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
hisir
f0273f00e1
Fixed when testing the openai compatible interface model, an error is reported when no object is returned ( #7808 )
2024-08-29 18:58:19 +08:00
sino
7cfebffbb8
chore: update default endpoint for ark provider ( #7741 )
2024-08-28 13:56:50 +08:00
crazywoola
da326baa5e
fix: tongyi Error: 'NoneType' object is not subscriptable ( #7705 )
2024-08-27 16:56:06 +08:00
sino
ee7d5e7206
feat: support Moonshot and GLM models tool call for volc ark provider ( #7666 )
2024-08-27 14:43:37 +08:00
Hélio Lúcio
7b7576ad55
Add Azure AI Studio as provider ( #7549 )
...
Co-authored-by: Hélio Lúcio <canais.hlucio@voegol.com.br>
2024-08-27 09:52:59 +08:00
代君
7c2bb31a55
[fix] openai's tool role dose not support name parameter. ( #7659 )
2024-08-26 18:52:34 +08:00
Seayon
561a61e7fe
Improve MIME type detection for image URLs ( #6531 )
...
Co-authored-by: seayon <zhaoxuyang@shouqianba.com>
2024-08-25 13:36:16 +08:00
sino
efc136cce5
feat: Introduce Ark SDK v3 and ensure compatibility with models of SDK v2 ( #7579 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2024-08-24 19:29:45 +08:00
噢哎哟喂
ad13011043
add JSON Mode support for moonshot models ( #7568 )
2024-08-23 16:24:45 +08:00
Fei He
6025002971
add qwen text-embedding-v3 support. ( #7567 )
2024-08-23 15:32:38 +08:00
orangeclk
a24717765e
feat: forward zhipu finish_reason ( #7560 )
2024-08-23 11:15:38 +08:00
orangeclk
f53454f81d
add finish_reason to the LLM node output ( #7498 )
2024-08-21 17:29:30 +08:00
非法操作
f7af8c7cc7
feat: gpt-4o-mini-2024-07-18 support json schema ( #7489 )
2024-08-21 15:11:29 +08:00
Xiyuan Chen
4e7b6aec3a
feat: support pinning, including, and excluding for model providers and tools ( #7419 )
...
Co-authored-by: GareArc <chen4851@purude.edu>
2024-08-21 11:16:43 +08:00
Nam Vu
6991a243aa
chore: correct _tts_invoke_streaming max length ( #7423 )
2024-08-20 10:20:04 +08:00
Chengyu Yan
1f944c6eeb
feat(api): support wenxin bge-large and tao embedding model. ( #7393 )
2024-08-19 22:25:09 +08:00
Xiao Ley
53cf756207
feat: OpenRouter add gpt-4o-2024-08-06 model ( #7409 )
2024-08-19 19:14:08 +08:00
-LAN-
0087afc2e3
fix(api/core/model_runtime/model_providers/__base/large_language_model.py): Add TEXT type checker ( #7407 )
2024-08-19 18:45:30 +08:00
SoaringEthan
acd72e3ab2
feat: support xinference's auth system ( #7369 )
2024-08-19 12:41:56 +08:00
Chengyu Yan
bfd905602f
feat(api): support wenxin text embedding ( #7377 )
2024-08-19 09:15:19 +08:00
sino
a0a67873aa
chore: optimize ark model parameters ( #7378 )
2024-08-19 08:44:19 +08:00
噢哎哟喂
baaa3f7f42
add base url for moonshot model ( #7360 )
2024-08-17 10:28:09 +08:00
Weaxs
3a33062405
feat: support siliconflow rerank ( #7337 )
2024-08-16 20:21:41 +08:00
Xiyuan Chen
c7df6783df
Revert "feat: support pinning, including, and excluding for Model Providers and Tools" ( #7324 )
2024-08-15 23:51:00 +08:00
噢哎哟喂
6fdbc7dbf3
fix error when use farui-plus model ( #7316 )
...
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2024-08-15 20:14:13 +08:00
Hongbin
d1a6702aa4
Update PerfXCloud Model List ( #7212 )
...
Co-authored-by: xhb <466010723@qq.com>
2024-08-15 19:42:15 +08:00
Xiyuan Chen
7619850855
feat: support pinning, including, and excluding for Model Providers and Tools ( #7283 )
2024-08-15 12:58:38 +08:00
非法操作
6ff7fd80a1
feat: support OPENAI json_schema ( #7258 )
2024-08-15 11:29:19 +08:00
非法操作
5aa373dc04
feat: add chatgpt-4o-latest ( #7289 )
2024-08-15 11:19:10 +08:00
Xiyuan Chen
d29b32fce2
fix: typo in upstage/llm/_position.yaml ( #7286 )
2024-08-15 08:39:35 +08:00
噢哎哟喂
52383d0161
add support for tongyi-farui ( #7248 )
...
