1094 Commits (c6996a48a45a79b3dfa719fa0402de1662a9c0a3)

Autor SHA1 Mensagem Data
  -LAN- c6996a48a4
refactor(api/core/app/segments): Support more kinds of Segments. (#6706) 1 ano atrás
  chenxu9741 6b50bb0fe6
issues #6655 Open ai tts issues (#6696) 1 ano atrás
  Sangmin Ahn ecb9c311b5
chore: make prompt generator max tokens configurable (#6693) 1 ano atrás
  Yeuoly 79cb23e8ac
security/SSRF vulns (#6682) 1 ano atrás
  longzhihun c5ac004f15
[seanguo] fix: unsupported filename in windows & add Mistral Large 2 (#6679) 1 ano atrás
  RookieAgent 78a339a794
modify llama3-1 yaml filename to support Windows pull operations (#6677) 1 ano atrás
  灰灰 5e4ac11df3
fix: code block segmentation problem of markdown document (#6465) 1 ano atrás
  tmuife 16b4f560cd
fix bugs(when using Oracle23ai as Vector DB) (#6658) 1 ano atrás
  -LAN- 75e6576c67
refactor(api/core/app/segments): implement `to_object` in ObjectVariable and ArrayVariable. (#6671) 1 ano atrás
  xielong ebcc07e3e9
feat: support max_retries in jina requests (#6585) 1 ano atrás
  Giga Group ca696fe94c
Add support of tool-call for model provider "hunyuan" (#6656) 1 ano atrás
  longzhihun 9815aab7a3
[seanguo] feat: add llama 3.1 support in bedrock (#6645) 1 ano atrás
  majian a876baf0a9
Resolve variable type parameter error (#6646) 1 ano atrás
  Jyong 91fd8521c3
fix reranking model field error (#6654) 1 ano atrás
  -LAN- 4ec9a87e46
fix(api/core/workflow/nodes/iteration/iteration_node.py): Extend output in iteration if output is a array. (#6647) 1 ano atrás
  -LAN- 31efe10c75
refactor(api/core/workflow/workflow_engine_manager.py): Remove (#6630) 1 ano atrás
  -LAN- 72bc9d5f2b
feat(api/core/app/segments/variables.py): Support description in Variable. (#6636) 1 ano atrás
  Jyong 600f13436d
remove rerank model must be required when retrieval_model is multiple (#6640) 1 ano atrás
  zhangzhiqiangcs d4c55748f1
doc: fix about model features (#6619) 1 ano atrás
  dufei 5af2df0cd5
fix: qwen fc error (#6620) 1 ano atrás
  Jyong e4bb943fe5
Feat/delete single dataset retrival (#6570) 1 ano atrás
  takatost 0fb741f269
fix: downgraded sentry-sdk to 1.44.1 due to claude LLM token returning 0 (#6597) 1 ano atrás
  takatost 4c85393a1d
feat: add GroqCloud llama3.1 series models support (#6596) 1 ano atrás
  sino d5c2680fde
feat: support llama3.1 series models for openrouter provider (#6595) 1 ano atrás
  -LAN- 85a883e281
fix(variables): NoneVariable should inherit from NoneSegment. (#6584) 1 ano atrás
  Joe 8123a00e97
feat: update prompt generate (#6516) 1 ano atrás
  -LAN- 2bc0632d0d
fix(segments): Support NoneType. (#6581) 1 ano atrás
  -LAN- ad7552ea8d
fix(api/core/workflow/nodes/llm/llm_node.py): Fix LLM Node error. (#6576) 1 ano atrás
  非法操作 c0ada940bd
fix: tool params not work as expected when develop a tool (#6550) 1 ano atrás
  Lance Mao 7c55c39085
feat: add tencent asr (#6091) 1 ano atrás
  -LAN- f019bc4bd7
feat(variables): Support `to_object`. (#6572) 1 ano atrás
  -LAN- cfc408095c
fix(api/nodes): Fallback to `get_any` in some nodes that use object or array. (#6566) 1 ano atrás
  takatost 6b5fac3004
fix: fetch context error in llm node (#6562) 1 ano atrás
  崔亮 0569c547ee
fix the issue of MILVUS_DATABASE has no effect. (#6424) 1 ano atrás
  tmuife 06fc1bce9e
Add search by full text when using Oracle23ai as vector DB (#6559) 1 ano atrás
  Sangmin Ahn 093b8ca475
fix: escape double quotation marks in the vector DB search query (#6506) 1 ano atrás
  Ryan Tian 5fcc2caeed
feat: add Mingdao HAP tool, implemented read and maintain HAP application worksheet data. (#6257) 1 ano atrás
  -LAN- cd7fa8027a
fix(api/core/model_manager.py): Avoid mutation during iteration. (#6536) 1 ano atrás
  -LAN- 5e6fc58db3
Feat/environment variables in workflow (#6515) 1 ano atrás
  Benjamin a67831773f
refactor: handle missing position file gracefully (#6513) 1 ano atrás
  sino dfb6f4fec6
fix: extract tool calls correctly while arguments is empty (#6503) 1 ano atrás
  Jyong f38034e455
clean vector collection redis cache (#6494) 1 ano atrás
  Matri 49ef9ef225
feat(tool): getimg.ai integration (#6260) 1 ano atrás
  Even c013086e64
fix: next suggest question logic problem (#6451) 1 ano atrás
  sino 4f9f175f25
fix: correct gpt-4o-mini max token (#6472) 1 ano atrás
  sino 9e168f9d1c
feat: support gpt-4o-mini for openrouter provider (#6447) 1 ano atrás
  Weaxs ea45496a74
update ernie models (#6454) 1 ano atrás
  Waffle 2ba05b041f
refactor(myscale):Set the default value of the myscale vector db in DifyConfig. (#6441) 1 ano atrás
  Richards Tu 8e49146a35
[EMERGENCY] Fix Anthropic header issue (#6445) 1 ano atrás
  takatost dad3fd2dc1
feat: add gpt-4o-mini (#6442) 1 ano atrás