v0.8.0

[laipz8200]

✨ What’s New in v0.8.0? ✨

Hey everyone, we’re excited to announce the release of version 0.8.0! This update brings a mix of new features, enhancements, and crucial bug fixes. Here’s a quick rundown:

🔥 Key Feature

Parallel Execution of Nodes in Workflows by @takatost, @zxhlyh, and @YIXIAO0 in #8192.

Nodes can now be executed in parallel within a workflow, greatly increasing the execution speed. This feature is especially beneficial for complex workflows that involve multiple steps or processes, allowing for quicker completion times and improved performance.

Dive deeper into the details and unleash the full potential of these new features by exploring our latest blog post and documentation!

🚀 New Features

• Support gpt-4o-2024-08-06 and json_schema for Azure OpenAI Service: Support for the latest GPT-4o model and JSON schema for Azure OpenAI by @hjlarry in feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service #7648
• Support Oracle Cloud Infrastructure Generative AI Service: Oracle Cloud Infrastructure is now a supported model provider by @tmuife in Add OCI(Oracle Cloud Infrastructure) Generative AI Service as a Model Provider #7775
• Support Fish Audio TTS: Added support for Fish Audio Text-to-Speech models by @leng-yue in feat: support fish audio TTS #7982

⚠️ Deprecated Features

• Deprecate N to 1 Retrieval by @zxhlyh in chore: offline n to 1 retrieval #8134
  The N-to-1 retrieval strategy is officially deprecated in this version, of which the entrance will be closed but applications that have selected this feature will still be retained. We recommend switching to the more flexible multi-path retrieval strategy to boost your application's retrieval efficiency.

⚙️ Enhancements

• Update App Published Time After Clicking Publish Button: The published time of an app now updates correctly when you click the publish button by @vicoooo26 in Feat: update app published time after clicking publish button #7801

🛠️ Bug Fixes

• Fix Notion Table Extract: Fixed issues with extracting data from Notion tables by @JohnJyong in improve the notion table extract #7925
• Fix Nvidia Rerank Top N Missed: Addressed issues with Nvidia rerank top N functionality by @JohnJyong in nvidia rerank top n missed #8185
• Fix Claude Credential Validation: Resolved credential validation issues for Claude by @crazywoola in fix: Claude can not validate credientials #8109

That’s it for this release! As always, we appreciate your feedback and contributions. Do it for you! 🚀

---

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 main
   git pull origin main

