fix: remove unused fields

Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>

.devcontainer/post_create_command.sh

@@ -7,5 +7,6 @@ echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run
 echo 'alias start-worker="cd /workspaces/dify/api && poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
 echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc
+echo 'alias stop-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify down"' >> ~/.bashrc
 
-source /home/vscode/.bashrc
+source /home/vscode/.bashrc

.github/pull_request_template.md

@@ -8,16 +8,9 @@ Please include a summary of the change and which issue is fixed. Please also inc
 
 # Screenshots
 
-<table>
-  <tr>
-  <td>Before: </td>
-  <td>After: </td>
-  </tr>
-  <tr>
-  <td>...</td>
-  <td>...</td>
-  </tr>
-</table>
+| Before | After |
+|--------|-------|
+| ...    | ...   |
 
 # Checklist
 

.github/workflows/api-tests.yml

@@ -50,9 +50,18 @@ jobs:
       - name: Run ModelRuntime
         run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
 
+      - name: Run dify config tests
+        run: poetry run -C api python dev/pytest/pytest_config_tests.py
+
       - name: Run Tool
         run: poetry run -C api bash dev/pytest/pytest_tools.sh
 
+      - name: Run mypy
+        run: |
+          pushd api
+          poetry run python -m mypy --install-types --non-interactive .
+          popd
+
       - name: Set up dotenvs
         run: |
           cp docker/.env.example docker/.env

.github/workflows/db-migration-test.yml

@@ -48,6 +48,8 @@ jobs:
           cp .env.example .env
 
       - name: Run DB Migration
+        env:
+          DEBUG: true
         run: |
           cd api
           poetry run python -m flask upgrade-db

.github/workflows/expose_service_ports.sh

@@ -9,5 +9,6 @@ yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compos
 yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["8091-8096:8091-8096"]' -i docker/docker-compose.yaml
 yq eval '.services.couchbase-server.ports += ["11210:11210"]' -i docker/docker-compose.yaml
+yq eval '.services.tidb.ports += ["4000:4000"]' -i docker/docker-compose.yaml
 
-echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"
+echo "Ports exposed for sandbox, weaviate, tidb, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"

.github/workflows/style.yml

@@ -37,6 +37,7 @@ jobs:
       - name: Ruff check
         if: steps.changed-files.outputs.any_changed == 'true'
         run: |
+          poetry run -C api ruff --version
           poetry run -C api ruff check ./api
           poetry run -C api ruff format --check ./api
 

.github/workflows/vdb-tests.yml

@@ -51,7 +51,7 @@ jobs:
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Stores (TiDB, Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
         uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
@@ -67,6 +67,7 @@ jobs:
             pgvector
             chroma
             elasticsearch
+            tidb
 
       - name: Test Vector Stores
         run: poetry run -C api bash dev/pytest/pytest_vdb.sh

README.md

@@ -147,6 +147,13 @@ Deploy Dify to Cloud Platform with a single click using [terraform](https://www.
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Using AWS CDK for Deployment
+
+Deploy Dify to AWS with [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_AR.md

@@ -190,6 +190,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform بواسطة @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### استخدام AWS CDK للنشر
+
+انشر Dify على AWS باستخدام [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK بواسطة @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## المساهمة
 
 لأولئك الذين يرغبون في المساهمة، انظر إلى [دليل المساهمة](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) لدينا. 
@@ -222,3 +229,10 @@ docker compose up -d
 ## الرخصة
 
 هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.
+## الكشف عن الأمان
+
+لحماية خصوصيتك، يرجى تجنب نشر مشكلات الأمان على GitHub. بدلاً من ذلك، أرسل أسئلتك إلى security@dify.ai وسنقدم لك إجابة أكثر تفصيلاً.
+
+## الرخصة
+
+هذا المستودع متاح تحت [رخصة البرنامج الحر Dify](LICENSE)، والتي تعتبر بشكل أساسي Apache 2.0 مع بعض القيود الإضافية.

README_CN.md

@@ -213,6 +213,13 @@ docker compose up -d
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### 使用 AWS CDK 部署
+
+使用 [CDK](https://aws.amazon.com/cdk/) 将 Dify 部署到 AWS
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)

README_ES.md

@@ -215,6 +215,13 @@ Despliega Dify en una plataforma en la nube con un solo clic utilizando [terrafo
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para el Despliegue
+
+Despliegue Dify en AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuir
 
 Para aquellos que deseen contribuir con código, consulten nuestra [Guía de contribución](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -248,3 +255,10 @@ Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En
 ## Licencia
 
 Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.
+## Divulgación de Seguridad
+
+Para proteger tu privacidad, evita publicar problemas de seguridad en GitHub. En su lugar, envía tus preguntas a security@dify.ai y te proporcionaremos una respuesta más detallada.
+
+## Licencia
+
+Este repositorio está disponible bajo la [Licencia de Código Abierto de Dify](LICENSE), que es esencialmente Apache 2.0 con algunas restricciones adicionales.

README_FR.md

@@ -213,6 +213,13 @@ Déployez Dify sur une plateforme cloud en un clic en utilisant [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform par @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Utilisation d'AWS CDK pour le déploiement
+
+Déployez Dify sur AWS en utilisant [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK par @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuer
 
 Pour ceux qui souhaitent contribuer du code, consultez notre [Guide de contribution](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
@@ -246,3 +253,10 @@ Pour protéger votre vie privée, veuillez éviter de publier des problèmes de
 ## Licence
 
 Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.
+## Divulgation de sécurité
+
+Pour protéger votre vie privée, veuillez éviter de publier des problèmes de sécurité sur GitHub. Au lieu de cela, envoyez vos questions à security@dify.ai et nous vous fournirons une réponse plus détaillée.
+
+## Licence
+
+Ce référentiel est disponible sous la [Licence open source Dify](LICENSE), qui est essentiellement l'Apache 2.0 avec quelques restrictions supplémentaires.

