-LAN-
e11d5ac708
feat(model_runtime): add new model 'claude-3-5-sonnet-20241022' ( #9708 )
2024-10-23 17:03:30 +08:00
Pan, Wen-Ming
ecc8beef3f
feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI ( #9688 )
2024-10-23 16:13:51 +08:00
ybalbert001
4989d0c904
add bedrock claude 3.5 v2 support ( #9685 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-10-23 13:54:21 +08:00
ice yao
1e829ceaf3
chore: format get_customizable_model_schema return value ( #9335 )
2024-10-21 19:05:44 +08:00
AAEE86
9b32bfb3db
feat: Updata tongyi models ( #9552 )
2024-10-21 19:04:45 +08:00
-LAN-
e61752bd3a
feat/enhance the multi-modal support ( #8818 )
2024-10-21 10:43:49 +08:00
chzphoenix
42fe208eda
refactor wenxin rerank ( #9486 )
...
Co-authored-by: cuihz <cuihz@knowbox.cn>
2024-10-21 09:03:25 +08:00
Ziyu Huang
660fc3bb34
Resolve 9508 openai compatible rerank ( #9511 )
2024-10-20 21:59:58 +08:00
Tao Wang
b92504bebc
Added Llama 3.2 Vision Models Speech2Text Models for Groq ( #9479 )
2024-10-18 18:10:33 +08:00
zhuhao
e0846792d2
feat: add yi custom llm intergration ( #9482 )
2024-10-18 17:23:21 +08:00
zhuhao
b3cde9900c
feat: add parameter top-k for the llm model provided by openrouter and siliconflow ( #9455 )
2024-10-18 08:21:54 +08:00
zhuhao
3fc0ebdd51
feat: add yi-lightning llm model for yi ( #9458 )
2024-10-18 08:19:58 +08:00
chzphoenix
211f416806
feat:add wenxin rerank ( #9431 )
...
Co-authored-by: cuihz <cuihz@knowbox.cn>
Co-authored-by: crazywoola <427733928@qq.com>
2024-10-17 19:18:32 +08:00
zhuhao
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension ( #9423 )
2024-10-17 19:12:42 +08:00
zhuhao
a45f8969a0
fix: remove the undefined variable line ( #9446 )
2024-10-17 17:25:14 +08:00
ybalbert001
fdcf87c70c
fix https://github.com/langgenius/dify/issues/9409 ( #9433 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-10-17 10:47:56 +08:00
ice yao
dd22e78515
fix: Deprecated gemma2-9b model in Fireworks AI Provider ( #9373 )
2024-10-16 10:44:54 +08:00
crazywoola
423df67042
fix: use gpt-4o-mini for validating credentials ( #9387 )
2024-10-16 10:18:06 +08:00
非法操作
da25b91980
fix: remove the stream option of zhipu and gemini ( #9319 )
2024-10-15 19:13:43 +08:00
Jason Tan
9b8aa9b75d
feat: add minimax abab6.5t support ( #9365 )
2024-10-15 19:00:05 +08:00
非法操作
4ffaabcc04
feat: add glm-4-flashx, deprecated chatglm_turbo ( #9357 )
2024-10-15 17:33:34 +08:00
Warren Wong
b597a0d31c
fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error ( #9326 )
...
Co-authored-by: wwwc <wwwc@outlook.com>
2024-10-15 16:26:44 +08:00
ice yao
5908fd6552
Adapt input type parameter with MiniMax embedding model ( #9342 )
2024-10-15 09:01:00 +08:00
ice yao
3f9d6759d4
feat: Add qwen2.5 72B Instruct model in Fireworks AI ( #9340 )
2024-10-14 23:15:34 +08:00
ice yao
aba70207ab
feat: Add fireworks custom llm intergration ( #9333 )
2024-10-14 22:50:31 +08:00
非法操作
ffc3f33670
chore: remove the copied zhipu_ai sdk ( #9270 )
2024-10-14 10:53:45 +08:00
AAEE86
fe41e8bc18
feat: add siliconflow custom add model interface ( #8745 )
2024-10-11 11:56:11 +08:00
Fei He
5c76131d3d
feat: add gte rerank for tongyi ( #9153 )
2024-10-11 10:35:56 +08:00
Charlie.Wei
6b6e94da08
Fix code indentation errors ( #9164 )
2024-10-10 15:26:38 +08:00
Ziyu Huang
fc60b554a1
Fixes #9159 : Modify to make it works to llama.cpp rerank API ( #9160 )
2024-10-10 15:18:07 +08:00
ronaksingh27
62051d5171
Corrected type annotation to "Any" from "any" all files in "model_providers" folder ( #9135 )
2024-10-10 10:34:25 +08:00
luckylhb90
2024a6c941
fix: vertex ai remote url error(Error: not enough values to unpack) ( #9134 )
...
