langgenius/dify 0.8.0

v0.8.0

on GitHub

✨ 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 #7648
• Support Oracle Cloud Infrastructure Generative AI Service: Oracle Cloud Infrastructure is now a supported model provider by @tmuife in #7775
• Support Fish Audio TTS: Added support for Fish Audio Text-to-Speech models by @leng-yue in #7982

⚠️ Deprecated Features

• Deprecate N to 1 Retrieval by @zxhlyh in #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 #7801

🛠️ Bug Fixes

• Fix Notion Table Extract: Fixed issues with extracting data from Notion tables by @JohnJyong in #7925
• Fix Nvidia Rerank Top N Missed: Addressed issues with Nvidia rerank top N functionality by @JohnJyong in #8185
• Fix Claude Credential Validation: Resolved credential validation issues for Claude by @crazywoola in #8109

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

Upgrade Guide

Docker compose deployments

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

New Contributors

• @jim60105 made their first contribution in #7934
• @os1ma made their first contribution in #7957
• @Sumkor made their first contribution in #7930
• @github-actions made their first contribution in #7965
• @wochuideng made their first contribution in #7976
• @leng-yue made their first contribution in #7982
• @Designerxsh made their first contribution in #8025
• @winsonwhe made their first contribution in #7709
• @zc277584121 made their first contribution in #8019
• @AAEE86 made their first contribution in #8070
• @thalessalazar made their first contribution in #8105
• @zouchengzhuo made their first contribution in #7871
• @cr-zhichen made their first contribution in #8093
• @yaoice made their first contribution in #8164

Full Changelog: 0.7.3...0.8.0