0.7.2
版本发布时间: 2024-08-26 20:14:04
langgenius/dify最新发布版本:0.14.2(2024-12-23 19:18:04)
✨ What’s New in v0.7.2? ✨
Hey everyone, we’re excited to bring you version 0.7.2 of our platform. This release is packed with new features, enhancements, and bug fixes to make your experience even better. Here’s a quick rundown:
🚀 New Features
- Added support for dialogue count in chatflow by @iamjoel in #7440.
- Added support for JSON Mode for Moonshot models by @oiuv in #7568.
- Added support for Qwen text-embedding-v3 by @droxer in #7567.
- Added support for the siliconflow text2img tool by @hjlarry in #7612.
- Added support for the OneBot protocol tool by @RockChinQ in #7583.
- Support for Wenxin BGE-Large and Tao embedding models by @CheneyYin in #7393.
⚙️ Enhancements
-
UI/UX Improvements:
- Improved tooltip content to support line breaks by @hjlarry in #7424.
- Improved the copywrite of the assigner node append mode description by @iamjoel in #7467.
- Improved the readability of the menu collapse by @JunIce in #4099.
- Updated theme-related CSS variables values by @iamjoel in #7442.
- Added Langfuse view button by @charli117 in #7578.
- Updated the "tag delete" confirm modal by @YIXIAO0 in #7522.
-
Backend Improvements:
- Applied Ruff reformatting across various API components by @bowenliang123 in #7590, #7591, #7594, #7599, and @laipz8200 in #7645.
- Support for CODE_MAX_PRECISION by @ZuzooVn in #7484.
- Increased max steps to 50 in workflows by @takatost in #4252.
- Added finish_reason to the LLM node output by @orangeclk in #7498.
- Added support for pgvector full-text search setting by @JohnJyong in #7427.
- Added support for sorting conversations by updated_at desc by @KinWang130 in #7348.
- Create S3 bucket if it doesn't exist by @moyueheng in #7514.
- Added storage type and Google Storage settings to worker by @KiyotakaMatsushita in #4266.
🛠️ Bug Fixes
- Fixed logs not including the current day by @leslie2046 in #7426.
- Fixed workflow end node deletion by @zxhlyh in #4240.
- Fixed image icon not showing correctly on the left panel in the workflow web app page by @xuzuodong in #7466.
- Fixed JSON schema not being saved correctly by @hjlarry in #7487.
- Fixed the issue of the refine_switches param being invalid in the Novita.AI tool by @XiaoLey in #7485.
- Fixed the tag input state lost issue by @YIXIAO0 in #7500.
- Fixed the wrong usage of created_at on the modal for API Key by @monstaruos in #7548.
- Fixed the workflow context menu popup issue by @YIXIAO0 in #7530.
- Fixed incorrect duplication when no target node is selected by @edo1z in #7539.
- Fixed voice language by @ZuzooVn in #7570.
- Fixed score_threshold is none, return all top K documents by @gongchangwangpi in #7581.
- Fixed the issue of not passing query parameters when the value is empty by @AmosZhu in #7585.
- Fixed the workflow zoom range for shortcuts by @YIXIAO0 in #7563.
- Fixed the tool node error by @luckylhb90 in #7459.
- Fixed document error message not being cleared by @wellCh4n in #7453.
- Fixed the issue of the refine_switches param being invalid in the Novita.AI tool by @XiaoLey in #7485.
- Fixed the tag input state lost issue by @YIXIAO0 in #7500.
- Fixed the wrong usage of created_at on the modal for API Key by @monstaruos in #7548.
- Fixed the workflow context menu popup issue by @YIXIAO0 in #7530.
- Fixed incorrect duplication when no target node is selected by @edo1z in #7539.
- Fixed voice language by @ZuzooVn in #7570.
- Fixed score_threshold is none, return all top K documents by @gongchangwangpi in #7581.
- Fixed the issue of not passing query parameters when the value is empty by @AmosZhu in #7585.
- Fixed the workflow zoom range for shortcuts by @YIXIAO0 in #7563.
- Fixed the tool node error by @luckylhb90 in #7459.
- Fixed document error message not being cleared by @wellCh4n in #7453.
📝 Documentation
- Updated certbot/README.md by @eltociear in #7528.
