Commit Graph

777 Commits (413dfd56283febdedf5ebb25ce27ff07fd86363b)

Author SHA1 Message Date
crazywoola 6222179a57
Revert "fix:deepseek tool call not working correctly" (#12463) 1 year ago
Infinitnet 4e6c86341d
Add 'document' feature to Sonnet 3.5 through OpenRouter (#12444) 1 year ago
呆萌闷油瓶 9677144015
fix:deepseek tool call not working correctly (#12437) 1 year ago
SiliconFlow, Inc 15797c556f
add fish-speech-1.5 from siliconflow (#12425) 1 year ago
-LAN- d3f5b1cbb6
refactor: use tiktoken for token calculation (#12416)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
SiliconFlow, Inc dc650c5368
Fixes #12414: Add cheaper model and long context model for Qwen2.5-72B-Instruct from siliconflow (#12415) 1 year ago
Alex Chen 2bb521b135
Support TTS and Speech2Text for Model Provider GPUStack (#12381) 1 year ago
SiliconFlow, Inc 409cc7d9b0
mark deprecated models in siliconflow #12399 (#12405)
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
Warren Chen 147d578922
[Fix] revert sagemaker llm to support model hub (#12378) 1 year ago
方程 6df17a334c
fix: Update the API call address for the text_embedding model (#12342)
Co-authored-by: 方程 <fangcheng@oschina.cn>
1 year ago
jifei 3c2e30f348
fix: #12143 support streaming mode content start with "data:" (#12171) 1 year ago
丹枫染秋色 7c1961e618
feat: Add response format support to GLM-4 (#12252) 1 year ago
xander-art baeddd4d15
feat:Add support for stop parameter in hunyuan model #12313 (#12315)
Co-authored-by: xander-art <xander-art@gmail.com>
1 year ago
-LAN- 6f5a8a33d9
refactor: replace gevent threadpool with ProcessPoolExecutor in GPT2Tokenizer (#12316)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Giovanny Gutiérrez d7c0bc8c23
feat: Add response format support for openai compat models (#12240)
Co-authored-by: Gio Gutierrez <giovannygutierrez@gmail.com>
1 year ago
yihong f30bf08580
fix: close #12215 for yi special case (#12222)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Warren Chen 9954ddb780
[Fix] modify sagemaker llm (#12274) 1 year ago
-LAN- 6a85960605
feat: implement asynchronous token counting in GPT2Tokenizer (#12239)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Kepler 2a909e634b
feat: support Ernie-lite-pro-128k (#12161)
Co-authored-by: bigfish49 <bigfish49@126.com>
1 year ago
jiangbo721 c98d91e44d
fix: o1 model error, use max_completion_tokens instead of max_tokens. (#12037)
Co-authored-by: 刘江波 <jiangbo721@163.com>
1 year ago
yihong 56e15d09a9
feat: mypy for all type check (#10921) 1 year ago
yihong 6a0ff3686c
fix: fix typo (#12034)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
-LAN- af2888d394
fix: remove json_schema if response format is disabled. (#12014)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
-LAN- 10caab1729
fix: change CredentialsValidateFailedError to inherit from ValueError (#11950)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
非法操作 366857cd26
fix: gemini system prompt with variable raise error (#11946) 1 year ago
-LAN- 455791b710
fix(model_runtime): make invoke as ValueError (#11929)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Kalo Chin 2681bafb76
fix: handle document fetching from URL in Anthropic LLM model, solving base64 decoding error (#11858) 1 year ago
yihong 7b03a0316d
fix: better memory usage from 800+ to 500+ (#11796)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
-LAN- 996a9135f6
feat(llm_node): support order in text and files (#11837)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
Dr.MerdanBay bb2f46d7cc
fix: add safe dictionary access for bedrock credentials (#11860) 1 year ago
yihong 463fbe2680
