v0.9.0

[laipz8200]

✨ What’s New in v0.9.0? ✨

Get ready for a feature-packed update! Version 0.9.0 brings major enhancements, new integrations, and crucial fixes. Let’s dive into the details:

🚀 New Features

🔄 Retrieval-Augmented Generation (RAG)

External Knowledge API: Now you can connect to third-party knowledge bases seamlessly (introduced by @JohnJyong in #8913).

• Simply provide the API endpoint, API key, and external knowledge ID to link with the external knowledge base.
• Supports retrieval and recall of external knowledge based on user queries.
• Enables integration of external knowledge bases within Dify applications.

Website Crawling: Now supports Jina Reader as additional alternative for website crawling, converting web page URL to LLM-friendly input format. Read Sync Data from Website for details. (@mapleeit in #8761).

🧠 Models

• Voyage AI: A new model provider added (thanks to @hwzhuhao in feat: add voyage ai as a new model provider #8747).
• Llama3.2: Now available with Fireworks and Groq providers for improved performance and variety (@yaoice in Add llama3.2 model in fireworks provider #8809 and @Howe829 in Add Llama3.2 models in Groq provider #8831).
• Introduced InternLM 2.5-20b and Qwen 2.5-coder-7b (@hwzhuhao in feat: add internlm2.5-20b and qwen2.5-coder-7b model #8862).
• Jamba: Another new model to expand our capabilities (@longzhihun in Add Jamba and Llama3.2 model support #8878).
• New Nomic embedding model provider introduced (@yaoice in Add nomic embedding model provider #8640).
• Support for o1 series models for OpenRouter (@sinomoe in #8358).
• DeepSeek-v2.5 added as a model provider for SiliconFlow (@hwzhuhao in #8639).
• Stream for Gemini now available (@AAEE86 in #8678).
• Vertex AI Gemini 1.5 002 and experimental models are now supported (@hellof20 in #8767).

🛠️ Other Updates

• Xinference TTS Stream Mode: Now live for a smoother text-to-speech experience (@leslie2046 in feat:use xinference tts stream mode #8616).
• Regenerate in Chat, Agent, and Chatflow applications (@xuzuodong in #7661).

⚙️ Enhancements

• Improved SVG output UX for a more seamless design experience (@xuzuodong in feat: improved SVG output UX #8765).
• Extended Jina Embeddings V3 API parameters (@DresAaron in feat: extend api params for Jina Embeddings V3 #8657).
• Deprecated older Mistral models for SiliconFlow to streamline performance (@hwzhuhao in feat: deprecate mistral model for siliconflow #8828).
• Added Min-connections and Max-connections settings for pgvector (@hwzhuhao in feat: add min-connection and max-connection for pgvector #8841).
• Error Handling Enhancements: Improved iteration filters and error logging for optimal performance (@hwzhuhao in refactor(ops): Optimize the iteration for filter_none_values and use logging.error to record logs when an exception occurs #8461).
• Enhanced operational flexibility with fully configurable WORKFLOW_ environment variables* (@fujita-h in Make WORKFLOW_* configurable as environment variables. #8644).
• Upgraded ElasticSearch from 8.14.x to 8.15.x to keep our infrastructure up-to-date (@bowenliang123 in dep: bump ElasticSearch from 8.14.x to 8.15.x #8197).

🛠️ Bug Fixes

• Fixed "Max submit count reached" error during workflow iterations (@takatost in fix(workflow): "Max submit count reached" error occurred when executing workflow as tool in iteration #8595).
• Corrected a linking error in help documents (@hjlarry in fix: a helper link error #8508).
• iOS TTS Stream: Now fully functional on Safari 17.1+ (@likenamehaojie in fixbug tts(stream) not work on ios safari(17.1+) #8645).
• Resolved JSONDecodeError in llm_generator.py (@ZuzooVn in fix: llm_generator.py JSONDecodeError #8504).
• Fixed errors when sending messages within chatflow and dialogs (@xuzuodong in fix: send message error when chatting with opening statement #8627 and fix: send message error when last sent message not succeeded #8682).
• Corrected Spark's LLM token calculation error for accurate token usage (@cherryhuahua in fix:Spark's large language model token calculation error #7911 #8755).
• Resolved embedded chat issues on iOS (@zxhlyh in fix: embedded chat on ios #8718).

