v0.10.0

[laipz8200]

🎉 What's New in v0.10.0? 🎉

Hello to all the innovators out there! We're excited to unveil v0.10.0, a powerhouse update designed to enhance your flexibility and efficiency. Let’s delve into the highlights:

🌟 Enhanced Multi-Modal Support

This central feature boosts your workflows and chatflows with greater flexibility:

• Advanced File Handling: Nodes like START, LLM, HTTP Request and IF-ELSE now seamlessly manage "File" types, simplifying the processing of various file formats within your workflows.

• New Functional Nodes:

  • Document Extractor: Converts documents into text effortlessly, making data extraction straightforward.
  • List Operator: Empowers you with operations to filter, sort, and limit arrays, enhancing data control and manipulation.

• Efficient Array Handling: Directly use array[string] and array[number] in LLM prompts for more agile data interactions.

Thanks to the tireless efforts of @zxhlyh in #9526 and @laipz8200 in #8818, this feature marks a significant leap forward.

Read more: Introducing Dify Workflow File Upload: A Demo on AI Podcast

✉️ Registry and Login with Email

Simplifying user access with:

• Email Registration & Login: Offers a secure, straightforward access method for users, optimizing the onboarding process. Shoutout to @douxc in New Auth Methods #8119 and @ZhouhaoJiang in Feat/new login #8120.

🚀 Additional Features

• Dataset Recall Testing API: Gain insights into data retrieval efficiency with this new API, brought to you by @gubinjie in feat: added dataset recall testing API #9300.
• Fireworks Model Integration: Access Qwen2.5 72B Instruct models for expanded AI capability, thanks to @yaoice in feat: Add fireworks custom llm intergration #9333 and feat: Add qwen2.5 72B Instruct model in Fireworks AI #9340.

🛠️ Enhancements

• Storybook Component Testing: Streamlined UI testing and visualization, expertly structured by @xuzuodong in feat: storybook #9324.
• Timezone Conversion Enhancements: Enhanced precision and usability with support in the Time Tool, thanks to @hwzhuhao in feat: add timezone conversion for time tool #9393.

🔧 Fixes

• Azure OpenAI Fixes: Resolved key issues with max token calculations for improved performance, managed by @somethingwentwell in fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error #9326.
• Endpoint Functionality Fixes: Strengthened the stability of the db-pool-stat endpoint, addressed by @hwzhuhao in fix: resolve the error with the db-pool-stat endpoint #9478.

v0.10.0 brings a wealth of innovations to simplify and elevate your workflow capabilities. Dive in and explore these enhancements to harness the full potential of AI-driven tasks. Your feedback is pivotal, so keep it coming. Happy building! 🚀

---

Upgrade Guide

Docker compose deployments

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 release branch:

   git checkout 0.10.0

3. Update Python dependencies:

   cd api
   poetry install

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

   poetry run flask db upgrade

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

---

What's Changed

• feat: added dataset recall testing API by @gubinjie in feat: added dataset recall testing API #9300
• feat: disable chat service API passing parent_message_id by @xuzuodong in feat: disable chat service API passing parent_message_id #8984
• fix: poetry installation in CI jobs by @bowenliang123 in fix: poetry installation in CI jobs #9336
• feat: Add fireworks custom llm intergration by @yaoice in feat: Add fireworks custom llm intergration #9333
• feat: Add qwen2.5 72B Instruct model in Fireworks AI by @yaoice in feat: Add qwen2.5 72B Instruct model in Fireworks AI #9340
• chore: clean-up unnecessary annotation on configs with non-null default value by @bowenliang123 in chore: clean-up unnecessary annotation on configs with non-null default value #9323
• refactor: remove unnecessary 'closing' usage for boto3 client by @y-omr in refactor: remove unnecessary 'closing' usage for boto3 client #9343
• Adapt input type parameter with MiniMax embedding model by @yaoice in Adapt input type parameter with MiniMax embedding model #9342
• refactor: Add an enumeration type and use the factory pattern to obtain the corresponding class by @hwzhuhao in refactor: Add an enumeration type and use the factory pattern to obtain the corresponding class #9356
• fix: In the output, the order of 'ta' is sometimes reversed as 'at'. In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 by @wsbao in fix: In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 #8791
• fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error by @somethingwentwell in fix: Azure OpenAI o1 max_completion_token and get_num_token_from_messages error #9326
• feat: add glm-4-flashx, deprecated chatglm_turbo by @hjlarry in feat: add glm-4-flashx, deprecated chatglm_turbo #9357
• fix: (fix: poetry installation in CI jobs #9336 followup) skip poetry preperation in style workflow when no change in api folder by @bowenliang123 in fix: (#9336 followup) skip poetry preperation in style workflow when no change in api folder #9362
• feat: add minimax abab6.5t support by @cuckootan in feat: add minimax abab6.5t support #9365
• fix: add missing vikingdb param in docker .env.example by @yaoice in fix: add missing vikingdb param in docker .env.example #9334
• fix: remove the stream option of zhipu and gemini by @hjlarry in fix: remove the stream option of zhipu and gemini #9319
• feat: Enable baiduvector intergration test by @yaoice in feat: Enable baiduvector intergration test #9369
• fix: use gpt-4o-mini for validating credentials by @crazywoola in fix: use gpt-4o-mini for validating credentials #9387
• feat: storybook by @xuzuodong in feat: storybook #9324
• fix: Deprecated gemma2-9b model in Fireworks AI Provider by @yaoice in fix: Deprecated gemma2-9b model in Fireworks AI Provider #9373
• feat: add timezone conversion for time tool by @hwzhuhao in feat: add timezone conversion for time tool #9393
• Fix/economical knowledge retrieval by @JohnJyong in Fix/economical knowledge retrieval #9396
• fix: incorrect webapp image displayed by @yuyinws in fix: incorrect webapp image displayed #9401
• refactor: update the default values of top-k parameter in vdb to be consistent by @hwzhuhao in refactor: update the default values of top-k parameter in vdb to be consistent #9367
• fix: resolve overlap issue with API Extension selector and modal by @DDDDD12138 in fix: resolve overlap issue with API Extension selector and modal #9407
• add clean 7 days datasets by @JohnJyong in add clean 7 days datasets #9424
• update dataset clean rule by @JohnJyong in update dataset clean rule #9426
• fix Bedrock cross region influence support response format #9409 by @ybalbert001 in fix https://github.com/langgenius/dify/issues/9409 #9433
• Update dify-sandbox version to 0.2.10 by @hexian2001 in Update dify-sandbox version to 0.2.10 #9439
• Fix: rerank switch and validation before run by @YIXIAO0 in Fix: rerank switch and validation before run #9416
• revert yarnlock by @zxhlyh in revert yarnlock #9445
• fix: enable Tencent Cloud Vector integration test by @yaoice in fix: enable Tencent Cloud Vector integration test #9441
• Fix/firefox overflow error by @WTW0313 in Fix/firefox overflow error #9438
• feat: add the workflow tool of comfyUI by @hjlarry in feat: add the workflow tool of comfyUI #9447
• fix: remove the undefined variable line by @hwzhuhao in fix: remove the undefined variable line #9446
• fix(workflow): Implement automatic variable addition from opening statement to start node by @Kevin9703 in fix(workflow): Implement automatic variable addition from opening statement to start node #9450
• refactor: move the embedding to the rag module and abstract the rerank runner for extension by @hwzhuhao in refactor: move the embedding to the rag module and abstract the rerank runner for extension #9423
• feat:add wenxin rerank by @chzphoenix in feat:add wenxin rerank #9431
• feat: add yi-lightning llm model for yi by @hwzhuhao in feat: add yi-lightning llm model for yi #9458
• fix: add missing vector type to migrate command by @yaoice in fix: add missing vector type to migrate command #9470
• fix: update mismatch vector type by @yaoice in fix: update mismatch vector type #9462
• feat: add parameter top-k for the llm model provided by openrouter and siliconflow by @hwzhuhao in feat: add parameter top-k for the llm model provided by openrouter and siliconflow #9455
• controller test by @s2oBCN in controller test #9469
• fix fetch apps by @horochx in fix fetch apps #9453
• fix: resolve the error with the db-pool-stat endpoint by @hwzhuhao in fix: resolve the error with the db-pool-stat endpoint #9478
• feat: add yi custom llm intergration by @hwzhuhao in feat: add yi custom llm intergration #9482
• Added Llama 3.2 Vision Models Speech2Text Models for Groq by @taowang1993 in Added Llama 3.2 Vision Models Speech2Text Models for Groq #9479
• add yuqye（https://www.yuque.com）tools by @lichengwu in add yuqye（https://www.yuque.com）tools #8960
• feat: Add volcengine tos storage test by @yaoice in feat: Add volcengine tos storage test #9495
• chore: update the description for storage_type by @userzhangqg in chore: update the description for storage_type #9492
• refine wording in license by @guchenhe in refine wording in license #9505
• fix: resolve the error of docker-compose startup when the storage is baidu-obs by @hwzhuhao in fix: resolve the error of docker-compose startup when the storage is baidu-obs #9502
• Resolve 9508 openai compatible rerank by @ziyu4huang in Resolve 9508 openai compatible rerank #9511
• feat: Add custom username and avatar define in discord tool by @yaoice in feat: Add custom username and avatar define in discord tool #9514
• fix: ignore all files except for .gitkeep under docker/nginx/ssl by gitignore by @kurokobo in fix: ignore all files except for .gitkeep under docker/nginx/ssl by gitignore #9518
• refactor wenxin rerank by @chzphoenix in refactor wenxin rerank #9486
• fix: draft run workflow node with image will raise error by @hjlarry in fix: draft run workflow node with image will raise error #9406
• New Auth Methods by @douxc in New Auth Methods #8119
• chore: translate i18n files by @github-actions in chore: translate i18n files #9523
• Feat/new login by @ZhouhaoJiang in Feat/new login #8120
• Feat/attachments by @zxhlyh in Feat/attachments #9526
• feat/enhance the multi-modal support by @laipz8200 in feat/enhance the multi-modal support #8818
• fix(dockerfile): update libsqlite3 package version by @laipz8200 in fix(dockerfile): update libsqlite3 package version #9530
• Fix: chatbot retrieval setting save issue by @YIXIAO0 in Fix: chatbot retrieval setting save issue #9536
• fix: RESET_PASSWORD_TOKEN_EXPIRY_HOURS error by @ZhouhaoJiang in fix: RESET_PASSWORD_TOKEN_EXPIRY_HOURS error #9542
• fix: list filter node url not work by @hjlarry in fix: list filter node url not work #9540
• fix: list filter node some operator raise error by @hjlarry in fix: list filter node some operator raise error #9539
• fix: input vars not auto rename in list operator by @iamjoel in fix: input vars not auto rename in list operator #9550
• feat(file-upload): add support for optional file source parameter by @laipz8200 in feat(file-upload): add support for optional file source parameter #9554
• fix: TOKEN_EXPIRY_MINUTES by @ZhouhaoJiang in fix: TOKEN_EXPIRY_MINUTES #9557
• fix: when upload file response 3** will raise error by @hjlarry in fix: when upload file response 3** will raise error #9555
• chore: translate i18n files by @github-actions in chore: translate i18n files #9528
• chore: update version to 0.10.0 in packaging and docker configurations by @laipz8200 in chore: update version to 0.10.0 in packaging and docker configurations #9534