Co-authored-by: hobo.l <hobo.l@binance.com>
2024-10-10 10:16:42 +08:00
呆萌闷油瓶
060897b25b
chore:add azure openai api version 2024-09-01-preview ( #9141 )
2024-10-10 10:07:49 +08:00
非法操作
499cc57082
fix: response_format of model_parameters will not be removed ( #9148 )
2024-10-10 10:07:21 +08:00
Charlie.Wei
55679b4389
azure add o1-mini、o1-preview models ( #9088 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-10-09 16:15:03 +08:00
Bowen Liang
240b66d737
chore: avoid implicit optional in type annotations of method ( #8727 )
2024-10-09 14:36:43 +08:00
crazywoola
3a0734d94c
Feat/9081 add support for llamaguard through groq provider ( #9083 )
2024-10-09 01:00:10 +08:00
Infinitnet
e741ee2f45
Correct max_tokens for OpenRouter Sonnet 3.5 ( #9068 )
2024-10-08 16:06:47 +08:00
非法操作
966e65bb66
fix: zhipu ai web_search not work ( #9058 )
2024-10-08 15:36:31 +08:00
zg0d233
fcfa1252a0
fix bug when adding openai or openai-compatible stt model instance ( #9006 )
2024-10-07 11:06:38 +08:00
Giannis Kepas
dc5839b6bb
feat: Update AWS Bedrock supported regions ( #8992 )
2024-10-03 15:17:28 +08:00
zhuhao
824a0dd63e
feat: add qwen2.5-72b and llama3.2 for openrouter ( #8956 )
2024-10-01 10:55:51 +08:00
CXwudi
0d84221b2c
chore: sort Gemini models ( #8951 )
2024-10-01 09:14:36 +08:00
CXwudi
cdd7e55a88
chore: add missing models from Voyage ( #8950 )
2024-10-01 09:14:21 +08:00
zhuhao
77aef9ff1d
refactor: optimize the calculation of rerank threshold and the logic for forbidden characters in model_uid ( #8879 )
2024-09-30 12:55:01 +08:00
zhuhao
fb49413a41
feat: add voyage ai as a new model provider ( #8747 )
2024-09-29 16:55:59 +08:00
zhuhao
42dfde6546
docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out ( #8871 )
2024-09-29 16:16:56 +08:00
chenxu9741
c531b4a911
fix : #8843 event: tts_message_end always return in api streaming resp… ( #8846 )
2024-09-29 16:13:20 +08:00
longzhihun
e4ed916baa
Add Jamba and Llama3.2 model support ( #8878 )
2024-09-29 16:12:56 +08:00
Bowen Liang
74f58f29f9
chore: bump ruff to 0.6.8 for fixing violation in SIM910 ( #8869 )
2024-09-29 00:29:59 +08:00
zhuhao
f97607370a
refactor: update Callback to an abstract class ( #8868 )
2024-09-28 21:41:02 +08:00
zhuhao
850492dafa
feat: deprecate gte-Qwen2-7B-instruct embedding model ( #8866 )
2024-09-28 21:40:27 +08:00
zhuhao
61c89a9168
feat: add internlm2.5-20b and qwen2.5-coder-7b model ( #8862 )
2024-09-28 16:31:02 +08:00
zhuhao
6cd22f3bca
fix: update qwen2.5-coder-7b model name ( #8861 )
2024-09-28 15:01:27 +08:00
CXwudi
0603359e2d
fix: delete harm catalog settings for gemini ( #8829 )
2024-09-27 13:49:03 +08:00
HowardChan
bb781764b8
Add Llama3.2 models in Groq provider ( #8831 )
2024-09-27 12:13:00 +08:00
zhuhao
29275c7447
feat: deprecate mistral model for siliconflow ( #8828 )
2024-09-27 12:11:56 +08:00
CXwudi
e5efd09ebb
chore: massive update of the Gemini models based on latest documentation ( #8822 )
2024-09-27 09:14:33 +08:00
wenmeng zhou
ecc951609d
add more detailed doc for models of qwen series ( #8799 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2024-09-26 22:32:33 +08:00
ice yao
063474f408
Add llama3.2 model in fireworks provider ( #8809 )
2024-09-26 22:21:01 +08:00
AAEE86
