v0.8.3

[laipz8200]

✨ What’s New in v0.8.3? ✨

Hey everyone! We’re thrilled to announce the release of version 0.8.3, and it brings something truly game-changing:

🚀 Major Feature Highlight

• Qwen 2.5 Series Models: The highlight of this release is the integration of the Qwen 2.5 Series models, seamlessly synced with Aliyun Bailian, brought to you by @soulteary in feat: sync Qwen API with Aliyun Bailian #8538. This major update significantly expands our model offerings, providing enhanced capabilities and greater flexibility for your projects. Whether you're working with AI-driven workflows or model-intensive tasks, the Qwen 2.5 Series offers unmatched performance and versatility.

🛠️ Additional Features & Improvements

In addition to the powerful Qwen models, we’ve also made several other improvements and fixes to optimize your experience:

• New Tools:
  • ComfyUI for Stable Diffusion: Enhanced image generation capabilities with the integration of ComfyUI by @QunBB in feat: Add ComfyUI tool for Stable Diffusion #8160.
  • Siliconflow Image-Gen Tool: Part of the flux dev suite, this tool, introduced by @hjlarry in feat: add flux dev of siliconflow image-gen tool #8450, further expands your creative toolkit.
• Timeout Configuration: Thanks to @kurokobo in feat: allow users to specify timeout for text generations and workflows by environment variable #8395, you now have full control over text generation and workflow timeouts via environment variables, giving you more flexibility in managing process execution times.

⚙️ Enhancements and Fixes

We've also worked on various optimizations and bug fixes to improve overall stability:

• Image Preview Optimization: Enhanced SVG rendering and image previews for a smoother user experience, thanks to @charli117 in add svg render & Image preview optimization #8387.
• Workflow Improvements: Including better result handling and improved multi-retrieval for datasets.
• Bug Fixes: Numerous fixes across authorization, token usage, and vector search methods to ensure smoother operations.

This release is all about delivering cutting-edge capabilities with the Qwen 2.5 Series models and refining the platform with additional tools and fixes. Huge thanks to our incredible contributors for making this version happen! 🚀

---

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.