README_JA.md

@@ -212,6 +212,13 @@ docker compose up -d
 ##### Google Cloud
 - [@sotazumによるGoogle Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK を使用したデプロイ
+
+[CDK](https://aws.amazon.com/cdk/) を使用して、DifyをAWSにデプロイします
+
+##### AWS 
+- [@KevinZhaoによるAWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 貢献
 
 コードに貢献したい方は、[Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)を参照してください。

README_KL.md

@@ -213,6 +213,13 @@ wa'logh nIqHom neH ghun deployment toy'wI' [terraform](https://www.terraform.io/
 ##### Google Cloud
 - [Google Cloud Terraform qachlot @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK atorlugh pilersitsineq
+
+wa'logh nIqHom neH ghun deployment toy'wI' [CDK](https://aws.amazon.com/cdk/) lo'laH.
+
+##### AWS 
+- [AWS CDK qachlot @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contributing
 
 For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_KR.md

@@ -205,6 +205,13 @@ Dify를 Kubernetes에 배포하고 프리미엄 스케일링 설정을 구성했
 ##### Google Cloud
 - [sotazum의 Google Cloud Terraform](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK를 사용한 배포
+
+[CDK](https://aws.amazon.com/cdk/)를 사용하여 AWS에 Dify 배포
+
+##### AWS 
+- [KevinZhao의 AWS CDK](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## 기여
 
 코드에 기여하고 싶은 분들은 [기여 가이드](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md)를 참조하세요.

README_PT.md

@@ -211,6 +211,13 @@ Implante o Dify na Plataforma Cloud com um único clique usando [terraform](http
 ##### Google Cloud
 - [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Usando AWS CDK para Implantação
+
+Implante o Dify na AWS usando [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK por @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Contribuindo
 
 Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 

README_SI.md

@@ -145,6 +145,13 @@ namestite Dify v Cloud Platform z enim klikom z uporabo [terraform](https://www.
 ##### Google Cloud
 - [Google Cloud Terraform by @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Uporaba AWS CDK za uvajanje
+
+Uvedite Dify v AWS z uporabo [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK by @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Prispevam
 
 Za tiste, ki bi radi prispevali kodo, si oglejte naš vodnik za prispevke . Hkrati vas prosimo, da podprete Dify tako, da ga delite na družbenih medijih ter na dogodkih in konferencah. 

README_TR.md

@@ -211,6 +211,13 @@ Dify'ı bulut platformuna tek tıklamayla dağıtın [terraform](https://www.ter
 ##### Google Cloud
 - [Google Cloud Terraform tarafından @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### AWS CDK ile Dağıtım
+
+[CDK](https://aws.amazon.com/cdk/) kullanarak Dify'ı AWS'ye dağıtın
+
+##### AWS 
+- [AWS CDK tarafından @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Katkıda Bulunma
 
 Kod katkısında bulunmak isteyenler için [Katkı Kılavuzumuza](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) bakabilirsiniz.

README_VI.md

@@ -207,6 +207,13 @@ Triển khai Dify lên nền tảng đám mây với một cú nhấp chuột b
 ##### Google Cloud
 - [Google Cloud Terraform bởi @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
 
+#### Sử dụng AWS CDK để Triển khai
+
+Triển khai Dify trên AWS bằng [CDK](https://aws.amazon.com/cdk/)
+
+##### AWS 
+- [AWS CDK bởi @KevinZhao](https://github.com/aws-samples/solution-for-deploying-dify-on-aws)
+
 ## Đóng góp
 
 Đối với những người muốn đóng góp mã, xem [Hướng dẫn Đóng góp](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) của chúng tôi. 

api/.env.example

@@ -56,20 +56,27 @@ DB_DATABASE=dify
 
 # Storage configuration
 # use for store upload files, private keys...
-# storage type: local, s3, aliyun-oss, azure-blob, baidu-obs, google-storage, huawei-obs, oci-storage, tencent-cos, volcengine-tos, supabase
-STORAGE_TYPE=local
-STORAGE_LOCAL_PATH=storage
+# storage type: opendal, s3, aliyun-oss, azure-blob, baidu-obs, google-storage, huawei-obs, oci-storage, tencent-cos, volcengine-tos, supabase
+STORAGE_TYPE=opendal
+
+# Apache OpenDAL storage configuration, refer to https://github.com/apache/opendal
+OPENDAL_SCHEME=fs
+OPENDAL_FS_ROOT=storage
+
+# S3 Storage configuration
 S3_USE_AWS_MANAGED_IAM=false
-S3_ENDPOINT=https://your-bucket-name.storage.s3.clooudflare.com
+S3_ENDPOINT=https://your-bucket-name.storage.s3.cloudflare.com
 S3_BUCKET_NAME=your-bucket-name
 S3_ACCESS_KEY=your-access-key
 S3_SECRET_KEY=your-secret-key
 S3_REGION=your-region
+
 # Azure Blob Storage configuration
 AZURE_BLOB_ACCOUNT_NAME=your-account-name
 AZURE_BLOB_ACCOUNT_KEY=your-account-key
-AZURE_BLOB_CONTAINER_NAME=yout-container-name
+AZURE_BLOB_CONTAINER_NAME=your-container-name
 AZURE_BLOB_ACCOUNT_URL=https://<your_account_name>.blob.core.windows.net
+
 # Aliyun oss Storage configuration
 ALIYUN_OSS_BUCKET_NAME=your-bucket-name
 ALIYUN_OSS_ACCESS_KEY=your-access-key
@@ -79,8 +86,9 @@ ALIYUN_OSS_AUTH_VERSION=v1
 ALIYUN_OSS_REGION=your-region
 # Don't start with '/'. OSS doesn't support leading slash in object names.
 ALIYUN_OSS_PATH=your-path
+
 # Google Storage configuration
-GOOGLE_STORAGE_BUCKET_NAME=yout-bucket-name
+GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name
 GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64=your-google-service-account-json-base64-string
 