9a4b53a212
feat: add stream for Gemini ( #8678 )
2024-09-26 19:08:59 +08:00
AAEE86
03edfbe6f5
feat: add qwen to add custom model parameters ( #8759 )
2024-09-26 19:04:25 +08:00
cx
128a66f7fe
fix: Ollama modelfeature set vision, and an exception occurred at the… ( #8783 )
2024-09-26 16:34:40 +08:00
Shenghang Tsai
a0b0809b1c
Add more models for SiliconFlow ( #8779 )
2024-09-26 11:29:53 +08:00
Aaron Ji
4c9ef6e830
fix: update usage for Jina Embeddings v3 ( #8771 )
2024-09-26 11:29:35 +08:00
zhuhao
ac73763726
chore: add input_type param desc for the _invoke method of text_embedding ( #8778 )
2024-09-26 11:23:09 +08:00
Pan, Wen-Ming
02ff6cca70
feat: add support for Vertex AI Gemini 1.5 002 and experimental models ( #8767 )
2024-09-25 21:27:26 +08:00
cherryhuahua
d0e0111f88
fix:Spark's large language model token calculation error #7911 ( #8755 )
2024-09-25 14:51:42 +08:00
ybalbert001
68c7e68a8a
Fix Issue: switch LLM of SageMaker endpoint doesn't take effect ( #8737 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-25 09:12:35 +08:00
ice yao
91f70d0bd9
Add embedding models in fireworks provider ( #8728 )
2024-09-25 08:47:11 +08:00
Jyong
4669eb24be
add embedding input type parameter ( #8724 )
2024-09-24 21:53:50 +08:00
Shota Totsuka
1c7877b048
fix: remove harm category setting from vertex ai ( #8721 )
2024-09-24 20:53:26 +08:00
ice yao
64baedb484
fix: update nomic model provider token calculation ( #8705 )
2024-09-24 14:04:07 +08:00
Benjamin
4638f99aaa
fix: change model provider name issue Ref #8691 ( #8710 )
2024-09-24 13:26:58 +08:00
AAEE86
aebe5fc68c
fix: Remove unsupported parameters in qwen model ( #8699 )
2024-09-24 13:06:21 +08:00
zhuhao
1ecf70dca0
feat: add mixedbread as a new model provider ( #8523 )
2024-09-24 11:20:15 +08:00
ybalbert001
7c485f8bb8
fix llm integration problem: It doesn't work on docker env ( #8701 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-24 10:33:30 +08:00
Sa Zhang
7f1b028840
fix: change the brand name to Jina AI ( #8691 )
...
Co-authored-by: sa zhang <sa.zhang@jina.ai>
2024-09-23 21:39:26 +08:00
Nam Vu
bef83a4d2e
fix: typos and improve naming conventions: ( #8687 )
2024-09-23 21:32:58 +08:00
ice yao
d7aada38a1
Add nomic embedding model provider ( #8640 )
2024-09-23 19:57:21 +08:00
AAEE86
a126d535cf
add Spark Max-32K ( #8676 )
2024-09-23 16:39:46 +08:00
AAEE86
3554a803e7
add zhipuai web search ( #8668 )
2024-09-23 16:19:42 +08:00
AAEE86
c66cecaa55
add Qwen model translate ( #8674 )
2024-09-23 16:18:55 +08:00
Aaron Ji
3618a97c20
feat: extend api params for Jina Embeddings V3 ( #8657 )
2024-09-23 13:45:09 +08:00
zhuhao
e34f04380d
feat: add deepseek-v2.5 for model provider siliconflow ( #8639 )
2024-09-22 21:44:06 +08:00
zhuhao
6df77038a2
docs: fix predefined_model_scale_out.md redirect error ( #8633 )
2024-09-22 16:45:45 +08:00
zhuhao
45c0a44411
feat: add qwen2.5 for model provider siliconflow ( #8630 )
2024-09-22 16:42:34 +08:00
CXwudi
97895ec41a
chore: add Gemini newest experimental models ( close #7121 ) ( #8621 )
2024-09-22 13:38:08 +08:00
sino
6d56d5c1f6
feat: support o1 series models for openrouter ( #8358 )
2024-09-22 10:23:50 +08:00
AAEE86
c9f1e18df1
Add model parameter translation ( #8509 )
...
