ace7ffab5f
feat: support comfyui workflow tool image generate image ( #9871 )
1 year ago
1b5adf40da
fix: moonshot response_format raise error ( #9847 )
1 year ago
18106a4fc6
add tidb on qdrant type ( #9831 )
...
Co-authored-by: Zhaofeng Miao <522856232@qq.com>
1 year ago
5b7b765090
fix: yuque book id should be string ( #9819 )
1 year ago
ac9f1e9de5
fix: duckduckgo image search not work ( #9821 )
1 year ago
2346b0ab99
chore: make doc extractor node also can extract text by file extension ( #9543 )
1 year ago
88dec6ef2b
Added description for .ppt, specify the reason for unstructured.io ( #9452 )
...
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
70ddc0ce43
openai compatiable api usage and id ( #9800 )
...
Co-authored-by: jinqi.guo <jinqi.guo@ubtrobot.com>
1 year ago
e2710161f6
fix: chart tool can't display chinese ( #9686 )
1 year ago
5f11fe521d
remove unstructured pdf extract ( #9794 )
1 year ago
d018b32d0b
fix(workflow): enhance prompt handling with vision support ( #9790 )
1 year ago
400392230b
fixed: variable reference error ( #9722 )
...
Co-authored-by: hobo.l <hobo.l@binance.com>
1 year ago
e11d5ac708
feat(model_runtime): add new model 'claude-3-5-sonnet-20241022' ( #9708 )
1 year ago
3e9d271b52
nltk security issue and upgrade unstructured ( #9558 )
1 year ago
ecc8beef3f
feat: added claude 3.5 sonnet v2 model to Google Cloud Vertex AI ( #9688 )
1 year ago
4989d0c904
add bedrock claude 3.5 v2 support ( #9685 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
1 year ago
9a5bdae07f
feat(condition): add support for 'exists' and 'not exists' operators ( #9687 )
1 year ago
ceb2c4f3ef
chore: reuse existing test functions with upstash vdb ( #9679 )
1 year ago
d5a93a6400
fix(variable_pool): handle invalid attributes in variable lookup ( #9646 )
1 year ago
8e7a752b2a
feat: add upstash as a new vector database provider ( #9644 )
1 year ago
999d3f1539
fix: add downstream nodes of this branch ( #9640 )
1 year ago
a7ee51e5d8
feat: add code generator ( #9051 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
1 year ago
a9db06f5e7
feat(Tools): Refactor the base table plugin ( #9182 )
...
Co-authored-by: 黎斌 <libin.23@bytedance.com>
1 year ago
5267f34e76
fix(segments): return empty string instead of "null" for text, log, and markdown properties ( #9651 )
1 year ago
36f66d40e5
refactor(api): simplify limit retrieval and return types ( #9641 )
1 year ago
5f12616cb9
fix: file type document is not supported ( #9618 )
1 year ago
7263af13ed
fix(http_request): simplify JSON handling in requests ( #9616 )
1 year ago
d992a809f5
fix: update the default model to gpt-4o-mini for duckduckgo ai chat ( #9614 )
1 year ago
5f12c17355
fix(core): use CreatedByRole enum for role consistency ( #9607 )
1 year ago
4d9160ca9f
refactor: use dify_config to replace legacy usage of flask app's config ( #9089 )
1 year ago
8f670f31b8
refactor(variables): replace deprecated 'get_any' with 'get' method ( #9584 )
1 year ago
5838345f48
fix(entities): add validator for `VisionConfig` to handle None values ( #9598 )
1 year ago
ac24300274
refactor(template_transform): use keyword-only arguments ( #9575 )
1 year ago
2e657b7b12
fix(workflow): handle NoneSegments in variable extraction ( #9585 )
1 year ago
c063617553
fix(workflow): improve database session handling and variable management ( #9581 )
1 year ago
38a4f0234d
fix(http_request): handle empty and string data inputs ( #9579 )
1 year ago
740a723072
fix(validation): improve variable handling and validation ( #9578 )
1 year ago
4ae0bb83f1
fix(file upload): correct upload method key for image config ( #9568 )
1 year ago
5459d812e7
fix(iteration): handle empty iterator gracefully ( #9565 )
1 year ago
faad247d85
fix(upload): correct incorrect dictionary key usage ( #9563 )
1 year ago
1e829ceaf3
chore: format get_customizable_model_schema return value ( #9335 )
1 year ago
9b32bfb3db
feat: Updata tongyi models ( #9552 )
1 year ago
f83ed19dfe
fix: list filter node some operator raise error ( #9539 )
1 year ago
53b14bde4d
fix: list filter node url not work ( #9540 )
1 year ago
e61752bd3a
feat/enhance the multi-modal support ( #8818 )
1 year ago
853b0e84cc
fix: draft run workflow node with image will raise error ( #9406 )
1 year ago
42fe208eda
refactor wenxin rerank ( #9486 )
...
Co-authored-by: cuihz <cuihz@knowbox.cn>
1 year ago
95ce10f23b
feat: Add custom username and avatar define in discord tool ( #9514 )
1 year ago
660fc3bb34
Resolve 9508 openai compatible rerank ( #9511 )
1 year ago
424a7da470
add yuqye（ https://www.yuque.com）tools ( #8960 )
...
Co-authored-by: 佐井 <chengwu.lcw@alibaba-inc.com>
1 year ago
b92504bebc
Added Llama 3.2 Vision Models Speech2Text Models for Groq ( #9479 )
1 year ago
e0846792d2
feat: add yi custom llm intergration ( #9482 )
1 year ago
b3cde9900c
feat: add parameter top-k for the llm model provided by openrouter and siliconflow ( #9455 )
1 year ago
2155bba5b0
fix: update mismatch vector type ( #9462 )
1 year ago
3fc0ebdd51
feat: add yi-lightning llm model for yi ( #9458 )
1 year ago
211f416806
feat:add wenxin rerank ( #9431 )
...
Co-authored-by: cuihz <cuihz@knowbox.cn>
Co-authored-by: crazywoola <427733928@qq.com>
1 year ago
b90ad587c2
refactor: move the embedding to the rag module and abstract the rerank runner for extension ( #9423 )
1 year ago
a45f8969a0
fix: remove the undefined variable line ( #9446 )
1 year ago
d3c06a3f76
feat: add the workflow tool of comfyUI ( #9447 )
1 year ago
fdcf87c70c
fix https://github.com/langgenius/dify/issues/9409 ( #9433 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
1 year ago
86594851cb
refactor: update the default values of top-k parameter in vdb to be consistent ( #9367 )
1 year ago
50635e9c15
Fix/economical knowledge retrieval ( #9396 )
1 year ago
7d3dad3d1d
feat: add timezone conversion for time tool ( #9393 )
1 year ago
dd22e78515
fix: Deprecated gemma2-9b model in Fireworks AI Provider ( #9373 )
1 year ago
423df67042
fix: use gpt-4o-mini for validating credentials ( #9387 )
1 year ago
da25b91980
fix: remove the stream option of zhipu and gemini ( #9319 )
1 year ago
9b8aa9b75d
feat: add minimax abab6.5t support ( #9365 )
1 year ago
4ffaabcc04
feat: add glm-4-flashx, deprecated chatglm_turbo ( #9357 )
1 year ago
b597a0d31c
fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error ( #9326 )
...
