有人转换为特定格式。同时在消息派发时统一处理@所有人的情况,确保通知能正确发送。
2025-07-23 15:22:04 +08:00
Junyan Qin
08e6f46b19 fix(deps): react-focus-scope pkg bug 2025-07-22 11:05:16 +08:00
Dong_master
8f8c8ff367 feat:add dashscopeapi stream
fix:dify 64chunk yield
2025-07-21 18:45:45 +08:00
Dong_master
63ec2a8c34 fix:lark message_id and dingtalk incoming_message 2025-07-21 17:28:11 +08:00
Dong_master
f58c8497c3 feat:add dingtalk stream
fix:adapter is_stream_output_supported bug
fix:stream message reply chunk in message_id
2025-07-20 23:53:20 +08:00
Junyan Qin
1497fdae56 doc(README): adjust structure 2025-07-20 22:10:32 +08:00
Junyan Qin
10a3cb40e1 perf(retrieve): ui 2025-07-20 17:57:33 +08:00
devin-ai-integration[bot]
dd1ec15a39 feat: add knowledge base retrieve test tab with Card-based UI (#1583)
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin>, u79E6u9A8Fu8A00 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>
2025-07-20 17:56:46 +08:00
devin-ai-integration[bot]
ea51cec57e feat: add pipeline sorting functionality with three sort options (#1582)
* feat: add pipeline sorting functionality with three sort options

Co-Authored-By: Junyan Qin <Chin>, u79E6u9A8Fu8A00 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>

* perf: ui

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin>, u79E6u9A8Fu8A00 in Chinese, you can call me my english name Rock Chin. <rockchinq@gmail.com>
2025-07-20 17:23:30 +08:00
Junyan Qin
28ce986a8c chore: release v4.1.0 2025-07-20 12:32:06 +08:00
Junyan Qin
489b145606 doc: update README 2025-07-20 12:30:41 +08:00
Junyan Qin (Chin)
5e92bffaa6 Merge pull request #1581 from langbot-app/RockChinQ-patch-1
Update README.md
2025-07-19 23:09:53 +08:00
Junyan Qin (Chin)
277d1b0e30 feat: rag engine (#1492)
* feat: add embeddings model management (#1461)

* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add knowledge page

* feat: add api for uploading files

* kb

* delete ap

* feat: add functions

* fix: modify rag database

* feat: add embeddings model management (#1461)

* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add knowledge page

* feat: add api for uploading files

* feat: add sidebar for rag and related i18n

* feat: add knowledge base page

* feat: basic entities of kb

* feat: complete support_type for 302ai and compshare requester

* perf: format

* perf: ruff check --fix

* feat: basic definition

* feat: rag fe framework

* perf: en comments

* feat: modify the rag.py

* perf: definitions

* fix: success method bad params

* fix: bugs

* fix: bug

* feat: kb dialog action

* fix: create knwoledge base issue

* fix: kb get api format

* fix: kb get api not contains model uuid

* fix: api bug

* fix: the fucking logger

* feat(fe): component for available apis

* fix: embbeding and chunking

* fix: ensure File.status is set correctly after storing data to avoid null values

* fix: add functions for deleting files

* feat(fe): file uploading

* perf: adjust ui

* fix: file be deleted twice

* feat(fe): complete kb ui

* fix: ui bugs

* fix: no longer require Query for invoking embedding

* feat: add embedder

* fix: delete embedding models file

* chore: stash

* chore: stash

* feat(rag): make embedding and retrieving available

* feat(rag): all APIs ok

* fix: delete utils

* feat: rag pipeline backend

* feat: combine kb with pipeline

* fix: .md file parse failed

* perf: debug output

* feat: add functions for frontend of kb

* perf(rag): ui and related apis

* perf(rag): use badge show doc status

* perf: open kb detail dialog after creating

* fix: linter error

* deps: remove sentence-transformers

* perf: description of default pipeline

* feat: add html and epub

* chore: no longer supports epub

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: WangCham <651122857@qq.com>
2025-07-19 22:06:11 +08:00
Junyan Qin
13f4ed8d2c chore: no longer supports epub 2025-07-19 21:56:50 +08:00
WangCham
91cb5ca36c feat: add html and epub 2025-07-19 19:57:57 +08:00
TwperBody
c34d54a6cb Fixed a bug where some Windows systems failed to recognize spaces. (#1577)
* Update package.json

* Update PluginMarketComponent.tsx

* Update PluginMarketComponent.tsx
2025-07-19 16:48:15 +08:00
TwperBody
2d1737da1f Optimize plugin display (#1578)
* Update package.json

* Update PluginMarketComponent.tsx

* Update PluginMarketComponent.tsx

* Update PluginMarketComponent.tsx

* Update package.json
2025-07-19 16:47:34 +08:00
Dong_master
adb0bf2473 feat:add dingtalk stream 2025-07-19 01:05:44 +08:00
Junyan Qin
a1b8b9d47b perf: description of default pipeline 2025-07-18 18:57:42 +08:00
Junyan Qin
8df14bf9d9 deps: remove sentence-transformers 2025-07-18 18:46:07 +08:00
Junyan Qin
c98d265a1e fix: linter error 2025-07-18 17:52:24 +08:00
Junyan Qin
4e6782a6b7 perf: open kb detail dialog after creating 2025-07-18 16:52:54 +08:00
Junyan Qin
5541e9e6d0 perf(rag): use badge show doc status 2025-07-18 16:38:55 +08:00
gaord
878ab0ef6b fix(wechatpad): @所有人的情况下,修复@机器人消息未被正确解析的问题 (#1575) 2025-07-18 12:52:30 +08:00
Junyan Qin
b61bd36b14 perf(rag): ui and related apis 2025-07-18 00:45:38 +08:00
Junyan Qin (Chin)
bb672d8f46 Merge branch 'master' into feat/rag 2025-07-18 00:45:24 +08:00
WangCham
ba1a26543b Merge branch 'feat/rag' of github.com:RockChinQ/LangBot into feat/rag 2025-07-17 23:57:52 +08:00
WangCham
cb868ee7b2 feat: add functions for frontend of kb 2025-07-17 23:52:46 +08:00
Junyan Qin
5dd5cb12ad perf: debug output 2025-07-17 23:34:35 +08:00
Junyan Qin
2dfa83ff22 fix: .md file parse failed 2025-07-17 23:22:20 +08:00
Junyan Qin
27bb4e1253 feat: combine kb with pipeline 2025-07-17 23:15:13 +08:00
WangCham
45afdbdfbb feat: rag pipeline backend 2025-07-17 15:05:11 +08:00
Dong_master
11e52a3ade feat:add telegram stream 2025-07-17 14:29:30 +08:00
WangCham
4cbbe9e000 fix: delete utils 2025-07-16 23:25:12 +08:00
WangCham
e986a0acaf fix: kb form 2025-07-16 22:50:17 +08:00
Junyan Qin
f5b893cfe0 feat: kill runtime process when exit in stdio mode 2025-07-16 22:43:39 +08:00
Junyan Qin
333ec346ef feat(rag): all APIs ok 2025-07-16 22:15:03 +08:00
Junyan Qin
2f2db4d445 feat(rag): make embedding and retrieving available 2025-07-16 21:17:18 +08:00
WangCham
e31883547d feat: add description for topk 2025-07-16 18:15:27 +08:00
WangCham
88c0066b06 feat: add topk 2025-07-16 17:20:13 +08:00
Junyan Qin
f731115805 chore: stash 2025-07-16 11:31:55 +08:00
Junyan Qin
67bc065ccd chore: stash 2025-07-15 22:09:10 +08:00
Dong_master
d15df3338f feat:add ppio and openrouter llm stream,and ppio think in content remove_think.
fix: giteeai stream no remove_think content add char"<think>"
2025-07-15 00:50:42 +08:00
Dong_master
c74cf38e9f feat:add deepseek and modelscope llm stream,and giteeai think in content remove_think 2025-07-14 23:53:55 +08:00
Dong_master
0e68a922bd perf:del dify stream in ai.yaml config.and enbale stream in lark.yaml.
fix:localagent remove_think bug
2025-07-14 01:42:42 +08:00
Dong_master
4e1d81c9f8 feat:add dify _agent_chat_message streaming 2025-07-14 00:40:02 +08:00
WangCham
199164fc4b fix: delete embedding models file 2025-07-13 23:12:08 +08:00
WangCham
c9c26213df Merge branch 'feat/rag' of github.com:RockChinQ/LangBot into feat/rag 2025-07-13 23:09:41 +08:00
WangCham
b7c57104c4 feat: add embedder 2025-07-13 23:04:03 +08:00
Dong_master
0be08d8882 fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大,以及有思考的think处理
feat:增加带有深度思考模型的think的去think操作
feat:dify中聊天机器人,chatflow对流式的支持
2025-07-13 22:41:39 +08:00
Junyan Qin
e0abd19636 feat: get plugin info 2025-07-13 22:14:22 +08:00
Junyan Qin
4380041c7f feat(ui): list plugins 2025-07-13 22:03:47 +08:00
Junyan Qin
65814a4644 feat: binary storage api 2025-07-13 21:39:33 +08:00
Junyan Qin
7237294008 perf: longer timeout for emit_event 2025-07-13 20:48:15 +08:00
Junyan Qin
214bc8ada9 feat: backward call apis 2025-07-13 20:45:45 +08:00
Junyan Qin
6a1de889b4 refactor: switch llm_entities to plugin sdk 2025-07-13 20:30:17 +08:00
Junyan Qin
4a319b2b20 feat: query-based apis 2025-07-13 18:41:04 +08:00
Junyan Qin
9f269d1614 feat: get bot uuid api 2025-07-13 17:44:20 +08:00
Junyan Qin
4b57771eb1 feat: reply_message api 2025-07-13 16:31:25 +08:00
Junyan Qin
5922be7e15 feat: command execution via plugin 2025-07-13 10:26:48 +08:00
Junyan Qin
cbe297dc59 fix: no longer require Query for invoking embedding 2025-07-12 21:23:19 +08:00
Junyan Qin
de76fed25a fix: ui bugs 2025-07-12 18:12:53 +08:00
Dong_master
301509b1db fix:修复了因为迭代数据只推入resq_messages和resq_message_chain导致缓存到内存中的数据和写入log中的数据量庞大,以及带有深度思考模型的think增加 2025-07-12 18:09:24 +08:00
Junyan Qin
a10e61735d feat(fe): complete kb ui 2025-07-12 18:00:54 +08:00
Junyan Qin
1ef0193028 fix: file be deleted twice 2025-07-12 17:47:53 +08:00
Junyan Qin
1e85d02ae4 perf: adjust ui 2025-07-12 17:29:39 +08:00
Junyan Qin
d78a329aa9 feat(fe): file uploading 2025-07-12 17:15:07 +08:00
WangCham
234b61e2f8 fix: add functions for deleting files 2025-07-12 01:37:44 +08:00
WangCham
9f43097361 fix: ensure File.status is set correctly after storing data to avoid null values 2025-07-12 01:21:02 +08:00
WangCham
f395cac893 fix: embbeding and chunking 2025-07-12 01:07:49 +08:00
Junyan Qin
fe122281fd feat(fe): component for available apis 2025-07-11 21:40:42 +08:00
Junyan Qin
6d788cadbc fix: the fucking logger 2025-07-11 21:37:31 +08:00
Junyan Qin
a79a22a74d fix: api bug 2025-07-11 21:30:47 +08:00
Junyan Qin
2ed3b68790 fix: kb get api not contains model uuid 2025-07-11 20:58:51 +08:00
Junyan Qin
bd9331ce62 fix: kb get api format 2025-07-11 20:57:09 +08:00
WangCham
14c161b733 fix: create knwoledge base issue 2025-07-11 18:14:03 +08:00
Junyan Qin
815cdf8b4a feat: kb dialog action 2025-07-11 17:22:43 +08:00
Junyan Qin
7d5503dab2 fix: bug 2025-07-11 16:49:55 +08:00
Junyan Qin
9ba1ad5bd3 fix: bugs 2025-07-11 16:38:08 +08:00
Junyan Qin
367d04d0f0 fix: success method bad params 2025-07-11 11:28:43 +08:00
Junyan Qin
75c3ddde19 perf: definitions 2025-07-10 16:45:59 +08:00
Junyan Qin
10a44c70b6 feat: switch command entities to sdk 2025-07-10 10:51:36 +08:00
WangCham
ac03a2dceb feat: modify the rag.py 2025-07-09 22:09:46 +08:00
Junyan Qin
5b044a1917 feat: add Tool component 2025-07-06 21:03:33 +08:00
Junyan Qin
cd25340826 perf: en comments 2025-07-06 16:08:02 +08:00
Junyan Qin
ebd8e014c6 feat: rag fe framework 2025-07-06 15:52:53 +08:00
Junyan Qin
bef0d73e83 feat: basic definition 2025-07-06 10:25:28 +08:00
Junyan Qin
8d28ace252 perf: ruff check --fix 2025-07-05 21:56:54 +08:00
Junyan Qin
39c062f73e perf: format 2025-07-05 21:56:17 +08:00
Junyan Qin
0e5c9e19e1 feat: complete support_type for 302ai and compshare requester 2025-07-05 21:03:14 +08:00
Junyan Qin
c5b62b6ba3 Merge remote-tracking branch 'wangcham/feat/rag' into feat/rag 2025-07-05 20:16:37 +08:00
Junyan Qin
bbf583ddb5 feat: basic entities of kb 2025-07-05 20:07:27 +08:00
Junyan Qin
22ef1a399e feat: add knowledge base page 2025-07-05 20:07:27 +08:00
Junyan Qin
0733f8878f feat: add sidebar for rag and related i18n 2025-07-05 20:07:27 +08:00
Junyan Qin
f36a61dbb2 feat: add api for uploading files 2025-07-05 20:07:15 +08:00
Junyan Qin
6d8936bd74 feat: add knowledge page 2025-07-05 20:07:15 +08:00
devin-ai-integration[bot]
d2b93b3296 feat: add embeddings model management (#1461)
* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>
2025-07-05 20:07:15 +08:00
WangCham
552fee9bac fix: modify rag database 2025-07-05 18:58:17 +08:00
WangCham
34fe8b324d feat: add functions 2025-07-05 18:58:16 +08:00
WangCham
c4671fbf1c delete ap 2025-07-05 18:58:16 +08:00
WangCham
4bcc06c955 kb 2025-07-05 18:58:16 +08:00
Junyan Qin
348f6d9eaa feat: add api for uploading files 2025-07-05 18:57:24 +08:00
Junyan Qin
157ffdc34c feat: add knowledge page 2025-07-05 18:57:24 +08:00
devin-ai-integration[bot]
c81d5a1a49 feat: add embeddings model management (#1461)
* feat: add embeddings model management backend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* feat: add embeddings model management frontend support

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* chore: revert HttpClient URL to production setting

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* refactor: integrate embeddings models into models page with tabs

Co-Authored-By: Junyan Qin <Chin> <rockchinq@gmail.com>

* perf: move files

* perf: remove `s`

* feat: allow requester to declare supported types in manifest

* feat(embedding): delete dimension and encoding format

* feat: add extra_args for embedding moels

* perf: i18n ref

* fix: linter err

* fix: lint err

* fix: linter err

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Junyan Qin <Chin> <rockchinq@gmail.com>
2025-07-05 18:57:23 +08:00
Dong_master
68cdd163d3 流式基本流程已通过修改了yield和return的冲突导致的问题 2025-07-04 03:26:44 +08:00
fdc
4005a8a3e2 增加了飞书中的流式但是好像还有问题 2025-07-03 22:58:17 +08:00
Junyan Qin
a60aa6f644 feat: runtime reconnecting 2025-07-02 22:20:20 +08:00
fdc
542409d48d Merge branch 'feat/streaming' of github.com:fdc310/LangBot into streaming_feature 2025-07-02 14:09:01 +08:00
Junyan Qin
1a10b40b17 refactor: use emit_event from connector 2025-07-02 12:46:30 +08:00
Junyan Qin
e2124054bf feat: switch all event emitting logic to new method 2025-07-02 11:58:10 +08:00
zejiewang
3c6e858c35 feat:support dify message streaming output (#1437)
* fix:lark adapter listeners init problem

* feat:support dify streaming mode

* feat:remove some log

* fix(bot form): field desc missing

* fix: not compatible with chatflow

---------

Co-authored-by: wangzejie <wangzejie@meicai.cn>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-07-02 11:07:31 +08:00
Junyan Qin
ee3da8aa17 feat: adapt more events 2025-07-02 11:04:03 +08:00
fdc
8670ae82a3 fix:修改手误message_id写进reply_message中 2025-07-02 10:49:50 +08:00
Junyan Qin
c246470b37 feat: minor changes adapt to event emitting 2025-07-01 22:44:46 +08:00
fdc
48c9d66ab8 chat中的流式修改 2025-07-01 18:03:05 +08:00
Junyan Qin
f474e42b79 fix: serialization bug in events emitting 2025-06-30 21:49:59 +08:00
Junyan Qin
5553a86ac8 feat: preliminary migration of events entities 2025-06-30 21:49:59 +08:00
Junyan Qin
01613b2f0d chore: remove adapter meta manifest from components.yaml 2025-06-30 21:49:59 +08:00
Junyan Qin
a177786063 feat: switch message platform adapters to sdk 2025-06-30 21:49:59 +08:00
Junyan Qin
62b2884011 chore: delete Query class 2025-06-30 21:47:40 +08:00
Junyan Qin
6b782f8761 feat: switch Query to langbot-plugin definition 2025-06-30 21:47:40 +08:00
Junyan Qin
0c2560cafb feat: switch tool entities and format 2025-06-30 21:47:40 +08:00
Junyan Qin
c5eeab2fd0 feat: listing plugins 2025-06-30 21:43:43 +08:00
Junyan Qin
6f2fd72af6 feat(plugin): basic communication 2025-06-30 21:43:43 +08:00
Junyan Qin
2d06f1cadb feat: connector for plugin runtime 2025-06-30 21:43:43 +08:00
Junyan Qin
af493c117c deps: add langbot-plugin 2025-06-30 21:43:42 +08:00
fdc
0eac9135c0 feat: 实现流式消息处理支持 2025-06-30 17:58:18 +08:00
328 changed files with 16040 additions and 7690 deletions

3
.gitignore vendored
View File

@@ -42,4 +42,5 @@ botpy.log*
test.py
/web_ui
.venv/
uv.lock
uv.lock
/test

View File

@@ -6,14 +6,16 @@
<div align="center">
简体中文 / [English](README_EN.md) / [日本語](README_JP.md) / (PR for your language)
<a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="FeaturedHelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
[English](README_EN.md) / 简体中文 / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)
[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
[![star](https://gitcode.com/langbot-app/LangBot/star/badge.svg)](https://gitcode.com/langbot-app/LangBot)
[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
<a href="https://langbot.app">项目主页</a>
<a href="https://docs.langbot.app/zh/insight/guide.html">部署文档</a>
@@ -25,12 +27,7 @@
</p>
## ✨ 特性
- 💬 大模型对话、Agent支持多种大模型适配群聊和私聊具有多轮对话、工具调用、多模态能力并深度适配 [Dify](https://dify.ai)。目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
- 🛠️ 高稳定性、功能完备:原生支持访问控制、限速、敏感词过滤等机制;配置简单,支持多种部署方式。支持多流水线配置,不同机器人用于不同应用场景。
- 🧩 插件扩展、活跃社区:支持事件驱动、组件扩展等插件机制;适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/);目前已有数百个插件。
- 😻 Web 管理面板:支持通过浏览器管理 LangBot 实例,不再需要手动编写配置文件。
LangBot 是一个开源的大语言模型原生即时通信机器人开发平台,旨在提供开箱即用的 IM 机器人开发体验,具有 Agent、RAG、MCP 等多种 LLM 应用功能,适配全球主流即时通信平台,并提供丰富的 API 接口,支持自定义开发。
## 📦 开始使用
@@ -64,23 +61,25 @@ docker compose up -d
直接使用发行版运行,查看文档[手动部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。
## 📸 效果展示
## 😎 保持更新
<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="450px"/>
点击仓库右上角 Star 和 Watch 按钮,获取最新动态。
<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="450px"/>
![star gif](https://docs.langbot.app/star.gif)
<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="450px"/>
## ✨ 特性
<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="450px"/>
- 💬 大模型对话、Agent支持多种大模型适配群聊和私聊具有多轮对话、工具调用、多模态、流式输出能力自带 RAG知识库实现并深度适配 [Dify](https://dify.ai)。
- 🤖 多平台支持:目前支持 QQ、QQ频道、企业微信、个人微信、飞书、Discord、Telegram 等平台。
- 🛠️ 高稳定性、功能完备:原生支持访问控制、限速、敏感词过滤等机制;配置简单,支持多种部署方式。支持多流水线配置,不同机器人用于不同应用场景。
- 🧩 插件扩展、活跃社区:支持事件驱动、组件扩展等插件机制;适配 Anthropic [MCP 协议](https://modelcontextprotocol.io/);目前已有数百个插件。
- 😻 Web 管理面板:支持通过浏览器管理 LangBot 实例,不再需要手动编写配置文件。
<img alt="回复效果(带有联网插件)" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
详细规格特性请访问[文档](https://docs.langbot.app/zh/insight/features.html)。
- WebUI Demo: https://demo.langbot.dev/
- 登录信息:邮箱:`demo@langbot.app` 密码:`langbot123456`
- 注意:仅展示webui效果,公开环境,请不要在其中填入您的任何敏感信息。
## 🔌 组件兼容性
或访问 demo 环境:https://demo.langbot.dev/
- 登录信息:邮箱:`demo@langbot.app` 密码:`langbot123456`
- 注意:仅展示 WebUI 效果,公开环境,请不要在其中填入您的任何敏感信息。
### 消息平台
@@ -97,10 +96,6 @@ docker compose up -d
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ | |
| LINE | 🚧 | |
| WhatsApp | 🚧 | |
🚧: 正在开发中
### 大模型能力
@@ -114,6 +109,7 @@ docker compose up -d
| [智谱AI](https://open.bigmodel.cn/) | ✅ | |
| [优云智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 资源平台 |
| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 资源平台 |
| [胜算云](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 资源平台 |
| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
| [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
@@ -147,9 +143,3 @@ docker compose up -d
<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
</a>
## 😎 保持更新
点击仓库右上角 Star 和 Watch 按钮,获取最新动态。
![star gif](https://docs.langbot.app/star.gif)