fix: better gard nan value from numpy for issue #11827 (#11864)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
非法操作 9d93ad1f16
feat: add gemini-2.0-flash-thinking-exp-1219 (#11863) 1 year ago
yihong 12d45e9114
fix: silicon change its model fix #11844 (#11847)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
barabicu d057067543
fix: remove ruff ignore SIM300 (#11810) 1 year ago
sino 560d375e0f
feat(ark): add doubao-pro-256k and doubao-embedding-large (#11831) 1 year ago
Agung Besti 3388d6636c
add-model-azure-gpt-4o-2024-11-20 (#11803)
Co-authored-by: agungbesti <agung.besti@insignia.co.id>
1 year ago
xander-art 56434db4f5
feat:add hunyuan model(hunyuan-role, hunyuan-large, hunyuan-large-rol… (#11766)
Co-authored-by: xanderdong <xanderdong@tencent.com>
1 year ago
-LAN- a5db7c9acb
feat: add openai o1 & update pricing and max_token of other models (#11780)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
非法操作 9048832a9a
chore: improve gemini models (#11745) 1 year ago
Shota Totsuka 7d5a385811
feat: use Gemini response metadata for token counting (#11743) 1 year ago
sino 99430a5931
feat(ark): support doubao vision series models (#11740) 1 year ago
非法操作 c9b4029ce7
chore: the consistency of MultiModalPromptMessageContent (#11721) 1 year ago
呆萌闷油瓶 cd4310df25
chore:update azure api version (#11711) 1 year ago
非法操作 74fdc16bd1
feat: enhance gemini models (#11497) 1 year ago
方程 fc8fdbacb4
feat: add gitee ai vl models (#11697)
Co-authored-by: 方程 <fangcheng@oschina.cn>
1 year ago
zhongliliu-butterfly daccb10d8c
fix: volcengine_maas and baichuan message error (#11625)
Co-authored-by: zhongliliu <liuzlx@digitalchina.com>
1 year ago
zhaobingshuang 79801f5c30
fix: deepseek reports an error when using Response Format #11677 (#11678)
Co-authored-by: zhaobs <zhaobs@cailian.net>
1 year ago
非法操作 cf0ff88120
feat: add grok-2-1212 and grok-2-vision-1212 (#11672) 1 year ago
yihong 7e154a467b
fix: better error message for stream (#11635)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
JasonVV bb3bc60f83
feat(model): add vertex_ai Gemini 2.0 Flash Exp (#11604) 1 year ago
crazywoola e7a4cfac4d
fix: name of llama-3.3-70b-specdec (#11596) 1 year ago
Alok Shrivastwa 6478aa1c9d
Added new models and Removed the deleted ones for Groq #11455 (#11456)
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: Alok Shrivastwa <Alok.Shrivastwa@microland.com>
1 year ago
Warren Chen 7b5839335a
[ref] use one method to get boto client for aws bedrock (#11506) 1 year ago
非法操作 926f604f09
feat: add gemini-2.0-flash-exp (#11570) 1 year ago
Tommy 42d986b96d
[Pixtral] Add new model ; add vision (#11231) 1 year ago
zkyTech fbc4ca980c
fix: Remove duplicate 'response_format' parameter from model YAML files (#11531)
Co-authored-by: zhangkunyuan <zhangkunyuan@cmhi.chinamobile.com>
1 year ago
Paul van Oorschot 80c52e0ea4
feat: Add llama-3.3 models for Groq (#11533) 1 year ago
orangeclk ec00b25793
feat: add siliconflow qwq and llama3.3 model (#11492) 1 year ago
Yingchun Lai 32f8439143
fix: add the missing abab6.5t-chat model of Minimax (#11484) 1 year ago
Kazuki Takamatsu 4d7cfd0de5
Fix model provider of vertex ai (#11437) 1 year ago
非法操作 7e1184c071
feat: support json_schema for ollama models (#11449) 1 year ago
非法操作 1ce51e57ab
feat: add gemini exp 1206 (#11444) 1 year ago
非法操作 142b4fd699
feat: add zhipu glm_4v_flash (#11440) 1 year ago
shirochan 5093337de1
FEAT: cohere rerank 3.5 model added (#11289) 1 year ago
Matsuda f54225568c
fix(model_runtime): add vision to Amazon Nova Lite and Pro (#11398) 1 year ago
Warren Chen 631cbcd781
[fix] rename yaml files to fit windows (#11379) 1 year ago