Co-authored-by: wwwc <wwwc@outlook.com>
1 year ago
fb32e5ca9a
fix: In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 ( #8791 )
1 year ago
cd7ab6231f
refactor: Add an enumeration type and use the factory pattern to obtain the corresponding class ( #9356 )
1 year ago
5908fd6552
Adapt input type parameter with MiniMax embedding model ( #9342 )
1 year ago
3f9d6759d4
feat: Add qwen2.5 72B Instruct model in Fireworks AI ( #9340 )
1 year ago
aba70207ab
feat: Add fireworks custom llm intergration ( #9333 )
1 year ago
fa47f0c707
chore: disable chat service API passing `parent_message_id` ( #8984 )
1 year ago
ffc3f33670
chore: remove the copied zhipu_ai sdk ( #9270 )
1 year ago
857055b797
fix: remove the latest message from the user that does not have any answer yet ( #9297 )
1 year ago
d15ba3939d
Add Volcengine VikingDB as new vector provider ( #9287 )
1 year ago
d97d3ff5fc
chore: add abstract decorator and output log when query embedding fails ( #9264 )
1 year ago
2ec6ffe478
feat:support baidu vector db ( #9185 )
1 year ago
23ce1fb1ba
chore: optimize the trace ops slow queries on node executions. ( #9282 )
1 year ago
29188e0562
chore: use cache instead of re-querying node record during workflow execution ( #9280 )
1 year ago
93af87a9e0
fix: move exception to debug mode ( #9258 )
1 year ago
42b02b3a5f
Fix/agent external knowledge retrieval ( #9241 )
1 year ago
d7b8e071dd
fix:#9222 create or update custum tools error ( #9228 )
1 year ago
80b62d50f5
Fix/add es num_candidates ( #9225 )
1 year ago
fe41e8bc18
feat: add siliconflow custom add model interface ( #8745 )
1 year ago
5c76131d3d
feat: add gte rerank for tongyi ( #9153 )
1 year ago
cabdb4ef17
fix retrieval resource positon missed ( #9155 )
...
Co-authored-by: Bowen Liang <liangbowen@gf.com.cn>
1 year ago
05c1ef75c4
feat: add allow_llm_to_see_data flag for vanna ( #9156 )
1 year ago
75f0a5e36a
fix: Typo Correction in jina.yaml ( #9161 )
1 year ago
477beae3bb
fix: missing usage of metadata in the chatflow app ( #9167 )
1 year ago
6b6e94da08
Fix code indentation errors ( #9164 )
1 year ago
fc60b554a1
Fixes #9159 : Modify to make it works to llama.cpp rerank API ( #9160 )
1 year ago
e947103b6d
Feat/add workflow sys params ( #9108 )
...
Co-authored-by: Joel <iamjoel007@gmail.com>
1 year ago
62051d5171
Corrected type annotation to "Any" from "any" all files in "model_providers" folder ( #9135 )
1 year ago
2024a6c941
fix: vertex ai remote url error(Error: not enough values to unpack) ( #9134 )
...
Co-authored-by: hobo.l <hobo.l@binance.com>
1 year ago
060897b25b
chore:add azure openai api version 2024-09-01-preview ( #9141 )
1 year ago
499cc57082
fix: response_format of model_parameters will not be removed ( #9148 )
1 year ago
511ffa4698
fix: follow-up (suggested questions) does not refer to the most recen… ( #9122 )
1 year ago
7a1da2409d
add generate conversation name error log ( #9117 )
1 year ago
55679b4389
azure add o1-mini、o1-preview models ( #9088 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
1 year ago
240b66d737
chore: avoid implicit optional in type annotations of method ( #8727 )
1 year ago
5fcd614186
feat: output the execution results of tool should only in debug mode ( #9104 )
1 year ago
4be1aa516c
feat: add tags for vanna tools ( #9102 )
1 year ago
5e250403d3
chore: add the missing tool names to the _position file ( #9099 )
1 year ago
f8af9c6ad0
refactor: Update countries & languages list for SearchApi engines ( #9090 )
1 year ago
57994e4a24
fix s3 presign url check problem, support two versions(v2,v4) ( #9093 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
1 year ago
3a0734d94c
Feat/9081 add support for llamaguard through groq provider ( #9083 )
1 year ago
5b7de7705e
feat: add timestamp conversion and timestamp retrieval for time tool ( #9085 )
1 year ago
5213650fed
feat: update the xinf tool's API key to optional ( #9073 )
1 year ago
e741ee2f45
Correct max_tokens for OpenRouter Sonnet 3.5 ( #9068 )
1 year ago
966e65bb66
fix: zhipu ai web_search not work ( #9058 )
1 year ago
2ab8bc679f
fix: Missing model information in llm span of Langfuse #9029 ( #9030 )
...
Co-authored-by: corel <corelchen@qq.com>
1 year ago
fcfa1252a0
fix bug when adding openai or openai-compatible stt model instance ( #9006 )
1 year ago
dc5839b6bb
feat: Update AWS Bedrock supported regions ( #8992 )
2 years ago
4373777871
Update json_in_md_parser.py ( #8983 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
415d27c8bf
feat(Tools): add discord incoming webhook for sending messages ( #7852 )
2 years ago
24ba9fdf6c
feat: enhance stepfun image generation tool ( #8954 )
2 years ago
824a0dd63e
feat: add qwen2.5-72b and llama3.2 for openrouter ( #8956 )
2 years ago
2deaece7e2
refactor: remove unnecessary comment ( #8949 )
2 years ago
0d84221b2c
chore: sort Gemini models ( #8951 )
2 years ago
cdd7e55a88
chore: add missing models from Voyage ( #8950 )
2 years ago
625e4c4c72
fix multiple retrieval in knowledge node ( #8942 )
2 years ago
4585cffce1
fix: Compatible with special characters in pg full-text search. ( #8921 )
...
Co-authored-by: Aurelius Huang <cm.huang@aftership.com>
2 years ago
9d221a5e19
external knowledge api ( #8913 )
...
Co-authored-by: Yi <yxiaoisme@gmail.com>
2 years ago
77aef9ff1d
refactor: optimize the calculation of rerank threshold and the logic for forbidden characters in model_uid ( #8879 )
2 years ago
503561f464
fix: fix the data validation consistency issue in keyword content review ( #8908 )
2 years ago
ada9d408ac
refactor(api/variables): VariableError as a ValueError. ( #8554 )
2 years ago
369e1e6f58
feat(website-crawl): add jina reader as additional alternative for website crawling ( #8761 )
2 years ago
fb49413a41
feat: add voyage ai as a new model provider ( #8747 )
2 years ago
42dfde6546
docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out ( #8871 )
2 years ago
c531b4a911
fix : #8843 event: tts_message_end always return in api streaming resp… ( #8846 )
2 years ago
e4ed916baa
Add Jamba and Llama3.2 model support ( #8878 )
2 years ago
74f58f29f9
chore: bump ruff to 0.6.8 for fixing violation in SIM910 ( #8869 )
2 years ago
f97607370a
refactor: update Callback to an abstract class ( #8868 )
2 years ago
850492dafa
feat: deprecate gte-Qwen2-7B-instruct embedding model ( #8866 )
2 years ago
61c89a9168
feat: add internlm2.5-20b and qwen2.5-coder-7b model ( #8862 )
2 years ago
49af18fbd6
fix: customize model credentials were invalid despite the provider credentials being active ( #8864 )
2 years ago
6cd22f3bca
fix: update qwen2.5-coder-7b model name ( #8861 )
2 years ago
27e33fb15c
chore: fix wrong VectorType match case ( #8857 )
2 years ago
55e6123db9
feat: add min-connection and max-connection for pgvector ( #8841 )
2 years ago
c828a5dfdf
feat(Tools): add feishu tools ( #8800 )
...
Co-authored-by: 黎斌 <libin.23@bytedance.com>
2 years ago
0603359e2d
fix: delete harm catalog settings for gemini ( #8829 )
2 years ago
bb781764b8
Add Llama3.2 models in Groq provider ( #8831 )
2 years ago
29275c7447
feat: deprecate mistral model for siliconflow ( #8828 )
2 years ago
4c1063e1c5
fix: AnalyticdbVector retrieval scores ( #8803 )
2 years ago
a36117e12d
Updated the YouTube channel to Dify's ( #8817 )
2 years ago
e5efd09ebb
chore: massive update of the Gemini models based on latest documentation ( #8822 )
2 years ago
ecc951609d
add more detailed doc for models of qwen series ( #8799 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
063474f408
Add llama3.2 model in fireworks provider ( #8809 )
2 years ago
9a4b53a212
feat: add stream for Gemini ( #8678 )
2 years ago
03edfbe6f5
feat: add qwen to add custom model parameters ( #8759 )
2 years ago
008e0efeb0
refactor: update delete method as an abstract method ( #8794 )
2 years ago
128a66f7fe
fix: Ollama modelfeature set vision, and an exception occurred at the… ( #8783 )
2 years ago
d1173a69f8
fix: the Image-1X tool ( #8787 )
2 years ago
a0b0809b1c
Add more models for SiliconFlow ( #8779 )
2 years ago
4c9ef6e830
fix: update usage for Jina Embeddings v3 ( #8771 )
2 years ago
0c96f0aa51
fix: credential *** should be string ( #8785 )
2 years ago
ac73763726
chore: add input_type param desc for the _invoke method of text_embedding ( #8778 )
2 years ago
5ba19d64e9
fix: TavilySearch tool get api link ( #8780 )
2 years ago
fefbc43fb0
chore: fix comfyui tool doc url ( #8775 )
2 years ago
02ff6cca70
feat: add support for Vertex AI Gemini 1.5 002 and experimental models ( #8767 )
2 years ago
d0e0111f88
fix:Spark's large language model token calculation error #7911 ( #8755 )
2 years ago
bf64ff215b
fix: . is missing in file_extension ( #8736 )
2 years ago
68c7e68a8a
Fix Issue: switch LLM of SageMaker endpoint doesn't take effect ( #8737 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2 years ago
91f70d0bd9
Add embedding models in fireworks provider ( #8728 )
2 years ago
4669eb24be
add embedding input type parameter ( #8724 )
2 years ago
debe5953a8
Fix/update jina ai products labels and descriptions ( #8730 )
...