 # Tencent COS Storage configuration
@@ -125,8 +133,8 @@ SUPABASE_URL=your-server-url
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-
-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase
+# Vector database configuration
+# support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -277,6 +285,7 @@ VIKINGDB_SOCKET_TIMEOUT=30
 LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
 LINDORM_USERNAME=admin
 LINDORM_PASSWORD=admin
+USING_UGC_INDEX=False
 
 # OceanBase Vector configuration
 OCEANBASE_VECTOR_HOST=127.0.0.1
@@ -295,8 +304,7 @@ UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
 UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 
 # Model configuration
-MULTIMODAL_SEND_IMAGE_FORMAT=base64
-MULTIMODAL_SEND_VIDEO_FORMAT=base64
+MULTIMODAL_SEND_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
 CODE_GENERATION_MAX_TOKENS=1024
 
@@ -329,6 +337,7 @@ NOTION_INTERNAL_SECRET=you-internal-secret
 ETL_TYPE=dify
 UNSTRUCTURED_API_URL=
 UNSTRUCTURED_API_KEY=
+SCARF_NO_ANALYTICS=true
 
 #ssrf
 SSRF_PROXY_HTTP_URL=
@@ -380,14 +389,17 @@ LOG_FILE_BACKUP_COUNT=5
 LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
 # Log Timezone
 LOG_TZ=UTC
+# Log format
+LOG_FORMAT=%(asctime)s,%(msecs)d %(levelname)-2s [%(filename)s:%(lineno)d] %(req_id)s %(message)s
 
 # Indexing configuration
-INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
+INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000
 
 # Workflow runtime configuration
 WORKFLOW_MAX_EXECUTION_STEPS=500
 WORKFLOW_MAX_EXECUTION_TIME=1200
 WORKFLOW_CALL_MAX_DEPTH=5
+WORKFLOW_PARALLEL_DEPTH_LIMIT=3
 MAX_VARIABLE_SIZE=204800
 
 # App configuration
@@ -410,4 +422,9 @@ POSITION_PROVIDER_EXCLUDES=
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
 
-CREATE_TIDB_SERVICE_JOB_ENABLED=false
+CREATE_TIDB_SERVICE_JOB_ENABLED=false
+
+# Maximum number of submitted thread count in a ThreadPool for parallel node execution
+MAX_SUBMIT_COUNT=100
+# Lockout duration in seconds
+LOGIN_LOCKOUT_DURATION=86400

api/.ruff.toml

@@ -0,0 +1,95 @@
+exclude = [
+    "migrations/*",
+]
+line-length = 120
+
+[format]
+quote-style = "double"
+
+[lint]
+preview = true
+select = [
+    "B", # flake8-bugbear rules
+    "C4", # flake8-comprehensions
+    "E", # pycodestyle E rules
+    "F", # pyflakes rules
+    "FURB", # refurb rules
+    "I", # isort rules
+    "N", # pep8-naming
+    "PT", # flake8-pytest-style rules
+    "PLC0208", # iteration-over-set
+    "PLC2801", # unnecessary-dunder-call
+    "PLC0414", # useless-import-alias
+    "PLE0604", # invalid-all-object
+    "PLE0605", # invalid-all-format
+    "PLR0402", # manual-from-import
+    "PLR1711", # useless-return
+    "PLR1714", # repeated-equality-comparison
+    "RUF013", # implicit-optional
+    "RUF019", # unnecessary-key-check
+    "RUF100", # unused-noqa
+    "RUF101", # redirected-noqa
+    "RUF200", # invalid-pyproject-toml
+    "RUF022", # unsorted-dunder-all
+    "S506", # unsafe-yaml-load
+    "SIM", # flake8-simplify rules
+    "TRY400", # error-instead-of-exception
+    "TRY401", # verbose-log-message
+    "UP", # pyupgrade rules
+    "W191", # tab-indentation
+    "W605", # invalid-escape-sequence
+]
+
+ignore = [
+    "E402", # module-import-not-at-top-of-file
+    "E711", # none-comparison
+    "E712", # true-false-comparison
+    "E721", # type-comparison
+    "E722", # bare-except
+    "E731", # lambda-assignment
+    "F821", # undefined-name
+    "F841", # unused-variable
+    "FURB113", # repeated-append
+    "FURB152", # math-constant
+    "UP007", # non-pep604-annotation
+    "UP032", # f-string
+    "B005", # strip-with-multi-characters
+    "B006", # mutable-argument-default
+    "B007", # unused-loop-control-variable
+    "B026", # star-arg-unpacking-after-keyword-arg
+    "B904", # raise-without-from-inside-except
+    "B905", # zip-without-explicit-strict
+    "N806", # non-lowercase-variable-in-function
+    "N815", # mixed-case-variable-in-class-scope
+    "PT011", # pytest-raises-too-broad
+    "SIM102", # collapsible-if
+    "SIM103", # needless-bool
+    "SIM105", # suppressible-exception
+    "SIM107", # return-in-try-except-finally
+    "SIM108", # if-else-block-instead-of-if-exp
+    "SIM113", # enumerate-for-loop
+    "SIM117", # multiple-with-statements
+    "SIM210", # if-expr-with-true-false
+]
+
+[lint.per-file-ignores]
+"__init__.py" = [
+    "F401", # unused-import
+    "F811", # redefined-while-unused
+]
+"configs/*" = [
+    "N802", # invalid-function-name
+]
+"libs/gmpy2_pkcs10aep_cipher.py" = [
+    "N803", # invalid-argument-name
+]
+"tests/*" = [
+    "F811", # redefined-while-unused
+    "F401", # unused-import
+]
+
+[lint.pyflakes]
+extend-generics = [
+    "_pytest.monkeypatch",
+    "tests.integration_tests",
+]

api/Dockerfile

@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-7 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/app.py