1. Back up your customized docker-compose YAML file (optional)

   cd docker
   cp docker-compose.yaml docker-compose.yaml.$(date +%s).bak

2. Get the latest code from the main branch

   git checkout main
   git pull origin main

3. Stop the service，Command, please execute in the docker directory

   docker compose down

4. Back up data

   tar -cvf volumes-$(date +%s).tgz volumes

5. Upgrade services

   docker compose up -d

Source Code deployments

1. Stop API server, Worker and Web frontend Server.

2. Get the latest code from the main branch:

   git checkout main
   git pull origin main

3. Update Python dependencies:

   cd api
   poetry install

4. Then, let's run the migration script:

   poetry shell
   flask db upgrade

5. Finally, run API server, Worker and Web frontend Server again.

---

What's Changed

• fix: ark token usage is none by @sinomoe in fix: ark token usage is none #8351
• fix: score_threshold handling in vector search methods by @laipz8200 in fix: score_threshold handling in vector search methods #8356
• chore: fix unnecessary string concatation in single line by @bowenliang123 in chore: fix unnecessary string concatation in single line #8311
• fix: o1-series model encounters an error when the generate mode is blocking by @takatost in fix: o1-series model encounters an error when the generate mode is blocking #8363
• fix: when edit load balancing config not pass the empty filed value hidden by @iamjoel in fix: when edit load balancing config not pass the empty filed value hidden #8366
• fix: add before send to remove langfuse defaultErrorResponse by @ZhouhaoJiang in fix: add before send to remove langfuse defaultErrorResponse #8361
• fix: edit load balancing not pass id by @iamjoel in fix: edit load balancing not pass id #8370
• fix(workflow): both parallel and single branch errors occur in if-else by @takatost in fix(workflow): both parallel and single branch errors occur in if-else #8378
• chore: update firecrawl scrape to V1 api by @hjlarry in chore: update firecrawl scrape to V1 api #8367
• support hunyuan-turbo by @xiandan-erizo in support hunyuan-turbo #8372
• chore: refurish python code by applying Pylint linter rules by @bowenliang123 in chore: refurish python code by applying Pylint linter rules #8322
• fix (chore: refurish python code by applying Pylint linter rules #8322 followup): resolve the violation of pylint rules by @bowenliang123 in fix (#8322 followup): resolve the violation of pylint rules #8391
• chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 by @bowenliang123 in chore: improve usage of striping prefix or suffix of string with Ruff 0.6.5 #8392
• fix: sandbox issue related httpx and requests by @Yeuoly in fix: sandbox issue related httpx and requests #8397
• fix: o1-mini 65563 -> 65536 by @crazywoola in fix: o1-mini 65563 -> 65536 #8388
• fix: pyproject.toml typo by @ZuzooVn in fix: pyproject.toml typo #8396
• fix(docker): aliyun oss path env key by @incca in fix(docker): aliyun oss path env key #8394
• Fix: Support Bedrock cross region inference Support Bedrock cross region inference  #8190 (Update Model name to distinguish between different region groups) by @ybalbert001 in Fix: Support Bedrock cross region inference #8190 (Update Model name to distinguish between different region groups) #8402
• fix: resolve runtime error when self.folder is None by @swingchen01 in fix: resolve runtime error when self.folder is None #8401
• fix:logs and rm unused codes in CacheEmbedding by @Howe829 in fix:logs and rm unused codes in CacheEmbedding #8409
• fix(workflow): the answer node after the iteration node containing the answer was output prematurely by @takatost in fix(workflow): the answer node after the iteration node containing the answer was output prematurely #8419
• fix: when the variable does not exist, an error should be prompted by @HiChen404 in fix: when the variable does not exist, an error should be prompted #8413
• Fix: operation postion of answer in logs by @JzoNgKVO in Fix: operation postion of answer in logs #8411
• feat: allow users to specify timeout for text generations and workflows by environment variable by @kurokobo in feat: allow users to specify timeout for text generations and workflows by environment variable #8395
• fix: sys_var startwith 'sys.' not 'sys' Variables starting with "sys" cannot be referenced correctly. #8421 by @yanxiyue in fix: sys_var startwith 'sys.' not 'sys' #8421 #8422
• chore: update Jina embedding model by @DresAaron in chore: update Jina embedding model #8376
• Fix: Support Bedrock cross region inference  #8190 (Update Model nam… by @ybalbert001 in Fix: https://github.com/langgenius/dify/issues/8190 (Update Model nam… #8426
• fix: delete the delay for the tooltips inside the add tool panel by @YIXIAO0 in fix: delete the delay for the tooltips inside the add tool panel #8436
