0.15.3

✨ What’s New in v0.15.3? ✨

Hey folks, it's time for another update, and we've got some exciting additions and improvements rolling out with version v0.15.3. Let’s dive into the highlights:

🚀 New Model Support

• DeepSeek Models: DeepSeek R1 is now supported across several platforms, including SiliconFlow, Azure AI Foundry, Ollama, Volcengine, OpenRouter, Nvidia Catalog, and more. This opens up new possibilities for leveraging AI reasoning and insights across diverse environments.

• Gemini 2.0 Series: Introducing the latest models in the Gemini 2.0 series, such as Gemini 2.0 Flash 001 and Gemini 2.0 Pro Exp. These models deliver exceptional performance and efficiency, perfect for high-precision, fast-processing tasks.

⚙️ Enhancements

• Firecrawl Upgrade: Updated to the v1 API by @ftonato, providing improved performance and more refined results.

• GLM-4-AIR-0111 Support: Dive into advanced natural language processing tasks more effectively with this addition by @Jhvcc.

• Agent Thinking Content Display: Visualize agent thinking paths with DeepSeek’s R1 model, providing better understanding and debugging capabilities, courtesy of @hjlarry.

🛠️ Bug Fixes

• SSRF Proxy File Descriptor Leak Fix: Eliminated file descriptor leaks to enhance performance in concurrent environments, thanks to @ZuzooVn.

• Page Crash on String Variable Property Access: Resolved issues where improper string handling could cause unintentional crashes, fixed by @iamjoel.

Keep exploring and integrating these new capabilities into your workflows. As always, happy building, and we look forward to hearing how you leverage these updates in your projects! 🔍🚀

---

Upgrade Guide

Docker compose deployments

[!WARNING]

The files in the docker-legacy directory will soon stop being maintained and will be removed from the repository. If you are still using them, please switch to the new version as soon as possible.

