opensource
/
dify
mirror of https://github.com/langgenius/dify.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
4,493 Commits 288 Branches 160 Tags 496 MiB
Commit Graph

1860 Commits

Author SHA1 Message Date
JasonVV 6d1264af4e feat(model): add vertex_ai Gemini 2.0 Flash Exp (#11604) 2024-12-16 11:02:47 +08:00
crazywoola cfd964880a fix: name of llama-3.3-70b-specdec (#11596) 2024-12-16 11:02:47 +08:00
Alok Shrivastwa 84d966d0d8 Added new models and Removed the deleted ones for Groq #11455 (#11456) 
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Alok Shrivastwa <Alok.Shrivastwa@microland.com>
 2024-12-16 11:02:47 +08:00
Warren Chen a926cd436f [ref] use one method to get boto client for aws bedrock (#11506) 2024-12-16 11:02:47 +08:00
yihong 561453b63f fix: support mdx files close #11557 (#11565) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-16 11:02:47 +08:00
Joe 39c678308b fix: change workflow trace id (#11585) 2024-12-16 11:02:47 +08:00
Jiang 880094cc7b Lindorm vdb (#11574) 
Co-authored-by: jiangzhijie <jiangzhijie.jzj@alibaba-inc.com>
 2024-12-16 11:00:37 +08:00
非法操作 3e6ff18e1b feat: add gemini-2.0-flash-exp (#11570) 2024-12-16 11:00:37 +08:00
liuzhenghua ec1efe5d54 Fix: RateLimit requests were not released when a streaming generation exception occurred (#11540) 2024-12-16 11:00:37 +08:00
Novice 72b1bed79d fix: iteration node in parallel mode token count error (#11539) 
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
 2024-12-16 11:00:37 +08:00
Novice 14912b2a1d Feat: continue on error (#11458) 
Co-authored-by: Novice Lee <novicelee@NovicedeMacBook-Pro.local>
Co-authored-by: Novice Lee <novicelee@NoviPro.local>
 2024-12-16 11:00:37 +08:00
Tommy 1a1d35607c [Pixtral] Add new model ; add vision (#11231) 2024-12-16 11:00:37 +08:00
zkyTech c82271af75 fix: Remove duplicate 'response_format' parameter from model YAML files (#11531) 
Co-authored-by: zhangkunyuan <zhangkunyuan@cmhi.chinamobile.com>
 2024-12-16 11:00:37 +08:00
Paul van Oorschot 0b7b12b003 feat: Add llama-3.3 models for Groq (#11533) 2024-12-16 11:00:37 +08:00
yihong 88df17694f Revert "fix: total tokens is wrong which is zero in inter way, close … (#11536) 2024-12-16 11:00:37 +08:00
yihong a571914ffc fix: issue 11247 that Completion mode content maybe list or str (#11504) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-16 11:00:37 +08:00
Wei Mingzhi e2a3c2e9da Remove the processing of single quote when testing API tools. (#11390) 2024-12-16 11:00:37 +08:00
非法操作 b76cee7ad8 chore: LOCAL_FILE also try to use remote_url as Prompt message (#11443) 2024-12-16 11:00:37 +08:00
-LAN- 0deb19e800 fix(app_generator_service): overload type hints (#11507) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-16 11:00:37 +08:00
orangeclk 5190cac072 feat: add siliconflow qwq and llama3.3 model (#11492) 2024-12-16 11:00:37 +08:00
Yingchun Lai 062a57589b fix: add the missing abab6.5t-chat model of Minimax (#11484) 2024-12-16 11:00:37 +08:00
-LAN- 186e39fd2f refactor(iteration_node): use Sequence and Mapping in parameters (#11483) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-16 10:59:56 +08:00
suzuki.sh eabf59f00d Fix the token count at the iteration node (#11235) 
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-16 10:59:56 +08:00
Kazuki Takamatsu 9dccb51fd0 Fix model provider of vertex ai (#11437) 2024-12-16 10:59:56 +08:00
非法操作 8ed235fa0b feat: support json_schema for ollama models (#11449) 2024-12-16 10:59:56 +08:00
非法操作 7bbb745e33 feat: add gemini exp 1206 (#11444) 2024-12-16 10:59:56 +08:00
非法操作 994b7a6603 feat: add zhipu glm_4v_flash (#11440) 2024-12-16 10:59:56 +08:00
yihong 24d43dceb4 fix: issue #10596 by making the iteration node outputs right (#11394) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-16 10:59:56 +08:00
Huỳnh Gia Bôi be9f58d065 fix(document_extractor): pptx file type and missing metadata_filename UnstructuredIO (#11364) 
Co-authored-by: Julian Huynh <julian.huynh@immersio.io>
 2024-12-16 10:59:56 +08:00
Jyong 898ea9bf0f update tidb batch get endpoint to basic mode (#11426) 2024-12-16 10:59:55 +08:00
Jyong 269698d8ce fix external retrieval without segment id (#11423) 2024-12-16 10:59:55 +08:00
shirochan 1e5a9acc74 FEAT: cohere rerank 3.5 model added (#11289) 2024-12-16 10:59:55 +08:00
Matsuda 8fd0eaf5b7 fix(model_runtime): add vision to Amazon Nova Lite and Pro (#11398) 2024-12-16 10:59:55 +08:00
Warren Chen c99b822ca5 [fix] rename yaml files to fit windows (#11379) 2024-12-16 10:59:15 +08:00
yihong 824877dd5f fix: some typos using typos (#11374) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-16 10:59:15 +08:00
Warren Chen 0bae1c6cb6 [feat] Add AWS Bedrock rerank (#11349) 
Co-authored-by: crazywoola <427733928@qq.com>
 2024-12-16 10:59:15 +08:00
Akira Noda eca466bdaa
chore: fix typo (#11359) 2024-12-05 09:04:30 +08:00
crazywoola d56abec195
Revert "Fix: iteration not in main thread pool" (#11358) 2024-12-04 21:22:22 +08:00
yihong 961e25f608
fix: better bedrock message handler close #10976 (#11317) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-04 19:46:40 +08:00
ybalbert001 1bae9b8ff7
update pricing for bedrock nova LLM models (#11336) 
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
 2024-12-04 16:16:41 +08:00
Jyong d7c1f43b49
fix tidb full-text-search vector missed (#11337) 2024-12-04 16:13:23 +08:00
非法操作 91e1ff5e30
chore: improve zhipu LLM (#11321) 2024-12-04 15:14:30 +08:00
ybalbert001 5908e10549
integrate amazon nove llms to dify (#11324) 
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
 2024-12-04 15:13:08 +08:00
-LAN- 464e6354c5
feat: correct the prompt grammar. (#11328) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-04 15:12:47 +08:00
非法操作 d470e55f8c
fix: http node download file always image type (#11319) 2024-12-04 12:15:26 +08:00
Jyong c58d2fce89
roll back rerank topn setting (#11297) 2024-12-03 17:34:56 +08:00
yihong e39e776d03
fix: better wenxin rerank handler, close #11252 (#11283) 
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
 2024-12-03 13:57:16 +08:00
Yi Xiao e135ffc2c1
Feat: upgrade variable assigner (#11285) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
 2024-12-03 13:56:40 +08:00
Bowen Liang e79eac688a
chore(lint): sort __all__ definitions (#11243) 2024-12-03 13:26:33 +08:00
-LAN- 643a90c48d
fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272) 
Signed-off-by: -LAN- <laipz8200@outlook.com>
 2024-12-03 09:16:25 +08:00