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 )
...
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Has been cancelled
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Has been cancelled
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Has been cancelled
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Has been cancelled
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Has been cancelled
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Has been cancelled
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
...
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
...
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
...
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
Mark stale issues and pull requests / stale (push) Has been cancelled
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
Mark stale issues and pull requests / stale (push) Has been cancelled
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 )
...
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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 )
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/amd64, build-api-amd64) (push) Waiting to run
Build and Push API & Web / build (api, DIFY_API_IMAGE_NAME, linux/arm64, build-api-arm64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/amd64, build-web-amd64) (push) Waiting to run
Build and Push API & Web / build (web, DIFY_WEB_IMAGE_NAME, linux/arm64, build-web-arm64) (push) Waiting to run
Build and Push API & Web / create-manifest (api, DIFY_API_IMAGE_NAME, merge-api-images) (push) Blocked by required conditions
Build and Push API & Web / create-manifest (web, DIFY_WEB_IMAGE_NAME, merge-web-images) (push) Blocked by required conditions
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
longzhihun
ed9e692263
feat: bedrock model runtime enhancement ( #6299 )
2024-07-16 15:54:39 +08:00
呆萌闷油瓶
d66d7146a3
chore:update azure GA version 2024-06-01 ( #6307 )
2024-07-16 10:32:18 +08:00
Onelevenvy
b47fa27a35
fix: zhipuai validate error when user's api key not support for chatglm_turbo in issue #6289 ( #6290 )
2024-07-15 19:27:18 +08:00
thibautleaux-kreactive
96c171805a
Update bedrock.yaml ( #6281 )
2024-07-15 16:53:03 +08:00
Benjamin
ec181649ae
Update model provider configuration for Triton Inference Server and X… ( #6274 )
2024-07-15 15:07:28 +08:00
Waffle
07add06c59
Feat/add zhipu CogView 3 tool ( #6210 )
2024-07-13 17:39:17 +08:00
Little 羊
7c2c949f01
Update ernie_bot.py ( #6236 )
2024-07-12 19:54:53 +08:00
耐小心
d7a6f25c63
fix: differentiate prompts fields based on function_calling_type ( #5880 )
2024-07-12 11:07:38 +08:00
crazywoola
ee3936916f
upgrade deepseek params ( #6215 )
2024-07-12 10:55:44 +08:00
Little 羊
2f064c68bc
Create ernie-4.0-turbo-8k-preview ( #6132 )
2024-07-11 20:20:07 +08:00
Su Yang
215661ef91
feat: add PerfXCloud, Qwen series #6116 ( #6117 )
2024-07-10 18:26:10 +08:00
chenxu9741
6ef401a9f0
feat:add tts-streaming config and future ( #5492 )
2024-07-09 11:33:58 +08:00
sino
85744b72e5
feat: support moonshot and glm base models for volcengine provider ( #6029 )
2024-07-07 01:17:33 +08:00
Masashi Tomooka
3b23d6764f
fix: token count includes base64 string of input images ( #5868 )
2024-07-06 16:53:32 +08:00
-LAN-
4d105d7bd7
feat(*): Swtich to dify_config. ( #6025 )
2024-07-06 12:05:13 +08:00
orangeclk
f8aaa57f31
feat: add retry mechanism for zhipuai ( #5926 )
2024-07-05 10:49:18 +08:00
-LAN-
d7f75d17cc
Chore/remove-unused-code ( #5917 )
2024-07-04 18:18:26 +08:00
longzhihun
aecdfa2d5c
feat: add claude3 function calling ( #5889 )
2024-07-03 22:21:02 +08:00
longzhihun
fdfbbde10d
[seanguo] modify bedrock Claude3 invoke method to converse API ( #5768 )
...
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-07-01 04:36:13 +08:00
takatost
0bf4817474
fix: _convert_prompt_message_to_dict parameters err ( #5716 )
2024-06-28 21:00:00 +08:00
呆萌闷油瓶
68ac433218
feat: add support Spark4.0 ( #5688 )
2024-06-28 17:39:11 +08:00
Kevin
b3d6726f65
Feature/add qwen llm ( #5659 )
2024-06-28 11:06:29 +08:00
liuzhenghua
2b080b5cfc
feature: Add presence_penalty and frequency_penalty parameters to the … ( #5637 )
...
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
2024-06-28 00:27:20 +08:00
takatost
3ccad33194
feat: add jina new pre-defined rerankers, include: jina-reranker-v2 ( #5657 )
2024-06-27 13:45:35 +08:00
sunxichen
bafc8a0bde
fix: tool call message role according to credentials ( #5625 )
...
Co-authored-by: sunxichen <sun.xc@digitalcnzz.com>
2024-06-27 12:35:27 +08:00
Bowen Liang
dcb72e0067
chore: apply flake8-comprehensions Ruff rules to improve collection comprehensions ( #5652 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-06-27 11:21:31 +08:00
Joe
4e2de638af
feat: add ops trace ( #5483 )
...