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 0.15.3
   

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: add pg vector index by @huangzhuo1949 in https://github.com/langgenius/dify/pull/12338
• feat: add giteeAI risk control identification. by @jiandanfeng in https://github.com/langgenius/dify/pull/12946
• fix: tools translate search by @Jhvcc in https://github.com/langgenius/dify/pull/12950
• fix: get property of string type variable caused page crash by @iamjoel in https://github.com/langgenius/dify/pull/12969
• refactor: Update Firecrawl to use v1 API by @ftonato in https://github.com/langgenius/dify/pull/12574
• Feat/prompt editor dark theme by @zxhlyh in https://github.com/langgenius/dify/pull/12976
• feat: add glm-4-air-0111 by @Jhvcc in https://github.com/langgenius/dify/pull/12997
• fix: wrong zh_Hans translation: Ohio by @iwaim in https://github.com/langgenius/dify/pull/13006
• Change typo in translation by @y10ab1 in https://github.com/langgenius/dify/pull/13004
• chore: add Japanese translation: model_providers/bedrock by @iwaim in https://github.com/langgenius/dify/pull/13016
• feat: add agent thinking content display of deepseek R1 by @hjlarry in https://github.com/langgenius/dify/pull/12949
• support bedrock kb: retrieve and generate by @warren830 in https://github.com/langgenius/dify/pull/13027
• fix: Unexpected tag creation when pressing enter during tag conversion by @miya in https://github.com/langgenius/dify/pull/13041
• Update Novita AI predefined models by @jasonhp in https://github.com/langgenius/dify/pull/13045
• fix: adjust iteration node dark style by @douxc in https://github.com/langgenius/dify/pull/13051
• feat: add inner API to create workspace without requiring email by @zhangx1n in https://github.com/langgenius/dify/pull/13021
• fix:Improve MIME type detection for remote URL uploads using python-magic by @yjc980121 in https://github.com/langgenius/dify/pull/12693
• fix: "Model schema not found" error only in agents (#12655) by @jiandanfeng in https://github.com/langgenius/dify/pull/12760
• fix qwen-vl blocking mode by @hieheihei in https://github.com/langgenius/dify/pull/13052
• Set default LOG_LEVEL to INFO for celery workers and beat by @osaimi in https://github.com/langgenius/dify/pull/13066
• Fixed Novita AI color and added DeepSeek R1 model by @jasonhp in https://github.com/langgenius/dify/pull/13074
• fix: fix the formatter is not applied on log file by @acelyc111 in https://github.com/langgenius/dify/pull/12704
• refactor: reduce duplciate code by inheritance by @acelyc111 in https://github.com/langgenius/dify/pull/13073
• refactor: Update Firecrawl API parameters and default settings by @ftonato in https://github.com/langgenius/dify/pull/13082
• add tongyi qwen2.5-14b/7b-instruct-1m model by @hieheihei in https://github.com/langgenius/dify/pull/13089
• refactor: avoid to use extra space when finding model by name by @acelyc111 in https://github.com/langgenius/dify/pull/13043
• feat: switch to chat messages before regenerated by @xuzuodong in https://github.com/langgenius/dify/pull/11301
• fix: deduct LLM quota after processing invoke result by @laipz8200 in https://github.com/langgenius/dify/pull/13075
• test(huggingface_hub): Skip the failed test temporarily. by @laipz8200 in https://github.com/langgenius/dify/pull/13142
• chore: fix wrong VectorType match case by @tmokmss in https://github.com/langgenius/dify/pull/13123
• feature. add feat to modify metadata via dataset api by @aplio in https://github.com/langgenius/dify/pull/13116
• pass model and cost so that langfuse can show cost by @obadakhalili in https://github.com/langgenius/dify/pull/13117
• feat: the think tag display of siliconflow's deepseek r1 by @hjlarry in https://github.com/langgenius/dify/pull/13153
• chore: upgrade libldap2 by @ZuzooVn in https://github.com/langgenius/dify/pull/13158
• nitpick: fix small typos in template.en.mdx by @aplio in https://github.com/langgenius/dify/pull/13156
• add azure openai api version 2024-12-01-preview by @kei-yamazaki in https://github.com/langgenius/dify/pull/13135
• fix: not install libmagic raise error by @hjlarry in https://github.com/langgenius/dify/pull/13146
• fix: set indexing technique from dataset during update-by-text by @aplio in https://github.com/langgenius/dify/pull/13155
• Solve circular dependency issue between workflow/constants.ts file and default.ts file by @obadakhalili in https://github.com/langgenius/dify/pull/13165
• chore(pyproject): Add type stubs into pyproject.toml by @laipz8200 in https://github.com/langgenius/dify/pull/13145
• Install apt dependencies using bookworm source, consistent with base image. Remove unnecessary, error-prone pins by @deephbz in https://github.com/langgenius/dify/pull/13176
• fix: Dollar Sign Handling in Markdown by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13178
• chore: add tests for build docker image when dockerfile changed by @bowenliang123 in https://github.com/langgenius/dify/pull/10732
