Impact Score: 5/10
Dify: v0.10.2
Source available — automated, not human-reviewed
Component: dify · Channel: stable. Automated analysis, not a compatibility certification. How this works.
Analysis updated: 2026-11-01.
⚡ Executive Summary (TL;DR)
Dify 0.10.2. Source highlight: ✨ What’s New in v0.10.2? ✨
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)
- **Markdown Buttons in Workflows:** Sprinkle some buttons in your markdown for workflows to make them pop. Shout out to @crazywoola in #9876.
- **Document Extractor Node with JSON Support:** You can now manage JSON types with extractor nodes for more flexible data extraction. Thanks to @Theysua in #9899.
- **Text-to-Image with Stable-Diffusion 3.5:** Bring your text to life with the new Stable-Diffusion-3.5-large integration using siliconflow. Props to @hwzhuhao in #9909.
- **Vectorizer Support in Workflows:** The Vectorizer tool is now at your disposal within workflows for better data manipulation—kudos to @hjlarry in #9932.
- feat: regenerate history switch navigation
- feat:Add host volume env variables for postgres, redis and weaviate
⚡ Performance & Enhancements (2)
- refactor(file_factory): improve filename and mime type determination
- docs: improve api documentation for advanced chat and workflow
🔧 Bug Fixes & Patches (6)
- **API Documentation Upgrade:** We've polished our API documentation for advanced chat and workflow functionalities. Special thanks to @kurokobo in #9882.
- **LLM Node Streaming Output Fix:** Fixed the LLM Node streaming output to properly function after IF-ELSE decisions, ensuring your workflows are on track. Thanks to @laipz8200 in #9875.
- **Workflow Code Generator Update:** Cleared up the Generate button from incorrect locations for a more intuitive workflow setup. Update by @Kota-Yamaguchi in #9740.
- **Enhanced Prompt Handling in Workflows:** Added vision support in prompts for more dynamic configurations. Nicely done by @laipz8200 in #9790.
- **Improved File Handling in HTTP Requests:** Your HTTP requests within workflows are now more robust. Much appreciated, @laipz8200 in #9944.
- **⚠️ Fix for Tool Var Type Error:** If you're using a "Number" parameter in "Workflow as Tool," please remove and re-add this tool to avoid any issues. Thanks to @iamjoel in #9937.
📄 View Raw Release Notes (Original Developer Log)
## ✨ What’s New in v0.10.2? ✨
We're back with version 0.10.2, packed with new features, crucial fixes, and improvements that will make your workflow smoother and more efficient. Let's break down what's included:
### 🚀 New Features
- **Markdown Buttons in Workflows:** Sprinkle some buttons in your markdown for workflows to make them pop. Shout out to @crazywoola in #9876.
- **Document Extractor Node with JSON Support:** You can now manage JSON types with extractor nodes for more flexible data extraction. Thanks to @Theysua in #9899.
- **Text-to-Image with Stable-Diffusion 3.5:** Bring your text to life with the new Stable-Diffusion-3.5-large integration using siliconflow. Props to @hwzhuhao in #9909.
- **Vectorizer Support in Workflows:** The Vectorizer tool is now at your disposal within workflows for better data manipulation—kudos to @hjlarry in #9932.
### 🛠️ Enhancements and Fixes
- **API Documentation Upgrade:** We've polished our API documentation for advanced chat and workflow functionalities. Special thanks to @kurokobo in #9882.
- **LLM Node Streaming Output Fix:** Fixed the LLM Node streaming output to properly function after IF-ELSE decisions, ensuring your workflows are on track. Thanks to @laipz8200 in #9875.
- **Workflow Code Generator Update:** Cleared up the Generate button from incorrect locations for a more intuitive workflow setup. Update by @Kota-Yamaguchi in #9740.
- **Enhanced Prompt Handling in Workflows:** Added vision support in prompts for more dynamic configurations. Nicely done by @laipz8200 in #9790.
- **Improved File Handling in HTTP Requests:** Your HTTP requests within workflows are now more robust. Much appreciated, @laipz8200 in #9944.
- **⚠️ Fix for Tool Var Type Error:** If you're using a "Number" parameter in "Workflow as Tool," please remove and re-add this tool to avoid any issues. Thanks to @iamjoel in #9937.
- **Chat Log Display Fix:** We've resolved the display problems for chat logs, making sure everything shows up correctly. Big thanks to @xuzuodong in #9777.
- **Vision Support for Tool Image Gen:** Image generation with vision models is now supported within your workflows—credit to @hjlarry in #9871.