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2024-08-14 14:09:13 +08:00
Onelevenvy
0f59d76997
fix: add context_size and max_chunks to Tongyi embedding to resolve issue #7189 ( #7227 )
2024-08-13 16:35:22 +08:00
shAlfred
a12ddc47e7
feat: add support of speech2text function for OpenAI-API-compatible and Siliconflow ( #7197 )
2024-08-12 21:38:59 +08:00
Weaxs
67b9fdaad7
siliconflow support bge-3 && bce-v1 embedding ( #7198 )
2024-08-12 19:14:43 +08:00
ybalbert001
f2cb1fb09f
Fix : Workflow "start" paste url not support s3 pre-signed URL ( #6855 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2024-08-11 16:45:15 +08:00
Yanyi Liu
5b32f2e0dd
Feat: Add model provider Text Embedding Inference for embedding and rerank ( #7132 )
2024-08-09 19:12:13 +08:00
Yanyi Liu
4cbeb6815b
Fix: Wrong cutoff length lead to empty input in openai compatible embedding model. ( #7133 )
2024-08-09 19:11:57 +08:00
forrestlinfeng
07511dfaf4
update stepfun model ( #7118 )
...
Co-authored-by: chenlinfeng <chenlinfeng@step.ai>
Co-authored-by: Tfsh <tianfs_fight@163.com>
2024-08-08 20:40:37 +08:00
小羽
7944ce0594
feat: wenxin add yi-34b-chat ( #7117 )
2024-08-08 20:01:21 +08:00
orangeclk
83acb53c08
feat: add zhipu embedding-3 ( #7100 )
2024-08-08 17:08:46 +08:00
shAlfred
a7162240e6
feat: add text-embedding functon and LLM models to Siliconflow ( #7090 )
2024-08-08 17:08:28 +08:00
小羽
34a9dbe826
Feat/add 360-zhinao provider ( #7069 )
2024-08-08 14:23:08 +08:00
orangeclk
f288d367ac
Add price info for zhipu models ( #7084 )
2024-08-08 14:17:05 +08:00
Waffle
5e2fa13126
feat: support glm-4-long ( #7070 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-08-08 10:54:39 +08:00
Joe
d7bb422a5c
fix: hunyuan assistant_prompt_message pydantic error ( #7062 )
2024-08-07 18:31:40 +08:00
majian
99b78dd198
feat: add gpt-4o-2024-08-06 ( #7046 )
2024-08-07 15:35:57 +08:00
crazywoola
3516989738
fix: typos in wenxin llm ( #7021 )
2024-08-06 22:33:03 +08:00
Sa Zhang
26991443ed
fix: Fix incorrect context size for jina-reranker-v2 model ( #7006 )
2024-08-06 21:08:29 +08:00
Yefori
bd3ed89516
feat: add function calling for deepseek models ( #6990 )
2024-08-06 13:37:27 +08:00
小羽
23ed15d19f
feat:nvidia add nemotron4-340b and microsoft/phi-3 ( #6973 )
2024-08-06 10:16:41 +08:00
takatost
6da14c2d48
security: fix api image security issues ( #6971 )
2024-08-05 20:21:08 +08:00
Pedro Gomes
a34285196b
Revise the wrong pricing of certain LLM models. ( #6967 )
2024-08-05 18:41:44 +08:00
takatost
ea30174057
chore: optimize streaming tts of xinference ( #6966 )
2024-08-05 18:23:23 +08:00
liuzhenghua
141e4e0276
fix: restore xinference secret field ( #6941 )
...
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
2024-08-04 22:32:24 +08:00
Weaxs
5e634a59a2
compatible xinference reranker server ( #6927 )
2024-08-04 13:49:38 +08:00
JuHyung Son
2e941bb91c
add new provider Solar ( #6884 )
2024-08-02 20:48:09 +08:00
sino
8166a8caf5
feat: update llama3.1 parameters for openrouter ( #6901 )
2024-08-02 13:13:34 +08:00
灰灰
56af1a0adf
pref: change ollama embedded api request ( #6876 )
2024-08-02 12:04:47 +08:00
dufei
f8617db012
fix tongyi tool calls ( #6896 )
2024-08-02 10:03:43 +08:00
Weaxs
cc4785f094
fix: xinference reranker return_documents ( #6888 )
2024-08-01 19:57:53 +08:00
chenxu9741
a9cd6df97e
Remove tts (blocking call) ( #6869 )
2024-08-01 14:50:22 +08:00
呆萌闷油瓶
f31142e758
Azure 4o mini options ( #6873 )
2024-08-01 14:04:18 +08:00
crazywoola
792f908afb
Revert "feat:Azure gpt4o mini" ( #6870 )
2024-08-01 13:32:03 +08:00
呆萌闷油瓶
14367ddc09
feat:Azure gpt4o mini ( #6866 )
2024-08-01 13:03:08 +08:00
Charlie.Wei
cbf7f21ade
Add azure gpt4omini ( #6862 )
...
Co-authored-by: luowei <glpat-EjySCyNjWiLqAED-YmwM>
Co-authored-by: crazywoola <427733928@qq.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-08-01 12:57:52 +08:00
Weaxs
f6e8e120a1
support xinference tts ( #6746 )
2024-08-01 11:59:15 +08:00
Joe
08f922d8c9
fix: anthropic max token NoneType error ( #6858 )
2024-08-01 11:30:00 +08:00
小羽
56b43f62d1
feat: nvidia add llama3.1 model ( #6844 )
2024-07-31 21:24:02 +08:00
Giga Group
4b410494b3
Add model parameter enable_enhance for hunyuan llm model ( #6847 )
...
