Dify 0.6.7stable Released May 09, 2024
Impact Score: 5/10

Dify: v0.6.7

Source available — automated, not human-reviewed

Component: dify · Channel: stable. Automated analysis, not a compatibility certification. How this works.

Analysis updated: 2026-11-01.

Compatibility not verified — check source notes
📄 .MD
⚡ Executive Summary (TL;DR)

Dify 0.6.7. Source highlight: ✨ What’s New in v0.6.7? ✨

Who Does This Impact? (Role-Based Analysis)

💻 Software Engineers & Devs

Check the source notes against the package and APIs you use before upgrading.

📊 Product & Engineering Leads

Use the documented changes to assess relevance to your product; release frequency alone is not a quality measure.

⚙️ DevOps & Security

Verify the target version, runtime requirements and rollback procedure in the official documentation.

✨ New Features & Capabilities (6)

  • Integrate `DeepSeek` Models by both @joshua20231026 and @soulteary in #4157 and #4162
  • Integrate `LeptonAI` Models by @joshua20231026 in #4079
  • New model support from `Azure OpenAI` for the `GPT-4-turbo-2024-04-09` model by @charli117 in #4144
  • Integrate `Volcengine MaaS` model provider by @sinomoe in #4142
  • Update to `bedrock.yaml` adds the Asia Pacific (Sydney) region by @chenx5 in #4016
  • `LocalAI` speech-to-text support by @Tomywang999 in #3921.

⚡ Performance & Enhancements (6)

  • Integration of OpenAI usage in streaming response by @Yeuoly in #4140
  • New HTTP node settings allow for increased maximum size environments by @Yeuoly in #4137
  • Improved Japanese translations make our platform more accessible to Japanese speakers by @Fyphen1223 in #4119.
  • Support for time formats in code sandbox by @Yeuoly in #4138
  • Update to `model_provider jina` to support custom URLs and models by @VoidIsVoid in #4110
  • Improved testing of the CodeExecutor with code templates and extracted CodeLanguage enum for better development practices by @bowenliang123 in #4098

🔧 Bug Fixes & Patches (6)

