650 Commits

Author SHA1 Message Date
Shota Totsuka
594666eb61
fix: use Gemini response metadata for token counting (#11226) 2024-11-30 17:30:55 +08:00
liujiamingtiny
6f9ce6a199
fix: fix azure open-4o-08-06 when enable json schema cant process content = "" (#11204)
Co-authored-by: jiaming.liu <jiaming.liu@zkh.com>
2024-11-29 17:26:07 +08:00
yihong
40fc6f529e
fix: gitee ai wrong default model, and better para (#11168)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-27 17:27:11 +08:00
Tao Wang
aa135a3780
Add TTS to OpenAI_API_Compatible (#11071) 2024-11-26 15:14:02 +08:00
-LAN-
5b7b328193
feat: Allow to contains files in the system prompt even model not support. (#11111) 2024-11-26 13:45:49 +08:00
-LAN-
1db14793fa
fix(anthropic_llm): Ignore non-text parts in the system prompt. (#11107) 2024-11-26 13:31:40 +08:00
fengjiajie
ab6dcf7032
fix: update the max tokens configuration for Azure GPT-4o (2024-08-06) to 16384 (#11074) 2024-11-25 21:13:02 +08:00
yihong
8aae235a71
fix: int None will cause error for context size (#11055)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-25 21:04:16 +08:00
Tao Wang
1065917872
Add grok-vision-beta to xAI + Update grok-beta Features (#11004) 2024-11-25 20:53:03 +08:00
yihong
2e00829b1e
fix: drop useless and wrong code for zhipu embedding (#11069)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-25 19:50:23 +08:00
SiliconFlow, Inc
a4fc057a1c
ISSUE=11042: add tts model in siliconflow (#11043) 2024-11-25 11:04:13 +08:00
Tao Wang
aae29e72ae
Fix Deepseek Function/Tool Calling (#11023) 2024-11-25 11:03:53 +08:00
cyflhn
03ba4bc760
fix error with xinference tool calling with qwen2-instruct and add timeout retry setttings for xinference (#11012)
Co-authored-by: crazywoola <427733928@qq.com>
2024-11-24 15:29:30 +08:00
Bowen Liang
6c8e208ef3
chore: bump minimum supported Python version to 3.11 (#10386) 2024-11-24 13:28:46 +08:00
kenwoodjw
096c0ad564
feat: Add support for TEI API key authentication (#11006)
Signed-off-by: kenwoodjw <blackxin55+@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-11-23 23:55:35 +08:00
Kazuhisa Wada
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) 2024-11-23 23:46:25 +08:00
yihong
448a19bf54
fix: fish audio wrong validate credentials interface (#11019)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-23 23:39:41 +08:00
非法操作
08ac36812b
feat: support LLM process document file (#10966)
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-11-22 19:32:44 +08:00
-LAN-
c5f7d650b5
feat: Allow using file variables directly in the LLM node and support more file types. (#10679)
Co-authored-by: Joel <iamjoel007@gmail.com>
2024-11-22 16:30:22 +08:00
CXwudi
d9579f418d
chore: Added the new gemini exp-1121 and learnlm-1.5 models (#10963) 2024-11-22 13:14:20 +08:00
Agung Besti
e8868a7fb9
feat: add gpt-4o-2024-11-20 (#10951)
Co-authored-by: akubesti <agung.besti@insignia.co.id>
2024-11-22 10:29:20 +08:00
LastHopeOfGPNU
1a6b961b5f
Resolve 8475 support rerank model from infinity (#10939)
Co-authored-by: linyanxu <linyanxu2@qq.com>
2024-11-21 18:03:49 +08:00
-LAN-
82575a7aea
fix(gpt-4o-audio-preview): Remove the vision feature (#10932) 2024-11-21 16:42:48 +08:00
