takatost 3fa5204b0c

feat: optimize performance (#1928)

2024-01-04 20:48:54 +08:00

..

__base

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

anthropic

fix: anthropic messages empty raise errors (#1893)

2024-01-03 22:12:14 +08:00

azure_openai

fix: array oob in azure openai embeddings (#1905)

2024-01-04 13:11:54 +08:00

baichuan

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

chatglm

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

cohere

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

google

fix: gemini block error (#1877)

2024-01-03 17:45:15 +08:00

huggingface_hub

fix: huggingface and replicate. (#1888)

2024-01-03 18:29:44 +08:00

jina

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

localai

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

minimax

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

openai

fix: openai embedding list out of bound (#1879)

2024-01-03 15:30:22 +08:00

openai_api_compatible

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

openllm

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

replicate

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

spark

fix: spark credentials validate (#1906)

2024-01-04 13:20:45 +08:00

tongyi

fix: tongyi generate error (#1904)

2024-01-04 12:57:45 +08:00

wenxin

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

xinference

fix: xinference cache (#1926)

2024-01-04 20:39:58 +08:00

zhipuai

fix: zhipuai chatglm turbo prompts must user, assistant in sequence (#1899)

2024-01-04 10:39:21 +08:00

__init__.py

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

_position.yaml

Model Runtime (#1858)

2024-01-02 23:42:00 +08:00

model_provider_factory.py

feat: optimize performance (#1928)

2024-01-04 20:48:54 +08:00