@@ -1,113 +1,30 @@
-import os
-import sys
+from libs import version_utils
 
-python_version = sys.version_info
-if not ((3, 11) <= python_version < (3, 13)):
-    print(f"Python 3.11 or 3.12 is required, current version is {python_version.major}.{python_version.minor}")
-    raise SystemExit(1)
-
-from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-import threading
-import time
-import warnings
-
-from flask import Response
-
-from app_factory import create_app
-
-# DO NOT REMOVE BELOW
-from events import event_handlers  # noqa: F401
-from extensions.ext_database import db
-
-# TODO: Find a way to avoid importing models here
-from models import account, dataset, model, source, task, tool, tools, web  # noqa: F401
-
-# DO NOT REMOVE ABOVE
+# preparation before creating app
+version_utils.check_supported_python_version()
 
 
-warnings.simplefilter("ignore", ResourceWarning)
+def is_db_command():
+    import sys
 
-os.environ["TZ"] = "UTC"
-# windows platform not support tzset
-if hasattr(time, "tzset"):
-    time.tzset()
+    if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
+        return True
+    return False
 
 
 # create app
-app = create_app()
-celery = app.extensions["celery"]
+if is_db_command():
+    from app_factory import create_migrations_app
 
-if dify_config.TESTING:
-    print("App is running in TESTING mode")
+    app = create_migrations_app()
+else:
+    from app_factory import create_app
+    from libs import threadings_utils
 
+    threadings_utils.apply_gevent_threading_patch()
 
-@app.after_request
-def after_request(response):
-    """Add Version headers to the response."""
-    response.headers.add("X-Version", dify_config.CURRENT_VERSION)
-    response.headers.add("X-Env", dify_config.DEPLOY_ENV)
-    return response
-
-
-@app.route("/health")
-def health():
-    return Response(
-        json.dumps({"pid": os.getpid(), "status": "ok", "version": dify_config.CURRENT_VERSION}),
-        status=200,
-        content_type="application/json",
-    )
-
-
-@app.route("/threads")
-def threads():
-    num_threads = threading.active_count()
-    threads = threading.enumerate()
-
-    thread_list = []
-    for thread in threads:
-        thread_name = thread.name
-        thread_id = thread.ident
-        is_alive = thread.is_alive()
-
-        thread_list.append(
-            {
-                "name": thread_name,
-                "id": thread_id,
-                "is_alive": is_alive,
-            }
-        )
-
-    return {
-        "pid": os.getpid(),
-        "thread_num": num_threads,
-        "threads": thread_list,
-    }
-
-
-@app.route("/db-pool-stat")
-def pool_stat():
-    engine = db.engine
-    return {
-        "pid": os.getpid(),
-        "pool_size": engine.pool.size(),
-        "checked_in_connections": engine.pool.checkedin(),
-        "checked_out_connections": engine.pool.checkedout(),
-        "overflow_connections": engine.pool.overflow(),
-        "connection_timeout": engine.pool.timeout(),
-        "recycle_time": db.engine.pool._recycle,
-    }
-
+    app = create_app()
+    celery = app.extensions["celery"]
 
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=5001)

api/app_factory.py

@@ -1,54 +1,14 @@
-import os
+import logging
+import time
 
 from configs import dify_config
-
-if not dify_config.DEBUG:
-    from gevent import monkey
-
-    monkey.patch_all()
-
-    import grpc.experimental.gevent
-
-    grpc.experimental.gevent.init_gevent()
-
-import json
-
-from flask import Flask, Response, request
-from flask_cors import CORS
-from werkzeug.exceptions import Unauthorized
-
-import contexts
-from commands import register_commands
-from configs import dify_config
-from extensions import (
-    ext_celery,
-    ext_code_based_extension,
-    ext_compress,
-    ext_database,
-    ext_hosting_provider,
-    ext_logging,
-    ext_login,
-    ext_mail,
-    ext_migrate,
-    ext_proxy_fix,
-    ext_redis,
-    ext_sentry,
-    ext_storage,
-)
-from extensions.ext_database import db
-from extensions.ext_login import login_manager
-from libs.passport import PassportService
-from services.account_service import AccountService
-
-
-class DifyApp(Flask):
-    pass
+from dify_app import DifyApp
 
 
 # ----------------------------
 # Application Factory Function
 # ----------------------------
-def create_flask_app_with_configs() -> Flask:
+def create_flask_app_with_configs() -> DifyApp:
     """
     create a raw flask app
     with configs loaded from .env file
@@ -56,123 +16,86 @@ def create_flask_app_with_configs() -> Flask:
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
 
-    # populate configs into system environment variables
-    for key, value in dify_app.config.items():
-        if isinstance(value, str):
-            os.environ[key] = value
-        elif isinstance(value, int | float | bool):
-            os.environ[key] = str(value)
-        elif value is None:
-            os.environ[key] = ""
-
     return dify_app
 
 
-def create_app() -> Flask:
+def create_app() -> DifyApp:
+    start_time = time.perf_counter()
     app = create_flask_app_with_configs()
-    app.secret_key = dify_config.SECRET_KEY
     initialize_extensions(app)
-    register_blueprints(app)
-    register_commands(app)
-
+    end_time = time.perf_counter()
+    if dify_config.DEBUG:
+        logging.info(f"Finished create_app ({round((end_time - start_time) * 1000, 2)} ms)")
     return app
 