• Modify params for bedrock retrieve generate by @warren830 in https://github.com/langgenius/dify/pull/13182
• feat: bedrock_endpoint_url by @2284730142 in https://github.com/langgenius/dify/pull/12838
• Feat: add linkedin to readme by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13203
• fix: SSRF proxy file descriptor leak in concurrent requests by @ZuzooVn in https://github.com/langgenius/dify/pull/13108
• Use DefaultAzureCredential for managed identity in azure blob extention by @te-chan2 in https://github.com/langgenius/dify/pull/11559
• fix: mypy checks violation in AzureBlobStorage by @bowenliang123 in https://github.com/langgenius/dify/pull/13215
• chore(model_runtime): Move deepseek ahead in the providers list. by @laipz8200 in https://github.com/langgenius/dify/pull/13197
• Fix new variables in the conversation opener would override prompt_variables by @HQidea in https://github.com/langgenius/dify/pull/13191
• chore: squash system dependencies installation steps by @bowenliang123 in https://github.com/langgenius/dify/pull/13206
• feat: Add o3-mini and o3-mini-2025-01-31 model variants by @Joshbly in https://github.com/langgenius/dify/pull/13129
• feat(model_providers): Add Groq DeepSeek-R1-Distill-Llama-70b by @laipz8200 in https://github.com/langgenius/dify/pull/13229
• feat: added deepseek r1 and v3 to siliconflow by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13238
• fix: updated _position.yaml to include the latest model already integ… by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13245
• feat: add think display for volcengine and generic openapi by @xhebox in https://github.com/langgenius/dify/pull/13234
• feat: add parameter "reasoning_effort" and Openai o3-mini by @k-zaku in https://github.com/langgenius/dify/pull/13243
• feat: added models :gemini 2.0 flash 001 and gemini 2.0 pro exp 02-05 by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13247
• feat(model): add gemini-2.0-flash-thinking-exp-01-21 by @wangiii in https://github.com/langgenius/dify/pull/13230
• fix: correct linewrap think display in generic openai api by @xhebox in https://github.com/langgenius/dify/pull/13260
• feat(model): add gemini-2.0 model by @wangiii in https://github.com/langgenius/dify/pull/13266
• feat(model_providers): Support deepseek for Azure AI Foundry by @laipz8200 in https://github.com/langgenius/dify/pull/13267
• Fix bug large data no render by @weiwenyan-dev in https://github.com/langgenius/dify/pull/12683
• feat(model_providers): Support deepseek-r1 for Nvidia Catalog by @laipz8200 in https://github.com/langgenius/dify/pull/13269
• Upgrade oracle models by @engchina in https://github.com/langgenius/dify/pull/13174
• chore(deps): bump katex from 0.16.10 to 0.16.21 in /web by @dependabot in https://github.com/langgenius/dify/pull/13270
• fix: add dataset edit permissions by @WTW0313 in https://github.com/langgenius/dify/pull/13223
• feat:add deepseek r1 think display for ollama provider by @leslie2046 in https://github.com/langgenius/dify/pull/13272
• feat: add deepseek models for volcengine provider by @xhdd123321 in https://github.com/langgenius/dify/pull/13283
• fix: incorrect transferMethod assignment for remote file by @le0zh in https://github.com/langgenius/dify/pull/13286
• feat:add think tag display for xinference deepseek r1 by @leslie2046 in https://github.com/langgenius/dify/pull/13291
• feat: added a couple of models not defined in vertex ai, that were already … by @Riddhimaan-Senapati in https://github.com/langgenius/dify/pull/13296
• Update README_TR.md by @kemalmeler in https://github.com/langgenius/dify/pull/13294
• feat(credits): Allow to configure model-credit mapping by @laipz8200 in https://github.com/langgenius/dify/pull/13274
• feat(model): add deepseek-r1 for openrouter by @sinomoe in https://github.com/langgenius/dify/pull/13312
• fix(credits): require model name equals by @laipz8200 in https://github.com/langgenius/dify/pull/13314
• chore: refactor the OpenAICompatible and improve thinking display by @hjlarry in https://github.com/langgenius/dify/pull/13299
• Fix the problem of Workflow terminates after parallel tasks execution, merge node not triggered by @lazyFrogLOL in https://github.com/langgenius/dify/pull/12498
• chore(*): Update style of thinking by @laipz8200 in https://github.com/langgenius/dify/pull/13319
• chore:improve thinking display for llm from xinference and ollama pro… by @leslie2046 in https://github.com/langgenius/dify/pull/13318
• fix: Azure AI Foundry model cannot be used in the workflow by @laipz8200 in https://github.com/langgenius/dify/pull/13323
• feat: add completion mode and context size options for LLM configuration by @laipz8200 in https://github.com/langgenius/dify/pull/13325
• chore(*): Bump version to 0.15.3 by @laipz8200 in https://github.com/langgenius/dify/pull/13308

Full Changelog: https://github.com/langgenius/dify/compare/0.15.2...0.15.3