84 Commits
Author SHA1 Message Date
dac72b078d feat: support bool type variable frontend (#24437)
Co-authored-by: QuantumGhost <[email protected]>
2025-08-26 18:16:05 +08:00
jiangbo721andGitHub 1d776c4cd0 feat: If combining text and files, place the text prompt after the fi… (#24472) 2025-08-25 17:51:46 +08:00
-LAN-andGitHub da9af7b547 [Chore/Refactor] Use centralized naive_utc_now for UTC datetime operations (#24352)
Signed-off-by: -LAN- <[email protected]>
2025-08-22 23:53:05 +08:00
Yongtao HuangGitHubYongtao Huangautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
106ab7f2a8 Fix: safe defaults for BaseModel dict fields (#24098)
Co-authored-by: Yongtao Huang <[email protected]>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-08-21 21:38:55 +08:00
crazywoolaandGitHub acba135de1 Revert "feat: support to upload files for visual model call when running LLM node for debugging in a single step" (#23922) 2025-08-14 15:52:19 +08:00
goofyGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
4da6ec787e feat: support to upload files for visual model call when running LLM node for debugging in a single step (#23521)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-08-13 14:07:13 +08:00
Yongtao HuangGitHubautofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
a434f6240f Chroe: some misc cleanup (#23203)
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
2025-07-31 15:33:39 +08:00
WillandGitHub 095bae01b2 fix: Invalid expected metadata value type error (#22793) 2025-07-22 22:28:16 +08:00
460a825ef1 refactor: decouple Node and NodeData (#22581)
Signed-off-by: -LAN- <[email protected]>
Co-authored-by: QuantumGhost <[email protected]>
2025-07-18 10:08:51 +08:00
Kalo ChinandGitHub 7a69b57823 Fix jinja2 variable naming inconsistencies (#22578) 2025-07-17 22:16:47 +08:00
816210d744 Expose LLM usage in workflows (#21766)
Co-authored-by: crazywoola <[email protected]>
2025-07-08 21:18:00 +08:00
0cb00d5fd2 refactor: move structured output support outside LLM Node (#21565)
Co-authored-by: Novice <[email protected]>
2025-06-27 14:55:31 +08:00
QuantumGhostandGitHub 10b738a296 feat: Persist Variables for Enhanced Debugging Workflow (#20699)
This pull request introduces a feature aimed at improving the debugging experience during workflow editing. With the addition of variable persistence, the system will automatically retain the output variables from previously executed nodes. These persisted variables can then be reused when debugging subsequent nodes, eliminating the need for repetitive manual input.

By streamlining this aspect of the workflow, the feature minimizes user errors and significantly reduces debugging effort, offering a smoother and more efficient experience.

Key highlights of this change:

- Automatic persistence of output variables for executed nodes.
- Reuse of persisted variables to simplify input steps for nodes requiring them (e.g., `code`, `template`, `variable_assigner`).
- Enhanced debugging experience with reduced friction.

Closes #19735.
2025-06-24 09:05:29 +08:00
-LAN-andGitHub 1e03c97663 fix(llm_node): missing parameters for structure outputs (#20915)
Signed-off-by: -LAN- <[email protected]>
2025-06-11 18:56:07 +08:00
JyongandGitHub 21a50e22d2 fix auto metadata filter (#20845) 2025-06-10 10:46:17 +02:00
QuantumGhostandGitHub c439e82038 refactor(api): Decouple ParameterExtractorNode from LLMNode (#20843)
- Extract methods used by `ParameterExtractorNode` from `LLMNode` into a separate file.
- Convert `ParameterExtractorNode` into a subclass of `BaseNode`.
- Refactor code referencing the extracted methods to ensure functionality and clarity.
- Fixes the issue that `ParameterExtractorNode` returns error when executed.
- Fix relevant test cases.

