| .. |
|
__base
|
8b15b742ad
generalize position helper for parsing _position.yaml and sorting objects by name (#2803)
|
vor 2 Jahren |
|
anthropic
|
2dee8a25d5
fix: anthropic system prompt not working (#2885)
|
vor 2 Jahren |
|
azure_openai
|
f6314f8e73
feat:support azure openai llm 0125 version (#2889)
|
vor 2 Jahren |
|
baichuan
|
cb79a90031
feat: Add tools for open weather search and image generation using the Spark API. (#2845)
|
vor 2 Jahren |
|
bedrock
|
507aa6d949
fix: Fix the problem of system not working (#2884)
|
vor 2 Jahren |
|
chatglm
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
vor 2 Jahren |
|
cohere
|
e54c9cd401
Feat/open ai compatible functioncall (#2783)
|
vor 2 Jahren |
|
google
|
3e63abd335
Feat/json mode (#2563)
|
vor 2 Jahren |
|
groq
|
1809f05904
Feat/add groq (#2733)
|
vor 2 Jahren |
|
huggingface_hub
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
vor 2 Jahren |
|
jina
|
8fe83750b7
Fix/jina tokenizer cache (#2735)
|
vor 2 Jahren |
|
localai
|
742be06ea9
Fix/localai (#2840)
|
vor 2 Jahren |
|
minimax
|
7f3dec7bee
fix error msg format issue (#2715)
|
vor 2 Jahren |
|
mistralai
|
e54c9cd401
Feat/open ai compatible functioncall (#2783)
|
vor 2 Jahren |
|
moonshot
|
174ee1b646
fix: parameter `user` exceeded max length when invoking moonshot llm (#2596)
|
vor 2 Jahren |
|
nvidia
|
518c1ceb94
Feat/add-NVIDIA-as-a-new-model-provider (#2900)
|
vor 2 Jahren |
|
ollama
|
fbbba6db92
feat: optimize ollama model default parameters (#2894)
|
vor 2 Jahren |
|
openai
|
83145486b0
fix: fix unstable function call response arguments missing (#2872)
|
vor 2 Jahren |
|
openai_api_compatible
|
e54c9cd401
Feat/open ai compatible functioncall (#2783)
|
vor 2 Jahren |
|
openllm
|
7f3dec7bee
fix error msg format issue (#2715)
|
vor 2 Jahren |
|
replicate
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
vor 2 Jahren |
|
spark
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
vor 2 Jahren |
|
togetherai
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
vor 2 Jahren |
|
tongyi
|
8133ba16b1
chore: update Qwen model params (#2892)
|
vor 2 Jahren |
|
triton_inference_server
|
240a94182e
Feat/add triton inference server (#2928)
|
vor 2 Jahren |
|
wenxin
|
3e63abd335
Feat/json mode (#2563)
|
vor 2 Jahren |
|
xinference
|
405a00bb2c
fix:delete the slash at the end of xinference provider server_url (#2730)
|
vor 2 Jahren |
|
yi
|
c534d95972
fix: yi model price correction (#2946)
|
vor 2 Jahren |
|
zhipuai
|
e7343cc67c
add max_tokens parameter rule for zhipuai glm4 and glm4v (#2861)
|
vor 2 Jahren |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
vor 2 Jahren |
|
_position.yaml
|
240a94182e
Feat/add triton inference server (#2928)
|
vor 2 Jahren |
|
model_provider_factory.py
|
8b15b742ad
generalize position helper for parsing _position.yaml and sorting objects by name (#2803)
|
vor 2 Jahren |
orangeclk
c534d95972
fix: yi model price correction (#2946)