| .. |
|
__base
|
c5f7d650b5
feat: Allow using file variables directly in the LLM node and support more file types. (#10679)
|
hai 1 ano |
|
anthropic
|
5b7b328193
feat: Allow to contains files in the system prompt even model not support. (#11111)
|
hai 1 ano |
|
azure_ai_studio
|
51db59622c
chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425)
|
hai 1 ano |
|
azure_openai
|
6f9ce6a199
fix: fix azure open-4o-08-06 when enable json schema cant process content = "" (#11204)
|
hai 1 ano |
|
baichuan
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
bedrock
|
16c41585e1
Fixing #11005: Incorrect max_tokens in yaml file for AWS Bedrock US Cross Region Inference version of 3.5 Sonnet v2 and 3.5 Haiku (#11013)
|
hai 1 ano |
|
chatglm
|
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules (#8296)
|
hai 1 ano |
|
cohere
|
0067b16d1e
fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883)
|
hai 1 ano |
|
deepseek
|
aae29e72ae
Fix Deepseek Function/Tool Calling (#11023)
|
hai 1 ano |
|
fireworks
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
fishaudio
|
448a19bf54
fix: fish audio wrong validate credentials interface (#11019)
|
hai 1 ano |
|
gitee_ai
|
40fc6f529e
fix: gitee ai wrong default model, and better para (#11168)
|
hai 1 ano |
|
google
|
594666eb61
fix: use Gemini response metadata for token counting (#11226)
|
hai 1 ano |
|
gpustack
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
groq
|
b92504bebc
Added Llama 3.2 Vision Models Speech2Text Models for Groq (#9479)
|
hai 1 ano |
|
huggingface_hub
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
huggingface_tei
|
096c0ad564
feat: Add support for TEI API key authentication (#11006)
|
hai 1 ano |
|
hunyuan
|
92a3898540
fix: resolve the incorrect model name of hunyuan-standard-256k (#10052)
|
hai 1 ano |
|
jina
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
leptonai
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
localai
|
1e829ceaf3
chore: format get_customizable_model_schema return value (#9335)
|
hai 1 ano |
|
minimax
|
5b8f03cd9d
add abab7-chat-preview model (#10654)
|
hai 1 ano |
|
mistralai
|
5ddb601e43
add MixtralAI Model (#8517)
|
hai 1 ano |
|
mixedbread
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
moonshot
|
1b5adf40da
fix: moonshot response_format raise error (#9847)
|
hai 1 ano |
|
nomic
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
novita
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
nvidia
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
nvidia_nim
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
oci
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
ollama
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
openai
|
aa135a3780
Add TTS to OpenAI_API_Compatible (#11071)
|
hai 1 ano |
|
openai_api_compatible
|
239bf97b47
fix: nvidia special embedding model payload close #11193 (#11239)
|
hai 1 ano |
|
openllm
|
0067b16d1e
fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883)
|
hai 1 ano |
|
openrouter
|
4d6b45427c
Support streaming output for OpenAI o1-preview and o1-mini (#10890)
|
hai 1 ano |
|
perfxcloud
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
replicate
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
sagemaker
|
51db59622c
chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425)
|
hai 1 ano |
|
siliconflow
|
a4fc057a1c
ISSUE=11042: add tts model in siliconflow (#11043)
|
hai 1 ano |
|
spark
|
d0e0111f88
fix:Spark's large language model token calculation error #7911 (#8755)
|
hai 1 ano |
|
stepfun
|
1e829ceaf3
chore: format get_customizable_model_schema return value (#9335)
|
hai 1 ano |
|
tencent
|
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules (#8296)
|
hai 1 ano |
|
togetherai
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
tongyi
|
08ac36812b
feat: support LLM process document file (#10966)
|
hai 1 ano |
|
triton_inference_server
|
1e829ceaf3
chore: format get_customizable_model_schema return value (#9335)
|
hai 1 ano |
|
upstage
|
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension (#9423)
|
hai 1 ano |
|
vertex_ai
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
vessl_ai
|
aa895cfa9b
fix: [VESSL-AI] edit some words in vessl_ai.yaml (#10417)
|
hai 1 ano |
|
volcengine_maas
|
80da0c5830
fix: default max_chunks set to 1 as other providers (#10937)
|
hai 1 ano |
|
voyage
|
8aae235a71
fix: int None will cause error for context size (#11055)
|
hai 1 ano |
|
wenxin
|
4d5546953a
add llm: ernie-4.0-turbo-128k of wenxin (#10135)
|
hai 1 ano |
|
x
|
1065917872
Add grok-vision-beta to xAI + Update grok-beta Features (#11004)
|
hai 1 ano |
|
xinference
|
03ba4bc760
fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012)
|
hai 1 ano |
|
yi
|
e0846792d2
feat: add yi custom llm intergration (#9482)
|
hai 1 ano |
|
zhinao
|
2cf1187b32
chore(api/core): apply ruff reformatting (#7624)
|
hai 1 ano |
|
zhipuai
|
2e00829b1e
fix: drop useless and wrong code for zhipu embedding (#11069)
|
hai 1 ano |
|
__init__.py
|
d069c668f8
Model Runtime (#1858)
|
%!s(int64=2) %!d(string=hai) anos |
|
_position.yaml
|
fb49413a41
feat: add voyage ai as a new model provider (#8747)
|
hai 1 ano |
|
model_provider_factory.py
|
4e7b6aec3a
feat: support pinning, including, and excluding for model providers and tools (#7419)
|
hai 1 ano |
yihong
239bf97b47
fix: nvidia special embedding model payload close #11193 (#11239)