• chore(workflow): Optimize the iteration when selecting a variable from a branch in the output variable causes iteration index err by @takatost in chore(workflow): Optimize the iteration when selecting a variable from a branch in the output variable causes iteration index err #8440
• Bugfix/fix feishu plugins by @hgnulb in Bugfix/fix feishu plugins #8443
• fix: Improve scrolling behavior for Conversation Opener by @ZuzooVn in fix: Improve scrolling behavior for Conversation Opener #8437
• add WorkflowClient.get_result, increase version number by @twisker in add WorkflowClient.get_result, increase version number #8435
• add svg render & Image preview optimization by @charli117 in add svg render & Image preview optimization #8387
• fix:docker-compose.middleware.yaml start the Weaviate container by default (docker-compose.middleware.yaml does not start the Weaviate container by default #8446) by @hwzhuhao in fix:docker-compose.middleware.yaml start the Weaviate container by default (#8446) #8447
• multi-retrival use dataset's top-k by @JohnJyong in multi-retrival use dataset's top-k #8416
• fix: internal error when tool authorization by @takatost in fix: internal error when tool authorization #8449
• [Python SDK] Add KnowledgeBaseClient and the corresponding test cases. by @twisker in [Python SDK] Add KnowledgeBaseClient and the corresponding test cases. #8465
• fix(RunOnce): change to form submission instead of onKeyDown and onClick by @MH4GF in fix(RunOnce): change to form submission instead of onKeyDown and onClick #8460
• chore: workflow BRANCH, PARALLEL i18n by @ZuzooVn in chore: workflow BRANCH, PARALLEL i18n #8452
• feat: add flux dev of siliconflow image-gen tool by @hjlarry in feat: add flux dev of siliconflow image-gen tool #8450
• feat: Add base URL settings and secure_ascii options to the Brave search tool by @XiaoLey in feat: Add base URL settings and secure_ascii options to the Brave search tool #8463
• chore: update the .gitignore file to include opensearch,pgvector,and myscale by @hwzhuhao in chore: update the .gitignore file to include opensearch,pgvector,and myscale #8470
• feat: Add ComfyUI tool for Stable Diffusion by @QunBB in feat: Add ComfyUI tool for Stable Diffusion #8160
• chore: Deprecate gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613 models by @laipz8200 in chore: Deprecate gpt-3.5-turbo-0613 and gpt-3.5-turbo-16k-0613 models #8500
• refactor: rename task_type to task for jina embeddings v3 by @bwanglzu in refactor: rename task_type to task for jina embeddings v3 #8488
• validate user permission before enter app detail page by @douxc in validate user permission before enter app detail page #8527
• feat: add format util unit and add pre-commit unit check by @LLmoskk in feat: add format util unit and add pre-commit unit check #8427
• fix: ci issues(missing duckduckgo-search==6.2.11, ruff lint issue) by @takatost in fix: ci issues(missing duckduckgo-search==6.2.11, ruff lint issue) #8543
• fix: thread_pool submit count in parallel workflow not releasing by @takatost in fix: thread_pool submit count in parallel workflow not releasing #8549
• feat: sync Qwen API with Aliyun Bailian by @soulteary in feat: sync Qwen API with Aliyun Bailian #8538
• add storage error log by @JohnJyong in add storage error log #8556
• chore: improve delimiter by @iamjoel in chore: improve delimiter #8552
• feat: add hunyuan-vision by @muzea in feat: add hunyuan-vision #8529
• fix: fix qwen series model type by @soulteary in fix: fix qwen series model type #8580
• Fix: update qwen model and model config by @soulteary in Fix: update qwen model and model config #8584
• ComfyUI tool use the new internal enumeration class "VariableKey" by @QunBB in ComfyUI tool use the new internal enumeration class "VariableKey" #8533
• chore: fix webpack dependencies order by @hjlarry in chore: fix webpack dependencies order #8542
• Update version to 0.8.3 in packaging and docker-compose files by @laipz8200 in Update version to 0.8.3 in packaging and docker-compose files #8590

New Contributors

• @xiandan-erizo made their first contribution in support hunyuan-turbo #8372
• @incca made their first contribution in fix(docker): aliyun oss path env key #8394
• @swingchen01 made their first contribution in fix: resolve runtime error when self.folder is None #8401
• @yanxiyue made their first contribution in fix: sys_var startwith 'sys.' not 'sys' #8421 #8422
• @DresAaron made their first contribution in chore: update Jina embedding model #8376
• @twisker made their first contribution in add WorkflowClient.get_result, increase version number #8435
• @bwanglzu made their first contribution in refactor: rename task_type to task for jina embeddings v3 #8488
• @LLmoskk made their first contribution in feat: add format util unit and add pre-commit unit check #8427
• @muzea made their first contribution in feat: add hunyuan-vision #8529

Full Changelog: 0.8.2...0.8.3

---

This discussion was created from the release v0.8.3.