 
-def initialize_extensions(app):
-    # Since the application instance is now created, pass it to each Flask
-    # extension instance to bind it to the Flask application instance (app)
-    ext_logging.init_app(app)
-    ext_compress.init_app(app)
-    ext_code_based_extension.init()
+def initialize_extensions(app: DifyApp):
+    from extensions import (
+        ext_app_metrics,
+        ext_blueprints,
+        ext_celery,
+        ext_code_based_extension,
+        ext_commands,
+        ext_compress,
+        ext_database,
+        ext_hosting_provider,
+        ext_import_modules,
+        ext_logging,
+        ext_login,
+        ext_mail,
+        ext_migrate,
+        ext_proxy_fix,
+        ext_redis,
+        ext_sentry,
+        ext_set_secretkey,
+        ext_storage,
+        ext_timezone,
+        ext_warnings,
+    )
+
+    extensions = [
+        ext_timezone,
+        ext_logging,
+        ext_warnings,
+        ext_import_modules,
+        ext_set_secretkey,
+        ext_compress,
+        ext_code_based_extension,
+        ext_database,
+        ext_app_metrics,
+        ext_migrate,
+        ext_redis,
+        ext_storage,
+        ext_celery,
+        ext_login,
+        ext_mail,
+        ext_hosting_provider,
+        ext_sentry,
+        ext_proxy_fix,
+        ext_blueprints,
+        ext_commands,
+    ]
+    for ext in extensions:
+        short_name = ext.__name__.split(".")[-1]
+        is_enabled = ext.is_enabled() if hasattr(ext, "is_enabled") else True
+        if not is_enabled:
+            if dify_config.DEBUG:
+                logging.info(f"Skipped {short_name}")
+            continue
+
+        start_time = time.perf_counter()
+        ext.init_app(app)
+        end_time = time.perf_counter()
+        if dify_config.DEBUG:
+            logging.info(f"Loaded {short_name} ({round((end_time - start_time) * 1000, 2)} ms)")
+
+
+def create_migrations_app():
+    app = create_flask_app_with_configs()
+    from extensions import ext_database, ext_migrate
+
+    # Initialize only required extensions
     ext_database.init_app(app)
-    ext_migrate.init(app, db)
-    ext_redis.init_app(app)
-    ext_storage.init_app(app)
-    ext_celery.init_app(app)
-    ext_login.init_app(app)
-    ext_mail.init_app(app)
-    ext_hosting_provider.init_app(app)
-    ext_sentry.init_app(app)
-    ext_proxy_fix.init_app(app)
+    ext_migrate.init_app(app)
 
-
-# Flask-Login configuration
-@login_manager.request_loader
-def load_user_from_request(request_from_flask_login):
-    """Load user based on the request."""
-    if request.blueprint not in {"console", "inner_api"}:
-        return None
-    # Check if the user_id contains a dot, indicating the old format
-    auth_header = request.headers.get("Authorization", "")
-    if not auth_header:
-        auth_token = request.args.get("_token")
-        if not auth_token:
-            raise Unauthorized("Invalid Authorization token.")
-    else:
-        if " " not in auth_header:
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-        auth_scheme, auth_token = auth_header.split(None, 1)
-        auth_scheme = auth_scheme.lower()
-        if auth_scheme != "bearer":
-            raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
-
-    decoded = PassportService().verify(auth_token)
-    user_id = decoded.get("user_id")
-
-    logged_in_account = AccountService.load_logged_in_account(account_id=user_id)
-    if logged_in_account:
-        contexts.tenant_id.set(logged_in_account.current_tenant_id)
-    return logged_in_account
-
-
-@login_manager.unauthorized_handler
-def unauthorized_handler():
-    """Handle unauthorized requests."""
-    return Response(
-        json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
-        status=401,
-        content_type="application/json",
-    )
-
-
-# register blueprint routers
-def register_blueprints(app):
-    from controllers.console import bp as console_app_bp
-    from controllers.files import bp as files_bp
-    from controllers.inner_api import bp as inner_api_bp
-    from controllers.service_api import bp as service_api_bp
-    from controllers.web import bp as web_bp
-
-    CORS(
-        service_api_bp,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-    )
-    app.register_blueprint(service_api_bp)
-
-    CORS(
-        web_bp,
-        resources={r"/*": {"origins": dify_config.WEB_API_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization", "X-App-Code"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(web_bp)
-
-    CORS(
-        console_app_bp,
-        resources={r"/*": {"origins": dify_config.CONSOLE_CORS_ALLOW_ORIGINS}},
-        supports_credentials=True,
-        allow_headers=["Content-Type", "Authorization"],
-        methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
-        expose_headers=["X-Version", "X-Env"],
-    )
-
-    app.register_blueprint(console_app_bp)
-
-    CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
-    app.register_blueprint(files_bp)
-
-    app.register_blueprint(inner_api_bp)
+    return app

api/commands.py

@@ -159,8 +159,7 @@ def migrate_annotation_vector_database():
         try:
             # get apps info
             apps = (
-                db.session.query(App)
-                .filter(App.status == "normal")
+                App.query.filter(App.status == "normal")
                 .order_by(App.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -259,7 +258,7 @@ def migrate_knowledge_vector_database():
     skipped_count = 0
     total_count = 0
     vector_type = dify_config.VECTOR_STORE
-    upper_colletion_vector_types = {
+    upper_collection_vector_types = {
         VectorType.MILVUS,
         VectorType.PGVECTOR,
         VectorType.RELYT,
@@ -267,7 +266,7 @@ def migrate_knowledge_vector_database():
         VectorType.ORACLE,
         VectorType.ELASTICSEARCH,
     }
-    lower_colletion_vector_types = {
+    lower_collection_vector_types = {
         VectorType.ANALYTICDB,
         VectorType.CHROMA,
         VectorType.MYSCALE,
@@ -285,8 +284,7 @@ def migrate_knowledge_vector_database():
     while True:
         try:
             datasets = (
-                db.session.query(Dataset)
-                .filter(Dataset.indexing_technique == "high_quality")
+                Dataset.query.filter(Dataset.indexing_technique == "high_quality")
                 .order_by(Dataset.created_at.desc())
                 .paginate(page=page, per_page=50)
             )
@@ -307,7 +305,7 @@ def migrate_knowledge_vector_database():
                         continue
                 collection_name = ""
                 dataset_id = dataset.id
-                if vector_type in upper_colletion_vector_types:
+                if vector_type in upper_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id)
                 elif vector_type == VectorType.QDRANT:
                     if dataset.collection_binding_id:
@@ -323,7 +321,7 @@ def migrate_knowledge_vector_database():
                     else:
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
 