New Contributors

• @wsbao made their first contribution in fix: In the output, the order of 'ta' is sometimes reversed as 'at'. #8015 #8791
• @yuyinws made their first contribution in fix: incorrect webapp image displayed #9401
• @hexian2001 made their first contribution in Update dify-sandbox version to 0.2.10 #9439
• @chzphoenix made their first contribution in feat:add wenxin rerank #9431
• @taowang1993 made their first contribution in Added Llama 3.2 Vision Models Speech2Text Models for Groq #9479
• @userzhangqg made their first contribution in chore: update the description for storage_type #9492

Full Changelog: 0.9.2...0.10.0

---

This discussion was created from the release v0.10.0.

[Smashhhhhhhhhh]

Although the 'Single File' is added to the input parameters of the workflow, why can't it be applied in the subsequent LLM? It's really a pity that there is no such function

[laipz8200]

We added a new Doc Extractor node to process document-typed files, other types will be supported later.

[Smashhhhhhhhhh]

We added a new Doc Extractor node to process document-typed files, other types will be supported later.我们添加了一个新的Doc Extractor节点来处理文档类型的文件，稍后将支持其他类型。

It would be very useful if you can add it as soon as possible, thanks

[Smashhhhhhhhhh]

We added a new Doc Extractor node to process document-typed files, other types will be supported later.

Multimodal LLM, all input parameters can be directly passed in url and mime/type, LLM will directly read and process them, I hope Dify can implement this function in 'LLM' Thank you

[jujuju102]

更新到0.10.0后，使用webapp图标替换应用界面的机器人图标功能失效了，更换webapp图标后，聊天界面机器人图标还是小机器人，之前版本是正常的。

[laipz8200]

Thanks for the report, we will fix this issue in the next version.

[jujuju102]

Thanks