yihong
80da0c5830
fix: default max_chunks set to 1 as other providers (#10937)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-21 16:36:05 +08:00
yihong
0067b16d1e
fix: refactor all 'or []' and 'or {}' logic to make code more clear (#10883)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
2024-11-21 10:34:43 +08:00
-LAN-
4d6b45427c
Support streaming output for OpenAI o1-preview and o1-mini (#10890) 2024-11-20 15:10:41 +08:00
ybalbert001
c3d11c8ff6
fix: aws presign url is not workable remote url (#10884)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-11-20 14:24:41 +08:00
GeorgeCaoJ
fbfc811a44
feat: support function call for ollama block chat api (#10784) 2024-11-20 11:15:19 +08:00
Ding Jiatong
3087913b74
Fix the situation where output_tokens/input_tokens may be None in response.usage (#10728) 2024-11-19 21:19:13 +08:00
Jyong
bd05df5cc5
fix tongyi embedding endpoint return None output (#10857) 2024-11-19 21:04:17 +08:00
非法操作
bc1013dacf
feat: support json schema for gemini models (#10835) 2024-11-19 17:49:58 +08:00
非法操作
ba537d657f
feat: add gemini-exp-1114 (#10779) 2024-11-18 09:49:22 +08:00
Bowen Liang
51db59622c
chore(lint): cleanup repeated cause exception in logging.exception replaced by helpful message (#10425) 2024-11-15 15:41:40 +08:00
Bowen Liang
365cb4b368
chore(lint): bump ruff from 0.6.9 to 0.7.3 (#10714) 2024-11-15 09:19:41 +08:00
SiliconFlow, Inc
e61242a337
feat: add vlm models from siliconflow (#10704) 2024-11-14 20:53:35 +08:00
orangeclk
317ae9233e
feat: add json response format for siliconflow models (#10657) 2024-11-14 08:58:22 +08:00
xiandan-erizo
5b8f03cd9d
add abab7-chat-preview model (#10654)
Co-authored-by: xiandan-erizo <xiandan-erizo@outlook.com>
2024-11-13 19:30:42 +08:00
方程
ef8022f715
Gitee AI Qwen2.5-72B model (#10595) 2024-11-12 21:40:32 +08:00
Kevin9703
e03ec0032b
fix: Azure OpenAI o1 max_completion_token error (#10593) 2024-11-12 21:40:13 +08:00
-LAN-
867bf70f1a
fix(model_runtime): ensure compatibility with O1 models by adjusting token parameters (#10537) 2024-11-11 16:06:53 +08:00
Jyong
0c1307b083
add jina rerank http timout parameter (#10476) 2024-11-11 13:28:11 +08:00
fdb02983rhy
05d43a4074
Fix: Correct the max tokens of Claude-3.5-Sonnet-20241022 for Bedrock and VertexAI (#10508) 2024-11-11 08:41:43 +08:00
larcane97
aa895cfa9b
fix: [VESSL-AI] edit some words in vessl_ai.yaml (#10417)
Co-authored-by: moon <moon@vessl.ai>
2024-11-11 08:38:26 +08:00
非法操作
033ab5490b
feat: support LLM understand video (#9828) 2024-11-08 13:22:52 +08:00
Bowen Liang
574c4a264f
chore(lint): Use logging.exception instead of logging.error (#10415) 2024-11-07 21:13:02 +08:00
Matsuda
1e8457441d
fix(model_runtime): remove vision from features for Claude 3.5 Haiku (#10360) 2024-11-06 17:42:18 +08:00
Infinitnet
5a9448245b
fix: remove unsupported vision in OpenRouter Haiku 3.5 (#10364) 2024-11-06 17:41:48 +08:00
Bowen Liang
d45d90e8ae
chore: lazy import sagemaker (#10342) 2024-11-06 12:45:22 +08:00
Infinitnet
bdadca1a65
feat: add support for anthropic/claude-3-5-haiku through OpenRouter (#10331) 2024-11-06 08:26:44 +08:00
非法操作
bf9349c4dc
feat: add xAI model provider (#10272) 2024-11-05 14:42:47 +08:00