View File

@@ -5,7 +5,7 @@
<div align="center">
[简体中文](README.md) / English / [日本語](README_JP.md) / (PR for your language)
English / [简体中文](README.md) / [繁體中文](README_TW.md) / [日本語](README_JP.md) / (PR for your language)
[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
@@ -21,12 +21,7 @@
</p>
## ✨ Features
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, and multi-modal capabilities. Deeply integrates with [Dify](https://dify.ai). Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
- 😻 [New] Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
LangBot is an open-source LLM native instant messaging robot development platform, aiming to provide out-of-the-box IM robot development experience, with Agent, RAG, MCP and other LLM application functions, adapting to global instant messaging platforms, and providing rich API interfaces, supporting custom development.
## 📦 Getting Started
@@ -60,23 +55,25 @@ Community contributed Zeabur template.
Directly use the released version to run, see the [Manual Deployment](https://docs.langbot.app/en/deploy/langbot/manual.html) documentation.
## 📸 Demo
## 😎 Stay Ahead
<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
![star gif](https://docs.langbot.app/star.gif)
<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
## ✨ Features
<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
- 💬 Chat with LLM / Agent: Supports multiple LLMs, adapt to group chats and private chats; Supports multi-round conversations, tool calls, multi-modal, and streaming output capabilities. Built-in RAG (knowledge base) implementation, and deeply integrates with [Dify](https://dify.ai).
- 🤖 Multi-platform Support: Currently supports QQ, QQ Channel, WeCom, personal WeChat, Lark, DingTalk, Discord, Telegram, etc.
- 🛠️ High Stability, Feature-rich: Native access control, rate limiting, sensitive word filtering, etc. mechanisms; Easy to use, supports multiple deployment methods. Supports multiple pipeline configurations, different bots can be used for different scenarios.
- 🧩 Plugin Extension, Active Community: Support event-driven, component extension, etc. plugin mechanisms; Integrate Anthropic [MCP protocol](https://modelcontextprotocol.io/); Currently has hundreds of plugins.
- 😻 Web UI: Support management LangBot instance through the browser. No need to manually write configuration files.
<img alt="Reply Effect (with Internet Plugin)" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
For more detailed specifications, please refer to the [documentation](https://docs.langbot.app/en/insight/features.html).
- WebUI Demo: https://demo.langbot.dev/
- Login information: Email: `demo@langbot.app` Password: `langbot123456`
- Note: Only the WebUI effect is shown, please do not fill in any sensitive information in the public environment.
## 🔌 Component Compatibility
Or visit the demo environment: https://demo.langbot.dev/
- Login information: Email: `demo@langbot.app` Password: `langbot123456`
- Note: For WebUI demo only, please do not fill in any sensitive information in the public environment.
### Message Platform
@@ -92,10 +89,6 @@ Directly use the released version to run, see the [Manual Deployment](https://do
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ | |
| LINE | 🚧 | |
| WhatsApp | 🚧 | |
🚧: In development
### LLMs
@@ -110,6 +103,7 @@ Directly use the released version to run, see the [Manual Deployment](https://do
| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | LLM and GPU resource platform |
| [Dify](https://dify.ai) | ✅ | LLMOps platform |
| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | LLM and GPU resource platform |
| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLM and GPU resource platform |
| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLM gateway(MaaS) |
| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
| [Ollama](https://ollama.com/) | ✅ | Local LLM running platform |
@@ -128,9 +122,3 @@ Thank you for the following [code contributors](https://github.com/langbot-app/L
<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
</a>
## 😎 Stay Ahead
Click the Star and Watch button in the upper right corner of the repository to get the latest updates.
![star gif](https://docs.langbot.app/star.gif)

View File

@@ -5,7 +5,7 @@
<div align="center">
[简体中文](README.md) / [English](README_EN.md) / 日本語 / (PR for your language)
[English](README_EN.md) / [简体中文](README.md) / [繁體中文](README_TW.md) / 日本語 / (PR for your language)
[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
@@ -21,12 +21,7 @@
</p>
## ✨ 機能
- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル機能をサポート。 [Dify](https://dify.ai) と深く統合。現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/);豊富なエコシステム、現在数百のプラグインが存在。
- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。
LangBot は、エージェント、RAG、MCP などの LLM アプリケーション機能を備えた、オープンソースの LLM ネイティブのインスタントメッセージングロボット開発プラットフォームです。世界中のインスタントメッセージングプラットフォームに適応し、豊富な API インターフェースを提供し、カスタム開発をサポートします。
## 📦 始め方
@@ -42,7 +37,7 @@ http://localhost:5300 にアクセスして使用を開始します。
詳細なドキュメントは[Dockerデプロイ](https://docs.langbot.app/en/deploy/langbot/docker.html)を参照してください。
#### BTPanelでのワンクリックデプロイ
#### Panelでのワンクリックデプロイ
LangBotはBTPanelにリストされています。BTPanelをインストールしている場合は、[ドキュメント](https://docs.langbot.app/en/deploy/langbot/one-click/bt.html)を使用して使用できます。
@@ -60,23 +55,25 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
リリースバージョンを直接使用して実行します。[手動デプロイ](https://docs.langbot.app/en/deploy/langbot/manual.html)のドキュメントを参照してください。
## 📸 デモ
## 😎 最新情報を入手
<img alt="bots" src="https://docs.langbot.app/webui/bot-page.png" width="400px"/>
リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。
<img alt="bots" src="https://docs.langbot.app/webui/create-model.png" width="400px"/>
![star gif](https://docs.langbot.app/star.gif)
<img alt="bots" src="https://docs.langbot.app/webui/edit-pipeline.png" width="400px"/>
## ✨ 機能
<img alt="bots" src="https://docs.langbot.app/webui/plugin-market.png" width="400px"/>
- 💬 LLM / エージェントとのチャット: 複数のLLMをサポートし、グループチャットとプライベートチャットに対応。マルチラウンドの会話、ツールの呼び出し、マルチモーダル、ストリーミング出力機能をサポート、RAG知識ベースを組み込み、[Dify](https://dify.ai) と深く統合。
- 🤖 多プラットフォーム対応: 現在、QQ、QQ チャンネル、WeChat、個人 WeChat、Lark、DingTalk、Discord、Telegram など、複数のプラットフォームをサポートしています。
- 🛠️ 高い安定性、豊富な機能: ネイティブのアクセス制御、レート制限、敏感な単語のフィルタリングなどのメカニズムをサポート。使いやすく、複数のデプロイ方法をサポート。複数のパイプライン設定をサポートし、異なるボットを異なる用途に使用できます。
- 🧩 プラグイン拡張、活発なコミュニティ: イベント駆動、コンポーネント拡張などのプラグインメカニズムをサポート。適配 Anthropic [MCP プロトコル](https://modelcontextprotocol.io/);豊富なエコシステム、現在数百のプラグインが存在。
- 😻 Web UI: ブラウザを通じてLangBotインスタンスを管理することをサポート。
<img alt="返信効果(インターネットプラグイン付き)" src="https://docs.langbot.app/QChatGPT-0516.png" width="500px"/>
詳細な仕様については、[ドキュメント](https://docs.langbot.app/en/insight/features.html)を参照してください。
- WebUIデモ: https://demo.langbot.dev/
- ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
- 注意: WebUIの効果のみを示しています。公開環境では機密情報を入力しないでください。
## 🔌 コンポーネントの互換性
または、デモ環境にアクセスしてください: https://demo.langbot.dev/
- ログイン情報: メール: `demo@langbot.app` パスワード: `langbot123456`
- 注意: WebUI のデモンストレーションのみの場合、公開環境では機密情報を入力しないでください。
### メッセージプラットフォーム
@@ -92,10 +89,6 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ | |
| LINE | 🚧 | |
| WhatsApp | 🚧 | |
🚧: 開発中
### LLMs
@@ -109,6 +102,7 @@ LangBotはBTPanelにリストされています。BTPanelをインストール
| [Zhipu AI](https://open.bigmodel.cn/) | ✅ | |
| [CompShare](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型とGPUリソースプラットフォーム |
| [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | LLMとGPUリソースプラットフォーム |
| [302.AI](https://share.302.ai/SuTG99) | ✅ | LLMゲートウェイ(MaaS) |
| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
| [Dify](https://dify.ai) | ✅ | LLMOpsプラットフォーム |
@@ -128,9 +122,3 @@ LangBot への貢献に対して、以下の [コード貢献者](https://github
<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
</a>
## 😎 最新情報を入手
リポジトリの右上にある Star と Watch ボタンをクリックして、最新の更新を取得してください。
![star gif](https://docs.langbot.app/star.gif)

140
README_TW.md Normal file
View File

@@ -0,0 +1,140 @@
<p align="center">
<a href="https://langbot.app">
<img src="https://docs.langbot.app/social_zh.png" alt="LangBot"/>
</a>
<div align="center"><a href="https://hellogithub.com/repository/langbot-app/LangBot" target="_blank"><img src="https://abroad.hellogithub.com/v1/widgets/recommend.svg?rid=5ce8ae2aa4f74316bf393b57b952433c&claim_uid=gtmc6YWjMZkT21R" alt="FeaturedHelloGitHub" style="width: 250px; height: 54px;" width="250" height="54" /></a>
[English](README_EN.md) / [简体中文](README.md) / 繁體中文 / [日本語](README_JP.md) / (PR for your language)
[![Discord](https://img.shields.io/discord/1335141740050649118?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb)](https://discord.gg/wdNEHETs87)
[![QQ Group](https://img.shields.io/badge/%E7%A4%BE%E5%8C%BAQQ%E7%BE%A4-966235608-blue)](https://qm.qq.com/q/JLi38whHum)
[![Ask DeepWiki](https://deepwiki.com/badge.svg)](https://deepwiki.com/langbot-app/LangBot)
[![GitHub release (latest by date)](https://img.shields.io/github/v/release/langbot-app/LangBot)](https://github.com/langbot-app/LangBot/releases/latest)
<img src="https://img.shields.io/badge/python-3.10 ~ 3.13 -blue.svg" alt="python">
[![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)
<a href="https://langbot.app">主頁</a>
<a href="https://docs.langbot.app/zh/insight/guide.html">部署文件</a>
<a href="https://docs.langbot.app/zh/plugin/plugin-intro.html">外掛介紹</a>
<a href="https://github.com/langbot-app/LangBot/issues/new?assignees=&labels=%E7%8B%AC%E7%AB%8B%E6%8F%92%E4%BB%B6&projects=&template=submit-plugin.yml&title=%5BPlugin%5D%3A+%E8%AF%B7%E6%B1%82%E7%99%BB%E8%AE%B0%E6%96%B0%E6%8F%92%E4%BB%B6">提交外掛</a>
</div>
</p>
LangBot 是一個開源的大語言模型原生即時通訊機器人開發平台,旨在提供開箱即用的 IM 機器人開發體驗,具有 Agent、RAG、MCP 等多種 LLM 應用功能,適配全球主流即時通訊平台,並提供豐富的 API 介面,支援自定義開發。
## 📦 開始使用
#### Docker Compose 部署
```bash
git clone https://github.com/langbot-app/LangBot
cd LangBot
docker compose up -d
```
訪問 http://localhost:5300 即可開始使用。
詳細文件[Docker 部署](https://docs.langbot.app/zh/deploy/langbot/docker.html)。
#### 寶塔面板部署
已上架寶塔面板,若您已安裝寶塔面板,可以根據[文件](https://docs.langbot.app/zh/deploy/langbot/one-click/bt.html)使用。
#### Zeabur 雲端部署
社群貢獻的 Zeabur 模板。
[![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
#### Railway 雲端部署
[![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)
#### 手動部署
直接使用發行版運行,查看文件[手動部署](https://docs.langbot.app/zh/deploy/langbot/manual.html)。
## 😎 保持更新
點擊倉庫右上角 Star 和 Watch 按鈕,獲取最新動態。
![star gif](https://docs.langbot.app/star.gif)
## ✨ 特性
- 💬 大模型對話、Agent支援多種大模型適配群聊和私聊具有多輪對話、工具調用、多模態、流式輸出能力自帶 RAG知識庫實現並深度適配 [Dify](https://dify.ai)。
- 🤖 多平台支援:目前支援 QQ、QQ頻道、企業微信、個人微信、飛書、Discord、Telegram 等平台。
- 🛠️ 高穩定性、功能完備:原生支援訪問控制、限速、敏感詞過濾等機制;配置簡單,支援多種部署方式。支援多流水線配置,不同機器人用於不同應用場景。
- 🧩 外掛擴展、活躍社群:支援事件驅動、組件擴展等外掛機制;適配 Anthropic [MCP 協議](https://modelcontextprotocol.io/);目前已有數百個外掛。
- 😻 Web 管理面板:支援通過瀏覽器管理 LangBot 實例,不再需要手動編寫配置文件。
詳細規格特性請訪問[文件](https://docs.langbot.app/zh/insight/features.html)。
或訪問 demo 環境https://demo.langbot.dev/
- 登入資訊:郵箱:`demo@langbot.app` 密碼:`langbot123456`
- 注意:僅展示 WebUI 效果,公開環境,請不要在其中填入您的任何敏感資訊。
### 訊息平台
| 平台 | 狀態 | 備註 |
| --- | --- | --- |
| QQ 個人號 | ✅ | QQ 個人號私聊、群聊 |
| QQ 官方機器人 | ✅ | QQ 官方機器人,支援頻道、私聊、群聊 |
| 微信 | ✅ | |
| 企微對外客服 | ✅ | |
| 微信公眾號 | ✅ | |
| Lark | ✅ | |
| DingTalk | ✅ | |
| Discord | ✅ | |
| Telegram | ✅ | |
| Slack | ✅ | |
### 大模型能力
| 模型 | 狀態 | 備註 |
| --- | --- | --- |
| [OpenAI](https://platform.openai.com/) | ✅ | 可接入任何 OpenAI 介面格式模型 |
| [DeepSeek](https://www.deepseek.com/) | ✅ | |
| [Moonshot](https://www.moonshot.cn/) | ✅ | |
| [Anthropic](https://www.anthropic.com/) | ✅ | |
| [xAI](https://x.ai/) | ✅ | |
| [智譜AI](https://open.bigmodel.cn/) | ✅ | |
| [勝算雲](https://www.shengsuanyun.com/?from=CH_KYIPP758) | ✅ | 大模型和 GPU 資源平台 |
| [優雲智算](https://www.compshare.cn/?ytag=GPU_YY-gh_langbot) | ✅ | 大模型和 GPU 資源平台 |
| [PPIO](https://ppinfra.com/user/register?invited_by=QJKFYD&utm_source=github_langbot) | ✅ | 大模型和 GPU 資源平台 |
| [302.AI](https://share.302.ai/SuTG99) | ✅ | 大模型聚合平台 |
| [Google Gemini](https://aistudio.google.com/prompts/new_chat) | ✅ | |
| [Dify](https://dify.ai) | ✅ | LLMOps 平台 |
| [Ollama](https://ollama.com/) | ✅ | 本地大模型運行平台 |
| [LMStudio](https://lmstudio.ai/) | ✅ | 本地大模型運行平台 |
| [GiteeAI](https://ai.gitee.com/) | ✅ | 大模型介面聚合平台 |
| [SiliconFlow](https://siliconflow.cn/) | ✅ | 大模型聚合平台 |
| [阿里雲百煉](https://bailian.console.aliyun.com/) | ✅ | 大模型聚合平台, LLMOps 平台 |
| [火山方舟](https://console.volcengine.com/ark/region:ark+cn-beijing/model?vendor=Bytedance&view=LIST_VIEW) | ✅ | 大模型聚合平台, LLMOps 平台 |
| [ModelScope](https://modelscope.cn/docs/model-service/API-Inference/intro) | ✅ | 大模型聚合平台 |
| [MCP](https://modelcontextprotocol.io/) | ✅ | 支援通過 MCP 協議獲取工具 |
### TTS
| 平台/模型 | 備註 |
| --- | --- |
| [FishAudio](https://fish.audio/zh-CN/discovery/) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
| [海豚 AI](https://www.ttson.cn/?source=thelazy) | [外掛](https://github.com/the-lazy-me/NewChatVoice) |
| [AzureTTS](https://portal.azure.com/) | [外掛](https://github.com/Ingnaryk/LangBot_AzureTTS) |
### 文生圖
| 平台/模型 | 備註 |
| --- | --- |
| 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin)
## 😘 社群貢獻
感謝以下[程式碼貢獻者](https://github.com/langbot-app/LangBot/graphs/contributors)和社群裡其他成員對 LangBot 的貢獻:
<a href="https://github.com/langbot-app/LangBot/graphs/contributors">
<img src="https://contrib.rocks/image?repo=langbot-app/LangBot" />
</a>

View File

@@ -9,7 +9,6 @@ spec:
components:
ComponentTemplate:
fromFiles:
- pkg/platform/adapter.yaml
- pkg/provider/modelmgr/requester.yaml
MessagePlatformAdapter:
fromDirs:

View File

@@ -1,6 +1,21 @@
version: "3"
services:
langbot_plugin_runtime:
image: rockchin/langbot:latest
container_name: langbot_plugin_runtime
volumes:
- ./data/plugins:/app/data/plugins
ports:
- 5401:5401
restart: on-failure
environment:
- TZ=Asia/Shanghai
command: ["uv", "run", "-m", "langbot_plugin.cli.__init__", "rt"]
networks:
- langbot_network
langbot:
image: rockchin/langbot:latest
container_name: langbot
@@ -11,6 +26,11 @@ services:
environment:
- TZ=Asia/Shanghai
ports:
- 5300:5300 # 供 WebUI 使用
- 2280-2290:2280-2290 # 供消息平台适配器方向连接
# 根据具体环境配置网络
- 5300:5300 # For web ui
- 2280-2290:2280-2290 # For platform webhook
networks:
- langbot_network
networks:
langbot_network:
driver: bridge

View File

@@ -253,6 +253,43 @@ class DingTalkClient:
await self.logger.error(f'failed to send proactive massage to group: {traceback.format_exc()}')
raise Exception(f'failed to send proactive massage to group: {traceback.format_exc()}')
async def create_and_card(
self, temp_card_id: str, incoming_message: dingtalk_stream.ChatbotMessage, quote_origin: bool = False
):
content_key = 'content'
card_data = {content_key: ''}
card_instance = dingtalk_stream.AICardReplier(self.client, incoming_message)
# print(card_instance)
# 先投放卡片: https://open.dingtalk.com/document/orgapp/create-and-deliver-cards
card_instance_id = await card_instance.async_create_and_deliver_card(
temp_card_id,
card_data,
)
return card_instance, card_instance_id
async def send_card_message(self, card_instance, card_instance_id: str, content: str, is_final: bool):
content_key = 'content'
try:
await card_instance.async_streaming(
card_instance_id,
content_key=content_key,
content_value=content,
append=False,
finished=is_final,
failed=False,
)
except Exception as e:
self.logger.exception(e)
await card_instance.async_streaming(
card_instance_id,
content_key=content_key,
content_value='',
append=False,
finished=is_final,
failed=True,
)
async def start(self):
"""启动 WebSocket 连接,监听消息"""
await self.client.start()

View File

@@ -3,7 +3,7 @@ from quart import request
import httpx
from quart import Quart
from typing import Callable, Dict, Any
from pkg.platform.types import events as platform_events
import langbot_plugin.api.entities.builtin.platform.events as platform_events
from .qqofficialevent import QQOfficialEvent
import json
import traceback
@@ -104,7 +104,7 @@ class QQOfficialClient:
return {'code': 0, 'message': 'success'}
except Exception as e:
await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
return {'error': str(e)}, 400
async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -168,7 +168,6 @@ class QQOfficialClient:
if not await self.check_access_token():
await self.get_access_token()
url = self.base_url + '/v2/users/' + user_openid + '/messages'
async with httpx.AsyncClient() as client:
headers = {
@@ -193,7 +192,6 @@ class QQOfficialClient:
if not await self.check_access_token():
await self.get_access_token()
url = self.base_url + '/v2/groups/' + group_openid + '/messages'
async with httpx.AsyncClient() as client:
headers = {
@@ -209,7 +207,7 @@ class QQOfficialClient:
if response.status_code == 200:
return
else:
await self.logger.error(f"发送群聊消息失败:{response.json()}")
await self.logger.error(f'发送群聊消息失败:{response.json()}')
raise Exception(response.read().decode())
async def send_channle_group_text_msg(self, channel_id: str, content: str, msg_id: str):
@@ -217,7 +215,6 @@ class QQOfficialClient:
if not await self.check_access_token():
await self.get_access_token()
url = self.base_url + '/channels/' + channel_id + '/messages'
async with httpx.AsyncClient() as client:
headers = {
@@ -240,7 +237,6 @@ class QQOfficialClient:
"""发送频道私聊消息"""
if not await self.check_access_token():
await self.get_access_token()
url = self.base_url + '/dms/' + guild_id + '/messages'
async with httpx.AsyncClient() as client:

View File

@@ -4,7 +4,7 @@ from quart import Quart, jsonify, request
from slack_sdk.web.async_client import AsyncWebClient
from .slackevent import SlackEvent
from typing import Callable
from pkg.platform.types import events as platform_events
import langbot_plugin.api.entities.builtin.platform.events as platform_events
class SlackClient:
@@ -34,7 +34,6 @@ class SlackClient:
if self.bot_user_id and bot_user_id == self.bot_user_id:
return jsonify({'status': 'ok'})
# 处理私信
if data and data.get('event', {}).get('channel_type') in ['im']:
@@ -52,7 +51,7 @@ class SlackClient:
return jsonify({'status': 'ok'})
except Exception as e:
await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
raise (e)
async def _handle_message(self, event: SlackEvent):
@@ -82,7 +81,7 @@ class SlackClient:
self.bot_user_id = response['message']['bot_id']
return
except Exception as e:
await self.logger.error(f"Error in send_message: {e}")
await self.logger.error(f'Error in send_message: {e}')
raise e
async def send_message_to_one(self, text: str, user_id: str):
@@ -93,7 +92,7 @@ class SlackClient:
return
except Exception as e:
await self.logger.error(f"Error in send_message: {traceback.format_exc()}")
await self.logger.error(f'Error in send_message: {traceback.format_exc()}')
raise e
async def run_task(self, host: str, port: int, *args, **kwargs):

