OpenSource
/
dify
Seguir 4
Destacar 0
Fork 0
Código Incidencias 0 Peticiones pull 0 Lanzamientos 152 Wiki Actividad
4906 Commits
4 Ramas
Árbol: 4a6cbda1b4
Ramas Etiquetas
${ item.name }
Crear rama ${ searchTerm }
desde '4a6cbda1b4'
${ noResults }
Commit Graph

2122 Commits (4a6cbda1b4fb912b3c080fd4a0029ed7e40b14f5)

Autor SHA1 Mensaje Fecha
  ybalbert001 c8357da13b
[Fix] Sagemaker LLM Provider can't adjust context size, it'a always 2… (#13462) hace 8 meses
  Fei He 7796984444
Fix: Removed model params except max_token for deepseek r1 in volcengine (#13446) hace 8 meses
  Fei He 75113c26c6
Feat : add deepseek support for tongyi (#13445) hace 8 meses
  xhe 939a9ecd21
chore: use the wrap thinking api for volcengine (#13432) hace 8 meses
  Riddhimaan-Senapati 811d72a727
feat: added a _position.yaml for vertex ai provider (#13367) hace 8 meses
  Naoki Takashima 37117c22d4
feat(model): support Gemini 2.0 Flash Lite Preview model (02-05) in Google's model provider (#13399) hace 8 meses
  Junjie.M 286cdc41ab
reasoning model unified think tag is <think></think> (#13392) hace 8 meses
  胡春东 cf36745770
fix(workflow_tool): enable File parameter support after workflow is published as a tool (#13175) hace 8 meses
  Kalo Chin c8dcde6cd0
fix: Gemini 2.0 Flash 001 model yaml file naming (#13372) hace 8 meses
  Riddhimaan-Senapati 8f9db61688
feat: added new silicon flow models (#13369) hace 8 meses
  Steven sun 38c31e64db
add enable_search parameter to qwen_max, plus, turbo (#13335) hace 8 meses
  -LAN- 413dfd5628
feat: add completion mode and context size options for LLM configuration (#13325) hace 8 meses
  -LAN- f9515901cc
fix: Azure AI Foundry model cannot be used in the workflow (#13323) hace 8 meses
  呆萌闷油瓶 3f42fabff8
chore:improve thinking display for llm from xinference and ollama pro… (#13318) hace 8 meses
  -LAN- 1caa578771
chore(*): Update style of thinking (#13319) hace 8 meses
  Lazy_Frog b7c11c1818
Fix the problem of Workflow terminates after parallel tasks execution, merge node not triggered (#12498) hace 8 meses
  非法操作 3eb3db0663
chore: refactor the OpenAICompatible and improve thinking display (#13299) hace 8 meses
  sino 6e5c915f96
feat(model): add deepseek-r1 for openrouter (#13312) hace 8 meses
  -LAN- 04d13a8116
feat(credits): Allow to configure model-credit mapping (#13274) hace 8 meses
  Riddhimaan-Senapati 2348abe4bf
feat: added a couple of models not defined in vertex ai, that were already … (#13296) hace 8 meses
  呆萌闷油瓶 f7e7a399d9
feat:add think tag display for xinference deepseek r1 (#13291) hace 8 meses
  zhu-an 16865d43a8
feat: add deepseek models for volcengine provider (#13283) hace 9 meses
  呆萌闷油瓶 0d13aee15c
feat:add deepseek r1 think display for ollama provider (#13272) hace 9 meses
  engchina 40dd63ecef
Upgrade oracle models (#13174) hace 9 meses
  -LAN- 6d66d6da15
feat(model_providers): Support deepseek-r1 for Nvidia Catalog (#13269) hace 9 meses
  -LAN- 87763fc234
feat(model_providers): Support deepseek for Azure AI Foundry (#13267) hace 9 meses
  JasonVV f6c44cae2e
feat(model): add gemini-2.0 model (#13266) hace 9 meses
  xhe da2ee04fce
fix: correct linewrap think display in generic openai api (#13260) hace 9 meses
  JasonVV 7673c36af3
feat(model): add gemini-2.0-flash-thinking-exp-01-21 (#13230) hace 9 meses
  Riddhimaan-Senapati 9457b2af2f
feat: added models :gemini 2.0 flash 001 and gemini 2.0 pro exp 02-05 (#13247) hace 9 meses
  k-zaku 7203991032
feat: add parameter "reasoning_effort" and Openai o3-mini (#13243) hace 9 meses
  xhe 5a685f7156
feat: add think display for volcengine and generic openapi (#13234) hace 9 meses
  Riddhimaan-Senapati a6a25030ad
fix: updated _position.yaml to include the latest model already integ… (#13245) hace 9 meses
  Riddhimaan-Senapati 00458a31d5
feat: added deepseek r1 and v3 to siliconflow (#13238) hace 9 meses
  -LAN- c6ddf6d6cc
feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b (#13229) hace 9 meses
  Joshbly 34b21b3065
feat: Add o3-mini and o3-mini-2025-01-31 model variants (#13129) hace 9 meses
  -LAN- 59ca44f493
chore(model_runtime): Move deepseek ahead in the providers list. (#13197) hace 9 meses
  Nam Vu a97cec57e4
fix: SSRF proxy file descriptor leak in concurrent requests (#13108) hace 9 meses
  MaFee921 1a2523fd15
feat: bedrock_endpoint_url (#12838) hace 9 meses
  Warren Chen 03243cb422
Modify params for bedrock retrieve generate (#13182) hace 9 meses
  Kei YAMAZAKI 7452032d81
add azure openai api version 2024-12-01-preview (#13135) hace 9 meses
  非法操作 840729afa5
feat: the think tag display of siliconflow's deepseek r1 (#13153) hace 9 meses
  -LAN- b47669b80b
fix: deduct LLM quota after processing invoke result (#13075) hace 9 meses
  Yingchun Lai b09c39c8dc
refactor: avoid to use extra space when finding model by name (#13043) hace 9 meses
  heyszt b4b09ddc3c
add tongyi qwen2.5-14b/7b-instruct-1m model (#13089) hace 9 meses
  Ademílson Tonato d0a21086bd
refactor: Update Firecrawl API parameters and default settings (#13082) hace 9 meses
  Yingchun Lai d44882c1b5
refactor: reduce duplciate code by inheritance (#13073) hace 9 meses
  Jason 560c5de1b7
Fixed Novita AI color and added DeepSeek R1 model (#13074) hace 9 meses
  heyszt 6c31ee36cd
fix qwen-vl blocking mode (#13052) hace 9 meses
  jiandanfeng edc29780ed
fix: "Model schema not found" error only in agents (#12655) (#12760) hace 9 meses