Co-authored-by: sa zhang <sa.zhang@jina.ai>
2 years ago
1c7877b048
fix: remove harm category setting from vertex ai ( #8721 )
2 years ago
64baedb484
fix: update nomic model provider token calculation ( #8705 )
2 years ago
4638f99aaa
fix: change model provider name issue Ref #8691 ( #8710 )
2 years ago
aebe5fc68c
fix: Remove unsupported parameters in qwen model ( #8699 )
2 years ago
1ecf70dca0
feat: add mixedbread as a new model provider ( #8523 )
2 years ago
7c485f8bb8
fix llm integration problem: It doesn't work on docker env ( #8701 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2 years ago
21e9608b23
feat: add xinference sd web ui api tool ( #8385 )
...
Signed-off-by: themanforfree <themanforfree@gmail.com>
2 years ago
7f1b028840
fix: change the brand name to Jina AI ( #8691 )
...
Co-authored-by: sa zhang <sa.zhang@jina.ai>
2 years ago
bef83a4d2e
fix: typos and improve naming conventions: ( #8687 )
2 years ago
8cc9e68363
fix: prompt for the follow-up suggestions ( #8685 )
2 years ago
d7aada38a1
Add nomic embedding model provider ( #8640 )
2 years ago
c7eacd1aac
chore: Optimize I18nObject class for better performance and readability ( #8681 )
2 years ago
a126d535cf
add Spark Max-32K ( #8676 )
2 years ago
3554a803e7
add zhipuai web search ( #8668 )
2 years ago
c66cecaa55
add Qwen model translate ( #8674 )
2 years ago
86f90fd9ff
chore: skip PLR6201 linter rule ( #8666 )
2 years ago
4c7beb9d7b
fix: Assignment exception ( #8663 )
...
Co-authored-by: fum <fum@investoday.com.cn>
2 years ago
3618a97c20
feat: extend api params for Jina Embeddings V3 ( #8657 )
2 years ago
03fdf5e7f8
chore: Enable Japanese descriptions for Tools ( #8646 )
2 years ago
e34f04380d
feat: add deepseek-v2.5 for model provider siliconflow ( #8639 )
2 years ago
6df77038a2
docs: fix predefined_model_scale_out.md redirect error ( #8633 )
2 years ago
45c0a44411
feat: add qwen2.5 for model provider siliconflow ( #8630 )
2 years ago
eaa7e9b1f0
fix: llm_generator.py JSONDecodeError ( #8504 )
2 years ago
8fd297f8b4
fix: redundant check for available_document_count ( #8491 )
2 years ago
97895ec41a
chore: add Gemini newest experimental models ( close #7121 ) ( #8621 )
2 years ago
6d56d5c1f6
feat: support o1 series models for openrouter ( #8358 )
2 years ago
c9f1e18df1
Add model parameter translation ( #8509 )
...
Co-authored-by: swingchen01 <swings@126.com>
Co-authored-by: 陈长君 <chenchangjun@shuwen.com>
2 years ago
740fad06c1
feat(tools/cogview): Updated cogview tool to support cogview-3 and the latest cogview-3-plus ( #8382 )
2 years ago
0665268578
Add Fireworks AI as new model provider ( #8428 )
2 years ago
c8b9bdebfe
feat:use xinference tts stream mode ( #8616 )
2 years ago
a587f0d3f1
docs: Add Japanese documentation for tools ( #8469 )
2 years ago
8c51d06222
feat: regenerate in `Chat`, `agent` and `Chatflow` app ( #7661 )
2 years ago
831c5a93af
refactor(ops): Optimize the iteration for filter_none_values and use logging.error to record logs when an exception occurs ( #8461 )
2 years ago
1a8dcae10e
add Qwen custom add model interface ( #8565 )
2 years ago
8219f9e090
fix: api/core/ops/ops_trace_manager.py ( #8501 )
2 years ago
5ddb601e43
add MixtralAI Model ( #8517 )
2 years ago
5541248264
Update the PerfXCloud provider model list，Update PerfXCloudProvider validate_provider_credentials method. ( #8587 )
...
Co-authored-by: xhb <466010723@qq.com>
2 years ago
e0a3307563
fix(workflow): "Max submit count reached" error occurred when executing workflow as tool in iteration ( #8595 )
2 years ago
1583283635
ComfyUI tool use the new internal enumeration class "VariableKey" ( #8533 )
2 years ago
c87f710d58
Fix: update qwen model and model config ( #8584 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
1568c5cae9
fix: fix qwen series model type ( #8580 )
2 years ago
a03919c3b3
feat: add hunyuan-vision ( #8529 )
2 years ago
d6de96c4b4
feat: sync Qwen API with Aliyun Bailian ( #8538 )
2 years ago
ffd2f61dd9
fix: thread_pool submit count in parallel workflow not releasing ( #8549 )
2 years ago
54b9e1f6d1
fix: ci issues(missing duckduckgo-search==6.2.11, ruff lint issue) ( #8543 )
2 years ago
6f222b49f2
refactor: rename task_type to task for jina embeddings v3 ( #8488 )
2 years ago
8dfe8c773a
chore: Deprecate gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613 models ( #8500 )
2 years ago
cf645c3ba1
feat: Add ComfyUI tool for Stable Diffusion ( #8160 )
2 years ago
6dba68f62d
feat: Add base URL settings and secure_ascii options to the Brave search tool ( #8463 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
3d083b758f
feat: add flux dev of siliconflow image-gen tool ( #8450 )
2 years ago
bf16de50fe
fix: internal error when tool authorization ( #8449 )
2 years ago
7e611ffbf3
multi-retrival use dataset's top-k ( #8416 )
2 years ago
72b7f8a949
Bugfix/fix feishu plugins ( #8443 )
...
Co-authored-by: 黎斌 <libin.23@bytedance.com>
2 years ago
88c9834ef2
chore(workflow): Optimize the iteration when selecting a variable from a branch in the output variable causes iteration index err ( #8440 )
2 years ago
b6ad7a1e06
Fix: https://github.com/langgenius/dify/issues/8190 (Update Model nam… ( #8426 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2 years ago
6f7625fa47
chore: update Jina embedding model ( #8376 )
2 years ago
f01602b570
fix(workflow): the answer node after the iteration node containing the answer was output prematurely ( #8419 )
2 years ago
0123498452
fix:logs and rm unused codes in CacheEmbedding ( #8409 )
2 years ago
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>
2 years ago
71b4480c4a
fix: o1-mini 65563 -> 65536 ( #8388 )
2 years ago
5b98acde2f
chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 ( #8392 )
2 years ago
aad6f340b3
fix ( #8322 followup): resolve the violation of pylint rules ( #8391 )
2 years ago
a1104ab97e
chore: refurish python code by applying Pylint linter rules ( #8322 )
2 years ago
1ab81b4972
support hunyuan-turbo ( #8372 )
...