-                elif vector_type in lower_colletion_vector_types:
+                elif vector_type in lower_collection_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
@@ -450,7 +448,8 @@ def convert_to_agent_apps():
                 if app_id not in proceeded_app_ids:
                     proceeded_app_ids.append(app_id)
                     app = db.session.query(App).filter(App.id == app_id).first()
-                    apps.append(app)
+                    if app is not None:
+                        apps.append(app)
 
             if len(apps) == 0:
                 break
@@ -555,14 +554,20 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str
     if language not in languages:
         language = "en-US"
 
-    name = name.strip()
+    # Validates name encoding for non-Latin characters.
+    name = name.strip().encode("utf-8").decode("utf-8") if name else None
 
     # generate random password
     new_password = secrets.token_urlsafe(16)
 
     # register account
-    account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
-
+    account = RegisterService.register(
+        email=email,
+        name=account_name,
+        password=new_password,
+        language=language,
+        create_workspace_required=False,
+    )
     TenantService.create_owner_tenant_if_not_exist(account, name)
 
     click.echo(
@@ -582,7 +587,7 @@ def upgrade_db():
             click.echo(click.style("Starting database migration.", fg="green"))
 
             # run db migration
-            import flask_migrate
+            import flask_migrate  # type: ignore
 
             flask_migrate.upgrade()
 
@@ -620,6 +625,10 @@ where sites.id is null limit 1000"""
 
                 try:
                     app = db.session.query(App).filter(App.id == app_id).first()
+                    if not app:
+                        print(f"App {app_id} not found")
+                        continue
+
                     tenant = app.tenant
                     if tenant:
                         accounts = tenant.get_accounts()
@@ -640,15 +649,3 @@ where sites.id is null limit 1000"""
                 break
 
     click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))
-
-
-def register_commands(app):
-    app.cli.add_command(reset_password)
-    app.cli.add_command(reset_email)
-    app.cli.add_command(reset_encrypt_key_pair)
-    app.cli.add_command(vdb_migrate)
-    app.cli.add_command(convert_to_agent_apps)
-    app.cli.add_command(add_qdrant_doc_id_index)
-    app.cli.add_command(create_tenant)
-    app.cli.add_command(upgrade_db)
-    app.cli.add_command(fix_app_site_missing)

api/configs/app_config.py

@@ -1,11 +1,51 @@
-from pydantic_settings import SettingsConfigDict
+import logging
+from typing import Any
 
-from configs.deploy import DeploymentConfig
-from configs.enterprise import EnterpriseFeatureConfig
-from configs.extra import ExtraServiceConfig
-from configs.feature import FeatureConfig
-from configs.middleware import MiddlewareConfig
-from configs.packaging import PackagingInfo
+from pydantic.fields import FieldInfo
+from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, SettingsConfigDict
+
+from .deploy import DeploymentConfig
+from .enterprise import EnterpriseFeatureConfig
+from .extra import ExtraServiceConfig
+from .feature import FeatureConfig
+from .middleware import MiddlewareConfig
+from .packaging import PackagingInfo
+from .remote_settings_sources import RemoteSettingsSource, RemoteSettingsSourceConfig, RemoteSettingsSourceName
+from .remote_settings_sources.apollo import ApolloSettingsSource
+
+logger = logging.getLogger(__name__)
+
+
+class RemoteSettingsSourceFactory(PydanticBaseSettingsSource):
+    def __init__(self, settings_cls: type[BaseSettings]):
+        super().__init__(settings_cls)
+
+    def get_field_value(self, field: FieldInfo, field_name: str) -> tuple[Any, str, bool]:
+        raise NotImplementedError
+
+    def __call__(self) -> dict[str, Any]:
+        current_state = self.current_state
+        remote_source_name = current_state.get("REMOTE_SETTINGS_SOURCE_NAME")
+        if not remote_source_name:
+            return {}
+
+        remote_source: RemoteSettingsSource | None = None
+        match remote_source_name:
+            case RemoteSettingsSourceName.APOLLO:
+                remote_source = ApolloSettingsSource(current_state)
+            case _:
+                logger.warning(f"Unsupported remote source: {remote_source_name}")
+                return {}
+
+        d: dict[str, Any] = {}
+
+        for field_name, field in self.settings_cls.model_fields.items():
+            field_value, field_key, value_is_complex = remote_source.get_field_value(field, field_name)
+            field_value = remote_source.prepare_field_value(field_name, field, field_value, value_is_complex)
+            if field_value is not None:
+                d[field_key] = field_value
+
+        return d
 
 
 class DifyConfig(
@@ -19,6 +59,8 @@ class DifyConfig(
     MiddlewareConfig,
     # Extra service configs
     ExtraServiceConfig,
+    # Remote source configs
+    RemoteSettingsSourceConfig,
     # Enterprise feature configs
     # **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
     EnterpriseFeatureConfig,
@@ -35,3 +77,20 @@ class DifyConfig(
     # please consider to arrange it in the proper config group of existed or added
     # for better readability and maintainability.
     # Thanks for your concentration and consideration.
+
+    @classmethod
+    def settings_customise_sources(
+        cls,
+        settings_cls: type[BaseSettings],
+        init_settings: PydanticBaseSettingsSource,
+        env_settings: PydanticBaseSettingsSource,
+        dotenv_settings: PydanticBaseSettingsSource,
+        file_secret_settings: PydanticBaseSettingsSource,
+    ) -> tuple[PydanticBaseSettingsSource, ...]:
+        return (
+            init_settings,
+            env_settings,
+            RemoteSettingsSourceFactory(settings_cls),
+            dotenv_settings,
+            file_secret_settings,
+        )

api/configs/deploy/__init__.py

@@ -17,11 +17,6 @@ class DeploymentConfig(BaseSettings):
         default=False,
     )
 
-    TESTING: bool = Field(
-        description="Enable testing mode for running automated tests",
-        default=False,
-    )
-
     EDITION: str = Field(
         description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
         default="SELF_HOSTED",

api/configs/feature/__init__.py

@@ -239,7 +239,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_CONSOLE_CORS_ALLOW_ORIGINS.split(",")
 
@@ -250,7 +249,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
@@ -433,12 +431,28 @@ class WorkflowConfig(BaseSettings):
         default=5,
     )
 
