OpenSource
/
dify
Vērot 4
Pievienot zvaigznīti 0
Atdalīts 0
Kods Problēmas 0 Izmaiņu pieprasījumi 0 Laidieni 152 Vikivietne Aktivitāte
6431 Revīzija
4 Atzari
Koks: 60c37fe492
Atzari Tagi
${ item.name }
Izveidot atzaru ${ searchTerm }
no '60c37fe492'
${ noResults }
Revīziju grafs

819 Revīzijas (60c37fe4920f2b75d0f3dbe1bb37ddd168640427)

Autors SHA1 Ziņojums Datums
  crazywoola 60c37fe492
Added a check to ensure the input `text` is a string before proceeding with parsing (#22809) pirms 3 mēnešiem
  Yeuoly 94a13d7d62
feat: add support for dark icons in provider and tool entities (#22081) pirms 3 mēnešiem
  Novice f3c8625fe2
fix: The statistics page cannot display the tokens consumed by agent node (#21861) pirms 4 mēnešiem
  Yeuoly 0cb00d5fd2
refactor: move structured output support outside LLM Node (#21565) pirms 4 mēnešiem
  -LAN- 5ccfb1f4ba
refactor: Improve model status handling and structured output (#20586) pirms 5 mēnešiem
  -LAN- 257bf13fef
refactor: Removes unused LLMMode value_of method (#20575) pirms 5 mēnešiem
  yihong 5a991295e0
fix: drop some type fixme (#20344) pirms 5 mēnešiem
  QuantumGhost 349c3cf7b8
feat(api): Add image multimodal support for LLMNode (#17372) pirms 6 mēnešiem
  Bowen Liang 12c96b93d9
immediately return initialed tiktokenizer instance and remove dead code in usage of tiktokenizer (#17957) pirms 6 mēnešiem
  QuantumGhost bd1bbfee4b
Enhance Code Consistency Across Repository with `.editorconfig` (#19023) pirms 6 mēnešiem
  Yeuoly abafa68647
refactor: rename plugin manager to plugin client and rename path from manager to impl (#18876) pirms 6 mēnešiem
  非法操作 c1559a7c8e
fix: LLMResultChunk cause concatenate str and list exception (#18852) pirms 6 mēnešiem
  bravomark 9bcc8041e9
fix: #18744 The model order defined in position.yaml in the Model Plugin is not taking effect. (#18756) pirms 6 mēnešiem
  ZalterCitty a1158cc946
fix: Update prompt message content types to use Literal and add union type for content (#17136) pirms 6 mēnešiem
  Novice f191d372f0
fix(promptMessage): correct field_serializer implementation for content serialization (#18458) pirms 6 mēnešiem
  Novice da9269ca97
feat: structured output (#17877) pirms 6 mēnešiem
  Vitor defd5520ea
fix: invalid new tool call creation logic during response handling in OAI-Compat model (#17781) pirms 6 mēnešiem
  -LAN- 8e6f6d64a4
feat: re-add prompt messages to result and chunks in llm (#17883) pirms 6 mēnešiem
  yihong f04d52c044
fix: autocorrect everything in api (#17859) pirms 6 mēnešiem
  -LAN- d3157b46ee
feat(large_language_model): Adds plugin-based token counting configuration option (#17706) pirms 6 mēnešiem
  非法操作 44f911a0a8
chore: docstring not match the function parameter (#17162) pirms 7 mēnešiem
  非法操作 8047d08b3b
chore: remove third party models (#13885) pirms 7 mēnešiem
  NanoNova a30945312a
fix: typos (#16385) pirms 7 mēnešiem
  Yongtao Huang 963b6f628a
Chore: PromptMessage is not an abstract base class (#15965) pirms 7 mēnešiem
  jiangbo721 037f200527
fix: invoke_error is not callable (#15555) pirms 7 mēnešiem
  Yeuoly 4668c4996a
feat: Add caching mechanism for plugin model schemas (#14898) pirms 8 mēnešiem
  Yingchun Lai 7259c0d69f
fix: fix a typo of get_customizable_model_schema method name (#14449) pirms 8 mēnešiem
  Yeuoly 490b6d092e
Fix/plugin race condition (#14253) pirms 8 mēnešiem
  jiangbo721 f535a2aa71
chore: prompt_message is actually assistant_message which is a bit am… (#13839) pirms 8 mēnešiem
  Yeuoly 403e2d58b9
Introduce Plugins (#13836) pirms 8 mēnešiem
  Yingchun Lai a3d3e30e3a
fix: fix tongyi models blocking mode with incremental_output=stream (#13620) pirms 8 mēnešiem
  yihong 1f38d4846b
fix: issue #13483 and #13434 (#13518) pirms 8 mēnešiem
  ybalbert001 c8357da13b
[Fix] Sagemaker LLM Provider can't adjust context size, it'a always 2… (#13462) pirms 8 mēnešiem
  Fei He 7796984444
Fix: Removed model params except max_token for deepseek r1 in volcengine (#13446) pirms 8 mēnešiem
  Fei He 75113c26c6
Feat : add deepseek support for tongyi (#13445) pirms 8 mēnešiem
  xhe 939a9ecd21
chore: use the wrap thinking api for volcengine (#13432) pirms 8 mēnešiem
  Riddhimaan-Senapati 811d72a727
feat: added a _position.yaml for vertex ai provider (#13367) pirms 8 mēnešiem
  Naoki Takashima 37117c22d4
feat(model): support Gemini 2.0 Flash Lite Preview model (02-05) in Google's model provider (#13399) pirms 8 mēnešiem
  Junjie.M 286cdc41ab
reasoning model unified think tag is <think></think> (#13392) pirms 8 mēnešiem
  Kalo Chin c8dcde6cd0
fix: Gemini 2.0 Flash 001 model yaml file naming (#13372) pirms 8 mēnešiem
  Riddhimaan-Senapati 8f9db61688
feat: added new silicon flow models (#13369) pirms 8 mēnešiem
  Steven sun 38c31e64db
add enable_search parameter to qwen_max, plus, turbo (#13335) pirms 8 mēnešiem
  -LAN- 413dfd5628
feat: add completion mode and context size options for LLM configuration (#13325) pirms 8 mēnešiem
  -LAN- f9515901cc
fix: Azure AI Foundry model cannot be used in the workflow (#13323) pirms 8 mēnešiem
  呆萌闷油瓶 3f42fabff8
chore:improve thinking display for llm from xinference and ollama pro… (#13318) pirms 8 mēnešiem
  -LAN- 1caa578771
chore(*): Update style of thinking (#13319) pirms 8 mēnešiem
  非法操作 3eb3db0663
chore: refactor the OpenAICompatible and improve thinking display (#13299) pirms 8 mēnešiem
  sino 6e5c915f96
feat(model): add deepseek-r1 for openrouter (#13312) pirms 8 mēnešiem
  Riddhimaan-Senapati 2348abe4bf
feat: added a couple of models not defined in vertex ai, that were already … (#13296) pirms 8 mēnešiem
  呆萌闷油瓶 f7e7a399d9
feat:add think tag display for xinference deepseek r1 (#13291) pirms 8 mēnešiem