OpenSource
/
dify
Vērot 4
Pievienot zvaigznīti 0
Atdalīts 0
Kods Problēmas 0 Izmaiņu pieprasījumi 0 Laidieni 152 Vikivietne Aktivitāte
6378 Revīzijas
4 Atzari
Koks: ff8fc96ebb
Atzari Tagi
${ item.name }
Izveidot atzaru ${ searchTerm }
no 'ff8fc96ebb'
${ noResults }
Revīziju grafs

76 Revīzijas (ff8fc96ebbc6d29fbd21e776b654f55d9415af6d)

Autors SHA1 Ziņojums Datums
  -LAN- 460a825ef1
refactor: decouple Node and NodeData (#22581) pirms 3 mēnešiem
  Kalo Chin 7a69b57823
Fix jinja2 variable naming inconsistencies (#22578) pirms 3 mēnešiem
  Davide Delbianco 816210d744
Expose LLM usage in workflows (#21766) pirms 3 mēnešiem
  Yeuoly 0cb00d5fd2
refactor: move structured output support outside LLM Node (#21565) pirms 4 mēnešiem
  QuantumGhost 10b738a296
feat: Persist Variables for Enhanced Debugging Workflow (#20699) pirms 4 mēnešiem
  -LAN- 1e03c97663
fix(llm_node): missing parameters for structure outputs (#20915) pirms 4 mēnešiem
  Jyong 21a50e22d2
fix auto metadata filter (#20845) pirms 4 mēnešiem
  QuantumGhost c439e82038
refactor(api): Decouple `ParameterExtractorNode` from `LLMNode` (#20843) pirms 4 mēnešiem
  Arcaner ad2f25875e
fix(llm_node): update file variable mapping to use vision configs (#20417) pirms 5 mēnešiem
  -LAN- 5ccfb1f4ba
refactor: Improve model status handling and structured output (#20586) pirms 5 mēnešiem
  -LAN- 72fdafc180
refactor: Replaces direct DB session usage with context managers (#20569) pirms 5 mēnešiem
  -LAN- a6ea15e63c
Refactor/message cycle manage and knowledge retrieval (#20460) pirms 5 mēnešiem
  -LAN- 32e779eef3
refactor(workflow): Rename NodeRunMetadataKey to WorkflowNodeExecutionMetadataKey (#20457) pirms 5 mēnešiem
  -LAN- 482e50aae9
Refactor/remove db from cycle manager (#20455) pirms 5 mēnešiem
  Will 58d9d35515
fix: inconsistent metadata definitions (#19343) pirms 5 mēnešiem
  Novice 0cfc82d731
fix(structured-output): reasoning model's json format parsing (#19261) pirms 6 mēnešiem
  QuantumGhost 349c3cf7b8
feat(api): Add image multimodal support for LLMNode (#17372) pirms 6 mēnešiem
  非法操作 c1559a7c8e
fix: LLMResultChunk cause concatenate str and list exception (#18852) 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 da9269ca97
feat: structured output (#17877) pirms 6 mēnešiem
  Jacky Wu ed5596a8f4
fix: avoid llm node result var not init issue while do retry. (#14286) pirms 7 mēnešiem
  LeanDeR 4f6a4f244c
fix(llm/nodes.py): Ensure that the output returns without any exceptions (#14880) pirms 8 mēnešiem
  yuhaowin 1e3197a1ea
Fixes 14217: database retrieve api and chat-messages api response doc_metadata (#14219) pirms 8 mēnešiem
  -LAN- 7a71498a3e
chore(quota): Update deduct quota (#14337) pirms 8 mēnešiem
  Yeuoly 403e2d58b9
Introduce Plugins (#13836) pirms 8 mēnešiem
  Vasu Negi 8a0aa91ed7
Non-Streaming Models Do Not Return Results Properly in _handle_invoke_result (#13571) 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 9 mēnešiem
  -LAN- 04d13a8116
feat(credits): Allow to configure model-credit mapping (#13274) pirms 9 mēnešiem
  -LAN- b47669b80b
fix: deduct LLM quota after processing invoke result (#13075) pirms 9 mēnešiem
  yihong 56e15d09a9
feat: mypy for all type check (#10921) pirms 10 mēnešiem
  JasonVV 4b1e13e982
Fix 11979 (#11984) pirms 10 mēnešiem
  -LAN- 996a9135f6
feat(llm_node): support order in text and files (#11837) pirms 10 mēnešiem
  Novice 79a710ce98
Feat: continue on error (#11458) pirms 10 mēnešiem
  yihong 716576043d
fix: issue 11247 that Completion mode content maybe list or str (#11504) pirms 10 mēnešiem
  -LAN- 464e6354c5
feat: correct the prompt grammar. (#11328) pirms 11 mēnešiem
  -LAN- 223a30401c
fix: LLM invoke error should not be raised (#11141) pirms 11 mēnešiem
  -LAN- 044e7b63c2
fix(llm_node): Ignore file if not supported. (#11114) pirms 11 mēnešiem
  -LAN- 5b7b328193
feat: Allow to contains files in the system prompt even model not support. (#11111) pirms 11 mēnešiem
  -LAN- cbb4e95928
fix(llm_node): Ignore user query when memory is disabled. (#11106) pirms 11 mēnešiem
  -LAN- 20c091a5e7
fix: user query be ignored if query_prompt_template is an empty string (#11103) pirms 11 mēnešiem
  -LAN- 60b5dac3ab
fix: query will be None if the query_prompt_template not exists (#11031) pirms 11 mēnešiem
  非法操作 08ac36812b
feat: support LLM process document file (#10966) pirms 11 mēnešiem
  -LAN- c5f7d650b5
feat: Allow using file variables directly in the LLM node and support more file types. (#10679) pirms 11 mēnešiem
  非法操作 033ab5490b
feat: support LLM understand video (#9828) pirms 1 gada
  -LAN- 38bca6731c
refactor(workflow): introduce specific error handling for LLM nodes (#10221) pirms 1 gada
  -LAN- 8b5ea39916
chore(llm_node): remove unnecessary type ignore for context assignment (#10216) pirms 1 gada
  -LAN- 3b53e06e0d
fix(workflow): refine variable type checks in LLMNode (#10051) pirms 1 gada
  -LAN- eb87e690ed
fix(llm-node): handle NoneSegment variables properly (#9978) pirms 1 gada
  -LAN- d018b32d0b
fix(workflow): enhance prompt handling with vision support (#9790) pirms 1 gada