📚 Documentation & Misc

• Enhanced documentation to clarify the importance of Celery Service (@fchange in Enhance Readme Documentation to Clarify the Importance of Celery Service #8558).
• Updated configurations in docker-compose files and related docs (@saifeiLee and others in docs: Update ssrf_proxy related doc link in docker-compose file #8516 and fix: change the brand name to Jina AI #8691).
• Added English versions for customizable model scale documentation to broaden accessibility (@hwzhuhao in docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out #8871).

With this release, we’re truly showcasing the power of Dify! We appreciate your continued support—explore the new features and share your feedback with us!

---

Upgrade Guide

Docker compose deployments

Warning

The docker-compose.yaml has been refactored. If you've made any changes to the file, make sure to check out the "Upgrade to new docker compose deployment" section above for usage and migration tips.

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 main branch:

   git checkout 0.9.0
   git pull origin 0.9.0

3. Update Python dependencies:

   cd api
   poetry install

4. Then, let's run the migration script:

   poetry shell
   flask db upgrade

5. Finally, run API server, Worker and Web frontend Server again.

---

What's Changed

• fix(workflow): "Max submit count reached" error occurred when executing workflow as tool in iteration by @takatost in fix(workflow): "Max submit count reached" error occurred when executing workflow as tool in iteration #8595
• fix: a helper link error by @hjlarry in fix: a helper link error #8508
• chore: translate i18n files by @github-actions in chore: translate i18n files #8557
• Enhance Readme Documentation to Clarify the Importance of Celery Service by @fchange in Enhance Readme Documentation to Clarify the Importance of Celery Service #8558
• docs: Update ssrf_proxy related doc link in docker-compose file by @saifeiLee in docs: Update ssrf_proxy related doc link in docker-compose file #8516
• Update the PerfXCloud provider model list，Update PerfXCloudProvider validate_provider_credentials method. by @BingGeX in Update the PerfXCloud provider model list，Update PerfXCloudProvider validate_provider_credentials method. #8587
• add MixtralAI Model by @AAEE86 in add MixtralAI Model #8517
• fix: api/core/ops/ops_trace_manager.py by @ZuzooVn in fix: api/core/ops/ops_trace_manager.py #8501
• add Qwen custom add model interface by @AAEE86 in add Qwen custom add model interface #8565
• refactor(ops): Optimize the iteration for filter_none_values and use logging.error to record logs when an exception occurs by @hwzhuhao in refactor(ops): Optimize the iteration for filter_none_values and use logging.error to record logs when an exception occurs #8461
• feat: update pyproject.toml by @ZhouhaoJiang in feat: update pyproject.toml #8368
• feat: regenerate in Chat, agent and Chatflow app by @xuzuodong in feat: regenerate in Chat, agent and Chatflow app #7661
• docs: Add Japanese documentation for tools by @totsukash in docs: Add Japanese documentation for tools #8469
• feat:use xinference tts stream mode by @leslie2046 in feat:use xinference tts stream mode #8616
• Add Fireworks AI as new model provider by @yaoice in Add Fireworks AI as new model provider #8428
• feat(tools/cogview): Updated cogview tool to support cogview-3 and the latest cogview-3-plus by @ox01024 in feat(tools/cogview): Updated cogview tool to support cogview-3 and the latest cogview-3-plus #8382
• Add model parameter translation by @AAEE86 in Add model parameter translation #8509
• fix: form input add tabIndex by @LLmoskk in fix: form input add tabIndex #8478
• feat: support o1 series models for openrouter by @sinomoe in feat: support o1 series models for openrouter #8358
• chore: add Gemini newest experimental models (close Add Gemini Pro Experimental #7121) by @CXwudi in chore: add Gemini newest experimental models (close #7121) #8621
• chore: enhance configuration descriptions by @ZuzooVn in chore: enhance configuration descriptions #8624
• fix: redundant check for available_document_count by @y-omr in fix: redundant check for available_document_count #8491
• fix: commands.py by @ZuzooVn in fix: commands.py #8483
• fix: llm_generator.py JSONDecodeError by @ZuzooVn in fix: llm_generator.py JSONDecodeError #8504