View File

@@ -1 +1 @@
from .client import WeChatPadClient
from .client import WeChatPadClient as WeChatPadClient

View File

@@ -1,4 +1,4 @@
from libs.wechatpad_api.util.http_util import async_request, post_json
from libs.wechatpad_api.util.http_util import post_json
class ChatRoomApi:
@@ -7,8 +7,6 @@ class ChatRoomApi:
self.token = token
def get_chatroom_member_detail(self, chatroom_name):
params = {
"ChatRoomName": chatroom_name
}
params = {'ChatRoomName': chatroom_name}
url = self.base_url + '/group/GetChatroomMemberDetail'
return post_json(url, token=self.token, data=params)

View File

@@ -1,32 +1,23 @@
from libs.wechatpad_api.util.http_util import async_request, post_json
from libs.wechatpad_api.util.http_util import post_json
import httpx
import base64
class DownloadApi:
def __init__(self, base_url, token):
self.base_url = base_url
self.token = token
def send_download(self, aeskey, file_type, file_url):
json_data = {
"AesKey": aeskey,
"FileType": file_type,
"FileURL": file_url
}
url = self.base_url + "/message/SendCdnDownload"
json_data = {'AesKey': aeskey, 'FileType': file_type, 'FileURL': file_url}
url = self.base_url + '/message/SendCdnDownload'
return post_json(url, token=self.token, data=json_data)
def get_msg_voice(self,buf_id, length, new_msgid):
json_data = {
"Bufid": buf_id,
"Length": length,
"NewMsgId": new_msgid,
"ToUserName": ""
}
url = self.base_url + "/message/GetMsgVoice"
def get_msg_voice(self, buf_id, length, new_msgid):
json_data = {'Bufid': buf_id, 'Length': length, 'NewMsgId': new_msgid, 'ToUserName': ''}
url = self.base_url + '/message/GetMsgVoice'
return post_json(url, token=self.token, data=json_data)
async def download_url_to_base64(self, download_url):
async with httpx.AsyncClient() as client:
response = await client.get(download_url)
@@ -36,4 +27,4 @@ class DownloadApi:
base64_str = base64.b64encode(file_bytes).decode('utf-8') # 返回字符串格式
return base64_str
else:
raise Exception('获取文件失败')
raise Exception('获取文件失败')

View File

@@ -1,11 +1,6 @@
from libs.wechatpad_api.util.http_util import post_json,async_request
from typing import List, Dict, Any, Optional
class FriendApi:
"""联系人API类处理所有与联系人相关的操作"""
def __init__(self, base_url: str, token: str):
self.base_url = base_url
self.token = token

View File

@@ -1,37 +1,34 @@
from libs.wechatpad_api.util.http_util import async_request,post_json,get_json
from libs.wechatpad_api.util.http_util import post_json, get_json
class LoginApi:
def __init__(self, base_url: str, token: str = None, admin_key: str = None):
'''
"""
Args:
base_url: 原始路径
token: token
admin_key: 管理员key
'''
"""
self.base_url = base_url
self.token = token
# self.admin_key = admin_key
def get_token(self, admin_key, day: int=365):
def get_token(self, admin_key, day: int = 365):
# 获取普通token
url = f"{self.base_url}/admin/GenAuthKey1"
json_data = {
"Count": 1,
"Days": day
}
url = f'{self.base_url}/admin/GenAuthKey1'
json_data = {'Count': 1, 'Days': day}
return post_json(base_url=url, token=admin_key, data=json_data)
def get_login_qr(self, Proxy: str = ""):
'''
def get_login_qr(self, Proxy: str = ''):
"""
Args:
Proxy:异地使用时代理
Returns:json数据
'''
"""
"""
{
@@ -49,54 +46,37 @@ class LoginApi:
}
"""
#获取登录二维码
url = f"{self.base_url}/login/GetLoginQrCodeNew"
# 获取登录二维码
url = f'{self.base_url}/login/GetLoginQrCodeNew'
check = False
if Proxy != "":
if Proxy != '':
check = True
json_data = {
"Check": check,
"Proxy": Proxy
}
json_data = {'Check': check, 'Proxy': Proxy}
return post_json(base_url=url, token=self.token, data=json_data)
def get_login_status(self):
# 获取登录状态
url = f'{self.base_url}/login/GetLoginStatus'
return get_json(base_url=url, token=self.token)
def logout(self):
# 退出登录
url = f'{self.base_url}/login/LogOut'
return post_json(base_url=url, token=self.token)
def wake_up_login(self, Proxy: str = ""):
def wake_up_login(self, Proxy: str = ''):
# 唤醒登录
url = f'{self.base_url}/login/WakeUpLogin'
check = False
if Proxy != "":
if Proxy != '':
check = True
json_data = {
"Check": check,
"Proxy": ""
}
json_data = {'Check': check, 'Proxy': ''}
return post_json(base_url=url, token=self.token, data=json_data)
def login(self,admin_key):
def login(self, admin_key):
login_status = self.get_login_status()
if login_status["Code"] == 300 and login_status["Text"] == "你已退出微信":
print("token已经失效重新获取")
if login_status['Code'] == 300 and login_status['Text'] == '你已退出微信':
print('token已经失效重新获取')
token_data = self.get_token(admin_key)
self.token = token_data["Data"][0]
self.token = token_data['Data'][0]

View File

@@ -1,5 +1,4 @@
from libs.wechatpad_api.util.http_util import async_request, post_json
from libs.wechatpad_api.util.http_util import post_json
class MessageApi:
@@ -7,8 +6,8 @@ class MessageApi:
self.base_url = base_url
self.token = token
def post_text(self, to_wxid, content, ats: list= []):
'''
def post_text(self, to_wxid, content, ats: list = []):
"""
Args:
app_id: 微信id
@@ -18,106 +17,64 @@ class MessageApi:
Returns:
'''
url = self.base_url + "/message/SendTextMessage"
"""
url = self.base_url + '/message/SendTextMessage'
"""发送文字消息"""
json_data = {
"MsgItem": [
{
"AtWxIDList": ats,
"ImageContent": "",
"MsgType": 0,
"TextContent": content,
"ToUserName": to_wxid
}
]
}
return post_json(base_url=url, token=self.token, data=json_data)
'MsgItem': [
{'AtWxIDList': ats, 'ImageContent': '', 'MsgType': 0, 'TextContent': content, 'ToUserName': to_wxid}
]
}
return post_json(base_url=url, token=self.token, data=json_data)
def post_image(self, to_wxid, img_url, ats: list= []):
def post_image(self, to_wxid, img_url, ats: list = []):
"""发送图片消息"""
# 这里好像可以尝试发送多个暂时未测试
json_data = {
"MsgItem": [
{
"AtWxIDList": ats,
"ImageContent": img_url,
"MsgType": 0,
"TextContent": '',
"ToUserName": to_wxid
}
'MsgItem': [
{'AtWxIDList': ats, 'ImageContent': img_url, 'MsgType': 0, 'TextContent': '', 'ToUserName': to_wxid}
]
}
url = self.base_url + "/message/SendImageMessage"
url = self.base_url + '/message/SendImageMessage'
return post_json(base_url=url, token=self.token, data=json_data)
def post_voice(self, to_wxid, voice_data, voice_forma, voice_duration):
"""发送语音消息"""
json_data = {
"ToUserName": to_wxid,
"VoiceData": voice_data,
"VoiceFormat": voice_forma,
"VoiceSecond": voice_duration
'ToUserName': to_wxid,
'VoiceData': voice_data,
'VoiceFormat': voice_forma,
'VoiceSecond': voice_duration,
}
url = self.base_url + "/message/SendVoice"
url = self.base_url + '/message/SendVoice'
return post_json(base_url=url, token=self.token, data=json_data)
def post_name_card(self, alias, to_wxid, nick_name, name_card_wxid, flag):
"""发送名片消息"""
param = {
"CardAlias": alias,
"CardFlag": flag,
"CardNickName": nick_name,
"CardWxId": name_card_wxid,
"ToUserName": to_wxid
'CardAlias': alias,
'CardFlag': flag,
'CardNickName': nick_name,
'CardWxId': name_card_wxid,
'ToUserName': to_wxid,
}
url = f"{self.base_url}/message/ShareCardMessage"
url = f'{self.base_url}/message/ShareCardMessage'
return post_json(base_url=url, token=self.token, data=param)
def post_emoji(self, to_wxid, emoji_md5, emoji_size:int=0):
def post_emoji(self, to_wxid, emoji_md5, emoji_size: int = 0):
"""发送emoji消息"""
json_data = {
"EmojiList": [
{
"EmojiMd5": emoji_md5,
"EmojiSize": emoji_size,
"ToUserName": to_wxid
}
]
}
url = f"{self.base_url}/message/SendEmojiMessage"
json_data = {'EmojiList': [{'EmojiMd5': emoji_md5, 'EmojiSize': emoji_size, 'ToUserName': to_wxid}]}
url = f'{self.base_url}/message/SendEmojiMessage'
return post_json(base_url=url, token=self.token, data=json_data)
def post_app_msg(self, to_wxid,xml_data, contenttype:int=0):
def post_app_msg(self, to_wxid, xml_data, contenttype: int = 0):
"""发送appmsg消息"""
json_data = {
"AppList": [
{
"ContentType": contenttype,
"ContentXML": xml_data,
"ToUserName": to_wxid
}
]
}
url = f"{self.base_url}/message/SendAppMessage"
json_data = {'AppList': [{'ContentType': contenttype, 'ContentXML': xml_data, 'ToUserName': to_wxid}]}
url = f'{self.base_url}/message/SendAppMessage'
return post_json(base_url=url, token=self.token, data=json_data)
def revoke_msg(self, to_wxid, msg_id, new_msg_id, create_time):
"""撤回消息"""
param = {
"ClientMsgId": msg_id,
"CreateTime": create_time,
"NewMsgId": new_msg_id,
"ToUserName": to_wxid
}
url = f"{self.base_url}/message/RevokeMsg"
return post_json(base_url=url, token=self.token, data=param)
param = {'ClientMsgId': msg_id, 'CreateTime': create_time, 'NewMsgId': new_msg_id, 'ToUserName': to_wxid}
url = f'{self.base_url}/message/RevokeMsg'
return post_json(base_url=url, token=self.token, data=param)

View File

@@ -12,12 +12,9 @@ class UserApi:
return get_json(base_url=url, token=self.token)
def get_qr_code(self, recover:bool=True, style:int=8):
def get_qr_code(self, recover: bool = True, style: int = 8):
"""获取自己的二维码"""
param = {
"Recover": recover,
"Style": style
}
param = {'Recover': recover, 'Style': style}
url = f'{self.base_url}/user/GetMyQRCode'
return post_json(base_url=url, token=self.token, data=param)
@@ -26,12 +23,8 @@ class UserApi:
url = f'{self.base_url}/equipment/GetSafetyInfo'
return post_json(base_url=url, token=self.token)
async def update_head_img(self, head_img_base64):
async def update_head_img(self, head_img_base64):
"""修改头像"""
param = {
"Base64": head_img_base64
}
param = {'Base64': head_img_base64}
url = f'{self.base_url}/user/UploadHeadImage'
return await async_request(base_url=url, token_key=self.token, json=param)
return await async_request(base_url=url, token_key=self.token, json=param)

View File

@@ -1,4 +1,3 @@
from libs.wechatpad_api.api.login import LoginApi
from libs.wechatpad_api.api.friend import FriendApi
from libs.wechatpad_api.api.message import MessageApi
@@ -7,9 +6,6 @@ from libs.wechatpad_api.api.downloadpai import DownloadApi
from libs.wechatpad_api.api.chatroom import ChatRoomApi
class WeChatPadClient:
def __init__(self, base_url, token, logger=None):
self._login_api = LoginApi(base_url, token)
@@ -20,16 +16,16 @@ class WeChatPadClient:
self._chatroom_api = ChatRoomApi(base_url, token)
self.logger = logger
def get_token(self,admin_key, day: int):
'''获取token'''
def get_token(self, admin_key, day: int):
"""获取token"""
return self._login_api.get_token(admin_key, day)
def get_login_qr(self, Proxy:str=""):
def get_login_qr(self, Proxy: str = ''):
"""登录二维码"""
return self._login_api.get_login_qr(Proxy=Proxy)
def awaken_login(self, Proxy:str=""):
'''唤醒登录'''
def awaken_login(self, Proxy: str = ''):
"""唤醒登录"""
return self._login_api.wake_up_login(Proxy=Proxy)
def log_out(self):
@@ -40,59 +36,57 @@ class WeChatPadClient:
"""获取登录状态"""
return self._login_api.get_login_status()
def send_text_message(self, to_wxid, message, ats: list=[]):
def send_text_message(self, to_wxid, message, ats: list = []):
"""发送文本消息"""
return self._message_api.post_text(to_wxid, message, ats)
return self._message_api.post_text(to_wxid, message, ats)
def send_image_message(self, to_wxid, img_url, ats: list=[]):
def send_image_message(self, to_wxid, img_url, ats: list = []):
"""发送图片消息"""
return self._message_api.post_image(to_wxid, img_url, ats)
return self._message_api.post_image(to_wxid, img_url, ats)
def send_voice_message(self, to_wxid, voice_data, voice_forma, voice_duration):
"""发送音频消息"""
return self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)
return self._message_api.post_voice(to_wxid, voice_data, voice_forma, voice_duration)
def send_app_message(self, to_wxid, app_message, type):
"""发送app消息"""
return self._message_api.post_app_msg(to_wxid, app_message, type)
return self._message_api.post_app_msg(to_wxid, app_message, type)
def send_emoji_message(self, to_wxid, emoji_md5, emoji_size):
"""发送emoji消息"""
return self._message_api.post_emoji(to_wxid,emoji_md5,emoji_size)
return self._message_api.post_emoji(to_wxid, emoji_md5, emoji_size)
def revoke_msg(self, to_wxid, msg_id, new_msg_id, create_time):
"""撤回消息"""
return self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)
return self._message_api.revoke_msg(to_wxid, msg_id, new_msg_id, create_time)
def get_profile(self):
"""获取用户信息"""
return self._user_api.get_profile()
def get_qr_code(self, recover:bool=True, style:int=8):
def get_qr_code(self, recover: bool = True, style: int = 8):
"""获取用户二维码"""
return self._user_api.get_qr_code(recover=recover, style=style)
return self._user_api.get_qr_code(recover=recover, style=style)
def get_safety_info(self):
"""获取设备信息"""
return self._user_api.get_safety_info()
return self._user_api.get_safety_info()
def update_head_img(self, head_img_base64):
def update_head_img(self, head_img_base64):
"""上传用户头像"""
return self._user_api.update_head_img(head_img_base64)
return self._user_api.update_head_img(head_img_base64)
def cdn_download(self, aeskey, file_type, file_url):
"""cdn下载"""
return self._download_api.send_download( aeskey, file_type, file_url)
return self._download_api.send_download(aeskey, file_type, file_url)
def get_msg_voice(self,buf_id, length, msgid):
def get_msg_voice(self, buf_id, length, msgid):
"""下载语音"""
return self._download_api.get_msg_voice(buf_id, length, msgid)
async def download_base64(self,url):
async def download_base64(self, url):
return await self._download_api.download_url_to_base64(download_url=url)
def get_chatroom_member_detail(self, chatroom_name):
"""查看群成员详情"""
return self._chatroom_api.get_chatroom_member_detail(chatroom_name)

View File

@@ -1,10 +1,9 @@
import requests
import aiohttp
def post_json(base_url, token, data=None):
headers = {
'Content-Type': 'application/json'
}
headers = {'Content-Type': 'application/json'}
url = base_url + f'?key={token}'
@@ -18,14 +17,12 @@ def post_json(base_url, token, data=None):
else:
raise RuntimeError(response.text)
except Exception as e:
print(f"http请求失败, url={url}, exception={e}")
print(f'http请求失败, url={url}, exception={e}')
raise RuntimeError(str(e))
def get_json(base_url, token):
headers = {
'Content-Type': 'application/json'
}
def get_json(base_url, token):
headers = {'Content-Type': 'application/json'}
url = base_url + f'?key={token}'
@@ -39,21 +36,18 @@ def get_json(base_url, token):
else:
raise RuntimeError(response.text)
except Exception as e:
print(f"http请求失败, url={url}, exception={e}")
print(f'http请求失败, url={url}, exception={e}')
raise RuntimeError(str(e))
import aiohttp
import asyncio
async def async_request(
base_url: str,
token_key: str,
method: str = 'POST',
params: dict = None,
# headers: dict = None,
data: dict = None,
json: dict = None
base_url: str,
token_key: str,
method: str = 'POST',
params: dict = None,
# headers: dict = None,
data: dict = None,
json: dict = None,
):
"""
通用异步请求函数
@@ -67,18 +61,11 @@ async def async_request(
:param json: JSON数据
:return: 响应文本
"""
headers = {
'Content-Type': 'application/json'
}
url = f"{base_url}?key={token_key}"
headers = {'Content-Type': 'application/json'}
url = f'{base_url}?key={token_key}'
async with aiohttp.ClientSession() as session:
async with session.request(
method=method,
url=url,
params=params,
headers=headers,
data=data,
json=json
method=method, url=url, params=params, headers=headers, data=data, json=json
) as response:
response.raise_for_status() # 如果状态码不是200抛出异常
result = await response.json()
@@ -89,4 +76,3 @@ async def async_request(
# return await result
# else:
# raise RuntimeError("请求失败",response.text)

View File

@@ -1,31 +1,34 @@
import qrcode
def print_green(text):
print(f"\033[32m{text}\033[0m")
print(f'\033[32m{text}\033[0m')
def print_yellow(text):
print(f"\033[33m{text}\033[0m")
print(f'\033[33m{text}\033[0m')
def print_red(text):
print(f"\033[31m{text}\033[0m")
print(f'\033[31m{text}\033[0m')
def make_and_print_qr(url):
"""生成并打印二维码
Args:
url: 需要生成二维码的URL字符串
Returns:
None
功能:
1. 在终端打印二维码的ASCII图形
2. 同时提供在线二维码生成链接作为备选
"""
print_green("请扫描下方二维码登录")
print_green('请扫描下方二维码登录')
qr = qrcode.QRCode()
qr.add_data(url)
qr.make()
qr.print_ascii(invert=True)
print_green(f"也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}")
print_green(f'也可以访问下方链接获取二维码:\nhttps://api.qrserver.com/v1/create-qr-code/?data={url}')

View File

@@ -8,7 +8,7 @@ from quart import Quart
import xml.etree.ElementTree as ET
from typing import Callable, Dict, Any
from .wecomevent import WecomEvent
from pkg.platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import aiofiles
@@ -57,7 +57,7 @@ class WecomClient:
if 'access_token' in data:
return data['access_token']
else:
await self.logger.error(f"获取accesstoken失败:{response.json()}")
await self.logger.error(f'获取accesstoken失败:{response.json()}')
raise Exception(f'未获取access token: {data}')
async def get_users(self):
@@ -129,7 +129,7 @@ class WecomClient:
response = await client.post(url, json=params)
data = response.json()
except Exception as e:
await self.logger.error(f"发送图片失败:{data}")
await self.logger.error(f'发送图片失败:{data}')
raise Exception('Failed to send image: ' + str(e))
# 企业微信错误码40014和42001代表accesstoken问题
@@ -164,7 +164,7 @@ class WecomClient:
self.access_token = await self.get_access_token(self.secret)
return await self.send_private_msg(user_id, agent_id, content)
if data['errcode'] != 0:
await self.logger.error(f"发送消息失败:{data}")
await self.logger.error(f'发送消息失败:{data}')
raise Exception('Failed to send message: ' + str(data))
async def handle_callback_request(self):
@@ -181,7 +181,7 @@ class WecomClient:
echostr = request.args.get('echostr')
ret, reply_echo_str = wxcpt.VerifyURL(msg_signature, timestamp, nonce, echostr)
if ret != 0:
await self.logger.error("验证失败")
await self.logger.error('验证失败')
raise Exception(f'验证失败,错误码: {ret}')
return reply_echo_str
@@ -189,9 +189,8 @@ class WecomClient:
encrypt_msg = await request.data
ret, xml_msg = wxcpt.DecryptMsg(encrypt_msg, msg_signature, timestamp, nonce)
if ret != 0:
await self.logger.error("消息解密失败")
await self.logger.error('消息解密失败')
raise Exception(f'消息解密失败,错误码: {ret}')
# 解析消息并处理
message_data = await self.get_message(xml_msg)
@@ -202,7 +201,7 @@ class WecomClient:
return 'success'
except Exception as e:
await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
return f'Error processing request: {str(e)}', 400
async def run_task(self, host: str, port: int, *args, **kwargs):
@@ -301,7 +300,7 @@ class WecomClient:
except binascii.Error as e:
raise ValueError(f'Invalid base64 string: {str(e)}')
else:
await self.logger.error("Image对象出错")
await self.logger.error('Image对象出错')
raise ValueError('image对象出错')
# 设置 multipart/form-data 格式的文件
@@ -325,7 +324,7 @@ class WecomClient:
self.access_token = await self.get_access_token(self.secret)
media_id = await self.upload_to_work(image)
if data.get('errcode', 0) != 0:
await self.logger.error(f"上传图片失败:{data}")
await self.logger.error(f'上传图片失败:{data}')
raise Exception('failed to upload file')
media_id = data.get('media_id')

View File

@@ -8,7 +8,7 @@ from quart import Quart
import xml.etree.ElementTree as ET
from typing import Callable
from .wecomcsevent import WecomCSEvent
from pkg.platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import aiofiles
@@ -187,7 +187,7 @@ class WecomCSClient:
self.access_token = await self.get_access_token(self.secret)
return await self.send_text_msg(open_kfid, external_userid, msgid, content)
if data['errcode'] != 0:
await self.logger.error(f"发送消息失败:{data}")
await self.logger.error(f'发送消息失败:{data}')
raise Exception('Failed to send message')
return data
@@ -227,7 +227,7 @@ class WecomCSClient:
return 'success'
except Exception as e:
if self.logger:
await self.logger.error(f"Error in handle_callback_request: {traceback.format_exc()}")
await self.logger.error(f'Error in handle_callback_request: {traceback.format_exc()}')
else:
traceback.print_exc()
return f'Error processing request: {str(e)}', 400