- Added CONTRIBUTING_VI i18n by @ZuzooVn in #7532.
That’s all for this release! As always, thank you for your contributions and feedback. Keep them coming, and happy coding! 🚀
Upgrade Guide
Docker compose deployments
[!WARNING] The
docker-compose.yaml
has been refactored. If you've made any changes to the file, make sure to check out the "Upgrade to new docker compose deployment" section above for usage and migration tips.
-
Back up your customized docker-compose YAML file (optional)
cd docker cp docker-compose.yaml docker-compose.yaml.$(date +%s).bak
-
Get the latest code from the main branch
git checkout main git pull origin main
-
Stop the service,Command, please execute in the docker directory
docker compose down
-
Back up data
tar -cvf volumes-$(date +%s).tgz volumes
-
Upgrade services
docker compose up -d
Source Code deployments
-
Stop API server, Worker and Web frontend Server.
-
Get the latest code from the main branch:
git checkout main git pull origin main
-
Update Python dependencies:
cd api poetry install
-
Then, let's run the migration script:
poetry shell flask db upgrade
-
Finally, run API server, Worker and Web frontend Server again.
What's Changed
- Web app support sending message using numpad enter by @xuzuodong in https://github.com/langgenius/dify/pull/7414
- feat(api): support wenxin bge-large and tao embedding model. by @CheneyYin in https://github.com/langgenius/dify/pull/7393
- chore: correct _tts_invoke_streaming max length by @ZuzooVn in https://github.com/langgenius/dify/pull/7423
- chore: #7196 i18n by @ZuzooVn in https://github.com/langgenius/dify/pull/7416
- fix: Logs do not include current day by @leslie2046 in https://github.com/langgenius/dify/pull/7426
- feat: add pgvector full_text_search by @jasonkang14 in https://github.com/langgenius/dify/pull/7396
- feat: support line break of tooltip content by @hjlarry in https://github.com/langgenius/dify/pull/7424
- add pgvector full text search settting by @JohnJyong in https://github.com/langgenius/dify/pull/7427
- chore(database): Rename table name from
workflow__conversation_variables
toworkflow_conversation_variables
. by @laipz8200 in https://github.com/langgenius/dify/pull/7432 - chore: remove .idea and .vscode from root path by @Yeuoly in https://github.com/langgenius/dify/pull/7437
- refactor(api/core/workflow/nodes/variable_assigner): Split into multi files. by @laipz8200 in https://github.com/langgenius/dify/pull/7434
- chore: add and update theme related css variables values by @iamjoel in https://github.com/langgenius/dify/pull/7442
- refactor(api/core/app/app_config/entities.py): Move Type to outside and add EXTERNAL_DATA_TOOL. by @laipz8200 in https://github.com/langgenius/dify/pull/7444
- fix(api/services/workflow/workflow_converter.py): Add NoneType checkers & format file. by @laipz8200 in https://github.com/langgenius/dify/pull/7446
- refactor(api/core/workflow/enums.py): Rename SystemVariable to SystemVariableKey. by @laipz8200 in https://github.com/langgenius/dify/pull/7445
- refactor(api/models/workflow.py): Add
__init__
to Workflow by @laipz8200 in https://github.com/langgenius/dify/pull/7443 - feat: Sort conversations by updated_at desc by @KinWang130 in https://github.com/langgenius/dify/pull/7348
- feat: support dialogue count in chatflow by @iamjoel in https://github.com/langgenius/dify/pull/7440
- fix: document error message can not be cleared by @wellCh4n in https://github.com/langgenius/dify/pull/7453
- chore: #7348 i18n by @ZuzooVn in https://github.com/langgenius/dify/pull/7451
- fix(tool): tool node error by @luckylhb90 in https://github.com/langgenius/dify/pull/7459
- fix: image icon not showing correctly on left panel in workflow web app page by @xuzuodong in https://github.com/langgenius/dify/pull/7466
- chore: improve the copywrite of the assigner node append mode description by @iamjoel in https://github.com/langgenius/dify/pull/7467
- feat: support pinning, including, and excluding for model providers and tools by @GareArc in https://github.com/langgenius/dify/pull/7419
