Dify: v0.4.0

**🎉🎉 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 https://github.com/langgenius/dify/pull/1793 * fix typo by @kztao in https://github.com/langgenius/dify/pull/1791 * Compatible with the situation where there is no user information. by @JohnJyong in https://github.com/langgenius/dify/pull/1792 * ppt & pptx improve by @JohnJyong in https://github.com/langgenius/dify/pull/1790 * Fix: delete member dropdown not shown by @crazywoola in https://github.com/langgenius/dify/pull/1794 * fix: settings/members dropdown ui by @crazywoola in https://github.com/langgenius/dify/pull/1797 * fix gpt 4v upload image issue by @JohnJyong in https://github.com/langgenius/dify/pull/1799 * feat: add billing switch. by @GarfieldDai in https://github.com/langgenius/dify/pull/1789 * Update README.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1802 * Update README.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1803 * Update README_ES.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1807 * Update README_JA.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1805 * Update README_CN.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1806 * Update README_CN.md by @joshua20231026 in https://github.com/langgenius/dify/pull/1804 * feat: add email template for invite new user in workspace by @crazywoola in https://github.com/langgenius/dify/pull/1810 * Fix azure openai gpt4v&1106 config by @charli117 in https://github.com/langgenius/dify/pull/1811 * fix: mail link color by @crazywoola in https://github.com/langgenius/dify/pull/1812 * Parse base64 eml file by @charli117 in https://github.com/langgenius/dify/pull/1796 * add link to canny to README, plus some rewording by @guchenhe in https://github.com/langgenius/dify/pull/1814 * feat: add roadmap and feedback link by @iamjoel in https://github.com/langgenius/dify/pull/1816 * fix unstructured requirements by @JohnJyong in https://github.com/langgenius/dify/pull/1821 * Fix Azure OpenAI Provider BASE_MODELS by @zhangao0086 in https://github.com/langgenius/dify/pull/1813 * fix: edited by is missing by @crazywoola in https://github.com/langgenius/dify/pull/1824 * Update README.md by @crazywoola in https://github.com/langgenius/dify/pull/1825 * fix: selection too long break ui by @iamjoel in https://github.com/langgenius/dify/pull/1826 * Fix chitchat lost context by @charli117 in https://github.com/langgenius/dify/pull/1828 * feat: nginx add "restart: always" by @takatost in https://github.com/langgenius/dify/pull/1829 * feat: comment db port to host by @takatost in https://github.com/langgenius/dify/pull/1831 * fix file type not support when preview by @JohnJyong in https://github.com/langgenius/dify/pull/1841 * fix segment update issue by @JohnJyong in https://github.com/langgenius/dify/pull/1844 * fix: splitting text ui broken by @iamjoel in https://github.com/langgenius/dify/pull/1848 * Feat/add community link to dropdown by @crazywoola in https://github.com/langgenius/dify/pull/1851 * ci: Bump Docker Github actions by @bowenliang123 in https://github.com/langgenius/dify/pull/1852 * Refactor BaseVectorIndex delete method by @waltcow in https://github.com/langgenius/dify/pull/1853 * Add data clean schedule by @JohnJyong in https://github.com/langgenius/dify/pull/1859 * fix file estimate issue by @JohnJyong in https://github.com/langgenius/dify/pull/1860 * Model Runtime by @takatost in https://github.com/langgenius/dify/pull/1858 * frontend for model runtime by @zxhlyh in https://github.com/langgenius/dify/pull/1861 ## New Contributors * @joshua20231026 made their first contribution in https://github.com/langgenius/dify/pull/1802 * @zhangao0086 made their first contribution in https://github.com/langgenius/dify/pull/1813 * @bowenliang123 made their first contribution in https://github.com/langgenius/dify/pull/1852 **Full Changelog**: https://github.com/langgenius/dify/compare/0.3.34...0.4.0