OpenSource
/
dify
關注 4
收藏 0
複製 0
程式碼 問題 0 合併請求 0 版本發佈 152 Wiki 活動
6258 提交
4 分支
目錄樹: 535fff62f3
分支列表 標籤
${ item.name }
建立分支 ${ searchTerm }
從 '535fff62f3'
${ noResults }
提交線圖

817 次程式碼提交 (535fff62f3d928d73c371126b36e2e6ab83ee23c)

作者 SHA1 備註 提交日期
  Novice f3c8625fe2
fix: The statistics page cannot display the tokens consumed by agent node (#21861) 4 月之前
  Yeuoly 0cb00d5fd2
refactor: move structured output support outside LLM Node (#21565) 4 月之前
  -LAN- 5ccfb1f4ba
refactor: Improve model status handling and structured output (#20586) 5 月之前
  -LAN- 257bf13fef
refactor: Removes unused LLMMode value_of method (#20575) 5 月之前
  yihong 5a991295e0
fix: drop some type fixme (#20344) 5 月之前
  QuantumGhost 349c3cf7b8
feat(api): Add image multimodal support for LLMNode (#17372) 6 月之前
  Bowen Liang 12c96b93d9
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957) 6 月之前
  QuantumGhost bd1bbfee4b
Enhance Code Consistency Across Repository with `.editorconfig` (#19023) 6 月之前
  Yeuoly abafa68647
refactor: rename plugin manager to plugin client and rename path from manager to impl (#18876) 6 月之前
  非法操作 c1559a7c8e
fix: LLMResultChunk cause concatenate str and list exception (#18852) 6 月之前
  bravomark 9bcc8041e9
fix: #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. (#18756) 6 月之前
  ZalterCitty a1158cc946
fix: Update prompt message content types to use Literal and add union type for content (#17136) 6 月之前
  Novice f191d372f0
fix(promptMessage): correct field_serializer implementation for content serialization (#18458) 6 月之前
  Novice da9269ca97
feat: structured output (#17877) 6 月之前
  Vitor defd5520ea
fix: invalid new tool call creation logic during response handling in OAI-Compat model (#17781) 6 月之前
  -LAN- 8e6f6d64a4
feat: re-add prompt messages to result and chunks in llm (#17883) 6 月之前
  yihong f04d52c044
fix: autocorrect everything in api (#17859) 6 月之前
  -LAN- d3157b46ee
feat(large_language_model): Adds plugin-based token counting configuration option (#17706) 6 月之前
  非法操作 44f911a0a8
chore: docstring not match the function parameter (#17162) 7 月之前
  非法操作 8047d08b3b
chore: remove third party models (#13885) 7 月之前
  NanoNova a30945312a
fix: typos (#16385) 7 月之前
  Yongtao Huang 963b6f628a
Chore: PromptMessage is not an abstract base class (#15965) 7 月之前
  jiangbo721 037f200527
fix: invoke_error is not callable (#15555) 7 月之前
  Yeuoly 4668c4996a
feat: Add caching mechanism for plugin model schemas (#14898) 8 月之前
  Yingchun Lai 7259c0d69f
fix: fix a typo of get_customizable_model_schema method name (#14449) 8 月之前
  Yeuoly 490b6d092e
Fix/plugin race condition (#14253) 8 月之前
  jiangbo721 f535a2aa71
chore: prompt_message is actually assistant_message which is a bit am… (#13839) 8 月之前
  Yeuoly 403e2d58b9
Introduce Plugins (#13836) 8 月之前
  Yingchun Lai a3d3e30e3a
fix: fix tongyi models blocking mode with incremental_output=stream (#13620) 8 月之前
  yihong 1f38d4846b
fix: issue #13483 and #13434 (#13518) 8 月之前
  ybalbert001 c8357da13b
[Fix] Sagemaker LLM Provider can't adjust context size, it'a always 2… (#13462) 8 月之前
  Fei He 7796984444
Fix: Removed model params except max_token for deepseek r1 in volcengine (#13446) 8 月之前
  Fei He 75113c26c6
Feat : add deepseek support for tongyi (#13445) 8 月之前
  xhe 939a9ecd21
chore: use the wrap thinking api for volcengine (#13432) 8 月之前
  Riddhimaan-Senapati 811d72a727
feat: added a _position.yaml for vertex ai provider (#13367) 8 月之前
  Naoki Takashima 37117c22d4
feat(model): support Gemini 2.0 Flash Lite Preview model (02-05) in Google's model provider (#13399) 8 月之前
  Junjie.M 286cdc41ab
reasoning model unified think tag is <think></think> (#13392) 8 月之前
  Kalo Chin c8dcde6cd0
fix: Gemini 2.0 Flash 001 model yaml file naming (#13372) 8 月之前
  Riddhimaan-Senapati 8f9db61688
feat: added new silicon flow models (#13369) 8 月之前
  Steven sun 38c31e64db
add enable_search parameter to qwen_max, plus, turbo (#13335) 8 月之前
  -LAN- 413dfd5628
feat: add completion mode and context size options for LLM configuration (#13325) 8 月之前
  -LAN- f9515901cc
fix: Azure AI Foundry model cannot be used in the workflow (#13323) 8 月之前
  呆萌闷油瓶 3f42fabff8
chore:improve thinking display for llm from xinference and ollama pro… (#13318) 8 月之前
  -LAN- 1caa578771
chore(*): Update style of thinking (#13319) 8 月之前
  非法操作 3eb3db0663
chore: refactor the OpenAICompatible and improve thinking display (#13299) 8 月之前
  sino 6e5c915f96
feat(model): add deepseek-r1 for openrouter (#13312) 8 月之前
  Riddhimaan-Senapati 2348abe4bf
feat: added a couple of models not defined in vertex ai, that were already … (#13296) 8 月之前
  呆萌闷油瓶 f7e7a399d9
feat:add think tag display for xinference deepseek r1 (#13291) 8 月之前
  zhu-an 16865d43a8
feat: add deepseek models for volcengine provider (#13283) 8 月之前
  呆萌闷油瓶 0d13aee15c
feat:add deepseek r1 think display for ollama provider (#13272) 8 月之前