Co-authored-by: sunkesi <sunkesi@hosecloud.com>
2 years ago
06b66216d7
chore: update firecrawl scrape to V1 api ( #8367 )
2 years ago
cd3eaed335
fix(workflow): both parallel and single branch errors occur in if-else ( #8378 )
2 years ago
24af4b9313
fix: o1-series model encounters an error when the generate mode is blocking ( #8363 )
2 years ago
6613b8f2e0
chore: fix unnecessary string concatation in single line ( #8311 )
2 years ago
08c486452f
fix: score_threshold handling in vector search methods ( #8356 )
2 years ago
a45ac6ab98
fix: ark token usage is none ( #8351 )
2 years ago
4637ddaa7f
feat: add o1-series models support in Agent App (ReACT only) ( #8350 )
2 years ago
49cee773c5
fixed score threshold is none ( #8342 )
2 years ago
e90d3c29ab
feat: add OpenAI o1 series models support ( #8328 )
2 years ago
153807f243
fix: response_format label ( #8326 )
2 years ago
5db0b56c5b
docs: update lambda_translate_utils.yaml ( #8293 )
2 years ago
404db1ae5b
Fix VariableEntityType Bug external-data-tool -> external_data_tool ( #8299 )
2 years ago
02c4b1af71
chore:add Azure openai api version 2024-08-01-preview ( #8291 )
2 years ago
d4985fb3aa
Fix: Support Bedrock cross region inference [ #8190 ]( https://github.com/langgenius/dify/issues/8190 ) ( #8317 )
2 years ago
40fb4d16ef
chore: refurbish Python code by applying refurb linter rules ( #8296 )
2 years ago
c69f5b07ba
chore: apply ruff E501 line-too-long linter rule ( #8275 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
56c90e212a
fix(workflow): missing content in the answer node stream output during iterations ( #8292 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
0f14873255
chore: cleanup ruff flake8-simplify linter rules ( #8286 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
781d294f49
chore: cleanup pycodestyle E rules ( #8269 )
2 years ago
f515af2232
let claude models in bedrock support the response_format parameter ( #8220 )
...
Co-authored-by: duyalei <>
2 years ago
4d2cd6703b
chore: remove useless code ( #8198 )
2 years ago
292220c596
chore: apply pep8-naming rules for naming convention ( #8261 )
2 years ago
53f37a6704
fix:ollama text embedding 500 error ( #8252 )
2 years ago
75c1a82556
Update Gitlab query field, add query by path ( #8244 )
2 years ago
342607f4a4
fix: truthy value ( #8208 )
2 years ago
5f4cdd66fa
fix(workflow): IF-ELSE nodes connected to the same subsequent node cause execution to stop ( #8247 )
2 years ago
82c42b9ec5
fix:error when adding the ollama embedding model ( #8236 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
cee0c51dbb
feat: add from_variable_selector for stream chunk / message event ( #8228 )
2 years ago
fdbbdb706f
fix(workflow): answers are output simultaneously across different braches in the question classifier node. ( #8225 )
2 years ago
f6dfe23cf8
fix(workflow): in multi-parallel execution with multiple conditional branches ( #8221 )
2 years ago
bb3002b173
revert page column ( #8217 )
2 years ago
2cf1187b32
chore(api/core): apply ruff reformatting ( #7624 )
2 years ago
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>
2 years ago
ed37439ef7
refactor(api/core): Improve type hints and apply ruff formatter in agent runner and model manager. ( #8166 )
2 years ago
af92f19291
filter excel empty sheet ( #8194 )
2 years ago
2d690801d1
nvidia rerank top n missed ( #8185 )
2 years ago
4313d92e6b
feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. ( #8167 )
2 years ago
0695543f63
Fix variable typo (cont) ( #8161 )
2 years ago
0bec6a037c
update qwen-long ( #8157 )
2 years ago
fa34b9aed6
Modify model parameters in Spark LLMs and zhipuai LLMs ( #8078 )
...
Co-authored-by: Charlie.Wei <luowei@cvte.com>
2 years ago
a27d4d58ec
fix: ollama text embedding 500 error ( #8131 )
2 years ago
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>
2 years ago
954580a4af
feat: support more model types and builtin tools on aws/sagemaker ( #8061 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2 years ago
ab7d79275e
fix: Claude can not validate credientials ( #8109 )
2 years ago
d28446301f
feat:add fishaudio in xinference ( #8100 )
2 years ago
feefeb44d7
fix LangSmith project config error ( #7996 )
2 years ago
2d7954c7da
Fix variable typo ( #8084 )
2 years ago
0cef25ef8c
Revert "fix: parameter rule" ( #8070 )
2 years ago
900fd82a92
fix: parameter rule ( #8064 )
2 years ago
44f963f281
If else add regexmatch ( #8059 )
...
Co-authored-by: 罗威 <luowei@cvte.com>
2 years ago
01858e1caf
ifEsle node add regex match ( #8007 )
2 years ago
2060db8e11
fix: change milvus init args from (host, port) to (url, token) ( #8019 )
...
Signed-off-by: ChengZi <chen.zhang@zilliz.com>
2 years ago
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>
2 years ago
d489b8b3e0
feat: return page number of pdf documents upon retrieval ( #7749 )
2 years ago
bd0992275c
feat: support fish audio TTS ( #7982 )
2 years ago
3e7597f2bd
feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service ( #7648 )
2 years ago
0e71f6db84
fix spliter length missed ( #7987 )
2 years ago
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>
2 years ago
0f72a8e89d
chore: refactor the beichuan model ( #7953 )
2 years ago
14af87527f
Feat:remove estimation of embedding cost ( #7950 )
...
Co-authored-by: jyong <718720800@qq.com>
2 years ago
83494cb4f5
fix:empty voice occurs when xinference CosyVoice tts model ( #7958 )
2 years ago
571415d1a4
fix: split text keep separator ( #7930 )
2 years ago
fee4d3f6ca
feat: ops trace add llm model ( #7306 )
2 years ago
80d14c9b22
fix(api): Code-Based Extension cause error on position map sorting ( #7934 )
...
Signed-off-by: 陳鈞 <jim60105@gmail.com>
2 years ago
596f160a1e
Chore/add default step 1x url ( #7933 )
2 years ago
d8b6c053a2
fix rerank model value is empty string ( #7937 )
2 years ago
01581dd35f
improve the notion table extract ( #7925 )
2 years ago
6f33351eb3
ignore linked images when image id is none ( #7890 )
2 years ago
a8b9e01b3e
fix: fixed typo on loading reranking_mode ( #7887 )
2 years ago
7193e189f3
Add perplexity search as a new tool ( #7861 )
2 years ago
3f2a806abe
fix: glm models prices and max_tokens correction ( #7882 )
2 years ago
1f56a20b62
feat: support auth by api key for ark provider ( #7845 )
2 years ago
0c2a62f847
fix: correct http timeout configs‘ default values and ignorance by HttpRequestNode ( #7762 )
2 years ago
dc015c380a
feat: add zhipu glm_4_plus and glm_4v_plus model ( #7824 )
2 years ago
f0273f00e1
Fixed when testing the openai compatible interface model, an error is reported when no object is returned ( #7808 )
2 years ago
962cdbbebd
chore: add app generator overload ( #7792 )
2 years ago
1262277714
chore: improve http executor configs ( #7730 )
2 years ago
26abbe8e5b
feat(Tools): add a tool to query the stock price from Alpha Vantage ( #7019 ) ( #7752 )
2 years ago
5d0914daea
fix: not able to pass array of string/number/object into variable aggregator groups ( #7757 )
2 years ago
7cfebffbb8
chore: update default endpoint for ark provider ( #7741 )
2 years ago
92cab33b73
feat(Tools): add feishu document and message plugins ( #6435 )
...
Co-authored-by: 黎斌 <libin.23@bytedance.com>
2 years ago
3f467613fc
feat: support configs for code execution request ( #7704 )
2 years ago
da326baa5e
fix: tongyi Error: 'NoneType' object is not subscriptable ( #7705 )
2 years ago
60001a62c4
fixed chunk_overlap is None ( #7703 )
2 years ago
ee7d5e7206
feat: support Moonshot and GLM models tool call for volc ark provider ( #7666 )
2 years ago
122ce41020
feat: rewrite Elasticsearch index and search code to achieve Elasticsearch vector and full-text search ( #7641 )
...