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

• feat: support auto generate i18n translate by @iamjoel in feat: support auto generate i18n translate #6964
• fix: frontend handle sometimes server not generate the wrong follow up data struct by @iamjoel in fix: frontend handle sometimes server not generate the wrong follow up data struct #7916
• improve the notion table extract by @JohnJyong in improve the notion table extract #7925
• Fix/segment create with api by @JohnJyong in Fix/segment create with api #7928
• chore: feat: chart for message count #7603 i18n by @ZuzooVn in chore: #7603 i18n #7931
• fix rerank model value is empty string by @JohnJyong in fix rerank model value is empty string #7937
• Chore/add default step 1x url by @crazywoola in Chore/add default step 1x url #7933
• Chore/add roadmap by @crazywoola in Chore/add roadmap #7943
• fix(api): Code-Based Extension cause error on position map sorting by @jim60105 in fix(api): Code-Based Extension cause error on position map sorting #7934
• chore: Chore/add roadmap #7943 i18n by @ZuzooVn in chore: #7943 i18n #7948
• Revert "fix: an issue of keyword search feature in application log list" by @takatost in Revert "fix: an issue of keyword search feature in application log list" #7949
• feat: ops trace add llm model by @ZhouhaoJiang in feat: ops trace add llm model #7306
• chore: fix inverted index japanese translation by @os1ma in chore: fix inverted index japanese translation #7957
• fix: split text keep separator by @Sumkor in fix: split text keep separator #7930
• Feat: update app published time after clicking publish button by @vicoooo26 in Feat: update app published time after clicking publish button #7801
• fix:empty voice occurs when xinference CosyVoice tts model by @leslie2046 in fix:empty voice occurs when xinference CosyVoice tts model #7958
• fix: get commit sha failed in translate action by @iamjoel in fix: get commit sha failed in translate action #7959
• feat: add health check for pg and redis in docker-compose.middleware.yaml (add health check for pg and redis in docker-compose.middleware.yaml #7961) by @hwzhuhao in feat: add health check for pg and redis in docker-compose.middleware.yaml (#7961) #7962
• Feat:remove estimation of embedding cost by @JzoNgKVO in Feat:remove estimation of embedding cost #7950
• chore: refactor the beichuan model by @hjlarry in chore: refactor the beichuan model #7953
• fix wrong error message by @JohnJyong in fix wrong error message #7972
• chore: translate i18n files by @github-actions in chore: translate i18n files #7965
• Concurrent calls to the Wenxin model, and the exception problem when obtaining the token is fixed by @wochuideng in Concurrent calls to the Wenxin model, and the exception problem when obtaining the token is fixed #7976
• fix spliter length missed by @JohnJyong in fix spliter length missed #7987
• feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service by @hjlarry in feat: add gpt-4o-2024-08-06 and json_schema for azure openAI service #7648
• feat: support fish audio TTS by @leng-yue in feat: support fish audio TTS #7982
• feat: return page number of pdf documents upon retrieval by @jasonkang14 in feat: return page number of pdf documents upon retrieval #7749
• Fix/datasets api description error by @Designerxsh in Fix/datasets api description error #8025
• feat: add video、audio、abbr href message rendering and optimize image rendering by @charli117 in feat: add video、audio、abbr href message rendering and optimize image rendering #6868
• Update milvus-standalone version and expose required ports for the container. by @winsonwhe in Update milvus-standalone version and expose required ports for the container. #7709
• support huawei cloud obs storage (support huawei cloud obs storage #7980) by @hwzhuhao in support huawei cloud obs storage (#7980) #7981
• Add OCI(Oracle Cloud Infrastructure) Generative AI Service as a Model Provider by @tmuife in Add OCI(Oracle Cloud Infrastructure) Generative AI Service as a Model Provider #7775
• fix the tooltip in tools node by @YIXIAO0 in fix the tooltip in tools node #8055
• chore: feat: Sort conversations by updated_at desc #7348, support query conversations by updated_at by @ZuzooVn in chore: #7348, support query conversations by updated_at #8047
• fix: change milvus init args from (host, port) to (url, token) by @zc277584121 in fix: change milvus init args from (host, port) to (url, token) #8019
• ifEsle node add regex match by @charli117 in ifEsle node add regex match #8007
• If else add regexmatch by @crazywoola in If else add regexmatch #8059
• fix: parameter rule by @crazywoola in fix: parameter rule #8064
• fix: overflow issues in chat history by @YIXIAO0 in fix: overflow issues in chat history #8062
• Revert "fix: parameter rule" by @AAEE86 in Revert "fix: parameter rule" #8070
• fix: i18n typo by @ZuzooVn in fix: i18n typo #8077
• fix: knowledge input by @crazywoola in fix: knowledge input #8065
• Fix variable typo by @ZuzooVn in Fix variable typo #8084
• feat: support redis sentinel mode by @erigo in feat: support redis sentinel mode #7756
• fix LangSmith project config error by @charli117 in fix LangSmith project config error #7996
• fix: parameter input by @crazywoola in fix: parameter input #8076
• feat:add fishaudio in xinference by @leslie2046 in feat:add fishaudio in xinference #8100
• chore: keep dify compose file consistent format by @soulteary in chore: keep dify compose file consistent format #8102
• Translate billing to PT-BR by @thalessalazar in Translate billing to PT-BR #8105
• fix: Claude can not validate credientials by @crazywoola in fix: Claude can not validate credientials #8109
• feat: support more model types and builtin tools on aws/sagemaker by @ybalbert001 in feat: support more model types and builtin tools on aws/sagemaker #8061
• Fix: tongyi code wrapper works not stable by @zouchengzhuo in Fix: tongyi code wrapper works not stable #7871
• add dify-sandbox health check in docker-compose.yaml (add dify-sandbox health check in docker-compose.yaml #8121) by @hwzhuhao in add dify-sandbox health check in docker-compose.yaml (#8121) #8124
• fix: ollama text embedding 500 error by @crazywoola in fix: ollama text embedding 500 error #8131
• chore: offline n to 1 retrieval by @zxhlyh in chore: offline n to 1 retrieval #8134
• Modify model parameters in Spark LLMs and zhipuai LLMs by @AAEE86 in Modify model parameters in Spark LLMs and zhipuai LLMs #8078
• fix: user-select style and pre-create iframe in embed.js by @cr-zhichen in fix: user-select style and pre-create iframe in embed.js #8093
• chore: translate i18n files by @github-actions in chore: translate i18n files #8135
• fix: html raw render by @crazywoola in fix: html raw render #8138
• Update LICENSE - remove 'SaaS' from restriction term definition by @guchenhe in Update LICENSE - remove 'SaaS' from restriction term definition #8143
• update qwen-long max token by @crazywoola in update qwen-long max token #8157
• Fix variable typo (cont) by @ZuzooVn in Fix variable typo (cont) #8161
• feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. by @laipz8200 in feat(api/core/model_runtime/entities/defaults.py): Add TOP_K in default parameters. #8167
• chore: bump super-linter to v7 by @bowenliang123 in chore: bump super-linter to v7 #8148
• add volcengine tos storage by @yaoice in add volcengine tos storage #8164
• code merge error by @JohnJyong in code merge error #8183
• chore: upgrade expat from 2.6.2-2 to 2.6.3-1 by @ZuzooVn in chore: upgrade expat from 2.6.2-2 to 2.6.3-1 #8182
• nvidia rerank top n missed by @JohnJyong in nvidia rerank top n missed #8185
• fix: The length of the tag should between 1 and 50 (The length of the tag does not match the actual error reported #8187) by @hwzhuhao in fix: The length of the tag should between 1 and 50 (#8187) #8188
• fix(api/core/rag/extractor/excel_extractor.py): filter excel empty sheet by @JohnJyong in fix(api/core/rag/extractor/excel_extractor.py): filter excel empty sheet #8194
• refactor(api/core): Improve type hints and apply ruff formatter in agent runner and model manager. by @laipz8200 in refactor(api/core): Improve type hints and apply ruff formatter in agent runner and model manager. #8166
• docs: replace docker-compose with docker compose by @crazywoola in docs: replace docker-compose with docker compose #8195
• feat: Parallel Execution of Nodes in Workflows by @takatost in feat: Parallel Execution of Nodes in Workflows #8192
• chore: translate i18n files by @github-actions in chore: translate i18n files #8202
• chore(api/core): apply ruff reformatting by @bowenliang123 in chore(api/core): apply ruff reformatting #7624
• fix: input chat input wrong padding by @iamjoel in fix: input chat input wrong padding #8207
• chore(api/models): apply ruff reformatting by @bowenliang123 in chore(api/models): apply ruff reformatting #7600
• fix the tooltip in tool nodes by @YIXIAO0 in fix the tooltip in tool nodes #8215
• revert page column by @JohnJyong in revert page column #8217
• fix(docker/docker-compose.yaml): Set default value for REDIS_SENTINEL_SOCKET_TIMEOUT and CELERY_SENTINEL_SOCKET_TIMEOUT by @laipz8200 in fix(docker/docker-compose.yaml): Set default value for REDIS_SENTINEL_SOCKET_TIMEOUT and CELERY_SENTINEL_SOCKET_TIMEOUT #8218

