-LAN- and GitHub
257bf13fef
refactor: Removes unused LLMMode value_of method ( #20575 )
...
Signed-off-by: -LAN- <[email protected] >
2025-06-03 16:36:10 +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
bravomark and GitHub
9bcc8041e9
fix : #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. ( #18756 )
2025-04-25 16:45:48 +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
Novice and GitHub
f191d372f0
fix(promptMessage): correct field_serializer implementation for content serialization ( #18458 )
2025-04-21 15:09:49 +08:00
Novice and GitHub
da9269ca97
feat: structured output ( #17877 )
2025-04-18 16:33:53 +08:00
-LAN- and GitHub
8e6f6d64a4
feat: re-add prompt messages to result and chunks in llm ( #17883 )
...
Signed-off-by: -LAN- <[email protected] >
2025-04-11 17:04:49 +08:00
yihong and GitHub
f04d52c044
fix: autocorrect everything in api ( #17859 )
...
Signed-off-by: yihong0618 <[email protected] >
2025-04-11 15:24:39 +08:00
Yongtao Huang and GitHub
963b6f628a
Chore: PromptMessage is not an abstract base class ( #15965 )
2025-03-18 10:57:52 +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
-LAN- and GitHub
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- and GitHub
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
yihong and GitHub
56e15d09a9
feat: mypy for all type check ( #10921 )
2024-12-24 18:38:51 +08:00
-LAN- and GitHub
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
非法操作 and GitHub
c9b4029ce7
chore: the consistency of MultiModalPromptMessageContent ( #11721 )
2024-12-17 15:01:38 +08:00
非法操作 and GitHub
74fdc16bd1
feat: enhance gemini models ( #11497 )
2024-12-17 12:05:13 +08:00
Bowen Liang and GitHub
e79eac688a
chore(lint): sort __all__ definitions ( #11243 )
2024-12-03 13:26:33 +08:00
Bowen Liang and GitHub
6c8e208ef3
chore: bump minimum supported Python version to 3.11 ( #10386 )
2024-11-24 13:28:46 +08:00
08ac36812b
feat: support LLM process document file ( #10966 )
...
Co-authored-by: -LAN- <[email protected] >
2024-11-22 19:32:44 +08:00
c5f7d650b5
feat: Allow using file variables directly in the LLM node and support more file types. ( #10679 )
...
Co-authored-by: Joel <[email protected] >
2024-11-22 16:30:22 +08:00
非法操作 and GitHub
033ab5490b
feat: support LLM understand video ( #9828 )
2024-11-08 13:22:52 +08:00
70ddc0ce43
openai compatiable api usage and id ( #9800 )
...
Co-authored-by: jinqi.guo <[email protected] >
2024-10-24 21:51:36 +08:00
-LAN- and GitHub
e61752bd3a
feat/enhance the multi-modal support ( #8818 )
2024-10-21 10:43:49 +08:00
Bowen Liang and GitHub
a1104ab97e
chore: refurish python code by applying Pylint linter rules ( #8322 )
2024-09-13 22:42:08 +08:00
c69f5b07ba
chore: apply ruff E501 line-too-long linter rule ( #8275 )
...
Co-authored-by: -LAN- <[email protected] >
2024-09-12 14:00:36 +08:00
Bowen Liang and GitHub
2cf1187b32
chore(api/core): apply ruff reformatting ( #7624 )
2024-09-10 17:00:20 +08:00
dabfd74622
feat: Parallel Execution of Nodes in Workflows ( #8192 )
...
Co-authored-by: StyleZhang <[email protected] >
Co-authored-by: Yi <[email protected] >
Co-authored-by: -LAN- <[email protected] >
2024-09-10 15:23:16 +08:00
-LAN- and GitHub
4313d92e6b
feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. ( #8167 )
2024-09-10 09:11:31 +08:00
非法操作 and GitHub
6ff7fd80a1
feat: support OPENAI json_schema ( #7258 )
2024-08-15 11:29:19 +08:00
-LAN- and GitHub
23fa3dedc4
fix(core): Fix incorrect type hints. ( #5427 )
2024-06-20 15:16:21 +08:00
-LAN- and GitHub
5a99aeb864
fix(core): Reorder field_validator and classmethod to fit Pydantic V2. ( #5257 )
2024-06-17 10:04:28 +08:00
Bowen Liang and GitHub
f976740b57
improve: mordernizing validation by migrating pydantic from 1.x to 2.x ( #4592 )
2024-06-14 01:05:37 +08:00
takatost and GitHub
b890c11c14
feat: filter empty content messages in llm node ( #3547 )
2024-04-17 13:30:33 +08:00
orangeclk and GitHub
4fb9606361
fix: max_token default help info improved ( #2951 )
2024-03-25 10:07:32 +08:00
呆萌闷油瓶 and GitHub
8f9125b08a
fix:typo ( #2808 )
2024-03-13 13:00:46 +08:00
Yeuoly and GitHub
40c646cf7a
Feat/model as tool ( #2744 )
2024-03-08 15:22:55 +08:00
Yeuoly and GitHub
3e63abd335
Feat/json mode ( #2563 )
2024-02-26 23:34:40 +08:00
300d9892a5
tts add voice choose ( #2391 )
...
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <[email protected] >
Co-authored-by: crazywoola <[email protected] >
2024-02-15 22:41:18 +08:00
Bowen Liang and GitHub
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version ( #2419 )
2024-02-09 15:21:33 +08:00
Bowen Liang and GitHub
843280f82b
enhancement: introduce Ruff for Python linter for reordering and removing unused imports with automated pre-commit and sytle check ( #2366 )
2024-02-06 13:21:13 +08:00
Yeuoly and GitHub
6d5b386394
Feat/blocking function call ( #2247 )
2024-01-30 15:25:37 +08:00
6355e61eb8
tts models support ( #2033 )
...
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <[email protected] >
Co-authored-by: crazywoola <[email protected] >
Co-authored-by: Yeuoly <[email protected] >
2024-01-24 01:05:37 +08:00
takatost and GitHub
b582fc13c3
fix: qwen top_p min/max wrong ( #2044 )
2024-01-16 01:12:55 +08:00
Bowen Liang and GitHub
cc9e74123c
improve: introduce isort for linting Python imports ( #1983 )
2024-01-12 12:34:01 +08:00
5b24d7129e
Azure openai init ( #1929 )
...
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <[email protected] >
Co-authored-by: crazywoola <[email protected] >
2024-01-09 19:17:47 +08:00
takatost and GitHub
7be77c19f5
fix: default model parameter precision ( #1864 )
2024-01-03 08:52:22 +08:00
d069c668f8
Model Runtime ( #1858 )
...
Co-authored-by: StyleZhang <[email protected] >
Co-authored-by: Garfield Dai <[email protected] >
Co-authored-by: chenhe <[email protected] >
Co-authored-by: jyong <[email protected] >
Co-authored-by: Joel <[email protected] >
Co-authored-by: Yeuoly <[email protected] >
2024-01-02 23:42:00 +08:00