Co-authored-by: takatost <takatost@gmail.com>
2024-06-26 17:33:29 +08:00
sino
877a2c144b
feat: support predefined models for openrouter ( #5494 )
2024-06-24 16:31:53 +08:00
-LAN-
ba67206bb9
fix(api/model_runtime/azure/llm): Switch to tool_call. ( #5541 )
2024-06-24 15:35:21 +08:00
vccler
48757e581e
fix: zhipu tool calling, this PR fixes the bug described in issue #5496 ( #5469 )
...
Co-authored-by: vccler <vccler@163.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-06-22 12:41:24 +08:00
LXM
e8ad0339a3
fix: tongyi json output ( #5396 )
2024-06-22 12:25:23 +08:00
crazywoola
91d38a535f
fix: max_tokens of qwen-plus & qwen-plus-chat ( #5480 )
2024-06-21 16:49:33 +08:00
Pan, Wen-Ming
95c882934e
feat: add support for Vertex AI claude-3-5-sonnet@20240620 ( #5475 )
...
Co-authored-by: Wenming Pan <pwm@google.com>
2024-06-21 16:45:56 +08:00
Su Yang
26b6fd2236
feat: add support for bedrock claude-3-5-sonnet-20240620 ( #5461 )
2024-06-21 10:21:35 +08:00
takatost
ff0f02d809
feat: add support for claude-3-5-sonnet-20240620 ( #5452 )
2024-06-21 00:23:15 +08:00
-LAN-
142dc0afd7
refactor: Remove unused code in large_language_model.py ( #5433 )
2024-06-20 16:20:40 +08:00
-LAN-
23fa3dedc4
fix(core): Fix incorrect type hints. ( #5427 )
2024-06-20 15:16:21 +08:00
Ikko Eltociear Ashimine
8266842809
chore: update llm.py ( #5335 )
2024-06-18 09:29:14 +08:00
Richards Tu
c163521b9e
Update and fix the model param of Deepseek ( #5329 )
2024-06-17 21:40:04 +08:00
Justin Wu
61f4f08744
Add bedrock command r models ( #4521 )
...
Co-authored-by: Justin Wu <justin.wu@ringcentral.com>
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-06-17 20:37:46 +08:00
-LAN-
5a99aeb864
fix(core): Reorder field_validator and classmethod to fit Pydantic V2. ( #5257 )
2024-06-17 10:04:28 +08:00
crazywoola
9a64aa76c1
fix: typo and check ( #5287 )
2024-06-17 09:15:43 +08:00
Pan, Wen-Ming
4b54843ed7
fix: run agent with Vertex AI Gemini models ( #5260 )
...
Co-authored-by: Wenming Pan <pwm@google.com>
2024-06-16 09:36:31 +08:00
kurokobo
2e842333b1
fix: correct typos in the icons for microsoft ( #5243 )
2024-06-15 21:02:47 +08:00
Masashi Tomooka
d9bee03ff6
fix: embedding job fails using IAM role ( #5252 )
2024-06-15 18:57:54 +08:00
Jyong
ba5f8afaa8
Feat/firecrawl data source ( #5232 )
...
Co-authored-by: Nicolas <nicolascamara29@gmail.com>
Co-authored-by: chenhe <guchenhe@gmail.com>
Co-authored-by: takatost <takatost@gmail.com>
2024-06-15 02:46:02 +08:00
Bin
0f35d07052
support ERNIE-4.0-8K-Latest ( #5216 )
2024-06-14 18:45:24 +08:00
-LAN-
7f44e88eda
fix(model_providers/ollama): Fix OllamaLargeLanguageModel to correctly set the stop option ( #5217 )
2024-06-14 18:26:14 +08:00
Jason
b7ff765d8d
Add novita.ai as model provider ( #4961 )
2024-06-14 18:23:06 +08:00
Masashi Tomooka
0633aae7dc
feat: allow to use IAM Role for Bedrock ( #5188 )
2024-06-14 15:18:42 +08:00
takatost
415022aa14
fix: pydantic2 error ( #5172 )
2024-06-14 03:05:04 +08:00
rerorero
b85ae146a7
fix: JSON mode with an image doesn't work for Gemini ( #5169 )
2024-06-14 02:32:09 +08:00
Pan, Wen-Ming
f13af5a811
fix(model_providers/vertex_ai): Vertex AI Anthropic models authentication failed ( #4971 )
2024-06-14 01:34:31 +08:00
Bowen Liang
f976740b57
improve: mordernizing validation by migrating pydantic from 1.x to 2.x ( #4592 )
2024-06-14 01:05:37 +08:00
kurokobo
e61f5d029a
chore(docs): fix minor small typos ( #5124 )
2024-06-13 17:36:01 +08:00
sino
8210637bc5
feat: support jina-clip-v1 embedding model ( #5146 )
2024-06-13 16:31:18 +08:00
呆萌闷油瓶
790543131a
chore:add some new api version for azure openai ( #5142 )
2024-06-13 16:30:47 +08:00
yanghx
adc948e87c
fix(api/core/model_runtime/model_providers/baichuan,localai): Parse ToolPromptMessage. #4943 ( #5138 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2024-06-13 13:08:30 +08:00
orangeclk
79e8489942
feat: support siliconflow ( #5129 )
2024-06-13 12:59:41 +08:00
xielong
ea69dc2a7e
feat: support hunyuan llm models ( #5013 )
...
