| .. |
|
agent
|
3542d55e67
improve: generalize tool parameter converter (#4786)
|
vor 1 Jahr |
|
app
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
callback_handler
|
e635f3dc1d
chore: remove langchain in tools (#3247)
|
vor 1 Jahr |
|
embedding
|
2e4dec365d
Compatible with unique index conflicts (#3183)
|
vor 1 Jahr |
|
entities
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
errors
|
d069c668f8
Model Runtime (#1858)
|
vor 1 Jahr |
|
extension
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
external_data_tool
|
7753ba2d37
FEAT: NEW WORKFLOW ENGINE (#3160)
|
vor 1 Jahr |
|
file
|
f40743183e
:wrench: Add env variable for time signature (#4650)
|
vor 1 Jahr |
|
helper
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
llm_generator
|
8811677154
feat: remove langchain from output parsers (#3473)
|
vor 1 Jahr |
|
memory
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
model_runtime
|
f44d1e62d2
fix: bedrock get_num_tokens prompt_messages parameter name err (#4932)
|
vor 1 Jahr |
|
moderation
|
7753ba2d37
FEAT: NEW WORKFLOW ENGINE (#3160)
|
vor 1 Jahr |
|
prompt
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
rag
|
7749b71fff
Optimize knowledge retrieval performance by batching dataset quries. (#4917)
|
vor 1 Jahr |
|
tools
|
09298a32e7
fix: vanna CVE-2024-5565 by disable visualize of ask func (#4930)
|
vor 1 Jahr |
|
workflow
|
7749b71fff
Optimize knowledge retrieval performance by batching dataset quries. (#4917)
|
vor 1 Jahr |
|
__init__.py
|
db43ed6f41
feat: add api-based extension & external data tool & moderation backend (#1403)
|
vor 2 Jahren |
|
hosting_configuration.py
|
60e7e17c86
feat: Add new Azure OpenAI Embedding models (#2758)
|
vor 1 Jahr |
|
indexing_runner.py
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
model_manager.py
|
d1dbbc1e33
feat: backend model load balancing support (#4927)
|
vor 1 Jahr |
|
provider_manager.py
|
b20d173324
pref: optimize feature model_load_balancing_enabled value fetch speed… (#4933)
|
vor 1 Jahr |
JasonVV
7749b71fff
Optimize knowledge retrieval performance by batching dataset quries. (#4917)