Closes #20840.
2025-06-10 11:47:50 +08:00
ArcanerandGitHub ad2f25875e fix(llm_node): update file variable mapping to use vision configs (#20417) 2025-06-05 09:58:24 +08:00
-LAN-andGitHub 5ccfb1f4ba refactor: Improve model status handling and structured output (#20586)
Signed-off-by: -LAN- <[email protected]>
2025-06-04 19:56:54 +08:00
-LAN-andGitHub 72fdafc180 refactor: Replaces direct DB session usage with context managers (#20569)
Signed-off-by: -LAN- <[email protected]>
2025-06-03 16:16:06 +08:00
-LAN-andGitHub a6ea15e63c Refactor/message cycle manage and knowledge retrieval (#20460)
Signed-off-by: -LAN- <[email protected]>
2025-05-30 14:36:44 +08:00
-LAN-andGitHub 32e779eef3 refactor(workflow): Rename NodeRunMetadataKey to WorkflowNodeExecutionMetadataKey (#20457)
Signed-off-by: -LAN- <[email protected]>
2025-05-30 04:47:56 +08:00
-LAN-andGitHub 482e50aae9 Refactor/remove db from cycle manager (#20455)
Signed-off-by: -LAN- <[email protected]>
2025-05-30 04:34:13 +08:00
WillandGitHub 58d9d35515 fix: inconsistent metadata definitions (#19343) 2025-05-08 16:33:28 +08:00
NoviceandGitHub 0cfc82d731 fix(structured-output): reasoning model's json format parsing (#19261) 2025-05-06 13:16:08 +08:00
349c3cf7b8 feat(api): Add image multimodal support for LLMNode (#17372)
Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.

This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.

To integrate file outputs into workflows, adjustments to the frontend code
are necessary.

For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.

Close #15814.