Co-authored-by: haokai <haokai@shuwen.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: Bowen Liang <bowenliang@apache.org>
Co-authored-by: wellCh4n <wellCh4n@foxmail.com>
2 years ago
e7afee1176
Langfuse view button ( #7684 )
2 years ago
a15080a1d7
bug: ( #7586 followup) fix config of CODE_MAX_STRING_LENGTH ( #7683 )
2 years ago
35431bce0d
fix dataset_id and index_node_id idx missed in document_segments tabl… ( #7681 )
2 years ago
7b7576ad55
Add Azure AI Studio as provider ( #7549 )
...
Co-authored-by: Hélio Lúcio <canais.hlucio@voegol.com.br>
2 years ago
162faee4f2
fix: set score_threshold to zero if it is None for MyScale vectordb ( #7640 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2 years ago
b7ff98d7ff
fix: Remove useless debug information. ( #7647 )
2 years ago
430e100142
refactor: Add @staticmethod decorator in `api/core` ( #7652 )
2 years ago
1473083a41
catch openai rate limit error ( #7658 )
2 years ago
7c2bb31a55
[fix] openai's tool role dose not support name parameter. ( #7659 )
2 years ago
ba82023445
fix: support float type for tool parameter's default value ( #7644 )
2 years ago
7ae728a9a3
fix nltk averaged_perceptron_tagger download and fix score limit is none ( #7582 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2 years ago
556f4ad5df
feat: add siliconflow text2img tool ( #7612 )
2 years ago
561a61e7fe
Improve MIME type detection for image URLs ( #6531 )
...
Co-authored-by: seayon <zhaoxuyang@shouqianba.com>
2 years ago
efc136cce5
feat: Introduce Ark SDK v3 and ensure compatibility with models of SDK v2 ( #7579 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
3ace01cfb3
chore: cleanup and rearrange unclassified configs into feature config groups ( #7586 )
2 years ago
e3d7c7c6f9
fix(onebot): use yarl to format url ( #7589 )
2 years ago
8807d880dc
Feat: add OneBot protocol tool ( #7583 )
2 years ago
70d6ab0bf5
Update stable_diffusion.py ( #7536 )
2 years ago
e42848f4b7
Do not pass query parameter when the value is empty ( #7585 )
2 years ago
f29685f8a1
fix score_threshold is none, return all top K documents ( #7581 )
2 years ago
ad13011043
add JSON Mode support for moonshot models ( #7568 )
2 years ago
9864b35465
langfuser add view button ( #7571 )
2 years ago
6025002971
add qwen text-embedding-v3 support. ( #7567 )
2 years ago
a24717765e
feat: forward zhipu finish_reason ( #7560 )
2 years ago
931e6f1625
Added Space between Chinese and English within tools' description ( #7545 )
2 years ago
f53454f81d
add finish_reason to the LLM node output ( #7498 )
2 years ago
784b11ce19
Chore/remove python dependencies selector ( #7494 )
2 years ago
715eb8fa32
fix rerank mode is none ( #7496 )
2 years ago
a02118d5bc
Fix/incorrect code template ( #7490 )
2 years ago
85fc0fdb51
chore: support CODE_MAX_PRECISION ( #7484 )
2 years ago
f7af8c7cc7
feat: gpt-4o-mini-2024-07-18 support json schema ( #7489 )
2 years ago
0c99a3d0c5
fix the issue of the refine_switches at param being invalid in the Novita.AI tool ( #7485 )
2 years ago
6435b4eb44
Separate CODE_MAX_DEPTH and set it as an environment variable ( #7474 )
2 years ago
4e7b6aec3a
feat: support pinning, including, and excluding for model providers and tools ( #7419 )
...
Co-authored-by: GareArc <chen4851@purude.edu>
2 years ago
9a715f6b68
fix(tool): tool node error ( #7459 )
...
Co-authored-by: hobo.l <hobo.l@binance.com>
2 years ago
b7778de224
fix: document error message can not be cleared ( #7453 )
2 years ago
e35e251863
feat: Sort conversations by updated_at desc ( #7348 )
...
Co-authored-by: wangpj <wangpj@hundsunc.om>
Co-authored-by: JzoNg <jzongcode@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
4f5f27cf2b
refactor(api/core/workflow/enums.py): Rename SystemVariable to SystemVariableKey. ( #7445 )
2 years ago
a10b207de2
refactor(api/core/app/app_config/entities.py): Move Type to outside and add EXTERNAL_DATA_TOOL. ( #7444 )
2 years ago
4f64a5d36d
refactor(api/core/workflow/nodes/variable_assigner): Split into multi files. ( #7434 )
2 years ago
53146ad685
feat: support line break of tooltip content ( #7424 )
2 years ago
0223fc6fd5
feat: add pgvector full_text_search ( #7396 )
2 years ago
6991a243aa
chore: correct _tts_invoke_streaming max length ( #7423 )
2 years ago
1f944c6eeb
feat(api): support wenxin bge-large and tao embedding model. ( #7393 )
2 years ago
4ff4859036
add CrossRef builtin tool: doi query and title query ( #7406 )
2 years ago
53cf756207
feat: OpenRouter add gpt-4o-2024-08-06 model ( #7409 )
2 years ago
0087afc2e3
fix(api/core/model_runtime/model_providers/__base/large_language_model.py): Add TEXT type checker ( #7407 )
2 years ago
acd72e3ab2
feat: support xinference's auth system ( #7369 )
2 years ago
bbb6fcc4f0
chore: update ruff from 0.5.x to 0.6.x ( #7384 )
2 years ago
a0c689c273
feat: add jina tokenizer tool ( #7375 )
2 years ago
bfd905602f
feat(api): support wenxin text embedding ( #7377 )
2 years ago
a0a67873aa
chore: optimize ark model parameters ( #7378 )
2 years ago
baaa3f7f42
add base url for moonshot model ( #7360 )
2 years ago
3a33062405
feat: support siliconflow rerank ( #7337 )
2 years ago
5a729a69cd
feat: tools/gitlab ( #7329 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
dbc1ae45de
chore: update docstrings ( #7343 )
2 years ago
c7df6783df
Revert "feat: support pinning, including, and excluding for Model Providers and Tools" ( #7324 )
2 years ago
6fdbc7dbf3
fix error when use farui-plus model ( #7316 )
...
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2 years ago
d1a6702aa4
Update PerfXCloud Model List ( #7212 )
...
Co-authored-by: xhb <466010723@qq.com>
2 years ago
ed85d8281a
fix: null annotation ( #7313 )
2 years ago
3f9720bca0
fix(api/core/app/segments/segments.py): Fix file to markdown. ( #7293 )
2 years ago
7619850855
feat: support pinning, including, and excluding for Model Providers and Tools ( #7283 )
2 years ago
8f16165f92
chore(api/core): Improve FileVar's type hint and imports. ( #7290 )
2 years ago
6ff7fd80a1
feat: support OPENAI json_schema ( #7258 )
2 years ago
5aa373dc04
feat: add chatgpt-4o-latest ( #7289 )
2 years ago
32dc963556
feat(api/workflow): Add `Conversation.dialogue_count` ( #7275 )
2 years ago
d2ccd8ba53
fix : #7222 docstrings ( #7276 )
2 years ago
d29b32fce2
fix: typo in upstage/llm/_position.yaml ( #7286 )
2 years ago
101db126c8
fix: missed rerank_mode when convert to DatasetEntity ( #7269 )
2 years ago
ba79088ffc
Fix SQL parser Error in MyScale vdb. ( #7255 )
2 years ago
3a27166c2e
chore: allow download audio/video through HTTP node ( #7224 )
2 years ago
52383d0161
add support for tongyi-farui ( #7248 )
...
Co-authored-by: 雪风 <xuefeng@shifaedu.cn>
2 years ago
48d2febebf
fix(api/core/tools/entities/tool_entities.py): Fix type define. ( #7250 )
2 years ago
986fd5bfc6
Add gitlab support ( #7179 )
...
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
f104b930cf
feat: support elasticsearch vector database ( #3558 )
...