16
main.py
View File

@@ -19,8 +19,14 @@ asciiart = r"""
async def main_entry(loop: asyncio.AbstractEventLoop):
parser = argparse.ArgumentParser(description='LangBot')
parser.add_argument('--skip-plugin-deps-check', action='store_true', help='跳过插件依赖项检查', default=False)
parser.add_argument('--standalone-runtime', action='store_true', help='使用独立插件运行时', default=False)
args = parser.parse_args()
if args.standalone_runtime:
from pkg.utils import platform
platform.standalone_runtime = True
print(asciiart)
import sys
@@ -47,13 +53,13 @@ async def main_entry(loop: asyncio.AbstractEventLoop):
if not args.skip_plugin_deps_check:
await deps.precheck_plugin_deps()
# 检查pydantic版本如果没有 pydantic.v1则把 pydantic 映射为 v1
import pydantic.version
# # 检查pydantic版本如果没有 pydantic.v1则把 pydantic 映射为 v1
# import pydantic.version
if pydantic.version.VERSION < '2.0':
import pydantic
# if pydantic.version.VERSION < '2.0':
# import pydantic
sys.modules['pydantic.v1'] = pydantic
# sys.modules['pydantic.v1'] = pydantic
# 检查配置文件

View File

@@ -14,8 +14,8 @@ preregistered_groups: list[type[RouterGroup]] = []
"""Pre-registered list of RouterGroup"""
def group_class(name: str, path: str) -> None:
"""Register a RouterGroup"""
def group_class(name: str, path: str) -> typing.Callable[[typing.Type[RouterGroup]], typing.Type[RouterGroup]]:
"""注册一个 RouterGroup"""
def decorator(cls: typing.Type[RouterGroup]) -> typing.Type[RouterGroup]:
cls.name = name
@@ -86,10 +86,11 @@ class RouterGroup(abc.ABC):
try:
return await f(*args, **kwargs)
except Exception: # auto 500
except Exception as e: # 自动 500
traceback.print_exc()
# return self.http_status(500, -2, str(e))
return self.http_status(500, -2, 'internal server error')
return self.http_status(500, -2, str(e))
new_f = handler_error
new_f.__name__ = (self.name + rule).replace('/', '__')
@@ -120,6 +121,6 @@ class RouterGroup(abc.ABC):
}
)
def http_status(self, status: int, code: int, msg: str) -> quart.Response:
"""Return a response with a specified status code"""
return self.fail(code, msg), status
def http_status(self, status: int, code: int, msg: str) -> typing.Tuple[quart.Response, int]:
"""返回一个指定状态码的响应"""
return (self.fail(code, msg), status)

View File

@@ -2,6 +2,10 @@ from __future__ import annotations
import quart
import mimetypes
import uuid
import asyncio
import quart.datastructures
from .. import group
@@ -20,3 +24,23 @@ class FilesRouterGroup(group.RouterGroup):
mime_type = 'image/jpeg'
return quart.Response(image_bytes, mimetype=mime_type)
@self.route('/documents', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> quart.Response:
request = quart.request
# get file bytes from 'file'
file = (await request.files)['file']
assert isinstance(file, quart.datastructures.FileStorage)
file_bytes = await asyncio.to_thread(file.stream.read)
extension = file.filename.split('.')[-1]
file_name = file.filename.split('.')[0]
file_key = file_name + '_' + str(uuid.uuid4())[:8] + '.' + extension
# save file to storage
await self.ap.storage_mgr.storage_provider.save(file_key, file_bytes)
return self.success(
data={
'file_id': file_key,
}
)

View File

@@ -0,0 +1,90 @@
import quart
from ... import group
@group.group_class('knowledge_base', '/api/v1/knowledge/bases')
class KnowledgeBaseRouterGroup(group.RouterGroup):
async def initialize(self) -> None:
@self.route('', methods=['POST', 'GET'])
async def handle_knowledge_bases() -> quart.Response:
if quart.request.method == 'GET':
knowledge_bases = await self.ap.knowledge_service.get_knowledge_bases()
return self.success(data={'bases': knowledge_bases})
elif quart.request.method == 'POST':
json_data = await quart.request.json
knowledge_base_uuid = await self.ap.knowledge_service.create_knowledge_base(json_data)
return self.success(data={'uuid': knowledge_base_uuid})
return self.http_status(405, -1, 'Method not allowed')
@self.route(
'/<knowledge_base_uuid>',
methods=['GET', 'DELETE', 'PUT'],
)
async def handle_specific_knowledge_base(knowledge_base_uuid: str) -> quart.Response:
if quart.request.method == 'GET':
knowledge_base = await self.ap.knowledge_service.get_knowledge_base(knowledge_base_uuid)
if knowledge_base is None:
return self.http_status(404, -1, 'knowledge base not found')
return self.success(
data={
'base': knowledge_base,
}
)
elif quart.request.method == 'PUT':
json_data = await quart.request.json
await self.ap.knowledge_service.update_knowledge_base(knowledge_base_uuid, json_data)
return self.success({})
elif quart.request.method == 'DELETE':
await self.ap.knowledge_service.delete_knowledge_base(knowledge_base_uuid)
return self.success({})
@self.route(
'/<knowledge_base_uuid>/files',
methods=['GET', 'POST'],
)
async def get_knowledge_base_files(knowledge_base_uuid: str) -> str:
if quart.request.method == 'GET':
files = await self.ap.knowledge_service.get_files_by_knowledge_base(knowledge_base_uuid)
return self.success(
data={
'files': files,
}
)
elif quart.request.method == 'POST':
json_data = await quart.request.json
file_id = json_data.get('file_id')
if not file_id:
return self.http_status(400, -1, 'File ID is required')
# 调用服务层方法将文件与知识库关联
task_id = await self.ap.knowledge_service.store_file(knowledge_base_uuid, file_id)
return self.success(
{
'task_id': task_id,
}
)
@self.route(
'/<knowledge_base_uuid>/files/<file_id>',
methods=['DELETE'],
)
async def delete_specific_file_in_kb(file_id: str, knowledge_base_uuid: str) -> str:
await self.ap.knowledge_service.delete_file(knowledge_base_uuid, file_id)
return self.success({})
@self.route(
'/<knowledge_base_uuid>/retrieve',
methods=['POST'],
)
async def retrieve_knowledge_base(knowledge_base_uuid: str) -> str:
json_data = await quart.request.json
query = json_data.get('query')
results = await self.ap.knowledge_service.retrieve_knowledge_base(knowledge_base_uuid, query)
return self.success(data={'results': results})

View File

@@ -11,7 +11,11 @@ class PipelinesRouterGroup(group.RouterGroup):
@self.route('', methods=['GET', 'POST'])
async def _() -> str:
if quart.request.method == 'GET':
return self.success(data={'pipelines': await self.ap.pipeline_service.get_pipelines()})
sort_by = quart.request.args.get('sort_by', 'created_at')
sort_order = quart.request.args.get('sort_order', 'DESC')
return self.success(
data={'pipelines': await self.ap.pipeline_service.get_pipelines(sort_by, sort_order)}
)
elif quart.request.method == 'POST':
json_data = await quart.request.json

View File

@@ -1,3 +1,5 @@
import json
import quart
from ... import group
@@ -9,10 +11,18 @@ class WebChatDebugRouterGroup(group.RouterGroup):
@self.route('/send', methods=['POST'])
async def send_message(pipeline_uuid: str) -> str:
"""Send a message to the pipeline for debugging"""
async def stream_generator(generator):
yield 'data: {"type": "start"}\n\n'
async for message in generator:
yield f'data: {json.dumps({"message": message})}\n\n'
yield 'data: {"type": "end"}\n\n'
try:
data = await quart.request.get_json()
session_type = data.get('session_type', 'person')
message_chain_obj = data.get('message', [])
is_stream = data.get('is_stream', False)
if not message_chain_obj:
return self.http_status(400, -1, 'message is required')
@@ -25,13 +35,33 @@ class WebChatDebugRouterGroup(group.RouterGroup):
if not webchat_adapter:
return self.http_status(404, -1, 'WebChat adapter not found')
result = await webchat_adapter.send_webchat_message(pipeline_uuid, session_type, message_chain_obj)
return self.success(
data={
'message': result,
if is_stream:
generator = webchat_adapter.send_webchat_message(
pipeline_uuid, session_type, message_chain_obj, is_stream
)
# 设置正确的响应头
headers = {
'Content-Type': 'text/event-stream',
'Transfer-Encoding': 'chunked',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
}
)
return quart.Response(stream_generator(generator), mimetype='text/event-stream', headers=headers)
else: # non-stream
result = None
async for message in webchat_adapter.send_webchat_message(
pipeline_uuid, session_type, message_chain_obj
):
result = message
if result is not None:
return self.success(
data={
'message': result,
}
)
else:
return self.http_status(400, -1, 'message is required')
except Exception as e:
return self.http_status(500, -1, f'Internal server error: {str(e)}')

View File

@@ -1,10 +1,11 @@
from __future__ import annotations
import base64
import quart
from .....core import taskmgr
from .. import group
from langbot_plugin.runtime.plugin.mgr import PluginInstallSource
@group.group_class('plugins', '/api/v1/plugins')
@@ -12,35 +13,22 @@ class PluginsRouterGroup(group.RouterGroup):
async def initialize(self) -> None:
@self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
plugins = self.ap.plugin_mgr.plugins()
plugins = await self.ap.plugin_connector.list_plugins()
plugins_data = [plugin.model_dump() for plugin in plugins]
return self.success(data={'plugins': plugins_data})
return self.success(data={'plugins': plugins})
@self.route(
'/<author>/<plugin_name>/toggle',
methods=['PUT'],
auth_type=group.AuthType.USER_TOKEN,
)
async def _(author: str, plugin_name: str) -> str:
data = await quart.request.json
target_enabled = data.get('target_enabled')
await self.ap.plugin_mgr.update_plugin_switch(plugin_name, target_enabled)
return self.success()
@self.route(
'/<author>/<plugin_name>/update',
'/<author>/<plugin_name>/upgrade',
methods=['POST'],
auth_type=group.AuthType.USER_TOKEN,
)
async def _(author: str, plugin_name: str) -> str:
ctx = taskmgr.TaskContext.new()
wrapper = self.ap.task_mgr.create_user_task(
self.ap.plugin_mgr.update_plugin(plugin_name, task_context=ctx),
self.ap.plugin_connector.upgrade_plugin(author, plugin_name, task_context=ctx),
kind='plugin-operation',
name=f'plugin-update-{plugin_name}',
label=f'Updating plugin {plugin_name}',
name=f'plugin-upgrade-{plugin_name}',
label=f'Upgrading plugin {plugin_name}',
context=ctx,
)
return self.success(data={'task_id': wrapper.id})
@@ -52,14 +40,14 @@ class PluginsRouterGroup(group.RouterGroup):
)
async def _(author: str, plugin_name: str) -> str:
if quart.request.method == 'GET':
plugin = self.ap.plugin_mgr.get_plugin(author, plugin_name)
plugin = await self.ap.plugin_connector.get_plugin_info(author, plugin_name)
if plugin is None:
return self.http_status(404, -1, 'plugin not found')
return self.success(data={'plugin': plugin.model_dump()})
return self.success(data={'plugin': plugin})
elif quart.request.method == 'DELETE':
ctx = taskmgr.TaskContext.new()
wrapper = self.ap.task_mgr.create_user_task(
self.ap.plugin_mgr.uninstall_plugin(plugin_name, task_context=ctx),
self.ap.plugin_connector.delete_plugin(author, plugin_name, task_context=ctx),
kind='plugin-operation',
name=f'plugin-remove-{plugin_name}',
label=f'Removing plugin {plugin_name}',
@@ -74,24 +62,19 @@ class PluginsRouterGroup(group.RouterGroup):
auth_type=group.AuthType.USER_TOKEN,
)
async def _(author: str, plugin_name: str) -> quart.Response:
plugin = self.ap.plugin_mgr.get_plugin(author, plugin_name)
plugin = await self.ap.plugin_connector.get_plugin_info(author, plugin_name)
if plugin is None:
return self.http_status(404, -1, 'plugin not found')
if quart.request.method == 'GET':
return self.success(data={'config': plugin.plugin_config})
return self.success(data={'config': plugin['plugin_config']})
elif quart.request.method == 'PUT':
data = await quart.request.json
await self.ap.plugin_mgr.set_plugin_config(plugin, data)
await self.ap.plugin_connector.set_plugin_config(author, plugin_name, data)
return self.success(data={})
@self.route('/reorder', methods=['PUT'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
data = await quart.request.json
await self.ap.plugin_mgr.reorder_plugins(data.get('plugins'))
return self.success()
@self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
data = await quart.request.json
@@ -102,7 +85,47 @@ class PluginsRouterGroup(group.RouterGroup):
self.ap.plugin_mgr.install_plugin(data['source'], task_context=ctx),
kind='plugin-operation',
name='plugin-install-github',
label=f'Installing plugin ...{short_source_str}',
label=f'Installing plugin from github ...{short_source_str}',
context=ctx,
)
return self.success(data={'task_id': wrapper.id})
@self.route('/install/marketplace', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
data = await quart.request.json
ctx = taskmgr.TaskContext.new()
wrapper = self.ap.task_mgr.create_user_task(
self.ap.plugin_connector.install_plugin(PluginInstallSource.MARKETPLACE, data, task_context=ctx),
kind='plugin-operation',
name='plugin-install-marketplace',
label=f'Installing plugin from marketplace ...{data}',
context=ctx,
)
return self.success(data={'task_id': wrapper.id})
@self.route('/install/local', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
file = (await quart.request.files).get('file')
if file is None:
return self.http_status(400, -1, 'file is required')
file_bytes = file.read()
file_base64 = base64.b64encode(file_bytes).decode('utf-8')
data = {
'plugin_file': file_base64,
}
ctx = taskmgr.TaskContext.new()
wrapper = self.ap.task_mgr.create_user_task(
self.ap.plugin_connector.install_plugin(PluginInstallSource.LOCAL, data, task_context=ctx),
kind='plugin-operation',
name='plugin-install-local',
label=f'Installing plugin from local ...{file.filename}',
context=ctx,
)

View File

@@ -9,18 +9,18 @@ class LLMModelsRouterGroup(group.RouterGroup):
@self.route('', methods=['GET', 'POST'])
async def _() -> str:
if quart.request.method == 'GET':
return self.success(data={'models': await self.ap.model_service.get_llm_models()})
return self.success(data={'models': await self.ap.llm_model_service.get_llm_models()})
elif quart.request.method == 'POST':
json_data = await quart.request.json
model_uuid = await self.ap.model_service.create_llm_model(json_data)
model_uuid = await self.ap.llm_model_service.create_llm_model(json_data)
return self.success(data={'uuid': model_uuid})
@self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
async def _(model_uuid: str) -> str:
if quart.request.method == 'GET':
model = await self.ap.model_service.get_llm_model(model_uuid)
model = await self.ap.llm_model_service.get_llm_model(model_uuid)
if model is None:
return self.http_status(404, -1, 'model not found')
@@ -29,11 +29,11 @@ class LLMModelsRouterGroup(group.RouterGroup):
elif quart.request.method == 'PUT':
json_data = await quart.request.json
await self.ap.model_service.update_llm_model(model_uuid, json_data)
await self.ap.llm_model_service.update_llm_model(model_uuid, json_data)
return self.success()
elif quart.request.method == 'DELETE':
await self.ap.model_service.delete_llm_model(model_uuid)
await self.ap.llm_model_service.delete_llm_model(model_uuid)
return self.success()
@@ -41,6 +41,49 @@ class LLMModelsRouterGroup(group.RouterGroup):
async def _(model_uuid: str) -> str:
json_data = await quart.request.json
await self.ap.model_service.test_llm_model(model_uuid, json_data)
await self.ap.llm_model_service.test_llm_model(model_uuid, json_data)
return self.success()
@group.group_class('models/embedding', '/api/v1/provider/models/embedding')
class EmbeddingModelsRouterGroup(group.RouterGroup):
async def initialize(self) -> None:
@self.route('', methods=['GET', 'POST'])
async def _() -> str:
if quart.request.method == 'GET':
return self.success(data={'models': await self.ap.embedding_models_service.get_embedding_models()})
elif quart.request.method == 'POST':
json_data = await quart.request.json
model_uuid = await self.ap.embedding_models_service.create_embedding_model(json_data)
return self.success(data={'uuid': model_uuid})
@self.route('/<model_uuid>', methods=['GET', 'PUT', 'DELETE'])
async def _(model_uuid: str) -> str:
if quart.request.method == 'GET':
model = await self.ap.embedding_models_service.get_embedding_model(model_uuid)
if model is None:
return self.http_status(404, -1, 'model not found')
return self.success(data={'model': model})
elif quart.request.method == 'PUT':
json_data = await quart.request.json
await self.ap.embedding_models_service.update_embedding_model(model_uuid, json_data)
return self.success()
elif quart.request.method == 'DELETE':
await self.ap.embedding_models_service.delete_embedding_model(model_uuid)
return self.success()
@self.route('/<model_uuid>/test', methods=['POST'])
async def _(model_uuid: str) -> str:
json_data = await quart.request.json
await self.ap.embedding_models_service.test_embedding_model(model_uuid, json_data)
return self.success()

View File

@@ -8,7 +8,8 @@ class RequestersRouterGroup(group.RouterGroup):
async def initialize(self) -> None:
@self.route('', methods=['GET'])
async def _() -> quart.Response:
return self.success(data={'requesters': self.ap.model_mgr.get_available_requesters_info()})
model_type = quart.request.args.get('type', '')
return self.success(data={'requesters': self.ap.model_mgr.get_available_requesters_info(model_type)})
@self.route('/<requester_name>', methods=['GET'])
async def _(requester_name: str) -> quart.Response:

View File

@@ -14,6 +14,11 @@ class SystemRouterGroup(group.RouterGroup):
'version': constants.semantic_version,
'debug': constants.debug_mode,
'enabled_platform_count': len(self.ap.platform_mgr.get_running_adapters()),
'cloud_service_url': (
self.ap.instance_config.data['plugin']['cloud_service_url']
if 'cloud_service_url' in self.ap.instance_config.data['plugin']
else 'https://space.langbot.app'
),
}
)
@@ -35,16 +40,7 @@ class SystemRouterGroup(group.RouterGroup):
return self.success(data=task.to_dict())
@self.route('/reload', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
json_data = await quart.request.json
scope = json_data.get('scope')
await self.ap.reload(scope=scope)
return self.success()
@self.route('/_debug/exec', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
@self.route('/debug/exec', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
if not constants.debug_mode:
return self.http_status(403, 403, 'Forbidden')
@@ -54,3 +50,39 @@ class SystemRouterGroup(group.RouterGroup):
ap = self.ap
return self.success(data=exec(py_code, {'ap': ap}))
@self.route('/debug/tools/call', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _() -> str:
if not constants.debug_mode:
return self.http_status(403, 403, 'Forbidden')
data = await quart.request.json
return self.success(
data=await self.ap.tool_mgr.execute_func_call(data['tool_name'], data['tool_parameters'])
)
@self.route(
'/debug/plugin/action',
methods=['POST'],
auth_type=group.AuthType.USER_TOKEN,
)
async def _() -> str:
if not constants.debug_mode:
return self.http_status(403, 403, 'Forbidden')
data = await quart.request.json
class AnoymousAction:
value = 'anonymous_action'
def __init__(self, value: str):
self.value = value
resp = await self.ap.plugin_connector.handler.call_action(
AnoymousAction(data['action']),
data['data'],
timeout=data.get('timeout', 10),
)
return self.success(data=resp)

View File

@@ -67,3 +67,19 @@ class UserRouterGroup(group.RouterGroup):
await self.ap.user_service.reset_password(user_email, new_password)
return self.success(data={'user': user_email})
@self.route('/change-password', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
async def _(user_email: str) -> str:
json_data = await quart.request.json
current_password = json_data['current_password']
new_password = json_data['new_password']
try:
await self.ap.user_service.change_password(user_email, current_password, new_password)
except argon2.exceptions.VerifyMismatchError:
return self.http_status(400, -1, 'Current password is incorrect')
except ValueError as e:
return self.http_status(400, -1, str(e))
return self.success(data={'user': user_email})

View File

@@ -14,11 +14,13 @@ from . import group
from .groups import provider as groups_provider
from .groups import platform as groups_platform
from .groups import pipelines as groups_pipelines
from .groups import knowledge as groups_knowledge
importutil.import_modules_in_pkg(groups)
importutil.import_modules_in_pkg(groups_provider)
importutil.import_modules_in_pkg(groups_platform)
importutil.import_modules_in_pkg(groups_pipelines)
importutil.import_modules_in_pkg(groups_knowledge)
class HTTPController:

View File

@@ -17,16 +17,20 @@ class BotService:
def __init__(self, ap: app.Application) -> None:
self.ap = ap
async def get_bots(self) -> list[dict]:
"""Get all bots"""
async def get_bots(self, include_secret: bool = True) -> list[dict]:
"""获取所有机器人"""
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_bot.Bot))
bots = result.all()
return [self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot) for bot in bots]
masked_columns = []
if not include_secret:
masked_columns = ['adapter_config']
async def get_bot(self, bot_uuid: str) -> dict | None:
"""Get bot"""
return [self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot, masked_columns) for bot in bots]
async def get_bot(self, bot_uuid: str, include_secret: bool = True) -> dict | None:
"""获取机器人"""
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_uuid)
)
@@ -36,7 +40,27 @@ class BotService:
if bot is None:
return None
return self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot)
masked_columns = []
if not include_secret:
masked_columns = ['adapter_config']
return self.ap.persistence_mgr.serialize_model(persistence_bot.Bot, bot, masked_columns)
async def get_runtime_bot_info(self, bot_uuid: str, include_secret: bool = True) -> dict:
"""获取机器人运行时信息"""
persistence_bot = await self.get_bot(bot_uuid, include_secret)
if persistence_bot is None:
raise Exception('Bot not found')
adapter_runtime_values = {}
runtime_bot = await self.ap.platform_mgr.get_bot_by_uuid(bot_uuid)
if runtime_bot is not None:
adapter_runtime_values['bot_account_id'] = runtime_bot.adapter.bot_account_id
persistence_bot['adapter_runtime_values'] = adapter_runtime_values
return persistence_bot
async def create_bot(self, bot_data: dict) -> str:
"""Create bot"""

