55 Commits

Author SHA1 Message Date
fdc310 32215e9a3f fix:Fixed the issue where the rich text processing in the DingTalk AP… (#1759)
* fix:Fixed the issue where the rich text processing in the DingTalk API did not account for multiple texts and images, as well as the presence of default line breaks. Also resolved the error in Dify caused by sending only images, which resulted in an empty query.

* fix:Considering the various possible scenarios, there are cases where plan_text is empty when there is file content, and there is no file (the message could not be parsed) and the content is empty.

* fix:Add the default modifiable prompt input for didify in the ai.yaml file to ensure that the error of query being empty occurs when receiving data.

* add: The config migration of Dify

* fix:Migration issue

* perf: minor fix

* chore: minor fix

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-11-10 21:42:09 +08:00
Copilot 3edae3e678 feat: Support multiple knowledge base binding in pipelines (#1766)
* Initial plan

* Add multi-knowledge base support to pipelines

- Created database migration dbm010 to convert knowledge-base field from string to array
- Updated default pipeline config to use knowledge-bases array
- Updated pipeline metadata to use knowledge-base-multi-selector type
- Modified localagent.py to retrieve from multiple knowledge bases and concatenate results
- Added KNOWLEDGE_BASE_MULTI_SELECTOR type to frontend form entities
- Implemented multi-selector UI component with dialog for selecting multiple knowledge bases

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Add i18n translations for multi-knowledge base selector

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Fix prettier formatting errors in DynamicFormItemComponent

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* Add accessibility attributes to knowledge base selector checkbox

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

* fix: minor fix

---------

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-11-08 13:45:09 +08:00
fdc310 e4729337c8 Feat/coze runner (#1714)
* feat:add coze api client and coze runner and coze config

* del print

* fix:Change the default setting of the plugin system to true

* fix:del multimodal-support config, default multimodal-support,and in cozeapi.py Obtain timeout and auto-save-history config

* chore: add comment for coze.com

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-10-17 18:13:03 +08:00
yhaoxuan ed869f7e81 feat: supported Tbox runner (#1680)
* add tboxsdk

* add tbox runner

* fix comment & add document link

* Update pkg/provider/runners/tboxapi.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: haoxuan.yhx <haoxuan.yhx@antgroup.com>
Co-authored-by: haoxuan <haoxuan@U-X69D6XTD-2229.local>
Co-authored-by: Junyan Qin (Chin) <rockchinq@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-09-29 17:37:15 +08:00
Junyan Qin (Chin) c8ffc79077 perf: disable long message processing as default (#1670) 2025-09-17 17:09:12 +08:00
ashen 345c8b113f feat: supported langflow api provider (#1646)
* add langflow api provider

* chore: migration

* feat: okay for non-stream req

* fix: langflow sse data extracting

* doc: add comment on langflow api

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-09-11 21:37:45 +08:00
Bruce d9fa1cbb06 perf: add cmd enable config & fix announce request timeout & fix send card with disconnect ai platform (#1633)
* add cmd config && fix bugs

* perf: use `get`

* update bansess fix block match rule

* perf: comment for access-control session str

---------

Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-08-28 12:59:50 +08:00
Junyan Qin 87ecb4e519 feat: add note for remove_think & remove dify remove cot code 2025-08-21 21:38:58 +08:00
Junyan Qin c33c9eaab0 chore: remove remove_think param in trigger.yaml 2025-08-06 15:45:35 +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 15e524c6e6 perf: move remove-think to output tab 2025-08-04 19:26:19 +08:00
Junyan Qin b9f768af25 perf: minor fixes 2025-08-04 19:26:18 +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 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
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 84129e3339 perf: minor fixes 2025-08-03 15:30:11 +08:00
Junyan Qin b61bd36b14 perf(rag): ui and related apis 2025-07-18 00:45:38 +08:00
WangCham 45afdbdfbb feat: rag pipeline backend 2025-07-17 15:05:11 +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 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
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
whw174660897 f17b06767e Feature add n8 n (#1468)
* feat(n8n): 添加n8n工作流API支持

添加n8n工作流API作为新的运行器类型,支持通过webhook调用n8n工作流,并提供多种认证方式(Basic、JWT、Header)。新增N8nAuthFormComponent用于处理n8n认证表单联动,并更新相关配置文件和测试用例。