yihong 5669cac16d
fix: some typos using typos (#11374)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Warren Chen 376726cf90
[feat] Add AWS Bedrock rerank (#11349)
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
yihong 961e25f608
fix: better bedrock message handler close #10976 (#11317)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
ybalbert001 1bae9b8ff7
update pricing for bedrock nova LLM models (#11336)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
1 year ago
非法操作 91e1ff5e30
chore: improve zhipu LLM (#11321) 1 year ago
ybalbert001 5908e10549
integrate amazon nove llms to dify (#11324)
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
1 year ago
yihong e39e776d03
fix: better wenxin rerank handler, close #11252 (#11283)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Bowen Liang e79eac688a
chore(lint): sort __all__ definitions (#11243) 1 year ago
-LAN- 643a90c48d
fix: use `removeprefix()` instead of `lstrip()` to remove the `data:` prefix (#11272)
Signed-off-by: -LAN- <laipz8200@outlook.com>
1 year ago
yihong 02572e8cca
fix: claude can not handle empty string (#11238)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
yihong 239bf97b47
fix: nvidia special embedding model payload close #11193 (#11239)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Shota Totsuka 594666eb61
fix: use Gemini response metadata for token counting (#11226) 1 year ago
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>
1 year ago
yihong 40fc6f529e
fix: gitee ai wrong default model, and better para (#11168)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Tao Wang aa135a3780
Add TTS to OpenAI_API_Compatible (#11071) 1 year ago
-LAN- 5b7b328193
feat: Allow to contains files in the system prompt even model not support. (#11111) 1 year ago
-LAN- 1db14793fa
fix(anthropic_llm): Ignore non-text parts in the system prompt. (#11107) 1 year ago
fengjiajie ab6dcf7032
fix: update the max tokens configuration for Azure GPT-4o (2024-08-06) to 16384 (#11074) 1 year ago
yihong 8aae235a71
fix: int None will cause error for context size (#11055)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
Tao Wang 1065917872
Add grok-vision-beta to xAI + Update grok-beta Features (#11004) 1 year ago
yihong 2e00829b1e
fix: drop useless and wrong code for zhipu embedding (#11069)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
SiliconFlow, Inc a4fc057a1c
ISSUE=11042: add tts model in siliconflow (#11043) 1 year ago
Tao Wang aae29e72ae
Fix Deepseek Function/Tool Calling (#11023) 1 year ago
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>
1 year ago
Bowen Liang 6c8e208ef3
chore: bump minimum supported Python version to 3.11 (#10386) 1 year ago
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>
1 year ago
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) 1 year ago
yihong 448a19bf54
fix: fish audio wrong validate credentials interface (#11019)
Signed-off-by: yihong0618 <zouzou0208@gmail.com>
1 year ago
非法操作 08ac36812b
feat: support LLM process document file (#10966)
Co-authored-by: -LAN- <laipz8200@outlook.com>
1 year ago
-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>
1 year ago
CXwudi d9579f418d
chore: Added the new gemini exp-1121 and learnlm-1.5 models (#10963) 1 year ago
Agung Besti e8868a7fb9
feat: add gpt-4o-2024-11-20 (#10951)
Co-authored-by: akubesti <agung.besti@insignia.co.id>
1 year ago
LastHopeOfGPNU 1a6b961b5f
Resolve 8475 support rerank model from infinity (#10939)
Co-authored-by: linyanxu <linyanxu2@qq.com>
1 year ago
-LAN- 82575a7aea
fix(gpt-4o-audio-preview): Remove the vision feature (#10932) 1 year ago