Co-authored-by: sun <sun@centen.cn>
2024-07-31 20:04:43 +08:00
Joe
df9bd36cab
fix: claude-3-5-sonnet-20240620 max token error ( #6843 )
2024-07-31 18:34:44 +08:00
longzhihun
9ce5cea911
feat: bedrock invoke enhancement ( #6808 )
2024-07-30 21:57:18 +08:00
SiliconFlow, Inc
3e18d32ce5
add deepseek-coder-v2 in siliconflow ( #6149 )
2024-07-29 18:45:19 +08:00
Charles
94d68b6a08
upgrade deepseek params ( #6744 )
2024-07-29 18:31:56 +08:00
Giga Group
c9ff0e3961
Add model hunyuan-embedding ( #6657 )
...
Co-authored-by: sun <sun@centen.cn>
2024-07-29 18:30:52 +08:00
Bowen Liang
20268708cc
chore: improve position map conversion and tolerate empty position yaml file ( #6541 )
2024-07-29 10:32:11 +08:00
-LAN-
83af50368f
fix(api/core/model_runtime/model_providers/azure_openai/llm/llm.py): Try to skip if delta.delta
is None. ( #6727 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2024-07-27 00:05:21 +08:00
Joe
e4542215cc
fix: tongyi empty tool_calls is not supported in message ( #6719 )
2024-07-26 18:10:13 +08:00
Jason
3d3677e912
Feat/model provider novita ( #6717 )
...
Co-authored-by: takatost <takatost@gmail.com>
2024-07-26 17:37:21 +08:00
chenxu9741
6b50bb0fe6
issues #6655 Open ai tts issues ( #6696 )
2024-07-26 14:55:49 +08:00
longzhihun
c5ac004f15
[seanguo] fix: unsupported filename in windows & add Mistral Large 2 ( #6679 )
2024-07-25 19:26:46 +08:00
RookieAgent
78a339a794
modify llama3-1 yaml filename to support Windows pull operations ( #6677 )
2024-07-25 18:58:55 +08:00
Giga Group
ca696fe94c
Add support of tool-call for model provider "hunyuan" ( #6656 )
...
Co-authored-by: sun <sun@centen.cn>
2024-07-25 11:27:58 +08:00
longzhihun
9815aab7a3
[seanguo] feat: add llama 3.1 support in bedrock ( #6645 )
2024-07-25 11:20:37 +08:00
zhangzhiqiangcs
d4c55748f1
doc: fix about model features ( #6619 )
2024-07-24 19:12:10 +08:00
dufei
5af2df0cd5
fix: qwen fc error ( #6620 )
...
Co-authored-by: dufei <du_fei@venusgroup.com.cn>
2024-07-24 16:56:06 +08:00
takatost
4c85393a1d
feat: add GroqCloud llama3.1 series models support ( #6596 )
2024-07-24 00:41:58 +08:00
sino
d5c2680fde
feat: support llama3.1 series models for openrouter provider ( #6595 )
2024-07-24 00:37:48 +08:00
Joe
8123a00e97
feat: update prompt generate ( #6516 )
2024-07-23 19:52:14 +08:00
Lance Mao
7c55c39085
feat: add tencent asr ( #6091 )
2024-07-23 16:38:39 +08:00
-LAN-
5e6fc58db3
Feat/environment variables in workflow ( #6515 )
...
Co-authored-by: JzoNg <jzongcode@gmail.com>
2024-07-22 15:29:39 +08:00
sino
4f9f175f25
fix: correct gpt-4o-mini max token ( #6472 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2024-07-19 18:24:58 +08:00
sino
9e168f9d1c
feat: support gpt-4o-mini for openrouter provider ( #6447 )
2024-07-19 13:09:41 +08:00
Weaxs
ea45496a74
update ernie models ( #6454 )
2024-07-19 13:08:39 +08:00
Richards Tu
8e49146a35
[EMERGENCY] Fix Anthropic header issue ( #6445 )
2024-07-19 07:38:15 +08:00
takatost
dad3fd2dc1
feat: add gpt-4o-mini ( #6442 )
2024-07-19 01:53:43 +08:00
ybalbert001
4a026fa352
Enhancement: add model provider - Amazon Sagemaker ( #6255 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-07-18 19:32:31 +08:00
themanforfree
ba181197c2
feat: api_key support for xinference ( #6417 )
...
Signed-off-by: themanforfree <themanforfree@gmail.com>
2024-07-18 18:58:46 +08:00
forrestlinfeng
3b5b548af3
Add Stepfun LLM Support ( #6346 )
2024-07-18 07:47:18 +08:00
Richards Tu
4782fb50c4
Support new Claude-3.5 Sonnet max token limit ( #6335 )
2024-07-18 07:47:06 +08:00
xielong
f3f052ba36
fix: rename model from ernie-4.0-8k-Latest to ernie-4.0-8k-latest ( #6383 )
2024-07-17 19:07:47 +08:00