| .. |
|
__init__.py
|
5fa2161b05
feat: server multi models support (#799)
|
hai 1 ano |
|
anthropic_model.py
|
2eba98a465
feat: optimize anthropic connection pool (#1066)
|
hai 1 ano |
|
azure_openai_model.py
|
cbf095465c
feat: remove llm client use (#1316)
|
hai 1 ano |
|
baichuan_model.py
|
fe14130b3c
refactor advanced prompt core. (#1350)
|
hai 1 ano |
|
base.py
|
fe14130b3c
refactor advanced prompt core. (#1350)
|
hai 1 ano |
|
chatglm_model.py
|
0796791de5
feat: hf inference endpoint stream support (#1028)
|
hai 1 ano |
|
huggingface_hub_model.py
|
fe14130b3c
refactor advanced prompt core. (#1350)
|
hai 1 ano |
|
localai_model.py
|
417c19577a
feat: add LocalAI local embedding model support (#1021)
|
hai 1 ano |
|
minimax_model.py
|
2851a9f04e
feat: optimize minimax llm call (#1312)
|
hai 1 ano |
|
openai_model.py
|
9822f687f7
fix: max tokens of OpenAI gpt-3.5-turbo-instruct to 4097 (#1338)
|
hai 1 ano |
|
openllm_model.py
|
fe14130b3c
refactor advanced prompt core. (#1350)
|
hai 1 ano |
|
replicate_model.py
|
0796791de5
feat: hf inference endpoint stream support (#1028)
|
hai 1 ano |
|
spark_model.py
|
0796791de5
feat: hf inference endpoint stream support (#1028)
|
hai 1 ano |
|
tongyi_model.py
|
c536f85b2e
fix: compatibility issues with the tongyi model. (#1310)
|
hai 1 ano |
|
wenxin_model.py
|
7c9b585a47
feat: support weixin ernie-bot-4 and chat mode (#1375)
|
hai 1 ano |
|
xinference_model.py
|
fe14130b3c
refactor advanced prompt core. (#1350)
|
hai 1 ano |
|
zhipuai_model.py
|
52ebffa857
fix: app config zhipu chatglm_std model, but it still use chatglm_lit… (#1377)
|
hai 1 ano |
Garfield Dai
fe14130b3c
refactor advanced prompt core. (#1350)