Co-authored-by: miendinh <miendinh@users.noreply.github.com>
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
0f59d76997
fix: add context_size and max_chunks to Tongyi embedding to resolve issue #7189 ( #7227 )
2 years ago
b3743a9ae5
chore: refactor searXNG tool ( #7220 )
2 years ago
935e72d449
Feat: conversation variable & variable assigner node ( #7222 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: Joel <iamjoel007@gmail.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
a12ddc47e7
feat: add support of speech2text function for OpenAI-API-compatible and Siliconflow ( #7197 )
2 years ago
67b9fdaad7
siliconflow support bge-3 && bce-v1 embedding ( #7198 )
2 years ago
ccb6ddd840
chore: bump Ruff to 0.5.7 ( #7174 )
2 years ago
f2cb1fb09f
Fix : Workflow "start" paste url not support s3 pre-signed URL ( #6855 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
2 years ago
ac60182c91
fix: solving http-request-tool bugs in workflow ( #6685 )
2 years ago
8b5761efb2
change secret input to text input in searxng ( #7160 )
2 years ago
5b32f2e0dd
Feat: Add model provider Text Embedding Inference for embedding and rerank ( #7132 )
2 years ago
4cbeb6815b
Fix: Wrong cutoff length lead to empty input in openai compatible embedding model. ( #7133 )
2 years ago
d338f69837
feat: add decode option to json process tools ( #7138 )
2 years ago
425174e82f
feat: update ops trace ( #7102 )
2 years ago
7201b56a6d
fix: workflow log run time error ( #7130 )
2 years ago
4dfa8eedb8
Feat/tool-D-ID ( #6278 )
2 years ago
07511dfaf4
update stepfun model ( #7118 )
...
Co-authored-by: chenlinfeng <chenlinfeng@step.ai>
Co-authored-by: Tfsh <tianfs_fight@163.com>
2 years ago
7944ce0594
feat: wenxin add yi-34b-chat ( #7117 )
2 years ago
ad682c394d
fix annotation reply is null ( #7103 )
2 years ago
83acb53c08
feat: add zhipu embedding-3 ( #7100 )
2 years ago
a7162240e6
feat: add text-embedding functon and LLM models to Siliconflow ( #7090 )
2 years ago
12095f8cd6
extract docx filter comment element ( #7092 )
2 years ago
4ffa706e4f
feat: add a builtin tool to support regex extraction. ( #7081 ) ( #7087 )
2 years ago
169cde6c3c
add nltk punkt resource ( #7063 )
2 years ago
34a9dbe826
Feat/add 360-zhinao provider ( #7069 )
2 years ago
f288d367ac
Add price info for zhipu models ( #7084 )
2 years ago
5e2fa13126
feat: support glm-4-long ( #7070 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2 years ago
67a2f14cef
fix(api/core/workflow/nodes/tool/tool_node.py): Keep None value in tool params. ( #7066 )
2 years ago
d7bb422a5c
fix: hunyuan assistant_prompt_message pydantic error ( #7062 )
2 years ago
40c6f3c724
fix: add redis lock to AnalyticdbVector init ( #6859 )
...
Co-authored-by: xiaozeyu <xiaozeyu.xzy@alibaba-inc.com>
2 years ago
df8f8c9a2c
feat(api/core/rag/datasource/vdb/analyticdb/analyticdb_vector.py): Checking config before init analyticdb ( #7050 )
2 years ago
536c43257b
refactor(*): Update hard-code '[__HIDDEN__]' to the constant. ( #7048 )
2 years ago
4e8f6b3603
chore(api/core/app/segments/segments.py): Remove todo tags. ( #7052 )
2 years ago
80c94f02e9
add vector field for other vectordb ( #7051 )
2 years ago
aad02113c6
fix(api/core/app/segments): Allow to contains boolean value in object segment ( #7047 )
2 years ago
72c75b75cf
feat: Add hyperlink parsing to the DOCX document. ( #7017 )
2 years ago
99b78dd198
feat: add gpt-4o-2024-08-06 ( #7046 )
2 years ago
a93bc83c8d
Provide output data also in json property of workflow tool ( #6924 ) ( #7027 )
2 years ago
3516989738
fix: typos in wenxin llm ( #7021 )
2 years ago
26991443ed
fix: Fix incorrect context size for jina-reranker-v2 model ( #7006 )
2 years ago
eece50acec
fix: tran list issue ( #7009 )
...
Co-authored-by: libing <libing@healink.cn>
2 years ago
28d4e5b045
Fix/reranking mode is null ( #7012 )
2 years ago
c53875ce8c
fix #6902 .docx handles images within tables and handles cross-column tables ( #6951 )
2 years ago
96dcf0fe8a
fix: code tool fails when null property exists in object ( #6988 )
2 years ago
bd3ed89516
feat: add function calling for deepseek models ( #6990 )
2 years ago
23ed15d19f
feat:nvidia add nemotron4-340b and microsoft/phi-3 ( #6973 )
2 years ago
312d905c9b
chore: update duckduckgo tool ( #6983 )
2 years ago
6da14c2d48
security: fix api image security issues ( #6971 )
2 years ago
a34285196b
Revise the wrong pricing of certain LLM models. ( #6967 )
2 years ago
ea30174057
chore: optimize streaming tts of xinference ( #6966 )
2 years ago
141e4e0276
fix: restore xinference secret field ( #6941 )
...
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
2 years ago
20d3e1d297
Fix increase_usage of total_price in agent_runner ( #6688 )
2 years ago
dff3f41ef6
Workflow TTS playback node filtering issue. ( #6877 )
2 years ago
5e634a59a2
compatible xinference reranker server ( #6927 )
2 years ago
26e46d365c
fix: workflow trace user_id error ( #6932 )
2 years ago
bcd7c8e921
fix: sending app trace data to other app trace provider ( #6931 )
2 years ago
2e941bb91c
add new provider Solar ( #6884 )
2 years ago
541bf1db5a
feat: add the tool Serper for Google search. ( #6786 ) ( #6790 )
2 years ago
f97a51ce24
fix: reranking disable timer error ( #6910 )
2 years ago
6aa02f8c63
dep: bump pgvecto-rs client from 0.1.x to 0.2.x ( #6891 )
2 years ago
bf3f1027c8
fix: code execution node not display clear reasons when sandbox res error ( #6830 )
2 years ago
8166a8caf5
feat: update llama3.1 parameters for openrouter ( #6901 )
2 years ago
44801df8f8
fix score threshold limit be None ( #6900 )
2 years ago
56af1a0adf
pref: change ollama embedded api request ( #6876 )
2 years ago
f8617db012
fix tongyi tool calls ( #6896 )
2 years ago
2ab9af3b38
delete weight_type in knowledge retrieval node ( #6892 )
2 years ago
cc4785f094
fix: xinference reranker return_documents ( #6888 )
2 years ago
a9cd6df97e
Remove tts (blocking call) ( #6869 )
2 years ago
f31142e758
Azure 4o mini options ( #6873 )
2 years ago
792f908afb
Revert "feat:Azure gpt4o mini" ( #6870 )
2 years ago
29e3c3061c
fix: remote image not display in answer node ( #6867 )
2 years ago
14367ddc09
feat:Azure gpt4o mini ( #6866 )
2 years ago
8157fccf6d
delete weight_type ( #6865 )
2 years ago
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>
2 years ago
f6e8e120a1
support xinference tts ( #6746 )
2 years ago
08f922d8c9
fix: anthropic max token NoneType error ( #6858 )
2 years ago
56b43f62d1
feat: nvidia add llama3.1 model ( #6844 )
2 years ago
4b410494b3
Add model parameter enable_enhance for hunyuan llm model ( #6847 )
...
Co-authored-by: sun <sun@centen.cn>
2 years ago
df9bd36cab
fix: claude-3-5-sonnet-20240620 max token error ( #6843 )
2 years ago
4be12b29b9
fix: improved error handling for spider tool ( #6835 )
2 years ago
c23aa50bea
Add AWS builtin Tools ( #6721 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
9ce5cea911
feat: bedrock invoke enhancement ( #6808 )
2 years ago
98d9837fbc
fix wrong charset when decoding Chinese content ( #6774 )
...