* chore: remove pip mirror url

* perf: simplify ret def of pipeline metadata

* feat(n8n): raise exc instead of ret as normal msg

* perf: add var `user_message_text`

* chore(n8n): migration and default config

* chore: required database version

---------

Co-authored-by: hengwei.wang <@>
Co-authored-by: Junyan Qin <rockchinq@gmail.com>
2025-05-30 22:23:57 +08:00
Junyan Qin 778693a804 perf: desc of random 2025-05-21 19:45:45 +08:00
Steven Lynn 4a988b89a2 fix: update auto-reply probability description in trigger.yaml (#1463) 2025-05-21 17:50:23 +08:00
fdc310 aba51409a7 feat:add qoute message process and add Whether to enable this function (#1446)
* 更新了wechatpad接口,以及适配器

* 更新了wechatpad接口,以及适配器

* 修复一些细节问题,比如at回复,以及启动登录和启动ws长连接的线程同步

* importutil中修复了在wi上启动替换斜杠问题,login中加上了一个login,暂时没啥用。wechatpad中做出了一些细节修改

* 更新了wechatpad接口,以及适配器

* 怎加了处理图片链接转换为image_base64发送

* feat(wechatpad): 调整日志+bugfix

* feat(wechatpad): fix typo

* 修正了发送语音api参数错误,添加了发送链接处理为base64数据(好像只有一部分链接可以)

* 修复了部分手抽的typo错误

* chore: remove manager.py

* feat:add qoute message process and add Whether to enable this function

* chore: add db migration for this change

---------

Co-authored-by: shinelin <shinelinxx@gmail.com>
Co-authored-by: Junyan Qin (Chin) <rockchinq@gmail.com>
2025-05-19 22:24:18 +08:00
Junyan Qin 219d328342 perf: completion some english translation 2025-05-14 17:00:03 +08:00
Junyan Qin c835555a59 chore: change zh_CN to zh_Hans 2025-05-14 16:44:48 +08:00
Junyan Qin d01858125c doc: add more comment for pipeline config 2025-05-11 15:14:32 +08:00
Junyan Qin e74de068ea perf: unify entities 2025-05-08 18:09:52 +08:00
Junyan Qin a2efb3ee15 chore: make track-function-calls false as default 2025-04-16 10:44:13 +08:00
Junyan Qin b64e1c609f refactor: remove adapter-qq-botpy.json metadata 2025-04-12 22:19:18 +08:00
Junyan Qin 5347094466 chore: remove llm-models and prompt related files 2025-04-03 18:20:00 +08:00
Junyan Qin 7f66efcdd5 refactor: switch pipeline_cfg related fields to new pipeline config 2025-04-03 17:57:51 +08:00
Junyan Qin 913e43d84c feat: make prompt object type array in pipeline config 2025-04-03 12:50:18 +08:00
Junyan Qin 5ff59f1b07 feat: pipeline invoking 2025-03-28 23:42:41 +08:00
Junyan Qin 9c4ea2d09b chore: typo in trigger.yaml 2025-03-26 23:20:11 +08:00
Junyan Qin (Chin) b85615cece chore: add pipeline config metadata (#1236) 2025-03-26 00:53:36 +08:00
Junyan Qin 2e93600437 feat: update llm-models.json template 2025-03-03 21:02:48 +08:00
Junyan Qin 3811700a78 chore: update llm-models.json template 2025-03-01 21:33:47 +08:00
Junyan Qin afabf9256b chore: add model info deepseek-reasoner 2025-01-28 15:14:23 +08:00
Junyan Qin 44b92909eb feat: add supports for zhipuai(chatglm) 2025-01-06 20:27:10 +08:00
Junyan Qin 0a68a77e28 feat: refactor 2025-01-04 22:24:05 +08:00
Junyan Qin 05da43f606 chore: 更新模型信息 2024-11-22 22:33:05 +08:00
RockChinQ b9049e91cf chore: 同步 llm-models.json 2024-05-22 20:31:46 +08:00
RockChinQ 2c478ccc25 feat: 模型vision支持性参数 2024-05-16 20:11:54 +08:00
RockChinQ 404e5492a3 chore: 同步现有模型信息 2024-05-16 18:29:23 +08:00
RockChinQ d5b5d667a5 feat: 模型视觉多模态支持 2024-05-15 21:40:18 +08:00
RockChinQ 9c6491e5ee feat: 支持 deepseek 的模型 2024-05-07 14:28:52 +00:00
RockChinQ dead8fa168 feat: 添加对 moonshot 模型的支持 2024-03-19 22:39:45 +08:00
RockChinQ 1dae7bd655 feat: 对 claude api 的基本支持 2024-03-17 12:44:45 -04:00