Commit Graph

432 Commits

Author SHA1 Message Date
liuzhenghua
141e4e0276
fix: restore xinference secret field (#6941)
Some checks are pending
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)
Some checks are pending
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