- Separate CODE_MAX_DEPTH and set it as an environment variable by @Hisir0909 in https://github.com/langgenius/dify/pull/7474
- fix: json schema not saved correctly by @hjlarry in https://github.com/langgenius/dify/pull/7487
- fix the issue of the refine_switches at param being invalid in the Novita.AI tool by @XiaoLey in https://github.com/langgenius/dify/pull/7485
- feat: gpt-4o-mini-2024-07-18 support json schema by @hjlarry in https://github.com/langgenius/dify/pull/7489
- feat: support CODE_MAX_PRECISION by @ZuzooVn in https://github.com/langgenius/dify/pull/7484
- Fix/incorrect code template by @Yeuoly in https://github.com/langgenius/dify/pull/7490
- fix rerank mode is none by @JohnJyong in https://github.com/langgenius/dify/pull/7496
- Chore/remove python dependencies selector by @Yeuoly in https://github.com/langgenius/dify/pull/7494
- add finish_reason to the LLM node output by @orangeclk in https://github.com/langgenius/dify/pull/7498
- Feat/7134 use dataset api create a dataset with permission by @crazywoola in https://github.com/langgenius/dify/pull/7508
- feat(storage): 🐛 Create S3 bucket if it doesn't exist by @moyueheng in https://github.com/langgenius/dify/pull/7514
- fix: tag input state lost issue by @YIXIAO0 in https://github.com/langgenius/dify/pull/7500
- feat: update the "tag delete" confirm modal by @YIXIAO0 in https://github.com/langgenius/dify/pull/7522
- fix: add missed modifications of
<AppIcon />
by @xuzuodong in https://github.com/langgenius/dify/pull/7512 - docs: update certbot/README.md by @eltociear in https://github.com/langgenius/dify/pull/7528
- docs: CONTRIBUTING_VI i18n by @ZuzooVn in https://github.com/langgenius/dify/pull/7532
- update nltk version to 3.8.1 by @JohnJyong in https://github.com/langgenius/dify/pull/7544
- Added Space between Chinese and English within tools' description by @AllenWriter in https://github.com/langgenius/dify/pull/7545
- fix: wrong usage of created_at on the modal for API Key by @monstaruos in https://github.com/langgenius/dify/pull/7548
- fix: correct response structure in openapi documentation of app by @realethanhsu in https://github.com/langgenius/dify/pull/7556
- Add N-to-1 warning translation for JP by @HanqingZ in https://github.com/langgenius/dify/pull/7553
- feat: forward zhipu finish_reason by @orangeclk in https://github.com/langgenius/dify/pull/7560
- chore: #6554 i18n by @ZuzooVn in https://github.com/langgenius/dify/pull/7562
- feat: set workflow zoom range for shortcut by @YIXIAO0 in https://github.com/langgenius/dify/pull/7563
- fix: workflow context menu popup issue by @YIXIAO0 in https://github.com/langgenius/dify/pull/7530
- fix: incorrect duplication when no target node is selected by @edo1z in https://github.com/langgenius/dify/pull/7539
- chore: improve the check time of variable name by @iamjoel in https://github.com/langgenius/dify/pull/7569
- chore: improve the check time of variable name in conversation and env var by @iamjoel in https://github.com/langgenius/dify/pull/7572
- Fix: voice language by @ZuzooVn in https://github.com/langgenius/dify/pull/7570
- add qwen text-embedding-v3 support. by @droxer in https://github.com/langgenius/dify/pull/7567
- langfuser add view button by @charli117 in https://github.com/langgenius/dify/pull/7571
- Langfuse view button by @charli117 in https://github.com/langgenius/dify/pull/7578
- add JSON Mode support for moonshot models by @oiuv in https://github.com/langgenius/dify/pull/7568
- fix score_threshold is none, return all top K documents by @gongchangwangpi in https://github.com/langgenius/dify/pull/7581
- fix: knowledge setting "knowledge name" input width by @YIXIAO0 in https://github.com/langgenius/dify/pull/7584
- Do not pass query parameter when the value is empty by @AmosZhu in https://github.com/langgenius/dify/pull/7585
- Update stable_diffusion.py by @flingjie in https://github.com/langgenius/dify/pull/7536
- Feat: add OneBot protocol tool by @RockChinQ in https://github.com/langgenius/dify/pull/7583
- fix(onebot): use yarl to format url by @RockChinQ in https://github.com/langgenius/dify/pull/7589