View File

@@ -0,0 +1,120 @@
from __future__ import annotations
import uuid
import sqlalchemy
from ....core import app
from ....entity.persistence import rag as persistence_rag
class KnowledgeService:
"""知识库服务"""
ap: app.Application
def __init__(self, ap: app.Application) -> None:
self.ap = ap
async def get_knowledge_bases(self) -> list[dict]:
"""获取所有知识库"""
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_rag.KnowledgeBase))
knowledge_bases = result.all()
return [
self.ap.persistence_mgr.serialize_model(persistence_rag.KnowledgeBase, knowledge_base)
for knowledge_base in knowledge_bases
]
async def get_knowledge_base(self, kb_uuid: str) -> dict | None:
"""获取知识库"""
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
)
knowledge_base = result.first()
if knowledge_base is None:
return None
return self.ap.persistence_mgr.serialize_model(persistence_rag.KnowledgeBase, knowledge_base)
async def create_knowledge_base(self, kb_data: dict) -> str:
"""创建知识库"""
kb_data['uuid'] = str(uuid.uuid4())
await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.KnowledgeBase).values(kb_data))
kb = await self.get_knowledge_base(kb_data['uuid'])
await self.ap.rag_mgr.load_knowledge_base(kb)
return kb_data['uuid']
async def update_knowledge_base(self, kb_uuid: str, kb_data: dict) -> None:
"""更新知识库"""
if 'uuid' in kb_data:
del kb_data['uuid']
if 'embedding_model_uuid' in kb_data:
del kb_data['embedding_model_uuid']
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(persistence_rag.KnowledgeBase)
.values(kb_data)
.where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
)
await self.ap.rag_mgr.remove_knowledge_base_from_runtime(kb_uuid)
kb = await self.get_knowledge_base(kb_uuid)
await self.ap.rag_mgr.load_knowledge_base(kb)
async def store_file(self, kb_uuid: str, file_id: str) -> int:
"""存储文件"""
# await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_rag.File).values(kb_id=kb_uuid, file_id=file_id))
# await self.ap.rag_mgr.store_file(file_id)
runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
if runtime_kb is None:
raise Exception('Knowledge base not found')
return await runtime_kb.store_file(file_id)
async def retrieve_knowledge_base(self, kb_uuid: str, query: str) -> list[dict]:
"""检索知识库"""
runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
if runtime_kb is None:
raise Exception('Knowledge base not found')
return [
result.model_dump() for result in await runtime_kb.retrieve(query, runtime_kb.knowledge_base_entity.top_k)
]
async def get_files_by_knowledge_base(self, kb_uuid: str) -> list[dict]:
"""获取知识库文件"""
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
)
files = result.all()
return [self.ap.persistence_mgr.serialize_model(persistence_rag.File, file) for file in files]
async def delete_file(self, kb_uuid: str, file_id: str) -> None:
"""删除文件"""
runtime_kb = await self.ap.rag_mgr.get_knowledge_base_by_uuid(kb_uuid)
if runtime_kb is None:
raise Exception('Knowledge base not found')
await runtime_kb.delete_file(file_id)
async def delete_knowledge_base(self, kb_uuid: str) -> None:
"""删除知识库"""
await self.ap.rag_mgr.delete_knowledge_base(kb_uuid)
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_rag.KnowledgeBase).where(persistence_rag.KnowledgeBase.uuid == kb_uuid)
)
# delete files
files = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_rag.File).where(persistence_rag.File.kb_id == kb_uuid)
)
for file in files:
# delete chunks
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_rag.Chunk).where(persistence_rag.Chunk.file_id == file.uuid)
)
# delete file
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_rag.File).where(persistence_rag.File.uuid == file.uuid)
)

View File

@@ -7,20 +7,28 @@ from ....core import app
from ....entity.persistence import model as persistence_model
from ....entity.persistence import pipeline as persistence_pipeline
from ....provider.modelmgr import requester as model_requester
from ....provider import entities as llm_entities
from langbot_plugin.api.entities.builtin.provider import message as provider_message
class ModelsService:
class LLMModelsService:
ap: app.Application
def __init__(self, ap: app.Application) -> None:
self.ap = ap
async def get_llm_models(self) -> list[dict]:
async def get_llm_models(self, include_secret: bool = True) -> list[dict]:
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.LLMModel))
models = result.all()
return [self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model) for model in models]
masked_columns = []
if not include_secret:
masked_columns = ['api_keys']
return [
self.ap.persistence_mgr.serialize_model(persistence_model.LLMModel, model, masked_columns)
for model in models
]
async def create_llm_model(self, model_data: dict) -> str:
model_data['uuid'] = str(uuid.uuid4())
@@ -99,7 +107,93 @@ class ModelsService:
await runtime_llm_model.requester.invoke_llm(
query=None,
model=runtime_llm_model,
messages=[llm_entities.Message(role='user', content='Hello, world!')],
messages=[provider_message.Message(role='user', content='Hello, world!')],
funcs=[],
extra_args=model_data.get('extra_args', {}),
)
class EmbeddingModelsService:
ap: app.Application
def __init__(self, ap: app.Application) -> None:
self.ap = ap
async def get_embedding_models(self) -> list[dict]:
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_model.EmbeddingModel))
models = result.all()
return [self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model) for model in models]
async def create_embedding_model(self, model_data: dict) -> str:
model_data['uuid'] = str(uuid.uuid4())
await self.ap.persistence_mgr.execute_async(
sqlalchemy.insert(persistence_model.EmbeddingModel).values(**model_data)
)
embedding_model = await self.get_embedding_model(model_data['uuid'])
await self.ap.model_mgr.load_embedding_model(embedding_model)
return model_data['uuid']
async def get_embedding_model(self, model_uuid: str) -> dict | None:
result = await self.ap.persistence_mgr.execute_async(
sqlalchemy.select(persistence_model.EmbeddingModel).where(
persistence_model.EmbeddingModel.uuid == model_uuid
)
)
model = result.first()
if model is None:
return None
return self.ap.persistence_mgr.serialize_model(persistence_model.EmbeddingModel, model)
async def update_embedding_model(self, model_uuid: str, model_data: dict) -> None:
if 'uuid' in model_data:
del model_data['uuid']
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(persistence_model.EmbeddingModel)
.where(persistence_model.EmbeddingModel.uuid == model_uuid)
.values(**model_data)
)
await self.ap.model_mgr.remove_embedding_model(model_uuid)
embedding_model = await self.get_embedding_model(model_uuid)
await self.ap.model_mgr.load_embedding_model(embedding_model)
async def delete_embedding_model(self, model_uuid: str) -> None:
await self.ap.persistence_mgr.execute_async(
sqlalchemy.delete(persistence_model.EmbeddingModel).where(
persistence_model.EmbeddingModel.uuid == model_uuid
)
)
await self.ap.model_mgr.remove_embedding_model(model_uuid)
async def test_embedding_model(self, model_uuid: str, model_data: dict) -> None:
runtime_embedding_model: model_requester.RuntimeEmbeddingModel | None = None
if model_uuid != '_':
for model in self.ap.model_mgr.embedding_models:
if model.model_entity.uuid == model_uuid:
runtime_embedding_model = model
break
if runtime_embedding_model is None:
raise Exception('model not found')
else:
runtime_embedding_model = await self.ap.model_mgr.init_runtime_embedding_model(model_data)
await runtime_embedding_model.requester.invoke_embedding(
model=runtime_embedding_model,
input_text=['Hello, world!'],
extra_args={},
)

View File

@@ -38,9 +38,21 @@ class PipelineService:
self.ap.pipeline_config_meta_output.data,
]
async def get_pipelines(self) -> list[dict]:
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
async def get_pipelines(self, sort_by: str = 'created_at', sort_order: str = 'DESC') -> list[dict]:
query = sqlalchemy.select(persistence_pipeline.LegacyPipeline)
if sort_by == 'created_at':
if sort_order == 'DESC':
query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.desc())
else:
query = query.order_by(persistence_pipeline.LegacyPipeline.created_at.asc())
elif sort_by == 'updated_at':
if sort_order == 'DESC':
query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.desc())
else:
query = query.order_by(persistence_pipeline.LegacyPipeline.updated_at.asc())
result = await self.ap.persistence_mgr.execute_async(query)
pipelines = result.all()
return [
self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)

View File

@@ -82,3 +82,18 @@ class UserService:
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
)
async def change_password(self, user_email: str, current_password: str, new_password: str) -> None:
ph = argon2.PasswordHasher()
user_obj = await self.get_user_by_email(user_email)
if user_obj is None:
raise ValueError('User not found')
ph.verify(user_obj.password, current_password)
hashed_password = ph.hash(new_password)
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(user.User).where(user.User.user == user_email).values(password=hashed_password)
)

View File

@@ -2,9 +2,12 @@ from __future__ import annotations
import typing
from ..core import app, entities as core_entities
from . import entities, operator, errors
from ..core import app
from . import operator
from ..utils import importutil
import langbot_plugin.api.entities.builtin.provider.session as provider_session
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
# 引入所有算子以便注册
from . import operators
@@ -13,13 +16,11 @@ importutil.import_modules_in_pkg(operators)
class CommandManager:
"""命令管理器"""
ap: app.Application
cmd_list: list[operator.CommandOperator]
"""
运行时命令列表,扁平存储,各个对象包含对应的子节点引用
Runtime command list, flat storage, each object contains a reference to the corresponding child node
"""
def __init__(self, ap: app.Application):
@@ -55,43 +56,28 @@ class CommandManager:
async def _execute(
self,
context: entities.ExecuteContext,
context: command_context.ExecuteContext,
operator_list: list[operator.CommandOperator],
operator: operator.CommandOperator = None,
) -> typing.AsyncGenerator[entities.CommandReturn, None]:
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""执行命令"""
found = False
if len(context.crt_params) > 0: # 查找下一个参数是否对应此节点的某个子节点名
for oper in operator_list:
if (context.crt_params[0] == oper.name or context.crt_params[0] in oper.alias) and (
oper.parent_class is None or oper.parent_class == operator.__class__
):
found = True
command_list = await self.ap.plugin_connector.list_commands()
context.crt_command = context.crt_params[0]
context.crt_params = context.crt_params[1:]
async for ret in self._execute(context, oper.children, oper):
yield ret
break
if not found: # 如果下一个参数未在此节点的子节点中找到,则执行此节点或者报错
if operator is None:
yield entities.CommandReturn(error=errors.CommandNotFoundError(context.crt_params[0]))
else:
if operator.lowest_privilege > context.privilege:
yield entities.CommandReturn(error=errors.CommandPrivilegeError(operator.name))
else:
async for ret in operator.execute(context):
yield ret
for command in command_list:
if command.metadata.name == context.command:
async for ret in self.ap.plugin_connector.execute_command(context):
yield ret
break
else:
yield command_context.CommandReturn(error=command_errors.CommandNotFoundError(context.command))
async def execute(
self,
command_text: str,
query: core_entities.Query,
session: core_entities.Session,
) -> typing.AsyncGenerator[entities.CommandReturn, None]:
query: pipeline_query.Query,
session: provider_session.Session,
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""执行命令"""
privilege = 1
@@ -99,8 +85,8 @@ class CommandManager:
if f'{query.launcher_type.value}_{query.launcher_id}' in self.ap.instance_config.data['admins']:
privilege = 2
ctx = entities.ExecuteContext(
query=query,
ctx = command_context.ExecuteContext(
query_id=query.query_id,
session=session,
command_text=command_text,
command='',
@@ -110,5 +96,9 @@ class CommandManager:
privilege=privilege,
)
ctx.command = ctx.params[0]
ctx.shift()
async for ret in self._execute(ctx, self.cmd_list):
yield ret

View File

@@ -1,74 +0,0 @@
from __future__ import annotations
import typing
import pydantic.v1 as pydantic
from ..core import entities as core_entities
from . import errors
from ..platform.types import message as platform_message
class CommandReturn(pydantic.BaseModel):
"""命令返回值"""
text: typing.Optional[str] = None
"""文本
"""
image: typing.Optional[platform_message.Image] = None
"""弃用"""
image_url: typing.Optional[str] = None
"""图片链接
"""
error: typing.Optional[errors.CommandError] = None
"""错误
"""
class Config:
arbitrary_types_allowed = True
class ExecuteContext(pydantic.BaseModel):
"""单次命令执行上下文"""
query: core_entities.Query
"""本次消息的请求对象"""
session: core_entities.Session
"""本次消息所属的会话对象"""
command_text: str
"""命令完整文本"""
command: str
"""命令名称"""
crt_command: str
"""当前命令
多级命令中crt_command为当前命令command为根命令。
例如:!plugin on Webwlkr
处理到plugin时command为plugincrt_command为plugin
处理到on时command为plugincrt_command为on
"""
params: list[str]
"""命令参数
整个命令以空格分割后的参数列表
"""
crt_params: list[str]
"""当前命令参数
多级命令中crt_params为当前命令参数params为根命令参数。
例如:!plugin on Webwlkr
处理到plugin时params为['on', 'Webwlkr']crt_params为['on', 'Webwlkr']
处理到on时params为['on', 'Webwlkr']crt_params为['Webwlkr']
"""
privilege: int
"""发起人权限"""

View File

@@ -1,26 +0,0 @@
class CommandError(Exception):
def __init__(self, message: str = None):
self.message = message
def __str__(self):
return self.message
class CommandNotFoundError(CommandError):
def __init__(self, message: str = None):
super().__init__('未知命令: ' + message)
class CommandPrivilegeError(CommandError):
def __init__(self, message: str = None):
super().__init__('权限不足: ' + message)
class ParamNotEnoughError(CommandError):
def __init__(self, message: str = None):
super().__init__('参数不足: ' + message)
class CommandOperationError(CommandError):
def __init__(self, message: str = None):
super().__init__('操作失败: ' + message)

View File

@@ -4,7 +4,7 @@ import typing
import abc
from ..core import app
from . import entities
from langbot_plugin.api.entities.builtin.command import context as command_context
preregistered_operators: list[typing.Type[CommandOperator]] = []
@@ -95,16 +95,18 @@ class CommandOperator(metaclass=abc.ABCMeta):
pass
@abc.abstractmethod
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""实现此方法以执行命令
支持多次yield以返回多个结果。
例如:一个安装插件的命令,可能会有下载、解压、安装等多个步骤,每个步骤都可以返回一个结果。
Args:
context (entities.ExecuteContext): 命令执行上下文
context (command_context.ExecuteContext): 命令执行上下文
Yields:
entities.CommandReturn: 命令返回封装
command_context.CommandReturn: 命令返回封装
"""
pass

View File

@@ -2,14 +2,17 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='cmd', help='显示命令列表', usage='!cmd\n!cmd <命令名称>')
class CmdOperator(operator.CommandOperator):
"""命令列表"""
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""执行"""
if len(context.crt_params) == 0:
reply_str = '当前所有命令: \n\n'
@@ -20,7 +23,7 @@ class CmdOperator(operator.CommandOperator):
reply_str += '\n使用 !cmd <命令名称> 查看命令的详细帮助'
yield entities.CommandReturn(text=reply_str.strip())
yield command_context.CommandReturn(text=reply_str.strip())
else:
cmd_name = context.crt_params[0]
@@ -33,9 +36,9 @@ class CmdOperator(operator.CommandOperator):
break
if cmd is None:
yield entities.CommandReturn(error=errors.CommandNotFoundError(cmd_name))
yield command_context.CommandReturn(error=command_errors.CommandNotFoundError(cmd_name))
else:
reply_str = f'{cmd.name}: {cmd.help}\n\n'
reply_str += f'使用方法: \n{cmd.usage}'
yield entities.CommandReturn(text=reply_str.strip())
yield command_context.CommandReturn(text=reply_str.strip())

View File

@@ -2,23 +2,26 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='del', help='删除当前会话的历史记录', usage='!del <序号>\n!del all')
class DelOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if context.session.conversations:
delete_index = 0
if len(context.crt_params) > 0:
try:
delete_index = int(context.crt_params[0])
except Exception:
yield entities.CommandReturn(error=errors.CommandOperationError('索引必须是整数'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('索引必须是整数'))
return
if delete_index < 0 or delete_index >= len(context.session.conversations):
yield entities.CommandReturn(error=errors.CommandOperationError('索引超出范围'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('索引超出范围'))
return
# 倒序
@@ -29,15 +32,17 @@ class DelOperator(operator.CommandOperator):
del context.session.conversations[to_delete_index]
yield entities.CommandReturn(text=f'已删除对话: {delete_index}')
yield command_context.CommandReturn(text=f'已删除对话: {delete_index}')
else:
yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))
@operator.operator_class(name='all', help='删除此会话的所有历史记录', parent_class=DelOperator)
class DelAllOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
context.session.conversations = []
context.session.using_conversation = None
yield entities.CommandReturn(text='已删除所有对话')
yield command_context.CommandReturn(text='已删除所有对话')

View File

@@ -1,19 +1,20 @@
from __future__ import annotations
from typing import AsyncGenerator
from .. import operator, entities
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context
@operator.operator_class(name='func', help='查看所有已注册的内容函数', usage='!func')
class FuncOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> AsyncGenerator[command_context.CommandReturn, None]:
reply_str = '当前已启用的内容函数: \n\n'
index = 1
all_functions = await self.ap.tool_mgr.get_all_functions(
plugin_enabled=True,
)
all_functions = await self.ap.tool_mgr.get_all_tools()
for func in all_functions:
reply_str += '{}. {}:\n{}\n\n'.format(
@@ -23,4 +24,4 @@ class FuncOperator(operator.CommandOperator):
)
index += 1
yield entities.CommandReturn(text=reply_str)
yield command_context.CommandReturn(text=reply_str)

View File

@@ -2,14 +2,17 @@ from __future__ import annotations
import typing
from .. import operator, entities
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context
@operator.operator_class(name='help', help='显示帮助', usage='!help\n!help <命令名称>')
class HelpOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
help = 'LangBot - 大语言模型原生即时通信机器人平台\n链接https://langbot.app'
help += '\n发送命令 !cmd 可查看命令列表'
yield entities.CommandReturn(text=help)
yield command_context.CommandReturn(text=help)

View File

@@ -3,26 +3,31 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='last', help='切换到前一个对话', usage='!last')
class LastOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if context.session.conversations:
# 找到当前会话的上一个会话
for index in range(len(context.session.conversations) - 1, -1, -1):
if context.session.conversations[index] == context.session.using_conversation:
if index == 0:
yield entities.CommandReturn(error=errors.CommandOperationError('已经是第一个对话了'))
yield command_context.CommandReturn(
error=command_errors.CommandOperationError('已经是第一个对话了')
)
return
else:
context.session.using_conversation = context.session.conversations[index - 1]
time_str = context.session.using_conversation.create_time.strftime('%Y-%m-%d %H:%M:%S')
yield entities.CommandReturn(
yield command_context.CommandReturn(
text=f'已切换到上一个对话: {index} {time_str}: {context.session.using_conversation.messages[0].readable_str()}'
)
return
else:
yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))

View File

@@ -2,19 +2,22 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='list', help='列出此会话中的所有历史对话', usage='!list\n!list <页码>')
class ListOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
page = 0
if len(context.crt_params) > 0:
try:
page = int(context.crt_params[0] - 1)
except Exception:
yield entities.CommandReturn(error=errors.CommandOperationError('页码应为整数'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('页码应为整数'))
return
record_per_page = 10
@@ -45,4 +48,4 @@ class ListOperator(operator.CommandOperator):
else:
content += f'\n当前会话: {using_conv_index} {context.session.using_conversation.create_time.strftime("%Y-%m-%d %H:%M:%S")}: {context.session.using_conversation.messages[0].readable_str() if len(context.session.using_conversation.messages) > 0 else "无内容"}'
yield entities.CommandReturn(text=f'{page + 1} 页 (时间倒序):\n{content}')
yield command_context.CommandReturn(text=f'{page + 1} 页 (时间倒序):\n{content}')

View File

@@ -2,26 +2,31 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='next', help='切换到后一个对话', usage='!next')
class NextOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if context.session.conversations:
# 找到当前会话的下一个会话
for index in range(len(context.session.conversations)):
if context.session.conversations[index] == context.session.using_conversation:
if index == len(context.session.conversations) - 1:
yield entities.CommandReturn(error=errors.CommandOperationError('已经是最后一个对话了'))
yield command_context.CommandReturn(
error=command_errors.CommandOperationError('已经是最后一个对话了')
)
return
else:
context.session.using_conversation = context.session.conversations[index + 1]
time_str = context.session.using_conversation.create_time.strftime('%Y-%m-%d %H:%M:%S')
yield entities.CommandReturn(
yield command_context.CommandReturn(
text=f'已切换到后一个对话: {index} {time_str}: {context.session.using_conversation.messages[0].content}'
)
return
else:
yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))

