v0.10.0

Important

If you have a Basic Chatbot or Text Generator App with the ‘Vision’ feature enabled, it will be necessary to republish the application following this update.

🎉 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 #8119 and @ZhouhaoJiang in #8120.

🚀 Additional Features

• Dataset Recall Testing API: Gain insights into data retrieval efficiency with this new API, brought to you by @gubinjie in #9300.
• Fireworks Model Integration: Access Qwen2.5 72B Instruct models for expanded AI capability, thanks to @yaoice in #9333 and #9340.

🛠️ Enhancements

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

🔧 Fixes

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

New Contributors

• @wsbao made their first contribution in #8791
• @yuyinws made their first contribution in #9401
• @hexian2001 made their first contribution in #9439
• @chzphoenix made their first contribution in #9431
• @taowang1993 made their first contribution in #9479
• @userzhangqg made their first contribution in #9492

Full Changelog: 0.9.2...0.10.0