  • Fixed the HTTP node timeout and URL checks in workflows to ensure smoother operations and reliability by @zxhlyh in #4175.
  • fix: workflow avg user interaction.
  • fix: unable to fetch CoT agent runner log
  • fix typo: writeOpner -> writeOpener
  • fix: agent log timezone
  • fix: transform None into correct dest type
📄 View Raw Release Notes (Original Developer Log)
## ✨ What’s New in v0.6.7? ✨ The latest update, v0.6.7, continues to refine and expand our features with an emphasis on integrations and accessibility. Key updates include: ### 🚀 New Features - Integrate `DeepSeek` Models by both @joshua20231026 and @soulteary in #4157 and #4162 - Integrate `LeptonAI` Models by @joshua20231026 in #4079 - New model support from `Azure OpenAI` for the `GPT-4-turbo-2024-04-09` model by @charli117 in #4144 - Integrate `Volcengine MaaS` model provider by @sinomoe in #4142 - Update to `bedrock.yaml` adds the Asia Pacific (Sydney) region by @chenx5 in #4016 - `LocalAI` speech-to-text support by @Tomywang999 in #3921. - Added support for vision models from xinference by @Minamiyama in #4094. - A new built-in tool for Slack Incoming Webhook by @ericyangpan in #4067 - Support for Aliyun OSS authentication V4 by @S96EA in #3886 - Added support for Polish (pl-PL) by @patryk20120 in #4128 ### ⚙️ Enhancements - Integration of OpenAI usage in streaming response by @Yeuoly in #4140 - New HTTP node settings allow for increased maximum size environments by @Yeuoly in #4137 - Improved Japanese translations make our platform more accessible to Japanese speakers by @Fyphen1223 in #4119. - Support for time formats in code sandbox by @Yeuoly in #4138 - Update to `model_provider jina` to support custom URLs and models by @VoidIsVoid in #4110 - Added BaseURL configuration for the Cohere model by @huangbaichao in #4152 - Improved testing of the CodeExecutor with code templates and extracted CodeLanguage enum for better development practices by @bowenliang123 in #4098 ### 🛠️ Bug Fixes - Fixed the HTTP node timeout and URL checks in workflows to ensure smoother operations and reliability by @zxhlyh in #4175. For additional enhancements and updates, refer to the What's Changed section below. ## Update Guide ### Docker compose deployments: 1. Get the latest code from the main branch: ```Shell git checkout main git pull origin main ``` 2. Go to the next step and update to the latest image: ```Shell cd docker 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: ```Shell git checkout main git pull origin main ``` 3. Update Python dependencies: ```Shell cd api pip install -r requirements.txt ``` 4. Then, let's run the migration script: ```Shell flask db upgrade ``` 5. Finally, run API server, Worker and Web frontend Server again. ## What's Changed * fix: workflow avg user interaction. by @GarfieldDai in https://github.com/langgenius/dify/pull/4056 * fix: unable to fetch CoT agent runner log by @sinomoe in https://github.com/langgenius/dify/pull/4052 * test: add integration tests on CodeExecutor with the sandbox service by @bowenliang123 in https://github.com/langgenius/dify/pull/4015 * fix typo: writeOpner -> writeOpener by @shoheiweb86 in https://github.com/langgenius/dify/pull/4060 * Feat: frontend support timezone of timestamp by @JzoNgKVO in https://github.com/langgenius/dify/pull/4070 * fix: agent log timezone by @Yeuoly in https://github.com/langgenius/dify/pull/4076 * feat: add a new built-in tool of Slack Incoming Webhook by @ericyangpan in https://github.com/langgenius/dify/pull/4067 * fix: transform None into correct dest type by @Yeuoly in https://github.com/langgenius/dify/pull/4077 * Revert "fix: hydration warning (#3897)" by @TinsFox in https://github.com/langgenius/dify/pull/4059 * Update bedrock.yaml add Region Asia Pacific (Sydney) by @chenx5 in https://github.com/langgenius/dify/pull/4016 * Leptonai integrate by @joshua20231026 in https://github.com/langgenius/dify/pull/4079 * Urgent Correction: Resolving Critical License Documentation Error in Dify's Japanese README by @LinkX-shomasakamoto in https://github.com/langgenius/dify/pull/4075 * improve: menu collapse readability by @JunIce in https://github.com/langgenius/dify/pull/4099 * fix: correct the license link by @buddypia in https://github.com/langgenius/dify/pull/4093 * fix: typo in get-automatic-res.tsx by @eltociear in https://github.com/langgenius/dify/pull/4097 * 🦄 refactor(dataset svc): delete check none by @baxiang in https://github.com/langgenius/dify/pull/4101 * feat: support aliyun oss auth v4 by @S96EA in https://github.com/langgenius/dify/pull/3886 * fix: prevent http node overwrite on open by @perzeuss in https://github.com/langgenius/dify/pull/4127 * feat: add http node max size env by @Yeuoly in https://github.com/langgenius/dify/pull/4137 * Improved Japanese translation by @Fyphen1223 in https://github.com/langgenius/dify/pull/4119 * improve: test CodeExecutor with code templates and extract CodeLanguage enum by @bowenliang123 in https://github.com/langgenius/dify/pull/4098 * feat: support time format by @Yeuoly in https://github.com/langgenius/dify/pull/4138 * feat: support openai stream usage by @Yeuoly in https://github.com/langgenius/dify/pull/4140 * bug fix: update minimax model_apis by @Weaxs in https://github.com/langgenius/dify/pull/4116 * feat(Languages): :alien: add pl-PL language by @patryk20120 in https://github.com/langgenius/dify/pull/4128 * azure_openai add gpt-4-turbo-2024-04-09 model by @charli117 in https://github.com/langgenius/dify/pull/4144 * fix: passing in 0 as a numeric variable will be converted to null by @takatost in https://github.com/langgenius/dify/pull/4148 * question classifier optimize by @JohnJyong in https://github.com/langgenius/dify/pull/4147 * fix: http authorization leakage by @Yeuoly in https://github.com/langgenius/dify/pull/4146 * Add support for local ai speech to text by @Tomywang999 in https://github.com/langgenius/dify/pull/3921 * feat: support vision models from xinference by @Minamiyama in https://github.com/langgenius/dify/pull/4094 * feat: update model_provider jina to support custom url and model by @VoidIsVoid in https://github.com/langgenius/dify/pull/4110 * fix dataset segment update api not effect issue by @JohnJyong in https://github.com/langgenius/dify/pull/4151 * feat: add proxy configuration for Cohere model by @huangbaichao in https://github.com/langgenius/dify/pull/4152 * fix: stop event propagation when deleting selected workflow var node by @lawvs in https://github.com/langgenius/dify/pull/4158 * Add-Deepseek by @joshua20231026 in https://github.com/langgenius/dify/pull/4157 * feat: DeepSeek by @soulteary in https://github.com/langgenius/dify/pull/4162 * Fix:typo Incorrect Japanese 2 by @sasaharukimedes in https://github.com/langgenius/dify/pull/4167 * Typo on deepseek.yaml and yi.yaml by @Yongtae723 in https://github.com/langgenius/dify/pull/4170 * feat: add volcengine maas model provider by @sinomoe in https://github.com/langgenius/dify/pull/4142 * fix: workflow http node timeout & url check by @zxhlyh in https://github.com/langgenius/dify/pull/4175 * fix: button widths by @tomoyuki28jp in https://github.com/langgenius/dify/pull/4145 * fix delete log annotation by @cainiaokan in https://github.com/langgenius/dify/pull/4201 * modify spelling errors: bulild -> build by @faukwaa in https://github.com/langgenius/dify/pull/4206 * version to 0.6.7 by @takatost in https://github.com/langgenius/dify/pull/4208 ## New Contributors * @shoheiweb86 made their first contribution in https://github.com/langgenius/dify/pull/4060 * @ericyangpan made their first contribution in https://github.com/langgenius/dify/pull/4067 * @chenx5 made their first contribution in https://github.com/langgenius/dify/pull/4016 * @LinkX-shomasakamoto made their first contribution in https://github.com/langgenius/dify/pull/4075 * @buddypia made their first contribution in https://github.com/langgenius/dify/pull/4093 * @S96EA made their first contribution in https://github.com/langgenius/dify/pull/3886 * @Fyphen1223 made their first contribution in https://github.com/langgenius/dify/pull/4119 * @Tomywang999 made their first contribution in https://github.com/langgenius/dify/pull/3921 * @Minamiyama made their first contribution in https://github.com/langgenius/dify/pull/4094 * @lawvs made their first contribution in https://github.com/langgenius/dify/pull/4158 * @sasaharukimedes made their first contribution in https://github.com/langgenius/dify/pull/4167 * @Yongtae723 made their first contribution in https://github.com/langgenius/dify/pull/4170 * @tomoyuki28jp made their first contribution in https://github.com/langgenius/dify/pull/4145 * @cainiaokan made their first contribution in https://github.com/langgenius/dify/pull/4201 * @faukwaa made their first contribution in https://github.com/langgenius/dify/pull/4206 **Full Changelog**: https://github.com/langgenius/dify/compare/0.6.6...0.6.7