New Contributors

• @jim60105 made their first contribution in fix(api): Code-Based Extension cause error on position map sorting #7934
• @os1ma made their first contribution in chore: fix inverted index japanese translation #7957
• @Sumkor made their first contribution in fix: split text keep separator #7930
• @github-actions made their first contribution in chore: translate i18n files #7965
• @wochuideng made their first contribution in Concurrent calls to the Wenxin model, and the exception problem when obtaining the token is fixed #7976
• @leng-yue made their first contribution in feat: support fish audio TTS #7982
• @Designerxsh made their first contribution in Fix/datasets api description error #8025
• @winsonwhe made their first contribution in Update milvus-standalone version and expose required ports for the container. #7709
• @zc277584121 made their first contribution in fix: change milvus init args from (host, port) to (url, token) #8019
• @AAEE86 made their first contribution in Revert "fix: parameter rule" #8070
• @thalessalazar made their first contribution in Translate billing to PT-BR #8105
• @zouchengzhuo made their first contribution in Fix: tongyi code wrapper works not stable #7871
• @cr-zhichen made their first contribution in fix: user-select style and pre-create iframe in embed.js #8093
• @yaoice made their first contribution in add volcengine tos storage #8164

Full Changelog: 0.7.3...0.8.0

---

This discussion was created from the release v0.8.0.

[sanbei101]

伟大的进步꒰ •ɷ• ꒱

[PNjobs]

Is the parallel flow only for chatflow? I upgraded and I dont see it in workflow

[laipz8200]

It is supported in both workflow and chatflow.