| .. |
|
__base
|
142dc0afd7
refactor: Remove unused code in large_language_model.py (#5433)
|
1 year ago |
|
anthropic
|
ff0f02d809
feat: add support for claude-3-5-sonnet-20240620 (#5452)
|
1 year ago |
|
azure_openai
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
baichuan
|
adc948e87c
fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138)
|
1 year ago |
|
bedrock
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
chatglm
|
228de1f12a
fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224)
|
1 year ago |
|
cohere
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
deepseek
|
c163521b9e
Update and fix the model param of Deepseek (#5329)
|
1 year ago |
|
google
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
groq
|
a4e4fb4094
fix: credentials validate failed for groqcloud model provider (#3817)
|
1 year ago |
|
huggingface_hub
|
063191889d
chore: apply ruff's pyupgrade linter rules to modernize Python code with targeted version (#2419)
|
1 year ago |
|
hunyuan
|
ea69dc2a7e
feat: support hunyuan llm models (#5013)
|
1 year ago |
|
jina
|
3ccad33194
feat: add jina new pre-defined rerankers, include: jina-reranker-v2 (#5657)
|
1 year ago |
|
leptonai
|
51a9e678f0
Leptonai integrate (#4079)
|
1 year ago |
|
localai
|
9a64aa76c1
fix: typo and check (#5287)
|
1 year ago |
|
minimax
|
4086f5051c
feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294)
|
1 year ago |
|
mistralai
|
de3b490f8e
Add mixtral 8x22b (#3606)
|
1 year ago |
|
moonshot
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
novita
|
b7ff765d8d
Add novita.ai as model provider (#4961)
|
1 year ago |
|
nvidia
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
nvidia_nim
|
696c5308a9
chore: optimize nvidia nim credential schema and info (#4898)
|
1 year ago |
|
ollama
|
7f44e88eda
fix(model_providers/ollama): Fix OllamaLargeLanguageModel to correctly set the stop option (#5217)
|
1 year ago |
|
openai
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
openai_api_compatible
|
bafc8a0bde
fix: tool call message role according to credentials (#5625)
|
1 year ago |
|
openllm
|
04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497)
|
1 year ago |
|
openrouter
|
877a2c144b
feat: support predefined models for openrouter (#5494)
|
1 year ago |
|
replicate
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
siliconflow
|
79e8489942
feat: support siliconflow (#5129)
|
1 year ago |
|
spark
|
13694293e3
fix: resolve header.uid' length must be less or equal than 32 on Spark V1.5 (#2983)
|
1 year ago |
|
togetherai
|
ba5f8afaa8
Feat/firecrawl data source (#5232)
|
1 year ago |
|
tongyi
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
triton_inference_server
|
5b447d61a6
feat: refactor tongyi models (#3496)
|
1 year ago |
|
vertex_ai
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
volcengine_maas
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
wenxin
|
0f35d07052
support ERNIE-4.0-8K-Latest (#5216)
|
1 year ago |
|
xinference
|
2b080b5cfc
feature: Add presence_penalty and frequency_penalty parameters to the … (#5637)
|
1 year ago |
|
yi
|
ece0f08a2b
add yi models (#4335)
|
1 year ago |
|
zhipuai
|
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions (#5652)
|
1 year ago |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
1 year ago |
|
_position.yaml
|
79e8489942
feat: support siliconflow (#5129)
|
1 year ago |
|
model_provider_factory.py
|
23fa3dedc4
fix(core): Fix incorrect type hints. (#5427)
|
1 year ago |
liuzhenghua
2b080b5cfc
feature: Add presence_penalty and frequency_penalty parameters to the … (#5637)