+    WORKFLOW_PARALLEL_DEPTH_LIMIT: PositiveInt = Field(
+        description="Maximum allowed depth for nested parallel executions",
+        default=3,
+    )
+
     MAX_VARIABLE_SIZE: PositiveInt = Field(
         description="Maximum size in bytes for a single variable in workflows. Default to 200 KB.",
         default=200 * 1024,
     )
 
 
+class WorkflowNodeExecutionConfig(BaseSettings):
+    """
+    Configuration for workflow node execution
+    """
+
+    MAX_SUBMIT_COUNT: PositiveInt = Field(
+        description="Maximum number of submitted thread count in a ThreadPool for parallel node execution",
+        default=100,
+    )
+
+
 class AuthConfig(BaseSettings):
     """
     Configuration for authentication and OAuth
@@ -474,6 +488,11 @@ class AuthConfig(BaseSettings):
         default=60,
     )
 
+    LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
+        default=86400,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -585,6 +604,11 @@ class RagEtlConfig(BaseSettings):
         default=None,
     )
 
+    SCARF_NO_ANALYTICS: Optional[str] = Field(
+        description="This is about whether to disable Scarf analytics in Unstructured library.",
+        default="false",
+    )
+
 
 class DataSetConfig(BaseSettings):
     """
@@ -640,18 +664,13 @@ class IndexingConfig(BaseSettings):
 
     INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: PositiveInt = Field(
         description="Maximum token length for text segmentation during indexing",
-        default=1000,
+        default=4000,
     )
 
 
-class VisionFormatConfig(BaseSettings):
-    MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
-        description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
-        default="base64",
-    )
-
-    MULTIMODAL_SEND_VIDEO_FORMAT: Literal["base64", "url"] = Field(
-        description="Format for sending videos in multimodal contexts ('base64' or 'url'), default is base64",
+class MultiModalTransferConfig(BaseSettings):
+    MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
+        description="Format for sending files in multimodal contexts ('base64' or 'url'), default is base64",
         default="base64",
     )
 
@@ -694,27 +713,27 @@ class PositionConfig(BaseSettings):
         default="",
     )
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_PROVIDER_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_PROVIDER_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_PROVIDER_EXCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_PINS_LIST(self) -> list[str]:
         return [item.strip() for item in self.POSITION_TOOL_PINS.split(",") if item.strip() != ""]
 
-    @computed_field
+    @property
     def POSITION_TOOL_INCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_INCLUDES.split(",") if item.strip() != ""}
 
-    @computed_field
+    @property
     def POSITION_TOOL_EXCLUDES_SET(self) -> set[str]:
         return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(",") if item.strip() != ""}
 
@@ -757,19 +776,20 @@ class FeatureConfig(
     FileAccessConfig,
     FileUploadConfig,
     HttpConfig,
-    VisionFormatConfig,
     InnerAPIConfig,
     IndexingConfig,
     LoggingConfig,
     MailConfig,
     ModelLoadBalanceConfig,
     ModerationConfig,
+    MultiModalTransferConfig,
     PositionConfig,
     RagEtlConfig,
     SecurityConfig,
     ToolConfig,
     UpdateConfig,
     WorkflowConfig,
+    WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
     # hosted services config

api/configs/middleware/__init__.py

@@ -1,54 +1,69 @@
-from typing import Any, Optional
+from typing import Any, Literal, Optional
 from urllib.parse import quote_plus
 
 from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed_field
 from pydantic_settings import BaseSettings
 
-from configs.middleware.cache.redis_config import RedisConfig
-from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
-from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
-from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
-from configs.middleware.storage.baidu_obs_storage_config import BaiduOBSStorageConfig
-from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
-from configs.middleware.storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
-from configs.middleware.storage.oci_storage_config import OCIStorageConfig
-from configs.middleware.storage.supabase_storage_config import SupabaseStorageConfig
-from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
-from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
-from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
-from configs.middleware.vdb.baidu_vector_config import BaiduVectorDBConfig
-from configs.middleware.vdb.chroma_config import ChromaConfig
-from configs.middleware.vdb.couchbase_config import CouchbaseConfig
-from configs.middleware.vdb.elasticsearch_config import ElasticsearchConfig
-from configs.middleware.vdb.lindorm_config import LindormConfig
-from configs.middleware.vdb.milvus_config import MilvusConfig
-from configs.middleware.vdb.myscale_config import MyScaleConfig
-from configs.middleware.vdb.oceanbase_config import OceanBaseVectorConfig
-from configs.middleware.vdb.opensearch_config import OpenSearchConfig
-from configs.middleware.vdb.oracle_config import OracleConfig
-from configs.middleware.vdb.pgvector_config import PGVectorConfig
-from configs.middleware.vdb.pgvectors_config import PGVectoRSConfig
-from configs.middleware.vdb.qdrant_config import QdrantConfig
-from configs.middleware.vdb.relyt_config import RelytConfig
-from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
-from configs.middleware.vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
-from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
-from configs.middleware.vdb.upstash_config import UpstashConfig
-from configs.middleware.vdb.vikingdb_config import VikingDBConfig
-from configs.middleware.vdb.weaviate_config import WeaviateConfig
+from .cache.redis_config import RedisConfig
+from .storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
+from .storage.amazon_s3_storage_config import S3StorageConfig
+from .storage.azure_blob_storage_config import AzureBlobStorageConfig
+from .storage.baidu_obs_storage_config import BaiduOBSStorageConfig
+from .storage.google_cloud_storage_config import GoogleCloudStorageConfig
+from .storage.huawei_obs_storage_config import HuaweiCloudOBSStorageConfig
+from .storage.oci_storage_config import OCIStorageConfig
+from .storage.opendal_storage_config import OpenDALStorageConfig
+from .storage.supabase_storage_config import SupabaseStorageConfig
+from .storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
+from .storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
+from .vdb.analyticdb_config import AnalyticdbConfig
+from .vdb.baidu_vector_config import BaiduVectorDBConfig
+from .vdb.chroma_config import ChromaConfig
+from .vdb.couchbase_config import CouchbaseConfig
+from .vdb.elasticsearch_config import ElasticsearchConfig
+from .vdb.lindorm_config import LindormConfig
+from .vdb.milvus_config import MilvusConfig
+from .vdb.myscale_config import MyScaleConfig
+from .vdb.oceanbase_config import OceanBaseVectorConfig
+from .vdb.opensearch_config import OpenSearchConfig
+from .vdb.oracle_config import OracleConfig
+from .vdb.pgvector_config import PGVectorConfig
+from .vdb.pgvectors_config import PGVectoRSConfig
+from .vdb.qdrant_config import QdrantConfig
+from .vdb.relyt_config import RelytConfig
+from .vdb.tencent_vector_config import TencentVectorDBConfig
+from .vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
+from .vdb.tidb_vector_config import TiDBVectorConfig
+from .vdb.upstash_config import UpstashConfig
+from .vdb.vikingdb_config import VikingDBConfig
+from .vdb.weaviate_config import WeaviateConfig
 