- chore: cleanup and rearrange unclassified configs into feature config groups by @bowenliang123 in https://github.com/langgenius/dify/pull/7586
- chore(api/configs): apply ruff reformat by @bowenliang123 in https://github.com/langgenius/dify/pull/7590
- chore(api/tests): apply ruff reformat #7590 by @bowenliang123 in https://github.com/langgenius/dify/pull/7591
- feat: Introduce Ark SDK v3 and ensure compatibility with models of SDK v2 by @sinomoe in https://github.com/langgenius/dify/pull/7579
- fix: typo in comment by @totsukash in https://github.com/langgenius/dify/pull/7606
- Improve MIME type detection for image URLs by @Seayon in https://github.com/langgenius/dify/pull/6531
- feat: add siliconflow text2img tool by @hjlarry in https://github.com/langgenius/dify/pull/7612
- feat: web sso by @ZhouhaoJiang in https://github.com/langgenius/dify/pull/7135
- Web app now supports SSO config by @douxc in https://github.com/langgenius/dify/pull/7137
- feat: replace show/hide workflow_steps with switch by @crazywoola in https://github.com/langgenius/dify/pull/7627
- feat: tooltip by @YIXIAO0 in https://github.com/langgenius/dify/pull/7634
- chore(api/tasks): apply ruff reformatting by @bowenliang123 in https://github.com/langgenius/dify/pull/7594
- chore(api/services): apply ruff reformatting by @bowenliang123 in https://github.com/langgenius/dify/pull/7599
- fix: use LOG_LEVEL for celery startup by @erigo in https://github.com/langgenius/dify/pull/7628
- feat: speed up the Docker build for dify-api for Chinese developers. by @erigo in https://github.com/langgenius/dify/pull/7626
- add:save_model_credentials error log by @pinsily in https://github.com/langgenius/dify/pull/7630
- fix nltk averaged_perceptron_tagger download and fix score limit is none by @JohnJyong in https://github.com/langgenius/dify/pull/7582
- chore(api/controllers): Apply Ruff Formatter. by @laipz8200 in https://github.com/langgenius/dify/pull/7645
- fix: support float type for tool parameter's default value by @hjlarry in https://github.com/langgenius/dify/pull/7644
- [fix] openai's tool role dose not support name parameter. by @sydnash in https://github.com/langgenius/dify/pull/7659
- Proposal to revise Japanese expressions by @snickerjp in https://github.com/langgenius/dify/pull/7664
- catch openai rate limit error by @JohnJyong in https://github.com/langgenius/dify/pull/7658
- refactor: Add @staticmethod decorator in
api/core
by @totsukash in https://github.com/langgenius/dify/pull/7652 - chore: Update version to 0.7.2 by @laipz8200 in https://github.com/langgenius/dify/pull/7646
New Contributors
- @jasonkang14 made their first contribution in https://github.com/langgenius/dify/pull/7396
- @KinWang130 made their first contribution in https://github.com/langgenius/dify/pull/7348
- @Hisir0909 made their first contribution in https://github.com/langgenius/dify/pull/7474
- @moyueheng made their first contribution in https://github.com/langgenius/dify/pull/7514
- @monstaruos made their first contribution in https://github.com/langgenius/dify/pull/7548
- @edo1z made their first contribution in https://github.com/langgenius/dify/pull/7539
- @droxer made their first contribution in https://github.com/langgenius/dify/pull/7567
- @gongchangwangpi made their first contribution in https://github.com/langgenius/dify/pull/7581
- @AmosZhu made their first contribution in https://github.com/langgenius/dify/pull/7585
- @flingjie made their first contribution in https://github.com/langgenius/dify/pull/7536
- @RockChinQ made their first contribution in https://github.com/langgenius/dify/pull/7583
- @totsukash made their first contribution in https://github.com/langgenius/dify/pull/7606
- @erigo made their first contribution in https://github.com/langgenius/dify/pull/7628
- @pinsily made their first contribution in https://github.com/langgenius/dify/pull/7630
- @sydnash made their first contribution in https://github.com/langgenius/dify/pull/7659
- @snickerjp made their first contribution in https://github.com/langgenius/dify/pull/7664
Full Changelog: https://github.com/langgenius/dify/compare/0.7.1...0.7.2