View File

@@ -2,7 +2,8 @@ from __future__ import annotations
import typing
import traceback
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(
@@ -11,7 +12,9 @@ from .. import operator, entities, errors
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>',
)
class PluginOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
plugin_list = self.ap.plugin_mgr.plugins()
reply_str = '所有插件({}):\n'.format(len(plugin_list))
idx = 0
@@ -27,32 +30,36 @@ class PluginOperator(operator.CommandOperator):
idx += 1
yield entities.CommandReturn(text=reply_str)
yield command_context.CommandReturn(text=reply_str)
@operator.operator_class(name='get', help='安装插件', privilege=2, parent_class=PluginOperator)
class PluginGetOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if len(context.crt_params) == 0:
yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件仓库地址'))
yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件仓库地址'))
else:
repo = context.crt_params[0]
yield entities.CommandReturn(text='正在安装插件...')
yield command_context.CommandReturn(text='正在安装插件...')
try:
await self.ap.plugin_mgr.install_plugin(repo)
yield entities.CommandReturn(text='插件安装成功,请重启程序以加载插件')
yield command_context.CommandReturn(text='插件安装成功,请重启程序以加载插件')
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件安装失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件安装失败: ' + str(e)))
@operator.operator_class(name='update', help='更新插件', privilege=2, parent_class=PluginOperator)
class PluginUpdateOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if len(context.crt_params) == 0:
yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
else:
plugin_name = context.crt_params[0]
@@ -60,24 +67,26 @@ class PluginUpdateOperator(operator.CommandOperator):
plugin_container = self.ap.plugin_mgr.get_plugin_by_name(plugin_name)
if plugin_container is not None:
yield entities.CommandReturn(text='正在更新插件...')
yield command_context.CommandReturn(text='正在更新插件...')
await self.ap.plugin_mgr.update_plugin(plugin_name)
yield entities.CommandReturn(text='插件更新成功,请重启程序以加载插件')
yield command_context.CommandReturn(text='插件更新成功,请重启程序以加载插件')
else:
yield entities.CommandReturn(error=errors.CommandError('插件更新失败: 未找到插件'))
yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: 未找到插件'))
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
@operator.operator_class(name='all', help='更新所有插件', privilege=2, parent_class=PluginUpdateOperator)
class PluginUpdateAllOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
try:
plugins = [p.plugin_name for p in self.ap.plugin_mgr.plugins()]
if plugins:
yield entities.CommandReturn(text='正在更新插件...')
yield command_context.CommandReturn(text='正在更新插件...')
updated = []
try:
for plugin_name in plugins:
@@ -85,20 +94,22 @@ class PluginUpdateAllOperator(operator.CommandOperator):
updated.append(plugin_name)
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
yield entities.CommandReturn(text='已更新插件: {}'.format(', '.join(updated)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
yield command_context.CommandReturn(text='已更新插件: {}'.format(', '.join(updated)))
else:
yield entities.CommandReturn(text='没有可更新的插件')
yield command_context.CommandReturn(text='没有可更新的插件')
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件更新失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件更新失败: ' + str(e)))
@operator.operator_class(name='del', help='删除插件', privilege=2, parent_class=PluginOperator)
class PluginDelOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if len(context.crt_params) == 0:
yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
else:
plugin_name = context.crt_params[0]
@@ -106,51 +117,55 @@ class PluginDelOperator(operator.CommandOperator):
plugin_container = self.ap.plugin_mgr.get_plugin_by_name(plugin_name)
if plugin_container is not None:
yield entities.CommandReturn(text='正在删除插件...')
yield command_context.CommandReturn(text='正在删除插件...')
await self.ap.plugin_mgr.uninstall_plugin(plugin_name)
yield entities.CommandReturn(text='插件删除成功,请重启程序以加载插件')
yield command_context.CommandReturn(text='插件删除成功,请重启程序以加载插件')
else:
yield entities.CommandReturn(error=errors.CommandError('插件删除失败: 未找到插件'))
yield command_context.CommandReturn(error=command_errors.CommandError('插件删除失败: 未找到插件'))
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件删除失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件删除失败: ' + str(e)))
@operator.operator_class(name='on', help='启用插件', privilege=2, parent_class=PluginOperator)
class PluginEnableOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if len(context.crt_params) == 0:
yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
else:
plugin_name = context.crt_params[0]
try:
if await self.ap.plugin_mgr.update_plugin_switch(plugin_name, True):
yield entities.CommandReturn(text='已启用插件: {}'.format(plugin_name))
yield command_context.CommandReturn(text='已启用插件: {}'.format(plugin_name))
else:
yield entities.CommandReturn(
error=errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
yield command_context.CommandReturn(
error=command_errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
)
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件状态修改失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件状态修改失败: ' + str(e)))
@operator.operator_class(name='off', help='禁用插件', privilege=2, parent_class=PluginOperator)
class PluginDisableOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
if len(context.crt_params) == 0:
yield entities.CommandReturn(error=errors.ParamNotEnoughError('请提供插件名称'))
yield command_context.CommandReturn(error=command_errors.ParamNotEnoughError('请提供插件名称'))
else:
plugin_name = context.crt_params[0]
try:
if await self.ap.plugin_mgr.update_plugin_switch(plugin_name, False):
yield entities.CommandReturn(text='已禁用插件: {}'.format(plugin_name))
yield command_context.CommandReturn(text='已禁用插件: {}'.format(plugin_name))
else:
yield entities.CommandReturn(
error=errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
yield command_context.CommandReturn(
error=command_errors.CommandError('插件状态修改失败: 未找到插件 {}'.format(plugin_name))
)
except Exception as e:
traceback.print_exc()
yield entities.CommandReturn(error=errors.CommandError('插件状态修改失败: ' + str(e)))
yield command_context.CommandReturn(error=command_errors.CommandError('插件状态修改失败: ' + str(e)))

View File

@@ -2,19 +2,22 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='prompt', help='查看当前对话的前文', usage='!prompt')
class PromptOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""执行"""
if context.session.using_conversation is None:
yield entities.CommandReturn(error=errors.CommandOperationError('当前没有对话'))
yield command_context.CommandReturn(error=command_errors.CommandOperationError('当前没有对话'))
else:
reply_str = '当前对话所有内容:\n\n'
for msg in context.session.using_conversation.messages:
reply_str += f'{msg.role}: {msg.content}\n'
yield entities.CommandReturn(text=reply_str)
yield command_context.CommandReturn(text=reply_str)

View File

@@ -2,15 +2,18 @@ from __future__ import annotations
import typing
from .. import operator, entities, errors
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context, errors as command_errors
@operator.operator_class(name='resend', help='重发当前会话的最后一条消息', usage='!resend')
class ResendOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
# 回滚到最后一条用户message前
if context.session.using_conversation is None:
yield entities.CommandReturn(error=errors.CommandError('当前没有对话'))
yield command_context.CommandReturn(error=command_errors.CommandError('当前没有对话'))
else:
conv_msg = context.session.using_conversation.messages
@@ -23,4 +26,4 @@ class ResendOperator(operator.CommandOperator):
conv_msg.pop()
# 不重发了,提示用户已删除就行了
yield entities.CommandReturn(text='已删除最后一次请求记录')
yield command_context.CommandReturn(text='已删除最后一次请求记录')

View File

@@ -2,13 +2,16 @@ from __future__ import annotations
import typing
from .. import operator, entities
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context
@operator.operator_class(name='reset', help='重置当前会话', usage='!reset')
class ResetOperator(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
"""执行"""
context.session.using_conversation = None
yield entities.CommandReturn(text='已重置当前会话')
yield command_context.CommandReturn(text='已重置当前会话')

View File

@@ -1,11 +0,0 @@
from __future__ import annotations
import typing
from .. import operator, entities
@operator.operator_class(name='update', help='更新程序', usage='!update', privilege=2)
class UpdateCommand(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
yield entities.CommandReturn(text='不再支持通过命令更新,请查看 LangBot 文档。')

View File

@@ -2,12 +2,15 @@ from __future__ import annotations
import typing
from .. import operator, entities
from .. import operator
from langbot_plugin.api.entities.builtin.command import context as command_context
@operator.operator_class(name='version', help='显示版本信息', usage='!version')
class VersionCommand(operator.CommandOperator):
async def execute(self, context: entities.ExecuteContext) -> typing.AsyncGenerator[entities.CommandReturn, None]:
async def execute(
self, context: command_context.ExecuteContext
) -> typing.AsyncGenerator[command_context.CommandReturn, None]:
reply_str = f'当前版本: \n{self.ap.ver_mgr.get_current_version()}'
try:
@@ -16,4 +19,4 @@ class VersionCommand(operator.CommandOperator):
except Exception:
pass
yield entities.CommandReturn(text=reply_str.strip())
yield command_context.CommandReturn(text=reply_str.strip())

View File

@@ -3,7 +3,6 @@ from __future__ import annotations
import logging
import asyncio
import traceback
import sys
import os
from ..platform import botmgr as im_mgr
@@ -12,7 +11,7 @@ from ..provider.modelmgr import modelmgr as llm_model_mgr
from ..provider.tools import toolmgr as llm_tool_mgr
from ..config import manager as config_mgr
from ..command import cmdmgr
from ..plugin import manager as plugin_mgr
from ..plugin import connector as plugin_connector
from ..pipeline import pool
from ..pipeline import controller, pipelinemgr
from ..utils import version as version_mgr, proxy as proxy_mgr, announce as announce_mgr
@@ -22,11 +21,14 @@ from ..api.http.service import user as user_service
from ..api.http.service import model as model_service
from ..api.http.service import pipeline as pipeline_service
from ..api.http.service import bot as bot_service
from ..api.http.service import knowledge as knowledge_service
from ..discover import engine as discover_engine
from ..storage import mgr as storagemgr
from ..utils import logcache
from . import taskmgr
from . import entities as core_entities
from ..rag.knowledge import kbmgr as rag_mgr
from ..vector import mgr as vectordb_mgr
class Application:
@@ -47,6 +49,8 @@ class Application:
model_mgr: llm_model_mgr.ModelManager = None
rag_mgr: rag_mgr.RAGManager = None
# TODO move to pipeline
tool_mgr: llm_tool_mgr.ToolManager = None
@@ -75,7 +79,7 @@ class Application:
# =========================
plugin_mgr: plugin_mgr.PluginManager = None
plugin_connector: plugin_connector.PluginRuntimeConnector = None
query_pool: pool.QueryPool = None
@@ -93,6 +97,8 @@ class Application:
persistence_mgr: persistencemgr.PersistenceManager = None
vector_db_mgr: vectordb_mgr.VectorDBManager = None
http_ctrl: http_controller.HTTPController = None
log_cache: logcache.LogCache = None
@@ -103,12 +109,16 @@ class Application:
user_service: user_service.UserService = None
model_service: model_service.ModelsService = None
llm_model_service: model_service.LLMModelsService = None
embedding_models_service: model_service.EmbeddingModelsService = None
pipeline_service: pipeline_service.PipelineService = None
bot_service: bot_service.BotService = None
knowledge_service: knowledge_service.KnowledgeService = None
def __init__(self):
pass
@@ -117,7 +127,7 @@ class Application:
async def run(self):
try:
await self.plugin_mgr.initialize_plugins()
await self.plugin_connector.initialize_plugins()
# 后续可能会允许动态重启其他任务
# 故为了防止程序在非 Ctrl-C 情况下退出,这里创建一个不会结束的协程
@@ -143,6 +153,7 @@ class Application:
name='http-api-controller',
scopes=[core_entities.LifecycleControlScope.APPLICATION],
)
self.task_mgr.create_task(
never_ending(),
name='never-ending-task',
@@ -157,6 +168,9 @@ class Application:
self.logger.error(f'Application runtime fatal exception: {e}')
self.logger.debug(f'Traceback: {traceback.format_exc()}')
def dispose(self):
self.plugin_connector.dispose()
async def print_web_access_info(self):
"""Print access webui tips"""
@@ -183,59 +197,3 @@ class Application:
""".strip()
for line in tips.split('\n'):
self.logger.info(line)
async def reload(
self,
scope: core_entities.LifecycleControlScope,
):
match scope:
case core_entities.LifecycleControlScope.PLATFORM.value:
self.logger.info('Hot reload scope=' + scope)
await self.platform_mgr.shutdown()
self.platform_mgr = im_mgr.PlatformManager(self)
await self.platform_mgr.initialize()
self.task_mgr.create_task(
self.platform_mgr.run(),
name='platform-manager',
scopes=[
core_entities.LifecycleControlScope.APPLICATION,
core_entities.LifecycleControlScope.PLATFORM,
],
)
case core_entities.LifecycleControlScope.PLUGIN.value:
self.logger.info('Hot reload scope=' + scope)
await self.plugin_mgr.destroy_plugins()
# 删除 sys.module 中所有的 plugins/* 下的模块
for mod in list(sys.modules.keys()):
if mod.startswith('plugins.'):
del sys.modules[mod]
self.plugin_mgr = plugin_mgr.PluginManager(self)
await self.plugin_mgr.initialize()
await self.plugin_mgr.initialize_plugins()
await self.plugin_mgr.load_plugins()
await self.plugin_mgr.initialize_plugins()
case core_entities.LifecycleControlScope.PROVIDER.value:
self.logger.info('Hot reload scope=' + scope)
await self.tool_mgr.shutdown()
llm_model_mgr_inst = llm_model_mgr.ModelManager(self)
await llm_model_mgr_inst.initialize()
self.model_mgr = llm_model_mgr_inst
llm_session_mgr_inst = llm_session_mgr.SessionManager(self)
await llm_session_mgr_inst.initialize()
self.sess_mgr = llm_session_mgr_inst
llm_tool_mgr_inst = llm_tool_mgr.ToolManager(self)
await llm_tool_mgr_inst.initialize()
self.tool_mgr = llm_tool_mgr_inst
case _:
pass

View File

@@ -51,8 +51,8 @@ async def main(loop: asyncio.AbstractEventLoop):
import signal
def signal_handler(sig, frame):
app_inst.dispose()
print('[Signal] Program exit.')
# ap.shutdown()
os._exit(0)
signal.signal(signal.SIGINT, signal_handler)

View File

@@ -1,18 +1,6 @@
from __future__ import annotations
import enum
import typing
import datetime
import asyncio
import pydantic.v1 as pydantic
from ..provider import entities as llm_entities
from ..provider.modelmgr import requester
from ..provider.tools import entities as tools_entities
from ..platform import adapter as msadapter
from ..platform.types import message as platform_message
from ..platform.types import events as platform_events
class LifecycleControlScope(enum.Enum):
@@ -20,157 +8,3 @@ class LifecycleControlScope(enum.Enum):
PLATFORM = 'platform'
PLUGIN = 'plugin'
PROVIDER = 'provider'
class LauncherTypes(enum.Enum):
"""一个请求的发起者类型"""
PERSON = 'person'
"""私聊"""
GROUP = 'group'
"""群聊"""
class Query(pydantic.BaseModel):
"""一次请求的信息封装"""
query_id: int
"""请求ID添加进请求池时生成"""
launcher_type: LauncherTypes
"""会话类型platform处理阶段设置"""
launcher_id: typing.Union[int, str]
"""会话IDplatform处理阶段设置"""
sender_id: typing.Union[int, str]
"""发送者IDplatform处理阶段设置"""
message_event: platform_events.MessageEvent
"""事件platform收到的原始事件"""
message_chain: platform_message.MessageChain
"""消息链platform收到的原始消息链"""
bot_uuid: typing.Optional[str] = None
"""机器人UUID。"""
pipeline_uuid: typing.Optional[str] = None
"""流水线UUID。"""
pipeline_config: typing.Optional[dict[str, typing.Any]] = None
"""流水线配置,由 Pipeline 在运行开始时设置。"""
adapter: msadapter.MessagePlatformAdapter
"""消息平台适配器对象单个app中可能启用了多个消息平台适配器此对象表明发起此query的适配器"""
session: typing.Optional[Session] = None
"""会话对象,由前置处理器阶段设置"""
messages: typing.Optional[list[llm_entities.Message]] = []
"""历史消息列表,由前置处理器阶段设置"""
prompt: typing.Optional[llm_entities.Prompt] = None
"""情景预设内容,由前置处理器阶段设置"""
user_message: typing.Optional[llm_entities.Message] = None
"""此次请求的用户消息对象,由前置处理器阶段设置"""
variables: typing.Optional[dict[str, typing.Any]] = None
"""变量由前置处理器阶段设置。在prompt中嵌入或由 Runner 传递到 LLMOps 平台。"""
use_llm_model: typing.Optional[requester.RuntimeLLMModel] = None
"""使用的对话模型,由前置处理器阶段设置"""
use_funcs: typing.Optional[list[tools_entities.LLMFunction]] = None
"""使用的函数,由前置处理器阶段设置"""
resp_messages: (
typing.Optional[list[llm_entities.Message]] | typing.Optional[list[platform_message.MessageChain]]
) = []
"""由Process阶段生成的回复消息对象列表"""
resp_message_chain: typing.Optional[list[platform_message.MessageChain]] = None
"""回复消息链从resp_messages包装而得"""
# ======= 内部保留 =======
current_stage: typing.Optional['pkg.pipeline.pipelinemgr.StageInstContainer'] = None
"""当前所处阶段"""
class Config:
arbitrary_types_allowed = True
# ========== 插件可调用的 API请求 API ==========
def set_variable(self, key: str, value: typing.Any):
"""设置变量"""
if self.variables is None:
self.variables = {}
self.variables[key] = value
def get_variable(self, key: str) -> typing.Any:
"""获取变量"""
if self.variables is None:
return None
return self.variables.get(key)
def get_variables(self) -> dict[str, typing.Any]:
"""获取所有变量"""
if self.variables is None:
return {}
return self.variables
class Conversation(pydantic.BaseModel):
"""对话,包含于 Session 中,一个 Session 可以有多个历史 Conversation但只有一个当前使用的 Conversation"""
prompt: llm_entities.Prompt
messages: list[llm_entities.Message]
create_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
update_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
use_llm_model: typing.Optional[requester.RuntimeLLMModel] = None
use_funcs: typing.Optional[list[tools_entities.LLMFunction]]
pipeline_uuid: str
"""流水线UUID。"""
bot_uuid: str
"""机器人UUID。"""
uuid: typing.Optional[str] = None
"""该对话的 uuid在创建时不会自动生成。而是当使用 Dify API 等由外部管理对话信息的服务时,用于绑定外部的会话。具体如何使用,取决于 Runner。"""
class Config:
arbitrary_types_allowed = True
class Session(pydantic.BaseModel):
"""会话,一个 Session 对应一个 {launcher_type.value}_{launcher_id}"""
launcher_type: LauncherTypes
launcher_id: typing.Union[int, str]
sender_id: typing.Optional[typing.Union[int, str]] = 0
use_prompt_name: typing.Optional[str] = 'default'
using_conversation: typing.Optional[Conversation] = None
conversations: typing.Optional[list[Conversation]] = pydantic.Field(default_factory=list)
create_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
update_time: typing.Optional[datetime.datetime] = pydantic.Field(default_factory=datetime.datetime.now)
semaphore: typing.Optional[asyncio.Semaphore] = None
"""当前会话的信号量,用于限制并发"""
class Config:
arbitrary_types_allowed = True

View File

@@ -1,14 +1,16 @@
from __future__ import annotations
import asyncio
from .. import stage, app
from ...utils import version, proxy, announce
from ...pipeline import pool, controller, pipelinemgr
from ...plugin import manager as plugin_mgr
from ...plugin import connector as plugin_connector
from ...command import cmdmgr
from ...provider.session import sessionmgr as llm_session_mgr
from ...provider.modelmgr import modelmgr as llm_model_mgr
from ...provider.tools import toolmgr as llm_tool_mgr
from ...rag.knowledge import kbmgr as rag_mgr
from ...platform import botmgr as im_mgr
from ...persistence import mgr as persistencemgr
from ...api.http.controller import main as http_controller
@@ -16,9 +18,11 @@ from ...api.http.service import user as user_service
from ...api.http.service import model as model_service
from ...api.http.service import pipeline as pipeline_service
from ...api.http.service import bot as bot_service
from ...api.http.service import knowledge as knowledge_service
from ...discover import engine as discover_engine
from ...storage import mgr as storagemgr
from ...utils import logcache
from ...vector import mgr as vectordb_mgr
from .. import taskmgr
@@ -59,10 +63,13 @@ class BuildAppStage(stage.BootingStage):
ap.persistence_mgr = persistence_mgr_inst
await persistence_mgr_inst.initialize()
plugin_mgr_inst = plugin_mgr.PluginManager(ap)
await plugin_mgr_inst.initialize()
ap.plugin_mgr = plugin_mgr_inst
await plugin_mgr_inst.load_plugins()
async def runtime_disconnect_callback(connector: plugin_connector.PluginRuntimeConnector) -> None:
await asyncio.sleep(3)
await plugin_connector_inst.initialize()
plugin_connector_inst = plugin_connector.PluginRuntimeConnector(ap, runtime_disconnect_callback)
await plugin_connector_inst.initialize()
ap.plugin_connector = plugin_connector_inst
cmd_mgr_inst = cmdmgr.CommandManager(ap)
await cmd_mgr_inst.initialize()
@@ -88,6 +95,15 @@ class BuildAppStage(stage.BootingStage):
await pipeline_mgr.initialize()
ap.pipeline_mgr = pipeline_mgr
rag_mgr_inst = rag_mgr.RAGManager(ap)
await rag_mgr_inst.initialize()
ap.rag_mgr = rag_mgr_inst
# 初始化向量数据库管理器
vectordb_mgr_inst = vectordb_mgr.VectorDBManager(ap)
await vectordb_mgr_inst.initialize()
ap.vector_db_mgr = vectordb_mgr_inst
http_ctrl = http_controller.HTTPController(ap)
await http_ctrl.initialize()
ap.http_ctrl = http_ctrl
@@ -95,8 +111,11 @@ class BuildAppStage(stage.BootingStage):
user_service_inst = user_service.UserService(ap)
ap.user_service = user_service_inst
model_service_inst = model_service.ModelsService(ap)
ap.model_service = model_service_inst
llm_model_service_inst = model_service.LLMModelsService(ap)
ap.llm_model_service = llm_model_service_inst
embedding_models_service_inst = model_service.EmbeddingModelsService(ap)
ap.embedding_models_service = embedding_models_service_inst
pipeline_service_inst = pipeline_service.PipelineService(ap)
ap.pipeline_service = pipeline_service_inst
@@ -104,5 +123,8 @@ class BuildAppStage(stage.BootingStage):
bot_service_inst = bot_service.BotService(ap)
ap.bot_service = bot_service_inst
knowledge_service_inst = knowledge_service.KnowledgeService(ap)
ap.knowledge_service = knowledge_service_inst
ctrl = controller.Controller(ap)
ap.ctrl = ctrl

View File

@@ -0,0 +1,22 @@
import sqlalchemy
from .base import Base
class BinaryStorage(Base):
"""Current for plugin use only"""
__tablename__ = 'binary_storages'
unique_key = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True)
key = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
owner_type = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
owner = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
value = sqlalchemy.Column(sqlalchemy.LargeBinary, nullable=False)
created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
updated_at = sqlalchemy.Column(
sqlalchemy.DateTime,
nullable=False,
server_default=sqlalchemy.func.now(),
onupdate=sqlalchemy.func.now(),
)

