306 次程式碼提交 (13fcd7a901b78219fb7ecae5aea250ca70ec6ddc)

作者 SHA1 備註 提交日期
  takatost 3929d289e0
feat: set default memory messages limit to infinite (#5002) 1 年之前
  Joe 5cdb95be1f
fix: gemini timeout error (#4955) 1 年之前
  Bowen Liang f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules (#4925) 1 年之前
  takatost f44d1e62d2
fix: bedrock get_num_tokens prompt_messages parameter name err (#4932) 1 年之前
  takatost d1dbbc1e33
feat: backend model load balancing support (#4927) 1 年之前
  Pan, Wen-Ming b98a1a3303
feat: added Anthropic Claude3 models to Google Cloud Vertex AI (#4870) 1 年之前
  takatost 696c5308a9
chore: optimize nvidia nim credential schema and info (#4898) 1 年之前
  Joshua 3c8a120e51
add-nvidia-mim (#4882) 1 年之前
  Pan, Wen-Ming cdbc260571
Bugfix: Vertex AI vision model not support image (#4853) 1 年之前
  Yash Parmar e0da0744b5
add: ollama keep alive parameter added. issue #4024 (#4655) 1 年之前
  Weaxs b189faca52
feat: update ernie model (#4756) 1 年之前
  xielong e1cd9aef8f
feat: support baichuan3 turbo, baichuan3 turbo 128k, and baichuan4 (#4762) 1 年之前
  crazywoola 705a6e3a8e
Fix/4742 ollama num gpu option not consistent with allowed values (#4751) 1 年之前
  xielong 793f0c1dd6
fix: Corrected schema link in model_runtime's README.md (#4757) 1 年之前
  xielong 88b4d69278
fix: Correct context size for banchuan2-53b and banchuan2-turbo (#4721) 1 年之前
  crazywoola 27dae156db
fix: colon in file mistral.mistral-small-2402-v1:0 (#4673) 1 年之前
  Giovanny Gutiérrez 2deb23e00e
fix: Show rerank in system for localai (#4652) 1 年之前
  longzhihun fe9bf5fc4a
[seanguo] add support of amazon titan v2 and modify the price of amazon titan v1 (#4643) 1 年之前
  miendinh f804adbff3
feat: Support for Vertex AI - load Default Application Configuration (#4641) 1 年之前
  Krasus.Chen f156014daa
update lite8k/speed8k/128k max_token to newest (#4636) 1 年之前
  Bowen Liang 3fda2245a4
improve: extract method for safe loading yaml file and avoid using PyYaml's FullLoader (#4031) 1 年之前
  Patryk Garstecki 296887754f
Support for Vertex AI (#4586) 1 年之前
  QuietRocket 9ae72cdcf4
feat: Add Gemini Flash (#4616) 1 年之前
  takatost 11642192d1
chore: add https://api.openai.com placeholder in OpenAI api base (#4604) 1 年之前
  呆萌闷油瓶 e57bdd4e58
chore:update gpt-3.5-turbo and gpt-4-turbo parameter for azure (#4596) 1 年之前
  somethingwentwell 461488e9bf
Add Azure OpenAI API version for GPT4o support (#4569) 1 年之前
  Justin Wu 3ab19be9ea
Fix bedrock claude wrong pricing (#4572) 1 年之前
  呆萌闷油瓶 d5a33a0323
feat:add gpt-4o for azure (#4568) 1 年之前
  Bowen Liang e8e213ad1e
chore: apply and fix flake8-bugbear lint rules (#4496) 1 年之前
  Ever 4086f5051c
feat:Provide parameter config for mask_sensitive_info of MiniMax mode… (#4294) 1 年之前
  fanghongtai 1cca100a48
fix:modify spelling errors: lanuage ->language in schema.md (#4499) 1 年之前
  Bowen Liang 04ad46dd31
chore: skip unnecessary key checks prior to accessing a dictionary (#4497) 1 年之前
  Yeuoly 091fba74cb
enhance: claude stream tool call (#4469) 1 年之前
  jiaqianjing 0ac5d621b6
add llm: ernie-character-8k of wenxin (#4448) 1 年之前
  sino 6e9066ebf4
feat: support doubao llm and embeding models (#4431) 1 年之前
  Yash Parmar 332baca538
FIX: fix the temperature value of ollama model (#4027) 1 年之前
  Yeuoly e8311357ff
feat: gpt-4o (#4346) 1 年之前
  orangeclk ece0f08a2b
add yi models (#4335) 1 年之前
  Weaxs 8cc492721b
fix: minimax streaming function_call message (#4271) 1 年之前
  Joshua a80fe20456
add-some-new-models-hosted-on-nvidia (#4303) 1 年之前
  呆萌闷油瓶 4796f9d914
feat:add gpt-4-turbo for azure (#4287) 1 年之前
  Sebastian.W a588df4371
Add rerank model type for LocalAI provider (#3952) 1 年之前
  Bowen Liang 228de1f12a
fix: miss usage of os.path.join for URL assembly and add tests on yarl (#4224) 1 年之前
  sino 4aa21242b6
feat: add volcengine maas model provider (#4142) 1 年之前
  Yong723 8ce93faf08
Typo on deepseek.yaml and yi.yaml (#4170) 1 年之前
  Su Yang 9f440c11e0
feat: DeepSeek (#4162) 1 年之前
  Joshua 58bd5627bf
Add-Deepseek (#4157) 1 年之前
  Moonlit 2fdd64c1b5
feat: add proxy configuration for Cohere model (#4152) 1 年之前
  VoidIsVoid 543a00e597
feat: update model_provider jina to support custom url and model (#4110) 1 年之前
  Minamiyama f361c7004d
feat: support vision models from xinference (#4094) 1 年之前