Co-authored-by: takatost <takatost@users.noreply.github.com>
Co-authored-by: Bowen Liang <bowenliang@apache.org>
2024-06-12 17:24:23 +08:00
Pika
ecc7f130b4
fix(typo): misspelling ( #5094 )
2024-06-12 17:01:21 +08:00
sino
0ce97e6315
feat: support doubao llm function calling ( #5100 )
2024-06-12 15:43:50 +08:00
rerorero
28997772a5
fix: remote_url doesn't work for gemini ( #5090 )
2024-06-12 13:14:53 +08:00
orangeclk
2050a8b8f0
feat: add glm4 new models and zhipu embedding-2 ( #5089 )
2024-06-12 08:22:17 +08:00
sino
5f870ac950
chore: update maas model provider description ( #5056 )
2024-06-11 11:22:22 +08:00
Jaxon Ley
2573b138bf
fix: update presence_penalty configuration for wenxin AI ernie-4.0-8k and ernie-3.5-8k models ( #5039 )
2024-06-09 14:44:11 +08:00
takatost
3929d289e0
feat: set default memory messages limit to infinite ( #5002 )
2024-06-06 17:39:44 +08:00
Joe
5cdb95be1f
fix: gemini timeout error ( #4955 )
2024-06-06 10:19:03 +08:00
Bowen Liang
f32b440c4a
chore: fix indention violations by applying E111 to E117 ruff rules ( #4925 )
2024-06-05 14:05:15 +08:00
takatost
f44d1e62d2
fix: bedrock get_num_tokens prompt_messages parameter name err ( #4932 )
2024-06-05 01:53:05 +08:00
takatost
d1dbbc1e33
feat: backend model load balancing support ( #4927 )
2024-06-05 00:13:04 +08:00
Pan, Wen-Ming
b98a1a3303
feat: added Anthropic Claude3 models to Google Cloud Vertex AI ( #4870 )
...
Co-authored-by: pwm <pwm@google.com>
2024-06-04 02:52:46 +08:00
takatost
696c5308a9
chore: optimize nvidia nim credential schema and info ( #4898 )
2024-06-04 02:26:26 +08:00
Joshua
3c8a120e51
add-nvidia-mim ( #4882 )
2024-06-03 21:10:18 +08:00
Pan, Wen-Ming
cdbc260571
Bugfix: Vertex AI vision model not support image ( #4853 )
2024-06-02 11:11:09 +08:00
Yash Parmar
e0da0744b5
add: ollama keep alive parameter added. issue #4024 ( #4655 )
2024-05-31 12:22:02 +08:00
Weaxs
b189faca52
feat: update ernie model ( #4756 )
2024-05-29 14:57:23 +08:00
xielong
e1cd9aef8f
feat: support baichuan3 turbo, baichuan3 turbo 128k, and baichuan4 ( #4762 )
2024-05-29 14:46:04 +08:00
crazywoola
705a6e3a8e
Fix/4742 ollama num gpu option not consistent with allowed values ( #4751 )
2024-05-29 13:33:35 +08:00
xielong
793f0c1dd6
fix: Corrected schema link in model_runtime's README.md ( #4757 )
2024-05-29 13:03:21 +08:00
xielong
88b4d69278
fix: Correct context size for banchuan2-53b and banchuan2-turbo ( #4721 )
2024-05-28 16:37:44 +08:00
crazywoola
27dae156db
fix: colon in file mistral.mistral-small-2402-v1:0 ( #4673 )
2024-05-27 13:15:20 +08:00
Giovanny Gutiérrez
2deb23e00e
fix: Show rerank in system for localai ( #4652 )
2024-05-27 12:09:51 +08:00
longzhihun
fe9bf5fc4a
[seanguo] add support of amazon titan v2 and modify the price of amazon titan v1 ( #4643 )
...
Co-authored-by: Chenhe Gu <guchenhe@gmail.com>
2024-05-26 23:30:22 +08:00
miendinh
f804adbff3
feat: Support for Vertex AI - load Default Application Configuration ( #4641 )
...
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2024-05-25 13:40:25 +08:00
Krasus.Chen
f156014daa
update lite8k/speed8k/128k max_token to newest ( #4636 )
...
Co-authored-by: Your Name <chen@krasus.red>
2024-05-24 19:33:42 +08:00
Bowen Liang
3fda2245a4
improve: extract method for safe loading yaml file and avoid using PyYaml's FullLoader ( #4031 )
2024-05-24 12:08:12 +08:00