Signed-off-by: -LAN- <[email protected]>
Co-authored-by: -LAN- <[email protected]>
2025-04-30 17:28:02 +08:00
非法操作andGitHub c1559a7c8e fix: LLMResultChunk cause concatenate str and list exception (#18852) 2025-04-27 11:32:14 +08:00
a1158cc946 fix: Update prompt message content types to use Literal and add union type for content (#17136)
Co-authored-by: 朱庆超 <[email protected]>
Co-authored-by: crazywoola <[email protected]>
2025-04-22 16:17:55 +08:00
NoviceandGitHub da9269ca97 feat: structured output (#17877) 2025-04-18 16:33:53 +08:00
Jacky WuandGitHub ed5596a8f4 fix: avoid llm node result var not init issue while do retry. (#14286) 2025-03-11 12:43:24 +08:00
LeanDeRandGitHub 4f6a4f244c fix(llm/nodes.py): Ensure that the output returns without any exceptions (#14880) 2025-03-05 14:35:08 +08:00
yuhaowinandGitHub 1e3197a1ea Fixes 14217: database retrieve api and chat-messages api response doc_metadata (#14219) 2025-02-27 14:56:46 +08:00
-LAN-andGitHub 7a71498a3e chore(quota): Update deduct quota (#14337)
Signed-off-by: -LAN- <[email protected]>
2025-02-25 20:10:08 +08:00
+110 403e2d58b9 Introduce Plugins (#13836)
Signed-off-by: yihong0618 <[email protected]>
Signed-off-by: -LAN- <[email protected]>
Signed-off-by: xhe <[email protected]>
Signed-off-by: dependabot[bot] <[email protected]>
Co-authored-by: takatost <[email protected]>
Co-authored-by: kurokobo <[email protected]>
Co-authored-by: Novice Lee <[email protected]>
Co-authored-by: zxhlyh <[email protected]>
Co-authored-by: AkaraChen <[email protected]>
Co-authored-by: Yi <[email protected]>
Co-authored-by: Joel <[email protected]>
Co-authored-by: JzoNg <[email protected]>
Co-authored-by: twwu <[email protected]>
Co-authored-by: Hiroshi Fujita <[email protected]>
Co-authored-by: AkaraChen <[email protected]>
Co-authored-by: NFish <[email protected]>
Co-authored-by: Wu Tianwei <[email protected]>
Co-authored-by: 非法操作 <[email protected]>
Co-authored-by: Novice <[email protected]>
Co-authored-by: Hiroki Nagai <[email protected]>
Co-authored-by: Gen Sato <[email protected]>
Co-authored-by: eux <[email protected]>
Co-authored-by: huangzhuo1949 <[email protected]>
Co-authored-by: huangzhuo <[email protected]>
Co-authored-by: lotsik <[email protected]>
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: nite-knite <[email protected]>
Co-authored-by: Jyong <[email protected]>
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: gakkiyomi <[email protected]>
Co-authored-by: CN-P5 <[email protected]>
Co-authored-by: CN-P5 <[email protected]>
Co-authored-by: Chuehnone <[email protected]>
Co-authored-by: yihong <[email protected]>
Co-authored-by: Kevin9703 <[email protected]>
Co-authored-by: -LAN- <[email protected]>
Co-authored-by: Boris Feld <[email protected]>
Co-authored-by: mbo <[email protected]>
Co-authored-by: mabo <[email protected]>
Co-authored-by: Warren Chen <[email protected]>
Co-authored-by: JzoNgKVO <[email protected]>
Co-authored-by: jiandanfeng <[email protected]>
Co-authored-by: zhu-an <[email protected]>
Co-authored-by: zhaoqingyu.1075 <[email protected]>
Co-authored-by: 海狸大師 <[email protected]>
Co-authored-by: Xu Song <[email protected]>
Co-authored-by: rayshaw001 <[email protected]>
Co-authored-by: Ding Jiatong <[email protected]>
Co-authored-by: Bowen Liang <[email protected]>
Co-authored-by: JasonVV <[email protected]>
Co-authored-by: le0zh <[email protected]>
Co-authored-by: zhuxinliang <[email protected]>
Co-authored-by: k-zaku <[email protected]>
Co-authored-by: luckylhb90 <[email protected]>
Co-authored-by: hobo.l <[email protected]>
Co-authored-by: jiangbo721 <[email protected]>
Co-authored-by: 刘江波 <[email protected]>
Co-authored-by: Shun Miyazawa <[email protected]>
Co-authored-by: EricPan <[email protected]>
Co-authored-by: crazywoola <[email protected]>
Co-authored-by: sino <[email protected]>
Co-authored-by: Jhvcc <[email protected]>
Co-authored-by: lowell <[email protected]>
Co-authored-by: Boris Polonsky <[email protected]>
Co-authored-by: Ademílson Tonato <[email protected]>
Co-authored-by: Ademílson Tonato <[email protected]>
Co-authored-by: IWAI, Masaharu <[email protected]>
Co-authored-by: Yueh-Po Peng (Yabi) <[email protected]>
Co-authored-by: Jason <[email protected]>
Co-authored-by: Xin Zhang <[email protected]>
Co-authored-by: yjc980121 <[email protected]>
Co-authored-by: heyszt <[email protected]>
Co-authored-by: Abdullah AlOsaimi <[email protected]>
Co-authored-by: Abdullah AlOsaimi <[email protected]>
Co-authored-by: Yingchun Lai <[email protected]>
Co-authored-by: Hash Brown <[email protected]>
