Commit Graph

2288 Commits

Author SHA1 Message Date
c03adcb154 Fix: style checks and unittests (#12603) 2025-01-10 16:40:39 +08:00
17babca362 Introducing: Plugin Mechanism (#12553) 2025-01-09 19:54:17 +08:00
3c014f3ae5 Feat/plugins (#12547)
Co-authored-by: AkaraChen <akarachen@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: twwu <twwu@dify.ai>
Co-authored-by: kurokobo <kuro664@gmail.com>
Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>
2025-01-09 18:47:41 +08:00
94a62f6b4e enhancement: remove unrequired deps 2025-01-09 17:06:38 +08:00
d76af08784 feat: add agent log icon 2025-01-09 16:55:17 +08:00
f748d6c7c4 fix: mypy issues 2025-01-09 16:53:30 +08:00
5ce4ddc0ed fix: change the agent strategy category 2025-01-09 11:13:00 +08:00
491d641485 feat: add agent node log 2025-01-09 08:32:32 +08:00
172c5f19cc fix: formatter 2025-01-08 21:11:58 +08:00
b7d168ac59 fix: mypy linter 2025-01-08 21:11:42 +08:00
fb309462ad Merge branch 'main' into fix/chore-fix 2025-01-08 20:36:22 +08:00
040a3b782c FEAT: support milvus to full text search (#11430)
Signed-off-by: YoungLH <974840768@qq.com>
2025-01-08 17:39:53 +08:00
d649037c3e feat: support single run doc extractor node (#11318) 2025-01-08 15:20:15 +08:00
0a49d3dd52 fix: tiktoken cannot be loaded without internet (#12478)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-08 14:49:44 +08:00
53bb37b749 fix: fix the incorrect plaintext file key when saving (#10429) 2025-01-08 12:52:45 +08:00
d2586278d6 Feat elasticsearch japanese (#12194) 2025-01-08 12:35:41 +08:00
6222179a57 Revert "fix:deepseek tool call not working correctly" (#12463) 2025-01-08 10:50:34 +08:00
05bda6f38d add tidb on qdrant redis lock (#12462) 2025-01-08 08:55:44 +08:00
b56d2b739b feat: add fc agent mode support 2025-01-08 07:41:17 +08:00
67228c9b26 fix: url with variable not work (#12452) 2025-01-07 21:55:51 +08:00
fb7b2c8ff3 fix: backwards invoke nodes 2025-01-07 20:52:25 +08:00
4e6c86341d Add 'document' feature to Sonnet 3.5 through OpenRouter (#12444) 2025-01-07 19:51:38 +08:00
2a14c67edc Fix #12448 - update bedrock retrieve tool, support hybrid search type and re… (#12446)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2025-01-07 19:51:23 +08:00
c3440a27fb fix 2025-01-07 18:59:13 +08:00
41f39bf3fc Fix newline characters in tables during document parsing (#12112)
Co-authored-by: hisir <admin@qq.com>
2025-01-07 17:26:24 +08:00
9677144015 fix:deepseek tool call not working correctly (#12437) 2025-01-07 17:25:38 +08:00
15797c556f add fish-speech-1.5 from siliconflow (#12425) 2025-01-07 15:27:34 +08:00
d3f5b1cbb6 refactor: use tiktoken for token calculation (#12416)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-07 13:32:30 +08:00
dc650c5368 Fixes #12414: Add cheaper model and long context model for Qwen2.5-72B-Instruct from siliconflow (#12415) 2025-01-07 11:28:24 +08:00
2bb521b135 Support TTS and Speech2Text for Model Provider GPUStack (#12381) 2025-01-07 09:42:11 +08:00
409cc7d9b0 mark deprecated models in siliconflow #12399 (#12405)
Co-authored-by: crazywoola <427733928@qq.com>
2025-01-07 09:08:58 +08:00
8d75abc976 fix: correct fetch_from for customizable models (#12400) 2025-01-06 21:16:39 +08:00
fe26be2312 fix: http method can be upper case and lower case close #11877 (#12401)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-06 20:35:53 +08:00
3799d40937 feat: support docker deployment for plugin 2025-01-06 20:28:50 +08:00
147d578922 [Fix] revert sagemaker llm to support model hub (#12378) 2025-01-06 18:01:45 +08:00
70698024f5 fix: empty delete bug (#12339)
Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com>
2025-01-03 20:46:39 +08:00
6df17a334c fix: Update the API call address for the text_embedding model (#12342)
Co-authored-by: 方程 <fangcheng@oschina.cn>
2025-01-03 19:19:17 +08:00
7ed6485f86 refactor: streamline initialization of application_generate_entity and task_state in task pipeline classes (#12326)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-03 18:41:44 +08:00
3c2e30f348 fix: #12143 support streaming mode content start with "data:" (#12171) 2025-01-03 16:33:37 +08:00
b873e6349c add child chunk preview number limit (#12309) 2025-01-03 16:14:27 +08:00
5f51a19de2 fix: allow meta to be None 2025-01-03 14:48:19 +08:00
7c1961e618 feat: Add response format support to GLM-4 (#12252) 2025-01-03 09:38:50 +08:00
baeddd4d15 feat:Add support for stop parameter in hunyuan model #12313 (#12315)
Co-authored-by: xander-art <xander-art@gmail.com>
2025-01-03 09:15:04 +08:00
6f5a8a33d9 refactor: replace gevent threadpool with ProcessPoolExecutor in GPT2Tokenizer (#12316)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2025-01-03 09:13:18 +08:00
c135967e59 refactor: simplify some exception catch code (#12246) 2025-01-02 14:25:12 +08:00
d7c0bc8c23 feat: Add response format support for openai compat models (#12240)
Co-authored-by: Gio Gutierrez <giovannygutierrez@gmail.com>
2025-01-02 09:59:34 +08:00
f30bf08580 fix: close #12215 for yi special case (#12222)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2025-01-02 09:58:34 +08:00
9954ddb780 [Fix] modify sagemaker llm (#12274) 2025-01-02 09:49:11 +08:00
b218df6920 fix: draft run single node can't get env variable (#12266) 2025-01-01 13:31:44 +08:00
c7911c7130 fix: improve JSON parsing error handling in Executor class (#12265)
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-12-31 17:03:07 +08:00