Co-authored-by: swingchen01 <swings@126.com>
Co-authored-by: 陈长君 <chenchangjun@shuwen.com>
2024-09-22 10:14:33 +08:00
Waffle
740fad06c1
feat(tools/cogview): Updated cogview tool to support cogview-3 and the latest cogview-3-plus ( #8382 )
2024-09-22 10:14:14 +08:00
ice yao
0665268578
Add Fireworks AI as new model provider ( #8428 )
2024-09-22 10:13:00 +08:00
呆萌闷油瓶
c8b9bdebfe
feat:use xinference tts stream mode ( #8616 )
2024-09-22 10:08:35 +08:00
AAEE86
1a8dcae10e
add Qwen custom add model interface ( #8565 )
2024-09-21 22:52:10 +08:00
AAEE86
5ddb601e43
add MixtralAI Model ( #8517 )
2024-09-21 18:08:07 +08:00
Hongbin
5541248264
Update the PerfXCloud provider model list，Update PerfXCloudProvider validate_provider_credentials method. ( #8587 )
...
Co-authored-by: xhb <466010723@qq.com>
2024-09-21 17:33:15 +08:00
Su Yang
c87f710d58
Fix: update qwen model and model config ( #8584 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-20 17:05:57 +08:00
Su Yang
1568c5cae9
fix: fix qwen series model type ( #8580 )
2024-09-20 15:29:33 +08:00
MuYu
a03919c3b3
feat: add hunyuan-vision ( #8529 )
2024-09-19 18:08:01 +08:00
Su Yang
d6de96c4b4
feat: sync Qwen API with Aliyun Bailian ( #8538 )
2024-09-19 17:08:59 +08:00
Wang Bo
6f222b49f2
refactor: rename task_type to task for jina embeddings v3 ( #8488 )
2024-09-18 14:53:15 +08:00
-LAN-
8dfe8c773a
chore: Deprecate gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613 models ( #8500 )
2024-09-18 14:38:09 +08:00
ybalbert001
b6ad7a1e06
Fix: https://github.com/langgenius/dify/issues/8190 (Update Model nam… ( #8426 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-14 17:14:18 +08:00
Aaron Ji
6f7625fa47
chore: update Jina embedding model ( #8376 )
2024-09-14 16:21:17 +08:00
ybalbert001
b613b11422
Fix: Support Bedrock cross region inference #8190 (Update Model name to distinguish between different region groups) ( #8402 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-14 11:06:20 +08:00
crazywoola
71b4480c4a
fix: o1-mini 65563 -> 65536 ( #8388 )
2024-09-14 02:39:58 +08:00
Bowen Liang
5b98acde2f
chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 ( #8392 )
2024-09-13 23:34:39 +08:00
Bowen Liang
a1104ab97e
chore: refurish python code by applying Pylint linter rules ( #8322 )
2024-09-13 22:42:08 +08:00
xiandan-erizo
1ab81b4972
support hunyuan-turbo ( #8372 )
...
Co-authored-by: sunkesi <sunkesi@hosecloud.com>
2024-09-13 20:21:48 +08:00
takatost
24af4b9313
fix: o1-series model encounters an error when the generate mode is blocking ( #8363 )
2024-09-13 15:37:54 +08:00
Bowen Liang
6613b8f2e0
chore: fix unnecessary string concatation in single line ( #8311 )
2024-09-13 14:24:49 +08:00
sino
a45ac6ab98
fix: ark token usage is none ( #8351 )
2024-09-13 14:19:24 +08:00
takatost
4637ddaa7f
feat: add o1-series models support in Agent App (ReACT only) ( #8350 )
2024-09-13 13:08:27 +08:00
takatost
e90d3c29ab
feat: add OpenAI o1 series models support ( #8328 )
2024-09-13 02:15:19 +08:00
Nam Vu
153807f243
fix: response_format label ( #8326 )
2024-09-12 23:17:29 +08:00
呆萌闷油瓶
02c4b1af71
chore:add Azure openai api version 2024-08-01-preview ( #8291 )
2024-09-12 20:22:57 +08:00
ybalbert001
d4985fb3aa
Fix: Support Bedrock cross region inference [ #8190 ]( https://github.com/langgenius/dify/issues/8190 ) ( #8317 )
2024-09-12 19:15:20 +08:00
Bowen Liang
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules ( #8296 )
2024-09-12 15:50:49 +08:00
Bowen Liang
c69f5b07ba
chore: apply ruff E501 line-too-long linter rule ( #8275 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-12 14:00:36 +08:00
Bowen Liang
0f14873255
chore: cleanup ruff flake8-simplify linter rules ( #8286 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-12 12:55:45 +08:00
Bowen Liang
781d294f49
chore: cleanup pycodestyle E rules ( #8269 )
2024-09-11 18:55:00 +08:00
yalei
f515af2232
let claude models in bedrock support the response_format parameter ( #8220 )
...
