langgenius/dify 0.4.0

v0.4.0

on GitHub

🎉🎉 Dify's Version 0.4 is out now.

We've made some serious under-the-hood changes to how the Model Runtime works, making it more straightforward for our specific needs, and paving the way for smoother model expansions and more robust production use.

What's Changed

• Model Runtime Rework: We've moved away from LangChain, simplifying the model layer. Now, expanding models is as easy as setting up the model provider in the backend with a bit of YAML.

  For more details, see: https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md

• App Generation Update: Replacing the old Redis Pubsub queue with threading.Queue for a more reliable, performant, and straightforward workflow.

• Model Providers Upgraded: Support for both preset and custom models, ideal for adding OpenAI fine-tuned models or fitting into various MaaS platforms. Plus, you can now check out supported models without any initial configuration.

• Context Size Definition: Introduced distinct context size settings, separate from Max Tokens, to handle the different limits and sizes in models like OpenAI's GPT-4 Turbo.

• Flexible Model Parameters: Customize your model's behavior with easily adjustable parameters through YAML.

• GPT-2 Tokenizer Files: Now cached within Dify's codebase, making builds quicker and solving issues related to acquiring tokenizer files in offline source deployments.

• Model List Display: The App now displays all supported preset models, including details on any that aren't available and how to configure them.

• New Model Additions: Including Google's Gemini Pro and Gemini Pro Vision models (Vision requires an image input), Azure OpenAI's GPT-4V, and support for OpenAI-API-compatible providers.

• Expanded Inference Support: Xorbit Inference now includes chat mode models, and there's a wider range of models supporting Agent inference.

• Updates & Fixes: We've updated other model providers to be in sync with the latest version APIs and features, and squashed a series of minor bugs for a smoother experience.

Catch you in the code,

The Dify Team 🛠️

Change Log

• fix: not return annotation author error happens by @iamjoel in #1793
• fix typo by @kztao in #1791
• Compatible with the situation where there is no user information. by @JohnJyong in #1792
• ppt & pptx improve by @JohnJyong in #1790
• Fix: delete member dropdown not shown by @crazywoola in #1794
• fix: settings/members dropdown ui by @crazywoola in #1797
• fix gpt 4v upload image issue by @JohnJyong in #1799
• feat: add billing switch. by @GarfieldDai in #1789
• Update README.md by @joshua20231026 in #1802
• Update README.md by @joshua20231026 in #1803
• Update README_ES.md by @joshua20231026 in #1807
• Update README_JA.md by @joshua20231026 in #1805
• Update README_CN.md by @joshua20231026 in #1806
• Update README_CN.md by @joshua20231026 in #1804
• feat: add email template for invite new user in workspace by @crazywoola in #1810
• Fix azure openai gpt4v&1106 config by @charli117 in #1811
• fix: mail link color by @crazywoola in #1812
• Parse base64 eml file by @charli117 in #1796
• add link to canny to README, plus some rewording by @guchenhe in #1814
• feat: add roadmap and feedback link by @iamjoel in #1816
• fix unstructured requirements by @JohnJyong in #1821
• Fix Azure OpenAI Provider BASE_MODELS by @zhangao0086 in #1813
• fix: edited by is missing by @crazywoola in #1824
• Update README.md by @crazywoola in #1825
• fix: selection too long break ui by @iamjoel in #1826
• Fix chitchat lost context by @charli117 in #1828
• feat: nginx add "restart: always" by @takatost in #1829
• feat: comment db port to host by @takatost in #1831
• fix file type not support when preview by @JohnJyong in #1841
• fix segment update issue by @JohnJyong in #1844
• fix: splitting text ui broken by @iamjoel in #1848
• Feat/add community link to dropdown by @crazywoola in #1851
• ci: Bump Docker Github actions by @bowenliang123 in #1852
• Refactor BaseVectorIndex delete method by @waltcow in #1853
• Add data clean schedule by @JohnJyong in #1859
• fix file estimate issue by @JohnJyong in #1860
• Model Runtime by @takatost in #1858
• frontend for model runtime by @zxhlyh in #1861

New Contributors

• @joshua20231026 made their first contribution in #1802
• @zhangao0086 made their first contribution in #1813
• @bowenliang123 made their first contribution in #1852

Full Changelog: 0.3.34...0.4.0