306 Commity (13fcd7a901b78219fb7ecae5aea250ca70ec6ddc)

Autor SHA1 Wiadomość Data
  vccler 48757e581e
fix: zhipu tool calling, this PR fixes the bug described in issue #5496 (#5469) 1 rok temu
  LXM e8ad0339a3
fix: tongyi json output (#5396) 1 rok temu
  crazywoola 91d38a535f
fix: max_tokens of qwen-plus & qwen-plus-chat (#5480) 1 rok temu
  Pan, Wen-Ming 95c882934e
feat: add support for Vertex AI claude-3-5-sonnet@20240620 (#5475) 1 rok temu
  Su Yang 26b6fd2236
feat: add support for bedrock claude-3-5-sonnet-20240620 (#5461) 1 rok temu
  takatost ff0f02d809
feat: add support for claude-3-5-sonnet-20240620 (#5452) 1 rok temu
  -LAN- 142dc0afd7
refactor: Remove unused code in large_language_model.py (#5433) 1 rok temu
  -LAN- 23fa3dedc4
fix(core): Fix incorrect type hints. (#5427) 1 rok temu
  Ikko Eltociear Ashimine 8266842809
chore: update llm.py (#5335) 1 rok temu
  Richards Tu c163521b9e
Update and fix the model param of Deepseek (#5329) 1 rok temu
  Justin Wu 61f4f08744
Add bedrock command r models (#4521) 1 rok temu
  -LAN- 5a99aeb864
fix(core): Reorder `field_validator` and `classmethod` to fit Pydantic V2. (#5257) 1 rok temu
  crazywoola 9a64aa76c1
fix: typo and check (#5287) 1 rok temu
  Pan, Wen-Ming 4b54843ed7
fix: run agent with Vertex AI Gemini models (#5260) 1 rok temu
  kurokobo 2e842333b1
fix: correct typos in the icons for microsoft (#5243) 1 rok temu
  Masashi Tomooka d9bee03ff6
fix: embedding job fails using IAM role (#5252) 1 rok temu
  Jyong ba5f8afaa8
Feat/firecrawl data source (#5232) 1 rok temu
  Bin 0f35d07052
support ERNIE-4.0-8K-Latest (#5216) 1 rok temu
  -LAN- 7f44e88eda
fix(model_providers/ollama): Fix OllamaLargeLanguageModel to correctly set the stop option (#5217) 1 rok temu
  Jason b7ff765d8d
Add novita.ai as model provider (#4961) 1 rok temu
  Masashi Tomooka 0633aae7dc
feat: allow to use IAM Role for Bedrock (#5188) 1 rok temu
  takatost 415022aa14
fix: pydantic2 error (#5172) 1 rok temu
  rerorero b85ae146a7
fix: JSON mode with an image doesn't work for Gemini (#5169) 1 rok temu
  Pan, Wen-Ming f13af5a811
fix(model_providers/vertex_ai): Vertex AI Anthropic models authentication failed (#4971) 1 rok temu
  Bowen Liang f976740b57
improve: mordernizing validation by migrating pydantic from 1.x to 2.x (#4592) 1 rok temu
  kurokobo e61f5d029a
chore(docs): fix minor small typos (#5124) 1 rok temu
  sino 8210637bc5
feat: support jina-clip-v1 embedding model (#5146) 1 rok temu
  呆萌闷油瓶 790543131a
chore:add some new api version for azure openai (#5142) 1 rok temu
  yanghx adc948e87c
fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 (#5138) 1 rok temu
  orangeclk 79e8489942
feat: support siliconflow (#5129) 1 rok temu
  xielong ea69dc2a7e
feat: support hunyuan llm models (#5013) 1 rok temu
  Pika ecc7f130b4
fix(typo): misspelling (#5094) 1 rok temu
  sino 0ce97e6315
feat: support doubao llm function calling (#5100) 1 rok temu
  rerorero 28997772a5
fix: remote_url doesn't work for gemini (#5090) 1 rok temu
  orangeclk 2050a8b8f0
feat: add glm4 new models and zhipu embedding-2 (#5089) 1 rok temu
  sino 5f870ac950
chore: update maas model provider description (#5056) 1 rok temu
  Jaxon Ley 2573b138bf
fix: update presence_penalty configuration for wenxin AI ernie-4.0-8k and ernie-3.5-8k models (#5039) 1 rok temu
  takatost 3929d289e0
feat: set default memory messages limit to infinite (#5002) 1 rok temu
  Joe 5cdb95be1f
fix: gemini timeout error (#4955) 1 rok temu
  Bowen Liang f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules (#4925) 1 rok temu
  takatost f44d1e62d2
fix: bedrock get_num_tokens prompt_messages parameter name err (#4932) 1 rok temu
  takatost d1dbbc1e33
feat: backend model load balancing support (#4927) 1 rok temu
  Pan, Wen-Ming b98a1a3303
feat: added Anthropic Claude3 models to Google Cloud Vertex AI (#4870) 1 rok temu
  takatost 696c5308a9
chore: optimize nvidia nim credential schema and info (#4898) 1 rok temu
  Joshua 3c8a120e51
add-nvidia-mim (#4882) 1 rok temu
  Pan, Wen-Ming cdbc260571
Bugfix: Vertex AI vision model not support image (#4853) 1 rok temu
  Yash Parmar e0da0744b5
add: ollama keep alive parameter added. issue #4024 (#4655) 1 rok temu
  Weaxs b189faca52
feat: update ernie model (#4756) 1 rok temu
  xielong e1cd9aef8f
feat: support baichuan3 turbo, baichuan3 turbo 128k, and baichuan4 (#4762) 1 rok temu
  crazywoola 705a6e3a8e
Fix/4742 ollama num gpu option not consistent with allowed values (#4751) 1 rok temu