Co-authored-by: duyalei <>
2024-09-11 18:24:50 +08:00
crazywoola
4d2cd6703b
chore: remove useless code ( #8198 )
2024-09-11 18:19:34 +08:00
Bowen Liang
292220c596
chore: apply pep8-naming rules for naming convention ( #8261 )
2024-09-11 16:40:52 +08:00
HowardChan
53f37a6704
fix:ollama text embedding 500 error ( #8252 )
2024-09-11 16:23:19 +08:00
Nam Vu
342607f4a4
fix: truthy value ( #8208 )
2024-09-11 15:44:53 +08:00
HowardChan
82c42b9ec5
fix:error when adding the ollama embedding model ( #8236 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2024-09-11 10:25:45 +08:00
Bowen Liang
2cf1187b32
chore(api/core): apply ruff reformatting ( #7624 )
2024-09-10 17:00:20 +08:00
takatost
dabfd74622
feat: Parallel Execution of Nodes in Workflows ( #8192 )
...
Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: Yi <yxiaoisme@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-09-10 15:23:16 +08:00
Jyong
2d690801d1
nvidia rerank top n missed ( #8185 )
2024-09-10 13:17:48 +08:00
-LAN-
4313d92e6b
feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. ( #8167 )
2024-09-10 09:11:31 +08:00
crazywoola
0bec6a037c
update qwen-long ( #8157 )
2024-09-09 19:09:42 +08:00
AAEE86
fa34b9aed6
Modify model parameters in Spark LLMs and zhipuai LLMs ( #8078 )
...
Co-authored-by: Charlie.Wei <luowei@cvte.com>
2024-09-09 15:36:47 +08:00
crazywoola
a27d4d58ec
fix: ollama text embedding 500 error ( #8131 )
2024-09-09 15:27:49 +08:00
邹成卓
a15791e788
Fix: tongyi code wrapper works not stable ( #7871 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-09-09 11:15:17 +08:00
ybalbert001
954580a4af
feat: support more model types and builtin tools on aws/sagemaker ( #8061 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-09-09 10:34:11 +08:00
crazywoola
ab7d79275e
fix: Claude can not validate credientials ( #8109 )
2024-09-09 10:22:42 +08:00
呆萌闷油瓶
d28446301f
feat:add fishaudio in xinference ( #8100 )
2024-09-08 23:58:02 +08:00
Nam Vu
2d7954c7da
Fix variable typo ( #8084 )
2024-09-08 13:14:11 +08:00
AAEE86
0cef25ef8c
Revert "fix: parameter rule" ( #8070 )
2024-09-07 10:44:56 +08:00
crazywoola
900fd82a92
fix: parameter rule ( #8064 )
2024-09-06 19:15:24 +08:00
tmuife
89aede80cc
Add OCI(Oracle Cloud Infrastructure) Generative AI Service as a Model Provider ( #7775 )
...
Co-authored-by: Walter Jin <jinshuhaicc@gmail.com>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: walter from vm <walter.jin@oracle.com>
2024-09-06 14:15:40 +08:00
Leng Yue
bd0992275c
feat: support fish audio TTS ( #7982 )
2024-09-05 14:18:39 +08:00
非法操作
3e7597f2bd
feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service ( #7648 )
2024-09-04 21:56:08 +08:00
wochuideng
f6b9982c23
Concurrent calls to the Wenxin model, and the exception problem when obtaining the token is fixed ( #7976 )
...
Co-authored-by: puqs1 <puqs1@lenovo.com>
2024-09-04 21:44:57 +08:00
非法操作
0f72a8e89d
chore: refactor the beichuan model ( #7953 )
2024-09-04 16:22:31 +08:00
呆萌闷油瓶
83494cb4f5
fix:empty voice occurs when xinference CosyVoice tts model ( #7958 )
2024-09-04 13:04:31 +08:00
orangeclk
3f2a806abe
fix: glm models prices and max_tokens correction ( #7882 )
2024-09-02 14:29:09 +08:00
sino
1f56a20b62
feat: support auth by api key for ark provider ( #7845 )
2024-08-31 10:56:32 +08:00
非法操作
dc015c380a
feat: add zhipu glm_4_plus and glm_4v_plus model ( #7824 )
2024-08-30 15:08:31 +08:00
