| .. |
|
agent
|
f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules (#4925)
|
hace 10 meses |
|
app
|
80a87f36ea
fix: missing iterator in task pipeline (#4948)
|
hace 10 meses |
|
callback_handler
|
e635f3dc1d
chore: remove langchain in tools (#3247)
|
hace 1 año |
|
embedding
|
2e4dec365d
Compatible with unique index conflicts (#3183)
|
hace 1 año |
|
entities
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
hace 10 meses |
|
errors
|
d069c668f8
Model Runtime (#1858)
|
hace 1 año |
|
extension
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
hace 10 meses |
|
external_data_tool
|
7753ba2d37
FEAT: NEW WORKFLOW ENGINE (#3160)
|
hace 1 año |
|
file
|
f40743183e
:wrench: Add env variable for time signature (#4650)
|
hace 11 meses |
|
helper
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
hace 10 meses |
|
llm_generator
|
8811677154
feat: remove langchain from output parsers (#3473)
|
hace 1 año |
|
memory
|
3929d289e0
feat: set default memory messages limit to infinite (#5002)
|
hace 10 meses |
|
model_runtime
|
ea69dc2a7e
feat: support hunyuan llm models (#5013)
|
hace 10 meses |
|
moderation
|
7753ba2d37
FEAT: NEW WORKFLOW ENGINE (#3160)
|
hace 1 año |
|
prompt
|
3929d289e0
feat: set default memory messages limit to infinite (#5002)
|
hace 10 meses |
|
rag
|
bdad993901
improve: generalize vector factory classes and vector type (#5033)
|
hace 10 meses |
|
tools
|
b7c72f7a97
dalle3 add style consistency parameter (#5067)
|
hace 10 meses |
|
workflow
|
73dee84cab
fix: add handling for non-string type in variable template parser (#4996)
|
hace 10 meses |
|
__init__.py
|
db43ed6f41
feat: add api-based extension & external data tool & moderation backend (#1403)
|
hace 1 año |
|
hosting_configuration.py
|
60e7e17c86
feat: Add new Azure OpenAI Embedding models (#2758)
|
hace 1 año |
|
indexing_runner.py
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
hace 10 meses |
|
model_manager.py
|
5986841e27
fix: issue where an error occurs when invoking TTS without selecting a voice (#5046)
|
hace 10 meses |
|
provider_manager.py
|
b20d173324
pref: optimize feature model_load_balancing_enabled value fetch speed… (#4933)
|
hace 10 meses |
xielong
ea69dc2a7e
feat: support hunyuan llm models (#5013)