Co-authored-by: zhangwb <zhangwb@zts.com.cn>
2 years ago
72963d1f13
fix: nonetype in webscraper validation ( #6788 )
2 years ago
a98284b1ef
refactor(api): Switch to `dify_config` ( #6750 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
b414ea41d6
dep: initial support for Milvus 2.4.x ( #6084 )
2 years ago
f78d0082ae
feat: implement function dispatch table for trace processing ( #6628 )
2 years ago
3e18d32ce5
add deepseek-coder-v2 in siliconflow ( #6149 )
2 years ago
94d68b6a08
upgrade deepseek params ( #6744 )
2 years ago
c9ff0e3961
Add model hunyuan-embedding ( #6657 )
...
Co-authored-by: sun <sun@centen.cn>
2 years ago
8dd68e2034
fix(api/core/moderation/output_moderation.py): Fix config call. ( #6769 )
2 years ago
cb01bf2986
chore: set logging level to debug when reading YAML files and falling back to default value in case of None ( #6758 )
2 years ago
20268708cc
chore: improve position map conversion and tolerate empty position yaml file ( #6541 )
2 years ago
829472a1d7
switch to diffy_config with Pydantic in files, moderation and app ( #6747 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
21f6caacd4
feat: enhance the firecrawl tool ( #6705 )
2 years ago
6a3bef8378
feat(api/core/app/segments): Update segment types and variables ( #6734 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
b6c3010f02
refactor(api/core/workflow/nodes/base_node.py): Update extract_variable_selector_to_variable_mapping method signature. ( #6733 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
90d2c01218
Feat/6725 can not get image url from cogview tool ( #6728 )
2 years ago
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>
2 years ago
cf258b7a67
add xlsx support hyperlink extract ( #6722 )
2 years ago
5d77dc4f58
feat(api/core/app/segments/parser.py): Remove blank segment in `convert_template` ( #6709 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
e4542215cc
fix: tongyi empty tool_calls is not supported in message ( #6719 )
2 years ago
3d3677e912
Feat/model provider novita ( #6717 )
...
Co-authored-by: takatost <takatost@gmail.com>
2 years ago
c6996a48a4
refactor(api/core/app/segments): Support more kinds of Segments. ( #6706 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
6b50bb0fe6
issues #6655 Open ai tts issues ( #6696 )
2 years ago
ecb9c311b5
chore: make prompt generator max tokens configurable ( #6693 )
2 years ago
79cb23e8ac
security/SSRF vulns ( #6682 )
2 years ago
c5ac004f15
[seanguo] fix: unsupported filename in windows & add Mistral Large 2 ( #6679 )
2 years ago
78a339a794
modify llama3-1 yaml filename to support Windows pull operations ( #6677 )
2 years ago
5e4ac11df3
fix: code block segmentation problem of markdown document ( #6465 )
2 years ago
16b4f560cd
fix bugs(when using Oracle23ai as Vector DB) ( #6658 )
2 years ago
75e6576c67
refactor(api/core/app/segments): implement `to_object` in ObjectVariable and ArrayVariable. ( #6671 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
ebcc07e3e9
feat: support max_retries in jina requests ( #6585 )
2 years ago
ca696fe94c
Add support of tool-call for model provider "hunyuan" ( #6656 )
...
Co-authored-by: sun <sun@centen.cn>
2 years ago
9815aab7a3
[seanguo] feat: add llama 3.1 support in bedrock ( #6645 )
2 years ago
a876baf0a9
Resolve variable type parameter error ( #6646 )
2 years ago
91fd8521c3
fix reranking model field error ( #6654 )
2 years ago
4ec9a87e46
fix(api/core/workflow/nodes/iteration/iteration_node.py): Extend output in iteration if output is a array. ( #6647 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
31efe10c75
refactor(api/core/workflow/workflow_engine_manager.py): Remove ( #6630 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
72bc9d5f2b
feat(api/core/app/segments/variables.py): Support description in Variable. ( #6636 )
...
Signed-off-by: -LAN- <laipz8200@outlook.com>
2 years ago
600f13436d
remove rerank model must be required when retrieval_model is multiple ( #6640 )
2 years ago
d4c55748f1
doc: fix about model features ( #6619 )
2 years ago
5af2df0cd5
fix: qwen fc error ( #6620 )
...
Co-authored-by: dufei <du_fei@venusgroup.com.cn>
2 years ago
e4bb943fe5
Feat/delete single dataset retrival ( #6570 )
2 years ago
0fb741f269
fix: downgraded sentry-sdk to 1.44.1 due to claude LLM token returning 0 ( #6597 )
2 years ago
4c85393a1d
feat: add GroqCloud llama3.1 series models support ( #6596 )
2 years ago
d5c2680fde
feat: support llama3.1 series models for openrouter provider ( #6595 )
2 years ago
85a883e281
fix(variables): NoneVariable should inherit from NoneSegment. ( #6584 )
2 years ago
8123a00e97
feat: update prompt generate ( #6516 )
2 years ago
2bc0632d0d
fix(segments): Support NoneType. ( #6581 )
2 years ago
ad7552ea8d
fix(api/core/workflow/nodes/llm/llm_node.py): Fix LLM Node error. ( #6576 )
2 years ago
c0ada940bd
fix: tool params not work as expected when develop a tool ( #6550 )
2 years ago
7c55c39085
feat: add tencent asr ( #6091 )
2 years ago
f019bc4bd7
feat(variables): Support `to_object`. ( #6572 )
2 years ago
cfc408095c
fix(api/nodes): Fallback to `get_any` in some nodes that use object or array. ( #6566 )
2 years ago
6b5fac3004
fix: fetch context error in llm node ( #6562 )
2 years ago
0569c547ee
fix the issue of MILVUS_DATABASE has no effect. ( #6424 )
2 years ago
06fc1bce9e
Add search by full text when using Oracle23ai as vector DB ( #6559 )
2 years ago
093b8ca475
fix: escape double quotation marks in the vector DB search query ( #6506 )
2 years ago
5fcc2caeed
feat: add Mingdao HAP tool, implemented read and maintain HAP application worksheet data. ( #6257 )
...
Co-authored-by: takatost <takatost@gmail.com>
2 years ago
cd7fa8027a
fix(api/core/model_manager.py): Avoid mutation during iteration. ( #6536 )
2 years ago
5e6fc58db3
Feat/environment variables in workflow ( #6515 )
...
Co-authored-by: JzoNg <jzongcode@gmail.com>
2 years ago
a67831773f
refactor: handle missing position file gracefully ( #6513 )
2 years ago
dfb6f4fec6
fix: extract tool calls correctly while arguments is empty ( #6503 )
2 years ago
f38034e455
clean vector collection redis cache ( #6494 )
2 years ago
49ef9ef225
feat(tool): getimg.ai integration ( #6260 )
2 years ago
c013086e64
fix: next suggest question logic problem ( #6451 )
...
Co-authored-by: evenyan <yikun.yan@ubtrobot.com>
2 years ago
4f9f175f25
fix: correct gpt-4o-mini max token ( #6472 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2 years ago
9e168f9d1c
feat: support gpt-4o-mini for openrouter provider ( #6447 )
2 years ago
ea45496a74
update ernie models ( #6454 )
2 years ago
2ba05b041f
refactor(myscale):Set the default value of the myscale vector db in DifyConfig. ( #6441 )
2 years ago
8e49146a35
[EMERGENCY] Fix Anthropic header issue ( #6445 )
2 years ago
dad3fd2dc1
feat: add gpt-4o-mini ( #6442 )
2 years ago
7b45a5d452
fix: Unable to display images generated by Dall-E 3 ( #6155 )
2 years ago
4a026fa352
Enhancement: add model provider - Amazon Sagemaker ( #6255 )
...
Co-authored-by: Yuanbo Li <ybalbert@amazon.com>
Co-authored-by: crazywoola <427733928@qq.com>
2 years ago
dc847ba145
Fix the vector retrieval sorting issue ( #6431 )
...
Co-authored-by: weifj <“weifj@tuyuansu.com.cn”>
2 years ago
c0ec40e483
fix(api/core/tools/provider/builtin/spider/tools/scraper_crawler.yaml): Fix wrong placeholder config in scraper crawler tool. ( #6432 )
2 years ago
ba181197c2
feat: api_key support for xinference ( #6417 )
...