• fix: send message error when chatting with opening statement by @xuzuodong in fix: send message error when chatting with opening statement #8627
• feat: add qwen2.5 for model provider siliconflow by @hwzhuhao in feat: add qwen2.5 for model provider siliconflow #8630
• docs: fix predefined_model_scale_out.md redirect error by @hwzhuhao in docs: fix predefined_model_scale_out.md redirect error #8633
• feat: add deepseek-v2.5 for model provider siliconflow by @hwzhuhao in feat: add deepseek-v2.5 for model provider siliconflow #8639
• Make WORKFLOW_* configurable as environment variables. by @fujita-h in Make WORKFLOW_* configurable as environment variables. #8644
• chore: Enable Japanese descriptions for Tools by @totsukash in chore: Enable Japanese descriptions for Tools #8646
• feat: extend api params for Jina Embeddings V3 by @DresAaron in feat: extend api params for Jina Embeddings V3 #8657
• fix: Assignment exception by @haike-1213 in fix: Assignment exception #8663
• chore: skip PLR6201 linter rule by @bowenliang123 in chore: skip PLR6201 linter rule #8666
• fix: png avatar upload as jpeg by @hjlarry in fix: png avatar upload as jpeg #8665
• add Qwen model translate by @AAEE86 in add Qwen model translate #8674
• add zhipuai web search by @AAEE86 in add zhipuai web search #8668
• add Spark Max-32K by @AAEE86 in add Spark Max-32K #8676
• chore: Optimize I18nObject class for better performance and readability by @ZuzooVn in chore: Optimize I18nObject class for better performance and readability #8681
• fix: send message error when last sent message not succeeded by @xuzuodong in fix: send message error when last sent message not succeeded #8682
• fixbug tts(stream) not work on ios safari(17.1+) by @likenamehaojie in fixbug tts(stream) not work on ios safari(17.1+) #8645
• fix: document_create_args_validate by @vikeychen in fix: document_create_args_validate #8569
• Add nomic embedding model provider by @yaoice in Add nomic embedding model provider #8640
• fix: prompt for the follow-up suggestions by @crazywoola in fix: prompt for the follow-up suggestions #8685
• fix: typos and improve naming conventions: by @ZuzooVn in fix: typos and improve naming conventions: #8687
• fix: change the brand name to Jina AI by @Nick17t in fix: change the brand name to Jina AI #8691
• feat: add xinference sd web ui api tool by @themanforfree in feat: add xinference sd web ui api tool #8385
• fix llm integration problem: It doesn't work on docker env by @ybalbert001 in fix llm integration problem: It doesn't work on docker env #8701
• feat: add mixedbread as a new model provider by @hwzhuhao in feat: add mixedbread as a new model provider #8523
• fix: Remove unsupported parameters in qwen model by @AAEE86 in fix: Remove unsupported parameters in qwen model #8699
• fix: change model provider name issue Ref fix: change the brand name to Jina AI #8691 by @BenjaminX in fix: change model provider name issue Ref #8691 #8710
• fix: update nomic model provider token calculation by @yaoice in fix: update nomic model provider token calculation #8705
• fix: embedded chat on ios by @zxhlyh in fix: embedded chat on ios #8718
• chore: remove windows platform timezone set by @hjlarry in chore: remove windows platform timezone set #8712
• fix: remove harm category setting from vertex ai by @totsukash in fix: remove harm category setting from vertex ai #8721
• Fix/update jina ai products labels and descriptions by @Nick17t in Fix/update jina ai products labels and descriptions #8730
• add embedding input type parameter by @JohnJyong in add embedding input type parameter #8724
• Add embedding models in fireworks provider by @yaoice in Add embedding models in fireworks provider #8728
• Fix Issue: switch LLM of SageMaker endpoint doesn't take effect by @ybalbert001 in Fix Issue: switch LLM of SageMaker endpoint doesn't take effect #8737
• fix: . is missing in file_extension by @crazywoola in fix: . is missing in file_extension #8736
• chore: make url display in the middle of http node by @hjlarry in chore: make url display in the middle of http node #8741
• chore: apply ruff reformat for python-client sdk by @hwzhuhao in chore: apply ruff reformat for python-client sdk #8752