- **System Parameters Standardization:** Our system parameters have been standardized across the board. Cheers to @laipz8200 in #9797.
- **Image Previews in DOCX:** Fixed issues with previews in 'docx' knowledge bases. Thanks again to @laipz8200 in #9893.
This release is all about enhancing your workflow capabilities and providing robust tools and documentation to back them up. Keep the feedback coming and happy building! 🌟
---
## Upgrade Guide
### Docker compose deployments
1. Back up your customized docker-compose YAML file (optional)
```bash
cd docker
cp docker-compose.yaml docker-compose.yaml.$(date +%s).bak
```
2. Get the latest code from the main branch
```bash
git checkout main
git pull origin main
```
3. Stop the service,Command, please execute in the docker directory
```bash
docker compose down
```
4. Back up data
```bash
tar -cvf volumes-$(date +%s).tgz volumes
```
5. Upgrade services
```bash
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:
```bash
git checkout 0.10.2
```
3. Update Python dependencies:
```bash
cd api
poetry install
```
7. Then, let's run the migration script:
```bash
poetry run flask db upgrade
```
8. Finally, run API server, Worker and Web frontend Server again.
---
## What's Changed
* Update Code Generator to use the currently configured model. by @Kota-Yamaguchi in https://github.com/langgenius/dify/pull/9740
* fix(api): handle missing upload_file_id for tool_file messages by @laipz8200 in https://github.com/langgenius/dify/pull/9756
* feat: regenerate history switch navigation by @xuzuodong in https://github.com/langgenius/dify/pull/8749
* feat:Add host volume env variables for postgres, redis and weaviate by @jter in https://github.com/langgenius/dify/pull/9761
* fix: fe can not start by @iamjoel in https://github.com/langgenius/dify/pull/9768
* Update README_CN.md by @sunner in https://github.com/langgenius/dify/pull/9766
* fix: chat log not showing correctly by @xuzuodong in https://github.com/langgenius/dify/pull/9777
* refactor(file_factory): improve filename and mime type determination by @laipz8200 in https://github.com/langgenius/dify/pull/9784
* fix(workflow): enhance prompt handling with vision support by @laipz8200 in https://github.com/langgenius/dify/pull/9790
* remove unstructured pdf extract by @JohnJyong in https://github.com/langgenius/dify/pull/9794
* fix: chart tool can't display chinese by @hjlarry in https://github.com/langgenius/dify/pull/9686
* chore(docker): correct package version for expat and perl in Dockerfile by @laipz8200 in https://github.com/langgenius/dify/pull/9801
* openai compatiable api usage and id by @guogeer in https://github.com/langgenius/dify/pull/9800
* chore(docker): add default for MAX_VARIABLE_SIZE in docker-compose by @laipz8200 in https://github.com/langgenius/dify/pull/9798
* feat(parameters): standardize system parameter field types and values by @laipz8200 in https://github.com/langgenius/dify/pull/9797
* chore: abstract common function with local storage by @yaoice in https://github.com/langgenius/dify/pull/9811
* Added description for .ppt, specify the reason for unstructured.io by @Theysua in https://github.com/langgenius/dify/pull/9452
* chore: make doc extractor node also can extract text by file extension by @hjlarry in https://github.com/langgenius/dify/pull/9543
* Feat: use file size limit from api by @JzoNgKVO in https://github.com/langgenius/dify/pull/9739
* feat(api): add generic file size limit parameter by @laipz8200 in https://github.com/langgenius/dify/pull/9812
* refactor: update load_stream method to directly yield file chunks by @hwzhuhao in https://github.com/langgenius/dify/pull/9806
* fix: duckduckgo image search not work by @hjlarry in https://github.com/langgenius/dify/pull/9821
* feat: create_empty_dataset api add the description parameter and update api docs by @rchlz in https://github.com/langgenius/dify/pull/9824
* fix: yuque book id should be string by @crazywoola in https://github.com/langgenius/dify/pull/9819
* chore: add local storage test by @yaoice in https://github.com/langgenius/dify/pull/9827
* add tidb on qdrant type by @JohnJyong in https://github.com/langgenius/dify/pull/9831
* fix: exclude failed answer when sending messages by @xuzuodong in https://github.com/langgenius/dify/pull/9835
* fix: moonshot response_format raise error by @hjlarry in https://github.com/langgenius/dify/pull/9847
* chore: code generator button should only display in code node by @hjlarry in https://github.com/langgenius/dify/pull/9842
* Fix: add check for maximum chunk length by @JzoNgKVO in https://github.com/langgenius/dify/pull/9837