Signed-off-by: themanforfree <themanforfree@gmail.com>
2 years ago
218930c897
fix tool icon get failed ( #6375 )
...
Co-authored-by: songyawen <songyawen@zkme.xyz>
2 years ago
c8f5dfcf17
refactor(rag): switch to dify_config. ( #6410 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
588615b20e
feat: Spider web scraper & crawler tool ( #5725 )
2 years ago
d5dca46854
feat: add a Tianditu tool ( #6320 )
...
Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com>
2 years ago
23e5eeec00
feat: added custom secure_ascii to the json_process tool ( #6401 )
2 years ago
3b5b548af3
Add Stepfun LLM Support ( #6346 )
2 years ago
4782fb50c4
Support new Claude-3.5 Sonnet max token limit ( #6335 )
2 years ago
8a80af39c9
refactor(models&tools): switch to dify_config in models and tools. ( #6394 )
...
Co-authored-by: Poorandy <andymonicamua1@gmail.com>
2 years ago
f3f052ba36
fix: rename model from ernie-4.0-8k-Latest to ernie-4.0-8k-latest ( #6383 )
2 years ago
fc37887a21
refactor(api/core/workflow/nodes/http_request): Remove `mask_authorization_header` because its alwary true. ( #6379 )
2 years ago
4e2fba404d
WebscraperTool bypass cloudflare site by cloudscraper ( #6337 )
2 years ago
0de224b153
fix wrong using of RetrievalMethod Enum ( #6345 )
2 years ago
ed9e692263
feat: bedrock model runtime enhancement ( #6299 )
2 years ago
cc0c826f36
Add tool: Google Translate ( #6156 )
2 years ago
d66d7146a3
chore:update azure GA version 2024-06-01 ( #6307 )
2 years ago
b47fa27a35
fix: zhipuai validate error when user's api key not support for chatglm_turbo in issue #6289 ( #6290 )
2 years ago
96c171805a
Update bedrock.yaml ( #6281 )
2 years ago
ec181649ae
Update model provider configuration for Triton Inference Server and X… ( #6274 )
2 years ago
4fdcb30ff8
fix: custom tool input number fail ( #6200 )
...
Co-authored-by: jinqi.guo <jinqi.guo@ubtrobot.com>
2 years ago
07add06c59
Feat/add zhipu CogView 3 tool ( #6210 )
2 years ago
0cbbaf3f68
fix: markdown proc will remove image ( #5855 )
2 years ago
7c2c949f01
Update ernie_bot.py ( #6236 )
2 years ago
a9ee52f2d7
Fix/firecrawl parameters issue ( #6213 )
2 years ago
7b225a5ab0
refactor(services/tasks): Swtich to dify_config witch Pydantic ( #6203 )
2 years ago
d7a6f25c63
fix: differentiate prompts fields based on function_calling_type ( #5880 )
2 years ago
ee3936916f
upgrade deepseek params ( #6215 )
2 years ago
2f064c68bc
Create ernie-4.0-turbo-8k-preview ( #6132 )
2 years ago
0e82072323
Fix if_else node compatibility with historical workflows. ( #6186 )
2 years ago
63e34e5227
feat: support MyScale vector database ( #6092 )
2 years ago
5660878f7b
chore: update the tool's doc ( #6167 )
2 years ago
9622fbb62f
feat: app rate limit ( #5844 )
...
Co-authored-by: liuzhenghua-jk <liuzhenghua-jk@360shuke.com>
Co-authored-by: takatost <takatost@gmail.com>
2 years ago
cc8dc6d35e
Revert "chore: update the tool's doc" ( #6153 )
2 years ago
215661ef91
feat: add PerfXCloud, Qwen series #6116 ( #6117 )
2 years ago
5a3e09518c
feat: add if elif ( #6094 )
2 years ago
1d2ab2126c
chore: update the tool's doc ( #6122 )
2 years ago
d27e3ab99d
chore: remove unresolved reference ( #6110 )
2 years ago
7c70eb87bc
feat: support AnalyticDB vector store ( #5586 )
...
Co-authored-by: xiaozeyu <xiaozeyu.xzy@alibaba-inc.com>
2 years ago
6ef401a9f0
feat:add tts-streaming config and future ( #5492 )
2 years ago
6610b4cee5
feat: add request_params field to jina_reader tool ( #5610 )
2 years ago
610da4f662
Fix authorization header validation to handle bearer types correctly - "authorization config header is required" error ( #6040 )
2 years ago
91c5818236
Modify slack webhook url validation to allow workflow ( #6041 ) ( #6042 )
...
Co-authored-by: Shunsuke Mabuchi <mabuchs@amazon.co.jp>
2 years ago
a877d4831d
Fix/incorrect parameter extractor memory ( #6038 )
2 years ago
d522308a29
chore: optimize memory fetch performance ( #6039 )
2 years ago
85744b72e5
feat: support moonshot and glm base models for volcengine provider ( #6029 )
2 years ago
3b23d6764f
fix: token count includes base64 string of input images ( #5868 )
2 years ago
4d105d7bd7
feat(*): Swtich to dify_config. ( #6025 )
2 years ago
eee779a923
fix: the input field of tool panel not worked as expected ( #6003 )
2 years ago
ab847c81fa
Add 2 firecrawl tools : Scrape and Search ( #6016 )
...
Co-authored-by: -LAN- <laipz8200@outlook.com>
2 years ago
23dc6edb99
chore: optimize memory messages fetch count limit ( #6021 )
2 years ago
非法操作
Jyong
crazywoola
Zixuan Cheng
guogeer
-LAN-
luckylhb90
Pan, Wen-Ming
ybalbert001
ice yao
Zven
feiyang_deepnova
Kota-Yamaguchi
走在修行的大街上
zhuhao
Bowen Liang
AAEE86
chzphoenix
Ziyu Huang
Oliver Lee
Tao Wang
Jason Tan
Warren Wong
Wei-shun Bao
Hash Brown
kurokobo
Shili Cao
takatost
AkisAya
Fei He
Sa Zhang
Charlie.Wei
Joe
ronaksingh27
呆萌闷油瓶
pinsily
SebastjanPrachovskij
Infinitnet
aiscrm
zg0d233
Giannis Kepas
omr
CXwudi
Aurelius Huang
Zhaofeng Miao
chenxu9741
longzhihun
HowardChan
8bitpd
Shai Perednik
wenmeng zhou
cx
Shenghang Tsai
Aaron Ji
Qun
cherryhuahua
Shota Totsuka
Benjamin
themanforfree
Nam Vu
haike-1213
sino
Waffle
Hongbin
Su Yang
MuYu
Wang Bo
Xiao Ley
xiandan-erizo
Ikko Eltociear Ashimine
Tamer
yalei
Leo.Wang
邹成卓
ChengZi
tmuife
Byeongjin Kang
Leng Yue
wochuideng
KVOJJJin
Sumkor
陳鈞
Joshua
orangeclk
hisir
Yeuoly
Leheng Lu
Kenn
Hélio Lúcio
Qin Liu
Zhi
代君
Seayon
Junyan Qin
Jie.F
Amos
张皮皮
噢哎哟喂
AllenWriter
Xiyuan Chen
wellCh4n
KinWang
Chengyu Yan
RookieAgent
SoaringEthan
Weaxs
pp
mochi
miendinh
Onelevenvy
shAlfred
灰灰
Yanyi Liu
Jeff Li
Matri
forrestlinfeng
小羽
Aero Kang
shAlfred
majian
Achim
Bryan
yanghx
Yefori
Pedro Gomes
liuzhenghua
JuHyung Son
dufei
小羽
Giga Group
William Espegren
eric-0x72
SiliconFlow, Inc
Charles
Vicky Guo
Jason
Sangmin Ahn
xielong
zhangzhiqiangcs
Lance Mao
崔亮
Ryan Tian
Even
Richards Tu
Weishan-0
leoterry
Songyawn
Poorandy
listeng
Poorandy
svcvit
thibautleaux-kreactive
tangyoha
Little 羊
耐小心
JasonVV
Zhuo Qiu
75py
Mab
Masashi Tomooka
ahasasjeb