View File

@@ -23,3 +23,24 @@ class LLMModel(Base):
server_default=sqlalchemy.func.now(),
onupdate=sqlalchemy.func.now(),
)
class EmbeddingModel(Base):
"""Embedding 模型"""
__tablename__ = 'embedding_models'
uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
name = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
description = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
requester = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
requester_config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
api_keys = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
extra_args = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default={})
created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
updated_at = sqlalchemy.Column(
sqlalchemy.DateTime,
nullable=False,
server_default=sqlalchemy.func.now(),
onupdate=sqlalchemy.func.now(),
)

View File

@@ -20,7 +20,6 @@ class LegacyPipeline(Base):
)
for_version = sqlalchemy.Column(sqlalchemy.String(255), nullable=False)
is_default = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=False)
stages = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
@@ -43,3 +42,4 @@ class PipelineRunRecord(Base):
started_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
finished_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False)
result = sqlalchemy.Column(sqlalchemy.JSON, nullable=False)
knowledge_base_uuid = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)

View File

@@ -13,6 +13,8 @@ class PluginSetting(Base):
enabled = sqlalchemy.Column(sqlalchemy.Boolean, nullable=False, default=True)
priority = sqlalchemy.Column(sqlalchemy.Integer, nullable=False, default=0)
config = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=dict)
install_source = sqlalchemy.Column(sqlalchemy.String(255), nullable=False, default='github')
install_info = sqlalchemy.Column(sqlalchemy.JSON, nullable=False, default=dict)
created_at = sqlalchemy.Column(sqlalchemy.DateTime, nullable=False, server_default=sqlalchemy.func.now())
updated_at = sqlalchemy.Column(
sqlalchemy.DateTime,

View File

@@ -0,0 +1,50 @@
import sqlalchemy
from .base import Base
# Base = declarative_base()
# DATABASE_URL = os.getenv('DATABASE_URL', 'sqlite:///./rag_knowledge.db')
# print("Using database URL:", DATABASE_URL)
# engine = create_engine(DATABASE_URL, connect_args={'check_same_thread': False})
# SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=engine)
# def create_db_and_tables():
# """Creates all database tables defined in the Base."""
# Base.metadata.create_all(bind=engine)
# print('Database tables created or already exist.')
class KnowledgeBase(Base):
__tablename__ = 'knowledge_bases'
uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
name = sqlalchemy.Column(sqlalchemy.String, index=True)
description = sqlalchemy.Column(sqlalchemy.Text)
created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())
embedding_model_uuid = sqlalchemy.Column(sqlalchemy.String, default='')
top_k = sqlalchemy.Column(sqlalchemy.Integer, default=5)
class File(Base):
__tablename__ = 'knowledge_base_files'
uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
kb_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
file_name = sqlalchemy.Column(sqlalchemy.String)
extension = sqlalchemy.Column(sqlalchemy.String)
created_at = sqlalchemy.Column(sqlalchemy.DateTime, default=sqlalchemy.func.now())
status = sqlalchemy.Column(sqlalchemy.String, default='pending') # pending, processing, completed, failed
class Chunk(Base):
__tablename__ = 'knowledge_base_chunks'
uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
file_id = sqlalchemy.Column(sqlalchemy.String(255), nullable=True)
text = sqlalchemy.Column(sqlalchemy.Text)
# class Vector(Base):
# __tablename__ = 'knowledge_base_vectors'
# uuid = sqlalchemy.Column(sqlalchemy.String(255), primary_key=True, unique=True)
# chunk_id = sqlalchemy.Column(sqlalchemy.String, nullable=True)
# embedding = sqlalchemy.Column(sqlalchemy.LargeBinary)

View File

@@ -0,0 +1,13 @@
from sqlalchemy import Column, Integer, ForeignKey, LargeBinary
from sqlalchemy.orm import declarative_base, relationship
Base = declarative_base()
class Vector(Base):
__tablename__ = 'vectors'
id = Column(Integer, primary_key=True, index=True)
chunk_id = Column(Integer, ForeignKey('chunks.id'), unique=True)
embedding = Column(LargeBinary) # Store embeddings as binary
chunk = relationship('Chunk', back_populates='vector')

View File

@@ -0,0 +1,13 @@
from __future__ import annotations
import pydantic
from typing import Any
class RetrieveResultEntry(pydantic.BaseModel):
id: str
metadata: dict[str, Any]
distance: float

View File

@@ -44,6 +44,38 @@ class PersistenceManager:
await self.create_tables()
# run migrations
database_version = await self.execute_async(
sqlalchemy.select(metadata.Metadata).where(metadata.Metadata.key == 'database_version')
)
database_version = int(database_version.fetchone()[1])
required_database_version = constants.required_database_version
if database_version < required_database_version:
migrations = migration.preregistered_db_migrations
migrations.sort(key=lambda x: x.number)
last_migration_number = database_version
for migration_cls in migrations:
migration_instance = migration_cls(self.ap)
if (
migration_instance.number > database_version
and migration_instance.number <= required_database_version
):
await migration_instance.upgrade()
await self.execute_async(
sqlalchemy.update(metadata.Metadata)
.where(metadata.Metadata.key == 'database_version')
.values({'value': str(migration_instance.number)})
)
last_migration_number = migration_instance.number
self.ap.logger.info(f'Migration {migration_instance.number} completed.')
self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
async def create_tables(self):
# create tables
async with self.get_db_engine().connect() as conn:
@@ -79,7 +111,7 @@ class PersistenceManager:
'stages': pipeline_service.default_stage_order,
'is_default': True,
'name': 'ChatPipeline',
'description': 'Default pipeline provided, your new bots will be automatically bound to this pipeline | 默认提供的流水线,您配置的机器人将自动绑定到此流水线',
'description': 'Default pipeline, new bots will be bound to this pipeline | 默认提供的流水线,您配置的机器人将自动绑定到此流水线',
'config': pipeline_config,
}
@@ -87,38 +119,6 @@ class PersistenceManager:
# =================================
# run migrations
database_version = await self.execute_async(
sqlalchemy.select(metadata.Metadata).where(metadata.Metadata.key == 'database_version')
)
database_version = int(database_version.fetchone()[1])
required_database_version = constants.required_database_version
if database_version < required_database_version:
migrations = migration.preregistered_db_migrations
migrations.sort(key=lambda x: x.number)
last_migration_number = database_version
for migration_cls in migrations:
migration_instance = migration_cls(self.ap)
if (
migration_instance.number > database_version
and migration_instance.number <= required_database_version
):
await migration_instance.upgrade()
await self.execute_async(
sqlalchemy.update(metadata.Metadata)
.where(metadata.Metadata.key == 'database_version')
.values({'value': str(migration_instance.number)})
)
last_migration_number = migration_instance.number
self.ap.logger.info(f'Migration {migration_instance.number} completed.')
self.ap.logger.info(f'Successfully upgraded database to version {last_migration_number}.')
async def execute_async(self, *args, **kwargs) -> sqlalchemy.engine.cursor.CursorResult:
async with self.get_db_engine().connect() as conn:
result = await conn.execute(*args, **kwargs)
@@ -128,10 +128,13 @@ class PersistenceManager:
def get_db_engine(self) -> sqlalchemy_asyncio.AsyncEngine:
return self.db.get_engine()
def serialize_model(self, model: typing.Type[sqlalchemy.Base], data: sqlalchemy.Base) -> dict:
def serialize_model(
self, model: typing.Type[sqlalchemy.Base], data: sqlalchemy.Base, masked_columns: list[str] = []
) -> dict:
return {
column.name: getattr(data, column.name)
if not isinstance(getattr(data, column.name), (datetime.datetime))
else getattr(data, column.name).isoformat()
for column in model.__table__.columns
if column.name not in masked_columns
}

View File

@@ -0,0 +1,20 @@
from .. import migration
@migration.migration_class(4)
class DBMigratePluginConfig(migration.DBMigration):
"""插件配置"""
async def upgrade(self):
"""升级"""
if 'plugin' not in self.ap.instance_config.data:
self.ap.instance_config.data['plugin'] = {
'runtime_ws_url': 'ws://localhost:5400/control/ws',
}
await self.ap.instance_config.dump_config()
async def downgrade(self):
"""降级"""
pass

View File

@@ -0,0 +1,38 @@
from .. import migration
import sqlalchemy
from ...entity.persistence import pipeline as persistence_pipeline
@migration.migration_class(4)
class DBMigrateRAGKBUUID(migration.DBMigration):
"""RAG知识库UUID"""
async def upgrade(self):
"""升级"""
# read all pipelines
pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
for pipeline in pipelines:
serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
config = serialized_pipeline['config']
if 'knowledge-base' not in config['ai']['local-agent']:
config['ai']['local-agent']['knowledge-base'] = ''
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(persistence_pipeline.LegacyPipeline)
.where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
.values(
{
'config': config,
'for_version': self.ap.ver_mgr.get_current_version(),
}
)
)
async def downgrade(self):
"""降级"""
pass

View File

@@ -0,0 +1,38 @@
from .. import migration
import sqlalchemy
from ...entity.persistence import pipeline as persistence_pipeline
@migration.migration_class(5)
class DBMigratePipelineRemoveCotConfig(migration.DBMigration):
"""Pipeline remove cot config"""
async def upgrade(self):
"""Upgrade"""
# read all pipelines
pipelines = await self.ap.persistence_mgr.execute_async(sqlalchemy.select(persistence_pipeline.LegacyPipeline))
for pipeline in pipelines:
serialized_pipeline = self.ap.persistence_mgr.serialize_model(persistence_pipeline.LegacyPipeline, pipeline)
config = serialized_pipeline['config']
if 'remove-think' not in config['output']['misc']:
config['output']['misc']['remove-think'] = False
await self.ap.persistence_mgr.execute_async(
sqlalchemy.update(persistence_pipeline.LegacyPipeline)
.where(persistence_pipeline.LegacyPipeline.uuid == serialized_pipeline['uuid'])
.values(
{
'config': config,
'for_version': self.ap.ver_mgr.get_current_version(),
}
)
)
async def downgrade(self):
"""Downgrade"""
pass

View File

@@ -0,0 +1,32 @@
import sqlalchemy
from .. import migration
@migration.migration_class(6)
class DBMigratePluginInstallSource(migration.DBMigration):
"""插件安装来源"""
async def upgrade(self):
"""升级"""
# 查询表结构获取所有列名(异步执行 SQL
result = await self.ap.persistence_mgr.execute_async(sqlalchemy.text('PRAGMA table_info(plugin_settings);'))
# fetchall() 是同步方法,无需 await
columns = [row[1] for row in result.fetchall()]
# 检查并添加 install_source 列
if 'install_source' not in columns:
await self.ap.persistence_mgr.execute_async(
sqlalchemy.text(
"ALTER TABLE plugin_settings ADD COLUMN install_source VARCHAR(255) NOT NULL DEFAULT 'github'"
)
)
# 检查并添加 install_info 列
if 'install_info' not in columns:
await self.ap.persistence_mgr.execute_async(
sqlalchemy.text("ALTER TABLE plugin_settings ADD COLUMN install_info JSON NOT NULL DEFAULT '{}'")
)
async def downgrade(self):
"""降级"""
pass

View File

@@ -1,7 +1,7 @@
from __future__ import annotations
from .. import stage, entities
from ...core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@stage.stage_class('BanSessionCheckStage')
@@ -14,7 +14,7 @@ class BanSessionCheckStage(stage.PipelineStage):
async def initialize(self, pipeline_config: dict):
pass
async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
found = False
mode = query.pipeline_config['trigger']['access-control']['mode']

View File

@@ -3,12 +3,11 @@ from __future__ import annotations
from ...core import app
from .. import stage, entities
from ...core import entities as core_entities
from . import filter as filter_model, entities as filter_entities
from ...provider import entities as llm_entities
from ...platform.types import message as platform_message
from langbot_plugin.api.entities.builtin.provider import message as provider_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
from ...utils import importutil
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from . import filters
importutil.import_modules_in_pkg(filters)
@@ -58,7 +57,7 @@ class ContentFilterStage(stage.PipelineStage):
async def _pre_process(
self,
message: str,
query: core_entities.Query,
query: pipeline_query.Query,
) -> entities.StageProcessResult:
"""请求llm前处理消息
只要有一个不通过就不放行,只放行 PASS 的消息
@@ -67,7 +66,7 @@ class ContentFilterStage(stage.PipelineStage):
if query.pipeline_config['safety']['content-filter']['scope'] == 'output-msg':
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
if not message.strip():
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
else:
for filter in self.filter_chain:
if filter_entities.EnableStage.PRE in filter.enable_stages:
@@ -86,14 +85,14 @@ class ContentFilterStage(stage.PipelineStage):
elif result.level == filter_entities.ResultLevel.PASS: # 传到下一个
message = result.replacement
query.message_chain = platform_message.MessageChain(platform_message.Plain(message))
query.message_chain = platform_message.MessageChain([platform_message.Plain(text=message)])
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
async def _post_process(
self,
message: str,
query: core_entities.Query,
query: pipeline_query.Query,
) -> entities.StageProcessResult:
"""请求llm后处理响应
只要是 PASS 或者 MASKED 的就通过此 filter将其 replacement 设置为message进入下一个 filter
@@ -123,7 +122,7 @@ class ContentFilterStage(stage.PipelineStage):
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
"""处理"""
if stage_inst_name == 'PreContentFilterStage':
contain_non_text = False
@@ -142,7 +141,7 @@ class ContentFilterStage(stage.PipelineStage):
return await self._pre_process(str(query.message_chain).strip(), query)
elif stage_inst_name == 'PostContentFilterStage':
# 仅处理 query.resp_messages[-1].content 是 str 的情况
if isinstance(query.resp_messages[-1], llm_entities.Message) and isinstance(
if isinstance(query.resp_messages[-1], provider_message.Message) and isinstance(
query.resp_messages[-1].content, str
):
return await self._post_process(query.resp_messages[-1].content, query)

View File

@@ -1,6 +1,6 @@
import enum
import pydantic.v1 as pydantic
import pydantic
class ResultLevel(enum.Enum):

View File

@@ -3,9 +3,9 @@ from __future__ import annotations
import abc
import typing
from ...core import app, entities as core_entities
from ...core import app
from . import entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
preregistered_filters: list[typing.Type[ContentFilter]] = []
@@ -60,8 +60,8 @@ class ContentFilter(metaclass=abc.ABCMeta):
pass
@abc.abstractmethod
async def process(self, query: core_entities.Query, message: str = None, image_url=None) -> entities.FilterResult:
"""Process message
async def process(self, query: pipeline_query.Query, message: str = None, image_url=None) -> entities.FilterResult:
"""处理消息
It is divided into two stages, depending on the value of enable_stages.
For content filters, you do not need to consider the stage of the message, you only need to check the message content.

View File

@@ -4,8 +4,7 @@ import aiohttp
from .. import entities
from .. import filter as filter_model
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
BAIDU_EXAMINE_URL = 'https://aip.baidubce.com/rest/2.0/solution/v1/text_censor/v2/user_defined?access_token={}'
BAIDU_EXAMINE_TOKEN_URL = 'https://aip.baidubce.com/oauth/2.0/token'
@@ -27,7 +26,7 @@ class BaiduCloudExamine(filter_model.ContentFilter):
) as resp:
return (await resp.json())['access_token']
async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
async with aiohttp.ClientSession() as session:
async with session.post(
BAIDU_EXAMINE_URL.format(await self._get_token()),

View File

@@ -3,7 +3,7 @@ import re
from .. import filter as filter_model
from .. import entities
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@filter_model.filter_class('ban-word-filter')
@@ -13,7 +13,7 @@ class BanWordFilter(filter_model.ContentFilter):
async def initialize(self):
pass
async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
found = False
for word in self.ap.sensitive_meta.data['words']:

View File

@@ -3,7 +3,7 @@ import re
from .. import entities
from .. import filter as filter_model
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@filter_model.filter_class('content-ignore')
@@ -16,7 +16,7 @@ class ContentIgnore(filter_model.ContentFilter):
entities.EnableStage.PRE,
]
async def process(self, query: core_entities.Query, message: str) -> entities.FilterResult:
async def process(self, query: pipeline_query.Query, message: str) -> entities.FilterResult:
if 'prefix' in query.pipeline_config['trigger']['ignore-rules']:
for rule in query.pipeline_config['trigger']['ignore-rules']['prefix']:
if message.startswith(rule):

View File

@@ -3,7 +3,10 @@ from __future__ import annotations
import asyncio
import traceback
from ..core import app, entities
from ..core import app
from ..core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
class Controller:
@@ -22,19 +25,19 @@ class Controller:
"""事件处理循环"""
try:
while True:
selected_query: entities.Query = None
selected_query: pipeline_query.Query = None
# 取请求
async with self.ap.query_pool:
queries: list[entities.Query] = self.ap.query_pool.queries
queries: list[pipeline_query.Query] = self.ap.query_pool.queries
for query in queries:
session = await self.ap.sess_mgr.get_session(query)
self.ap.logger.debug(f'Checking query {query} session {session}')
if not session.semaphore.locked():
if not session._semaphore.locked():
selected_query = query
await session.semaphore.acquire()
await session._semaphore.acquire()
break
@@ -46,7 +49,7 @@ class Controller:
if selected_query:
async def _process_query(selected_query: entities.Query):
async def _process_query(selected_query: pipeline_query.Query):
async with self.semaphore: # 总并发上限
# find pipeline
# Here firstly find the bot, then find the pipeline, in case the bot adapter's config is not the latest one.
@@ -59,7 +62,7 @@ class Controller:
await pipeline.run(selected_query)
async with self.ap.query_pool:
(await self.ap.sess_mgr.get_session(selected_query)).semaphore.release()
(await self.ap.sess_mgr.get_session(selected_query))._semaphore.release()
# 通知其他协程,有新的请求可以处理了
self.ap.query_pool.condition.notify_all()
@@ -68,8 +71,8 @@ class Controller:
kind='query',
name=f'query-{selected_query.query_id}',
scopes=[
entities.LifecycleControlScope.APPLICATION,
entities.LifecycleControlScope.PLATFORM,
core_entities.LifecycleControlScope.APPLICATION,
core_entities.LifecycleControlScope.PLATFORM,
],
)

View File

@@ -3,10 +3,10 @@ from __future__ import annotations
import enum
import typing
import pydantic.v1 as pydantic
from ..platform.types import message as platform_message
import pydantic
from ..core import entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.builtin.platform.message as platform_message
class ResultType(enum.Enum):
@@ -20,7 +20,7 @@ class ResultType(enum.Enum):
class StageProcessResult(pydantic.BaseModel):
result_type: ResultType
new_query: entities.Query
new_query: pipeline_query.Query
user_notice: typing.Optional[
typing.Union[

View File

@@ -5,10 +5,9 @@ import traceback
from . import strategy
from .. import stage, entities
from ...core import entities as core_entities
from ...platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
from ...utils import importutil
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from . import strategies
importutil.import_modules_in_pkg(strategies)
@@ -67,8 +66,8 @@ class LongTextProcessStage(stage.PipelineStage):
await self.strategy_impl.initialize()
async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
# Check if it contains non-Plain components
async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
# 检查是否包含非 Plain 组件
contains_non_plain = False
for msg in query.resp_message_chain[-1]:

View File

@@ -3,9 +3,9 @@ from __future__ import annotations
from .. import strategy as strategy_model
from ....core import entities as core_entities
from ....platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.builtin.platform.message as platform_message
ForwardMessageDiaplay = platform_message.ForwardMessageDiaplay
Forward = platform_message.Forward
@@ -13,7 +13,7 @@ Forward = platform_message.Forward
@strategy_model.strategy_class('forward')
class ForwardComponentStrategy(strategy_model.LongTextStrategy):
async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
display = ForwardMessageDiaplay(
title='Group chat history',
brief='[Chat history]',

View File

@@ -8,10 +8,10 @@ import re
from PIL import Image, ImageDraw, ImageFont
import functools
from ....platform.types import message as platform_message
from .. import strategy as strategy_model
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.builtin.platform.message as platform_message
@strategy_model.strategy_class('image')
@@ -27,7 +27,7 @@ class Text2ImageStrategy(strategy_model.LongTextStrategy):
encoding='utf-8',
)
async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
img_path = self.text_to_image(
text_str=message,
save_as='temp/{}.png'.format(int(time.time())),
@@ -131,7 +131,7 @@ class Text2ImageStrategy(strategy_model.LongTextStrategy):
text_str: str,
save_as='temp.png',
width=800,
query: core_entities.Query = None,
query: pipeline_query.Query = None,
):
text_str = text_str.replace('\t', ' ')

View File

@@ -4,8 +4,9 @@ import typing
from ...core import app
from ...core import entities as core_entities
from ...platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
preregistered_strategies: list[typing.Type[LongTextStrategy]] = []
@@ -49,8 +50,8 @@ class LongTextStrategy(metaclass=abc.ABCMeta):
pass
@abc.abstractmethod
async def process(self, message: str, query: core_entities.Query) -> list[platform_message.MessageComponent]:
"""Process long text
async def process(self, message: str, query: pipeline_query.Query) -> list[platform_message.MessageComponent]:
"""处理长文本
If the text length exceeds the threshold, this method will be called.