• fix:Spark's large language model token calculation error Spark's large language model token calculation error #7911 by @cherryhuahua in fix:Spark's large language model token calculation error #7911 #8755
• fix: expose the configuration of HTTP request node to Docker by @zhuiyue132 in fix: expose the configuration of HTTP request node to Docker #8716
• Add GitHub Actions Workflow for Web Tests by @xuzuodong in Add GitHub Actions Workflow for Web Tests #8753
• fix: the translation result may cause a different meaning by @douxc in fix: the translation result may cause a different meaning #8763
• feat: add support for Vertex AI Gemini 1.5 002 and experimental models by @hellof20 in feat: add support for Vertex AI Gemini 1.5 002 and experimental models #8767
• dep: bump ElasticSearch from 8.14.x to 8.15.x by @bowenliang123 in dep: bump ElasticSearch from 8.14.x to 8.15.x #8197
• chore: fix comfyui tool doc url by @QunBB in chore: fix comfyui tool doc url #8775
• fix: TavilySearch tool get api link by @hjlarry in fix: TavilySearch tool get api link #8780
• chore: add input_type param desc for the _invoke method of text_embedding by @hwzhuhao in chore: add input_type param desc for the _invoke method of text_embedding #8778
• fix: credential *** should be string by @hjlarry in fix: credential *** should be string #8785
• fix: update usage for Jina Embeddings v3 by @DresAaron in fix: update usage for Jina Embeddings v3 #8771
• Add more models for SiliconFlow by @jackalcooper in Add more models for SiliconFlow #8779
• fix: the Image-1X tool by @hjlarry in fix: the Image-1X tool #8787
• fix: start node input config modal raise 'variable name is required' by @hjlarry in fix: start node input config modal raise 'variable name is required' #8793
• fix: Ollama modelfeature set vision, and an exception occurred at the… by @free-cx in fix: Ollama modelfeature set vision, and an exception occurred at the… #8783
• refactor: update delete method as an abstract method by @hwzhuhao in refactor: update delete method as an abstract method #8794
• fix: workflow as tool always outdated by @hjlarry in fix: workflow as tool always outdated #8798
• fix: change wrong company name by @iamjoel in fix: change wrong company name #8801
• feat: add qwen to add custom model parameters by @AAEE86 in feat: add qwen to add custom model parameters #8759
• feat: add stream for Gemini by @AAEE86 in feat: add stream for Gemini #8678
• feat: improved SVG output UX by @xuzuodong in feat: improved SVG output UX #8765
• Add llama3.2 model in fireworks provider by @yaoice in Add llama3.2 model in fireworks provider #8809
• add more detailed doc for models of qwen series by @wenmengzhou in add more detailed doc for models of qwen series  #8799
• chore: massive update of the Gemini models based on latest documentation by @CXwudi in chore: massive update of the Gemini models based on latest documentation #8822
• Updated the YouTube channel to Dify's by @shaiss in Updated the YouTube channel to Dify's #8817
• feat: add pgvecto-rs and analyticdb in docker/.env.example by @hwzhuhao in feat: add pgvecto-rs and analyticdb in docker/.env.example #8823
• fix: close log status option raise error by @hjlarry in fix: close log status option raise error #8826
• fix: AnalyticdbVector retrieval scores by @lpdink in fix: AnalyticdbVector retrieval scores #8803
• feat: deprecate mistral model for siliconflow by @hwzhuhao in feat: deprecate mistral model for siliconflow #8828
• Add Llama3.2 models in Groq provider by @Howe829 in Add Llama3.2 models in Groq provider #8831
• fix: delete harm catalog settings for gemini by @CXwudi in fix: delete harm catalog settings for gemini #8829
• feat(Tools): add feishu tools by @hgnulb in feat(Tools): add feishu tools #8800
• feat: add min-connection and max-connection for pgvector by @hwzhuhao in feat: add min-connection and max-connection for pgvector #8841
• chore: fix wrong VectorType match case by @yaoice in chore: fix wrong VectorType match case #8857
• fix(workflow/nodes/knowledge-retrieval/use-config): Preserve rerankin… by @Kevin9703 in fix(workflow/nodes/knowledge-retrieval/use-config): Preserve rerankin… #8842
• fix: update qwen2.5-coder-7b model name by @hwzhuhao in fix: update qwen2.5-coder-7b model name #8861
• fix: customize model credentials were invalid despite the provider credentials being active by @takatost in fix: customize model credentials were invalid despite the provider credentials being active #8864