Co-authored-by: zuodongxu <[email protected]>
Co-authored-by: Masashi Tomooka <[email protected]>
Co-authored-by: aplio <[email protected]>
Co-authored-by: Obada Khalili <[email protected]>
Co-authored-by: Nam Vu <[email protected]>
Co-authored-by: Kei YAMAZAKI <[email protected]>
Co-authored-by: TechnoHouse <[email protected]>
Co-authored-by: Riddhimaan-Senapati <[email protected]>
Co-authored-by: MaFee921 <[email protected]>
Co-authored-by: te-chan <[email protected]>
Co-authored-by: HQidea <[email protected]>
Co-authored-by: Joshbly <[email protected]>
Co-authored-by: xhe <[email protected]>
Co-authored-by: weiwenyan-dev <[email protected]>
Co-authored-by: ex_wenyan.wei <[email protected]>
Co-authored-by: engchina <[email protected]>
Co-authored-by: engchina <[email protected]>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: 呆萌闷油瓶 <[email protected]>
Co-authored-by: Kemal <[email protected]>
Co-authored-by: Lazy_Frog <[email protected]>
Co-authored-by: Yi Xiao <[email protected]>
Co-authored-by: Steven sun <[email protected]>
Co-authored-by: steven <[email protected]>
Co-authored-by: Kalo Chin <[email protected]>
Co-authored-by: Katy Tao <[email protected]>
Co-authored-by: depy <[email protected]>
Co-authored-by: 胡春东 <[email protected]>
Co-authored-by: Junjie.M <[email protected]>
Co-authored-by: MuYu <[email protected]>
Co-authored-by: Naoki Takashima <[email protected]>
Co-authored-by: Summer-Gu <[email protected]>
Co-authored-by: Fei He <[email protected]>
Co-authored-by: ybalbert001 <[email protected]>
Co-authored-by: Yuanbo Li <[email protected]>
Co-authored-by: douxc <[email protected]>
Co-authored-by: liuzhenghua <[email protected]>
Co-authored-by: Wu Jiayang <[email protected]>
Co-authored-by: Your Name <[email protected]>
Co-authored-by: kimjion <[email protected]>
Co-authored-by: AugNSo <[email protected]>
Co-authored-by: llinvokerl <[email protected]>
Co-authored-by: liusurong.lsr <[email protected]>
Co-authored-by: Vasu Negi <[email protected]>
Co-authored-by: Hundredwz <[email protected]>
Co-authored-by: Xiyuan Chen <[email protected]>
2025-02-17 17:05:13 +08:00
8a0aa91ed7 Non-Streaming Models Do Not Return Results Properly in _handle_invoke_result (#13571)
Co-authored-by: crazywoola <[email protected]>
2025-02-14 17:02:04 +08:00
-LAN-andGitHub 413dfd5628 feat: add completion mode and context size options for LLM configuration (#13325)
Signed-off-by: -LAN- <[email protected]>
2025-02-07 15:08:53 +08:00
-LAN-andGitHub f9515901cc fix: Azure AI Foundry model cannot be used in the workflow (#13323)
Signed-off-by: -LAN- <[email protected]>
2025-02-07 14:52:57 +08:00
-LAN-andGitHub 04d13a8116 feat(credits): Allow to configure model-credit mapping (#13274)
Signed-off-by: -LAN- <[email protected]>
2025-02-07 11:01:31 +08:00
-LAN-andGitHub b47669b80b fix: deduct LLM quota after processing invoke result (#13075)
Signed-off-by: -LAN- <[email protected]>
2025-02-02 12:05:11 +08:00
yihongandGitHub 56e15d09a9 feat: mypy for all type check (#10921) 2024-12-24 18:38:51 +08:00
JasonVVandGitHub 4b1e13e982 Fix 11979 (#11984) 2024-12-23 14:30:04 +08:00
-LAN-andGitHub 996a9135f6 feat(llm_node): support order in text and files (#11837)
Signed-off-by: -LAN- <[email protected]>
2024-12-20 14:12:50 +08:00
79a710ce98 Feat: continue on error (#11458)
Co-authored-by: Novice Lee <[email protected]>
Co-authored-by: Novice Lee <[email protected]>
2024-12-11 14:22:42 +08:00
yihongandGitHub 716576043d fix: issue 11247 that Completion mode content maybe list or str (#11504)
Signed-off-by: yihong0618 <[email protected]>
2024-12-10 23:22:14 +08:00
-LAN-andGitHub 464e6354c5 feat: correct the prompt grammar. (#11328)
Signed-off-by: -LAN- <[email protected]>
2024-12-04 15:12:47 +08:00
-LAN-andGitHub 223a30401c fix: LLM invoke error should not be raised (#11141)
Signed-off-by: -LAN- <[email protected]>
2024-11-26 20:56:48 +08:00
-LAN-andGitHub 044e7b63c2 fix(llm_node): Ignore file if not supported. (#11114) 2024-11-26 14:14:14 +08:00
-LAN-andGitHub 5b7b328193 feat: Allow to contains files in the system prompt even model not support. (#11111) 2024-11-26 13:45:49 +08:00
-LAN-andGitHub cbb4e95928 fix(llm_node): Ignore user query when memory is disabled. (#11106) 2024-11-26 13:07:32 +08:00
-LAN-andGitHub 20c091a5e7 fix: user query be ignored if query_prompt_template is an empty string (#11103) 2024-11-26 12:47:59 +08:00
-LAN-andGitHub 60b5dac3ab fix: query will be None if the query_prompt_template not exists (#11031)
Signed-off-by: -LAN- <[email protected]>
2024-11-24 21:06:51 +08:00