View File

@@ -1,10 +1,9 @@
from __future__ import annotations
from .. import stage, entities
from ...core import entities as core_entities
from . import truncator
from ...utils import importutil
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from . import truncators
importutil.import_modules_in_pkg(truncators)
@@ -29,8 +28,8 @@ class ConversationMessageTruncator(stage.PipelineStage):
else:
raise ValueError(f'Unknown truncator: {use_method}')
async def process(self, query: core_entities.Query, stage_inst_name: str) -> entities.StageProcessResult:
"""Process"""
async def process(self, query: pipeline_query.Query, stage_inst_name: str) -> entities.StageProcessResult:
"""处理"""
query = await self.trun.truncate(query)
return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

View File

@@ -3,8 +3,8 @@ from __future__ import annotations
import typing
import abc
from ...core import entities as core_entities, app
from ...core import app
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
preregistered_truncators: list[typing.Type[Truncator]] = []
@@ -47,7 +47,7 @@ class Truncator(abc.ABC):
pass
@abc.abstractmethod
async def truncate(self, query: core_entities.Query) -> core_entities.Query:
async def truncate(self, query: pipeline_query.Query) -> pipeline_query.Query:
"""截断
一般只需要操作query.messages也可以扩展操作query.prompt, query.user_message。

View File

@@ -1,15 +1,15 @@
from __future__ import annotations
from .. import truncator
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@truncator.truncator_class('round')
class RoundTruncator(truncator.Truncator):
"""Truncate the conversation message chain to adapt to the LLM message length limit."""
async def truncate(self, query: core_entities.Query) -> core_entities.Query:
"""Truncate"""
async def truncate(self, query: pipeline_query.Query) -> pipeline_query.Query:
"""截断"""
max_round = query.pipeline_config['ai']['local-agent']['max-round']
temp_messages = []

View File

@@ -5,14 +5,18 @@ import traceback
import sqlalchemy
from ..core import app, entities
from ..core import app
from . import entities as pipeline_entities
from ..entity.persistence import pipeline as persistence_pipeline
from . import stage
from ..platform.types import message as platform_message, events as platform_events
from ..plugin import events
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.platform.events as platform_events
import langbot_plugin.api.entities.events as events
from ..utils import importutil
import langbot_plugin.api.entities.builtin.provider.session as provider_session
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from . import (
resprule,
bansess,
@@ -75,17 +79,17 @@ class RuntimePipeline:
self.pipeline_entity = pipeline_entity
self.stage_containers = stage_containers
async def run(self, query: entities.Query):
async def run(self, query: pipeline_query.Query):
query.pipeline_config = self.pipeline_entity.config
await self.process_query(query)
async def _check_output(self, query: entities.Query, result: pipeline_entities.StageProcessResult):
async def _check_output(self, query: pipeline_query.Query, result: pipeline_entities.StageProcessResult):
"""检查输出"""
if result.user_notice:
# 处理str类型
if isinstance(result.user_notice, str):
result.user_notice = platform_message.MessageChain(platform_message.Plain(result.user_notice))
result.user_notice = platform_message.MessageChain([platform_message.Plain(text=result.user_notice)])
elif isinstance(result.user_notice, list):
result.user_notice = platform_message.MessageChain(*result.user_notice)
@@ -93,12 +97,20 @@ class RuntimePipeline:
query.message_event, platform_events.GroupMessage
):
result.user_notice.insert(0, platform_message.At(query.message_event.sender.id))
await query.adapter.reply_message(
message_source=query.message_event,
message=result.user_notice,
quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
)
if await query.adapter.is_stream_output_supported():
await query.adapter.reply_message_chunk(
message_source=query.message_event,
bot_message=query.resp_messages[-1],
message=result.user_notice,
quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
is_final=[msg.is_final for msg in query.resp_messages][0],
)
else:
await query.adapter.reply_message(
message_source=query.message_event,
message=result.user_notice,
quote_origin=query.pipeline_config['output']['misc']['quote-origin'],
)
if result.debug_notice:
self.ap.logger.debug(result.debug_notice)
if result.console_notice:
@@ -109,7 +121,7 @@ class RuntimePipeline:
async def _execute_from_stage(
self,
stage_index: int,
query: entities.Query,
query: pipeline_query.Query,
):
"""从指定阶段开始执行,实现了责任链模式和基于生成器的阶段分叉功能。
@@ -136,7 +148,7 @@ class RuntimePipeline:
while i < len(self.stage_containers):
stage_container = self.stage_containers[i]
query.current_stage = stage_container # 标记到 Query 对象里
query.current_stage_name = stage_container.inst_name # 标记到 Query 对象里
result = stage_container.inst.process(query, stage_container.inst_name)
@@ -144,23 +156,27 @@ class RuntimePipeline:
result = await result
if isinstance(result, pipeline_entities.StageProcessResult): # 直接返回结果
self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {result}')
self.ap.logger.debug(
f'Stage {stage_container.inst_name} processed query {query.query_id} res {result.result_type}'
)
await self._check_output(query, result)
if result.result_type == pipeline_entities.ResultType.INTERRUPT:
self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
break
elif result.result_type == pipeline_entities.ResultType.CONTINUE:
query = result.new_query
elif isinstance(result, typing.AsyncGenerator): # 生成器
self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} gen')
self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query.query_id} gen')
async for sub_result in result:
self.ap.logger.debug(f'Stage {stage_container.inst_name} processed query {query} res {sub_result}')
self.ap.logger.debug(
f'Stage {stage_container.inst_name} processed query {query.query_id} res {sub_result.result_type}'
)
await self._check_output(query, sub_result)
if sub_result.result_type == pipeline_entities.ResultType.INTERRUPT:
self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query}')
self.ap.logger.debug(f'Stage {stage_container.inst_name} interrupted query {query.query_id}')
break
elif sub_result.result_type == pipeline_entities.ResultType.CONTINUE:
query = sub_result.new_query
@@ -169,38 +185,39 @@ class RuntimePipeline:
i += 1
async def process_query(self, query: entities.Query):
async def process_query(self, query: pipeline_query.Query):
"""处理请求"""
try:
# ======== 触发 MessageReceived 事件 ========
event_type = (
events.PersonMessageReceived
if query.launcher_type == entities.LauncherTypes.PERSON
if query.launcher_type == provider_session.LauncherTypes.PERSON
else events.GroupMessageReceived
)
event_ctx = await self.ap.plugin_mgr.emit_event(
event=event_type(
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
message_chain=query.message_chain,
query=query,
)
event_obj = event_type(
query=query,
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
message_chain=query.message_chain,
)
event_ctx = await self.ap.plugin_connector.emit_event(event_obj)
if event_ctx.is_prevented_default():
return
self.ap.logger.debug(f'Processing query {query}')
self.ap.logger.debug(f'Processing query {query.query_id}')
await self._execute_from_stage(0, query)
except Exception as e:
inst_name = query.current_stage.inst_name if query.current_stage else 'unknown'
inst_name = query.current_stage_name if query.current_stage_name else 'unknown'
self.ap.logger.error(f'处理请求时出错 query_id={query.query_id} stage={inst_name} : {e}')
self.ap.logger.error(f'Traceback: {traceback.format_exc()}')
finally:
self.ap.logger.debug(f'Query {query} processed')
self.ap.logger.debug(f'Query {query.query_id} processed')
del self.ap.query_pool.cached_queries[query.query_id]
class PipelineManager:

View File

@@ -3,10 +3,11 @@ from __future__ import annotations
import asyncio
import typing
from ..core import entities
from ..platform import adapter as msadapter
from ..platform.types import message as platform_message
from ..platform.types import events as platform_events
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.platform.events as platform_events
import langbot_plugin.api.entities.builtin.provider.session as provider_session
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.definition.abstract.platform.adapter as abstract_platform_adapter
class QueryPool:
@@ -16,7 +17,10 @@ class QueryPool:
pool_lock: asyncio.Lock
queries: list[entities.Query]
queries: list[pipeline_query.Query]
cached_queries: dict[int, pipeline_query.Query]
"""Cached queries, used for plugin backward api call, will be removed after the query completely processed"""
condition: asyncio.Condition
@@ -24,34 +28,38 @@ class QueryPool:
self.query_id_counter = 0
self.pool_lock = asyncio.Lock()
self.queries = []
self.cached_queries = {}
self.condition = asyncio.Condition(self.pool_lock)
async def add_query(
self,
bot_uuid: str,
launcher_type: entities.LauncherTypes,
launcher_type: provider_session.LauncherTypes,
launcher_id: typing.Union[int, str],
sender_id: typing.Union[int, str],
message_event: platform_events.MessageEvent,
message_chain: platform_message.MessageChain,
adapter: msadapter.MessagePlatformAdapter,
adapter: abstract_platform_adapter.AbstractMessagePlatformAdapter,
pipeline_uuid: typing.Optional[str] = None,
) -> entities.Query:
) -> pipeline_query.Query:
async with self.condition:
query = entities.Query(
query_id = self.query_id_counter
query = pipeline_query.Query(
bot_uuid=bot_uuid,
query_id=self.query_id_counter,
query_id=query_id,
launcher_type=launcher_type,
launcher_id=launcher_id,
sender_id=sender_id,
message_event=message_event,
message_chain=message_chain,
variables={},
resp_messages=[],
resp_message_chain=[],
adapter=adapter,
pipeline_uuid=pipeline_uuid,
)
self.queries.append(query)
self.cached_queries[query_id] = query
self.query_id_counter += 1
self.condition.notify_all()

View File

@@ -3,10 +3,10 @@ from __future__ import annotations
import datetime
from .. import stage, entities
from ...core import entities as core_entities
from ...provider import entities as llm_entities
from ...plugin import events
from ...platform.types import message as platform_message
from langbot_plugin.api.entities.builtin.provider import message as provider_message
import langbot_plugin.api.entities.events as events
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@stage.stage_class('PreProcessor')
@@ -26,7 +26,7 @@ class PreProcessor(stage.PipelineStage):
async def process(
self,
query: core_entities.Query,
query: pipeline_query.Query,
stage_inst_name: str,
) -> entities.StageProcessResult:
"""Process"""
@@ -49,77 +49,73 @@ class PreProcessor(stage.PipelineStage):
query.bot_uuid,
)
conversation.use_llm_model = llm_model
# Set query
# 设置query
query.session = session
query.prompt = conversation.prompt.copy()
query.messages = conversation.messages.copy()
query.use_llm_model = llm_model
query.use_llm_model_uuid = llm_model.model_entity.uuid
if selected_runner == 'local-agent':
query.use_funcs = (
conversation.use_funcs if query.use_llm_model.model_entity.abilities.__contains__('func_call') else None
)
query.use_funcs = []
query.variables = {
if llm_model.model_entity.abilities.__contains__('func_call'):
query.use_funcs = await self.ap.tool_mgr.get_all_tools()
variables = {
'session_id': f'{query.session.launcher_type.value}_{query.session.launcher_id}',
'conversation_id': conversation.uuid,
'msg_create_time': (
int(query.message_event.time) if query.message_event.time else int(datetime.datetime.now().timestamp())
),
}
query.variables.update(variables)
# Check if this model supports vision, if not, remove all images
# TODO this checking should be performed in runner, and in this stage, the image should be reserved
if selected_runner == 'local-agent' and not query.use_llm_model.model_entity.abilities.__contains__('vision'):
if selected_runner == 'local-agent' and not llm_model.model_entity.abilities.__contains__('vision'):
for msg in query.messages:
if isinstance(msg.content, list):
for me in msg.content:
if me.type == 'image_url':
msg.content.remove(me)
content_list = []
content_list: list[provider_message.ContentElement] = []
plain_text = ''
qoute_msg = query.pipeline_config['trigger'].get('misc', '').get('combine-quote-message')
for me in query.message_chain:
if isinstance(me, platform_message.Plain):
content_list.append(llm_entities.ContentElement.from_text(me.text))
content_list.append(provider_message.ContentElement.from_text(me.text))
plain_text += me.text
elif isinstance(me, platform_message.Image):
if selected_runner != 'local-agent' or query.use_llm_model.model_entity.abilities.__contains__(
'vision'
):
if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
if me.base64 is not None:
content_list.append(llm_entities.ContentElement.from_image_base64(me.base64))
content_list.append(provider_message.ContentElement.from_image_base64(me.base64))
elif isinstance(me, platform_message.Quote) and qoute_msg:
for msg in me.origin:
if isinstance(msg, platform_message.Plain):
content_list.append(llm_entities.ContentElement.from_text(msg.text))
content_list.append(provider_message.ContentElement.from_text(msg.text))
elif isinstance(msg, platform_message.Image):
if selected_runner != 'local-agent' or query.use_llm_model.model_entity.abilities.__contains__(
'vision'
):
if selected_runner != 'local-agent' or llm_model.model_entity.abilities.__contains__('vision'):
if msg.base64 is not None:
content_list.append(llm_entities.ContentElement.from_image_base64(msg.base64))
content_list.append(provider_message.ContentElement.from_image_base64(msg.base64))
query.variables['user_message_text'] = plain_text
query.user_message = llm_entities.Message(role='user', content=content_list)
# =========== Trigger event PromptPreProcessing
query.user_message = provider_message.Message(role='user', content=content_list)
# =========== 触发事件 PromptPreProcessing
event_ctx = await self.ap.plugin_mgr.emit_event(
event=events.PromptPreProcessing(
session_name=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
default_prompt=query.prompt.messages,
prompt=query.messages,
query=query,
)
event = events.PromptPreProcessing(
session_name=f'{query.session.launcher_type.value}_{query.session.launcher_id}',
default_prompt=query.prompt.messages,
prompt=query.messages,
query=query,
)
event_ctx = await self.ap.plugin_connector.emit_event(event)
query.prompt.messages = event_ctx.event.default_prompt
query.messages = event_ctx.event.prompt

View File

@@ -3,8 +3,8 @@ from __future__ import annotations
import abc
from ...core import app
from ...core import entities as core_entities
from .. import entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
class MessageHandler(metaclass=abc.ABCMeta):
@@ -19,7 +19,7 @@ class MessageHandler(metaclass=abc.ABCMeta):
@abc.abstractmethod
async def handle(
self,
query: core_entities.Query,
query: pipeline_query.Query,
) -> entities.StageProcessResult:
raise NotImplementedError

View File

@@ -1,18 +1,21 @@
from __future__ import annotations
import uuid
import typing
import traceback
from .. import handler
from ... import entities
from ....core import entities as core_entities
from ....provider import runner as runner_module
from ....plugin import events
from ....platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.events as events
from ....utils import importutil
from ....provider import runners
import langbot_plugin.api.entities.builtin.provider.session as provider_session
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
importutil.import_modules_in_pkg(runners)
@@ -20,33 +23,32 @@ importutil.import_modules_in_pkg(runners)
class ChatMessageHandler(handler.MessageHandler):
async def handle(
self,
query: core_entities.Query,
query: pipeline_query.Query,
) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
"""Process"""
# Call API
# generator
"""处理"""
# API
# 生成器
# Trigger plugin event
# 触发插件事件
event_class = (
events.PersonNormalMessageReceived
if query.launcher_type == core_entities.LauncherTypes.PERSON
if query.launcher_type == provider_session.LauncherTypes.PERSON
else events.GroupNormalMessageReceived
)
event_ctx = await self.ap.plugin_mgr.emit_event(
event=event_class(
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
text_message=str(query.message_chain),
query=query,
)
event = event_class(
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
text_message=str(query.message_chain),
query=query,
)
event_ctx = await self.ap.plugin_connector.emit_event(event)
if event_ctx.is_prevented_default():
if event_ctx.event.reply is not None:
mc = platform_message.MessageChain(event_ctx.event.reply)
query.resp_messages.append(mc)
yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
@@ -54,10 +56,14 @@ class ChatMessageHandler(handler.MessageHandler):
yield entities.StageProcessResult(result_type=entities.ResultType.INTERRUPT, new_query=query)
else:
if event_ctx.event.alter is not None:
# if isinstance(event_ctx.event, str): # Currently not considering multi-modal alter
# if isinstance(event_ctx.event, str): # 现在暂时不考虑多模态alter
query.user_message.content = event_ctx.event.alter
text_length = 0
try:
is_stream = await query.adapter.is_stream_output_supported()
except AttributeError:
is_stream = False
try:
for r in runner_module.preregistered_runners:
@@ -65,22 +71,42 @@ class ChatMessageHandler(handler.MessageHandler):
runner = r(self.ap, query.pipeline_config)
break
else:
raise ValueError(f'Request runner not found: {query.pipeline_config["ai"]["runner"]["runner"]}')
raise ValueError(f'未找到请求运行器: {query.pipeline_config["ai"]["runner"]["runner"]}')
if is_stream:
resp_message_id = uuid.uuid4()
await query.adapter.create_message_card(str(resp_message_id), query.message_event)
async for result in runner.run(query):
result.resp_message_id = str(resp_message_id)
if query.resp_messages:
query.resp_messages.pop()
if query.resp_message_chain:
query.resp_message_chain.pop()
async for result in runner.run(query):
query.resp_messages.append(result)
query.resp_messages.append(result)
self.ap.logger.info(f'对话({query.query_id})流式响应: {self.cut_str(result.readable_str())}')
self.ap.logger.info(f'Response({query.query_id}): {self.cut_str(result.readable_str())}')
if result.content is not None:
text_length += len(result.content)
if result.content is not None:
text_length += len(result.content)
yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
else:
async for result in runner.run(query):
query.resp_messages.append(result)
self.ap.logger.info(f'对话({query.query_id})响应: {self.cut_str(result.readable_str())}')
if result.content is not None:
text_length += len(result.content)
yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
query.session.using_conversation.messages.append(query.user_message)
query.session.using_conversation.messages.extend(query.resp_messages)
except Exception as e:
self.ap.logger.error(f'Request failed({query.query_id}): {type(e).__name__} {str(e)}')
self.ap.logger.error(f'对话({query.query_id})请求失败: {type(e).__name__} {str(e)}')
traceback.print_exc()
hide_exception_info = query.pipeline_config['output']['misc']['hide-exception']

View File

@@ -4,16 +4,17 @@ import typing
from .. import handler
from ... import entities
from ....core import entities as core_entities
from ....provider import entities as llm_entities
from ....plugin import events
from ....platform.types import message as platform_message
import langbot_plugin.api.entities.builtin.provider.message as provider_message
import langbot_plugin.api.entities.builtin.platform.message as platform_message
import langbot_plugin.api.entities.builtin.provider.session as provider_session
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
import langbot_plugin.api.entities.events as events
class CommandHandler(handler.MessageHandler):
async def handle(
self,
query: core_entities.Query,
query: pipeline_query.Query,
) -> typing.AsyncGenerator[entities.StageProcessResult, None]:
"""Process"""
@@ -28,23 +29,23 @@ class CommandHandler(handler.MessageHandler):
event_class = (
events.PersonCommandSent
if query.launcher_type == core_entities.LauncherTypes.PERSON
if query.launcher_type == provider_session.LauncherTypes.PERSON
else events.GroupCommandSent
)
event_ctx = await self.ap.plugin_mgr.emit_event(
event=event_class(
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
command=spt[0],
params=spt[1:] if len(spt) > 1 else [],
text_message=str(query.message_chain),
is_admin=(privilege == 2),
query=query,
)
event = event_class(
launcher_type=query.launcher_type.value,
launcher_id=query.launcher_id,
sender_id=query.sender_id,
command=spt[0],
params=spt[1:] if len(spt) > 1 else [],
text_message=str(query.message_chain),
is_admin=(privilege == 2),
query=query,
)
event_ctx = await self.ap.plugin_connector.emit_event(event)
if event_ctx.is_prevented_default():
if event_ctx.event.reply is not None:
mc = platform_message.MessageChain(event_ctx.event.reply)
@@ -64,7 +65,7 @@ class CommandHandler(handler.MessageHandler):
async for ret in self.ap.cmd_mgr.execute(command_text=command_text, query=query, session=session):
if ret.error is not None:
query.resp_messages.append(
llm_entities.Message(
provider_message.Message(
role='command',
content=str(ret.error),
)
@@ -74,16 +75,16 @@ class CommandHandler(handler.MessageHandler):
yield entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)
elif ret.text is not None or ret.image_url is not None:
content: list[llm_entities.ContentElement] = []
content: list[provider_message.ContentElement] = []
if ret.text is not None:
content.append(llm_entities.ContentElement.from_text(ret.text))
content.append(provider_message.ContentElement.from_text(ret.text))
if ret.image_url is not None:
content.append(llm_entities.ContentElement.from_image_url(ret.image_url))
content.append(provider_message.ContentElement.from_image_url(ret.image_url))
query.resp_messages.append(
llm_entities.Message(
provider_message.Message(
role='command',
content=content,
)

View File

@@ -1,10 +1,10 @@
from __future__ import annotations
from ...core import entities as core_entities
from . import handler
from .handlers import chat, command
from .. import entities
from .. import stage
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
@stage.stage_class('MessageProcessor')
@@ -30,7 +30,7 @@ class Processor(stage.PipelineStage):
async def process(
self,
query: core_entities.Query,
query: pipeline_query.Query,
stage_inst_name: str,
) -> entities.StageProcessResult:
"""Process"""

View File

@@ -2,7 +2,8 @@ from __future__ import annotations
import abc
import typing
from ...core import app, entities as core_entities
from ...core import app
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
preregistered_algos: list[typing.Type[ReteLimitAlgo]] = []
@@ -33,7 +34,7 @@ class ReteLimitAlgo(metaclass=abc.ABCMeta):
@abc.abstractmethod
async def require_access(
self,
query: core_entities.Query,
query: pipeline_query.Query,
launcher_type: str,
launcher_id: typing.Union[int, str],
) -> bool:
@@ -53,7 +54,7 @@ class ReteLimitAlgo(metaclass=abc.ABCMeta):
@abc.abstractmethod
async def release_access(
self,
query: core_entities.Query,
query: pipeline_query.Query,
launcher_type: str,
launcher_id: typing.Union[int, str],
):

View File

@@ -3,7 +3,7 @@ import asyncio
import time
import typing
from .. import algo
from ....core import entities as core_entities
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
# 固定窗口算法
@@ -32,7 +32,7 @@ class FixedWindowAlgo(algo.ReteLimitAlgo):
async def require_access(
self,
query: core_entities.Query,
query: pipeline_query.Query,
launcher_type: str,
launcher_id: typing.Union[int, str],
) -> bool:
@@ -91,7 +91,7 @@ class FixedWindowAlgo(algo.ReteLimitAlgo):
async def release_access(
self,
query: core_entities.Query,
query: pipeline_query.Query,
launcher_type: str,
launcher_id: typing.Union[int, str],
):

View File

@@ -4,9 +4,10 @@ import typing
from .. import entities, stage
from . import algo
from ...core import entities as core_entities
from ...utils import importutil
import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
from . import algos
importutil.import_modules_in_pkg(algos)
@@ -39,7 +40,7 @@ class RateLimit(stage.PipelineStage):
async def process(
self,
query: core_entities.Query,
query: pipeline_query.Query,
stage_inst_name: str,
) -> typing.Union[
entities.StageProcessResult,

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