• feat: add internlm2.5-20b and qwen2.5-coder-7b model by @hwzhuhao in feat: add internlm2.5-20b and qwen2.5-coder-7b model #8862
• feat: deprecate gte-Qwen2-7B-instruct embedding model by @hwzhuhao in feat: deprecate gte-Qwen2-7B-instruct embedding model #8866
• refactor: update Callback to an abstract class by @hwzhuhao in refactor: update Callback to an abstract class #8868
• chore: bump ruff to 0.6.8 for fixing violation in SIM910 by @bowenliang123 in chore: bump ruff to 0.6.8 for fixing violation in SIM910 #8869
• fix(workflow): update tagging logic in GitHub Actions by @laipz8200 in fix(workflow): update tagging logic in GitHub Actions #8882
• Add Jamba and Llama3.2 model support by @longzhihun in Add Jamba and Llama3.2 model support #8878
• fix: event: tts_message_end always return in api streaming response_mode #8843 event: tts_message_end always return in api streaming resp… by @ic-xu in fix: #8843 event: tts_message_end always return in api streaming resp… #8846
• docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out by @hwzhuhao in docs: add english versions for the files customizable_model_scale_out and predefined_model_scale_out #8871
• feat: add voyage ai as a new model provider by @hwzhuhao in feat: add voyage ai as a new model provider #8747
• feat(website-crawl): add jina reader as additional alternative for website crawling by @mapleeit in feat(website-crawl): add jina reader as additional alternative for website crawling #8761
• feat(api): add version comparison logic by @laipz8200 in feat(api): add version comparison logic #8902
• refactor(api/variables): VariableError as a ValueError. by @laipz8200 in refactor(api/variables): VariableError as a ValueError. #8554
• fix: fix the data validation consistency issue in keyword content review by @hwzhuhao in fix: fix the data validation consistency issue in keyword content review #8908
• refactor: optimize the calculation of rerank threshold and the logic for forbidden characters in model_uid by @hwzhuhao in refactor: optimize the calculation of rerank threshold and the logic for forbidden characters in model_uid #8879
• external knowledge api by @JohnJyong in external knowledge api #8913
• fix: line in iteration node is not straight by @YIXIAO0 in fix: line in iteration node is not straight #8918
• fix: Compatible with special characters in pg full-text search. by @ThreeFish-AI in fix: Compatible with special characters in pg full-text search. #8921
• chore: translate i18n files by @github-actions in chore: translate i18n files #8917
• fix: fix the issue with the system model configuration update by @hwzhuhao in fix: fix the issue with the system model configuration update #8923
• Feat: add debounce for search in logs by @JzoNgKVO in Feat: add debounce for search in logs #8924
• chore(versioning): bump version to 0.9.0 by @laipz8200 in chore(versioning): bump version to 0.9.0 #8911

New Contributors

• @fchange made their first contribution in Enhance Readme Documentation to Clarify the Importance of Celery Service #8558
• @CXwudi made their first contribution in chore: add Gemini newest experimental models (close #7121) #8621
• @fujita-h made their first contribution in Make WORKFLOW_* configurable as environment variables. #8644
• @haike-1213 made their first contribution in fix: Assignment exception #8663
• @likenamehaojie made their first contribution in fixbug tts(stream) not work on ios safari(17.1+) #8645
• @cherryhuahua made their first contribution in fix:Spark's large language model token calculation error #7911 #8755
• @zhuiyue132 made their first contribution in fix: expose the configuration of HTTP request node to Docker #8716
• @jackalcooper made their first contribution in Add more models for SiliconFlow #8779
• @free-cx made their first contribution in fix: Ollama modelfeature set vision, and an exception occurred at the… #8783
• @wenmengzhou made their first contribution in add more detailed doc for models of qwen series  #8799
• @shaiss made their first contribution in Updated the YouTube channel to Dify's #8817
• @mapleeit made their first contribution in feat(website-crawl): add jina reader as additional alternative for website crawling #8761

Full Changelog: 0.8.3...0.9.0

---

This discussion was created from the release v0.9.0.