* chore: update api docs by @JzoNgKVO in https://github.com/langgenius/dify/pull/9832
* chore: translate i18n files by @github-actions in https://github.com/langgenius/dify/pull/9853
* Marking the last piece of data on each page is a duplicate issue, which can be solved by adding the id field to the order by rig and using a unique field by @yuanboao in https://github.com/langgenius/dify/pull/9799
* feat: allow answer node use chat_var and env_var by @hjlarry in https://github.com/langgenius/dify/pull/9226
* fix: segement settings of documents raise error by @hjlarry in https://github.com/langgenius/dify/pull/8971
* upgrade nltk, unstructured and starlette by @JohnJyong in https://github.com/langgenius/dify/pull/9860
* chore: add default value for redis configuration by @hwzhuhao in https://github.com/langgenius/dify/pull/9864
* feat: support comfyui workflow tool image generate image by @hjlarry in https://github.com/langgenius/dify/pull/9871
* feat: support button in markdown by @crazywoola in https://github.com/langgenius/dify/pull/9876
* fix: wrong element object by @virgosoy in https://github.com/langgenius/dify/pull/9868
* fix(workflow): Take back LLM streaming output after IF-ELSE by @laipz8200 in https://github.com/langgenius/dify/pull/9875
* fix users had already joined a workspace, but the system still first … by @G81192 in https://github.com/langgenius/dify/pull/9834
* docs: improve api documentation for advanced chat and workflow by @kurokobo in https://github.com/langgenius/dify/pull/9882
* Update README.md by @leilei-jiang in https://github.com/langgenius/dify/pull/9886
* Update README.md by @leilei-jiang in https://github.com/langgenius/dify/pull/9889
* Update README.md by @leilei-jiang in https://github.com/langgenius/dify/pull/9890
* Update README.md by @leilei-jiang in https://github.com/langgenius/dify/pull/9891
* fix(api): add signature generation for image previews by @laipz8200 in https://github.com/langgenius/dify/pull/9893
* feat(workflow): Support JSON type in document extractor node by @Theysua in https://github.com/langgenius/dify/pull/9899
* chore: Extract common functions of the base model in Azure OpenAI Provider by @yaoice in https://github.com/langgenius/dify/pull/9907
* fix(tools): remove the undefined variable parameter_type by @hwzhuhao in https://github.com/langgenius/dify/pull/9908
* feat: add stable-diffusion-3-5-large for the text-to-image tool with siliconflow by @hwzhuhao in https://github.com/langgenius/dify/pull/9909
* fix: enterprise create workspace by @ZhouhaoJiang in https://github.com/langgenius/dify/pull/9921
* add document lock for multi-thread by @JohnJyong in https://github.com/langgenius/dify/pull/9873
* Remove invalid languages error by @seikyo-cho-lvgs in https://github.com/langgenius/dify/pull/9928
* fix: tool var type error by @iamjoel in https://github.com/langgenius/dify/pull/9937
* Modify and add jp translation by @HanqingZ in https://github.com/langgenius/dify/pull/9930
* feat: add models for gitee.ai by @fchange in https://github.com/langgenius/dify/pull/9490
* feat: support Vectorizer can be used in workflow by @hjlarry in https://github.com/langgenius/dify/pull/9932
* feat(tools): add Baidu translation tool by @XiaoLey in https://github.com/langgenius/dify/pull/9943
* feat(http-request-executor): enhance file handling in HTTP requests by @laipz8200 in https://github.com/langgenius/dify/pull/9944
* fix: separator change add too many backslash by @iamjoel in https://github.com/langgenius/dify/pull/9949
* Docs: fix docs url by @AllenWriter in https://github.com/langgenius/dify/pull/9954
* Fix/external api update by @JohnJyong in https://github.com/langgenius/dify/pull/9955
* chore: update version to 0.10.2 in packaging and docker configurations by @laipz8200 in https://github.com/langgenius/dify/pull/9924
## New Contributors
* @jter made their first contribution in https://github.com/langgenius/dify/pull/9761
* @sunner made their first contribution in https://github.com/langgenius/dify/pull/9766
* @rchlz made their first contribution in https://github.com/langgenius/dify/pull/9824
* @yuanboao made their first contribution in https://github.com/langgenius/dify/pull/9799
* @virgosoy made their first contribution in https://github.com/langgenius/dify/pull/9868
* @G81192 made their first contribution in https://github.com/langgenius/dify/pull/9834
* @seikyo-cho-lvgs made their first contribution in https://github.com/langgenius/dify/pull/9928
**Full Changelog**: https://github.com/langgenius/dify/compare/0.10.1...0.10.2