 
 class StorageConfig(BaseSettings):
-    STORAGE_TYPE: str = Field(
+    STORAGE_TYPE: Literal[
+        "opendal",
+        "s3",
+        "aliyun-oss",
+        "azure-blob",
+        "baidu-obs",
+        "google-storage",
+        "huawei-obs",
+        "oci-storage",
+        "tencent-cos",
+        "volcengine-tos",
+        "supabase",
+        "local",
+    ] = Field(
         description="Type of storage to use."
-        " Options: 'local', 's3', 'aliyun-oss', 'azure-blob', 'baidu-obs', 'google-storage', 'huawei-obs', "
-        "'oci-storage', 'tencent-cos', 'volcengine-tos', 'supabase'. Default is 'local'.",
-        default="local",
+        " Options: 'opendal', '(deprecated) local', 's3', 'aliyun-oss', 'azure-blob', 'baidu-obs', 'google-storage', "
+        "'huawei-obs', 'oci-storage', 'tencent-cos', 'volcengine-tos', 'supabase'. Default is 'opendal'.",
+        default="opendal",
     )
 
     STORAGE_LOCAL_PATH: str = Field(
         description="Path for local storage when STORAGE_TYPE is set to 'local'.",
         default="storage",
+        deprecated=True,
     )
 
 
@@ -73,7 +88,7 @@ class KeywordStoreConfig(BaseSettings):
     )
 
 
-class DatabaseConfig:
+class DatabaseConfig(BaseSettings):
     DB_HOST: str = Field(
         description="Hostname or IP address of the database server.",
         default="localhost",
@@ -115,7 +130,6 @@ class DatabaseConfig:
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_DATABASE_URI(self) -> str:
         db_extras = (
             f"{self.DB_EXTRAS}&client_encoding={self.DB_CHARSET}" if self.DB_CHARSET else self.DB_EXTRAS
@@ -153,7 +167,6 @@ class DatabaseConfig:
     )
 
     @computed_field
-    @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -191,7 +204,6 @@ class CeleryConfig(DatabaseConfig):
     )
 
     @computed_field
-    @property
     def CELERY_RESULT_BACKEND(self) -> str | None:
         return (
             "db+{}".format(self.SQLALCHEMY_DATABASE_URI)
@@ -199,7 +211,6 @@ class CeleryConfig(DatabaseConfig):
             else self.CELERY_BROKER_URL
         )
 
-    @computed_field
     @property
     def BROKER_USE_SSL(self) -> bool:
         return self.CELERY_BROKER_URL.startswith("rediss://") if self.CELERY_BROKER_URL else False
@@ -235,6 +246,7 @@ class MiddlewareConfig(
     GoogleCloudStorageConfig,
     HuaweiCloudOBSStorageConfig,
     OCIStorageConfig,
+    OpenDALStorageConfig,
     S3StorageConfig,
     SupabaseStorageConfig,
     TencentCloudCOSStorageConfig,

api/configs/middleware/storage/baidu_obs_storage_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class BaiduOBSStorageConfig(BaseModel):
+class BaiduOBSStorageConfig(BaseSettings):
     """
     Configuration settings for Baidu Object Storage Service (OBS)
     """

api/configs/middleware/storage/huawei_obs_storage_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class HuaweiCloudOBSStorageConfig(BaseModel):
+class HuaweiCloudOBSStorageConfig(BaseSettings):
     """
     Configuration settings for Huawei Cloud Object Storage Service (OBS)
     """

api/configs/middleware/storage/opendal_storage_config.py

@@ -0,0 +1,9 @@
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class OpenDALStorageConfig(BaseSettings):
+    OPENDAL_SCHEME: str = Field(
+        default="fs",
+        description="OpenDAL scheme.",
+    )

api/configs/middleware/storage/supabase_storage_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class SupabaseStorageConfig(BaseModel):
+class SupabaseStorageConfig(BaseSettings):
     """
     Configuration settings for Supabase Object Storage Service
     """

api/configs/middleware/storage/volcengine_tos_storage_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class VolcengineTOSStorageConfig(BaseModel):
+class VolcengineTOSStorageConfig(BaseSettings):
     """
     Configuration settings for Volcengine Tinder Object Storage (TOS)
     """

api/configs/middleware/vdb/analyticdb_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field, PositiveInt
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
 
 
-class AnalyticdbConfig(BaseModel):
+class AnalyticdbConfig(BaseSettings):
     """
     Configuration for connecting to Alibaba Cloud AnalyticDB for PostgreSQL.
     Refer to the following documentation for details on obtaining credentials:

api/configs/middleware/vdb/couchbase_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class CouchbaseConfig(BaseModel):
+class CouchbaseConfig(BaseSettings):
     """
     Couchbase configs
     """

api/configs/middleware/vdb/lindorm_config.py

@@ -21,3 +21,14 @@ class LindormConfig(BaseSettings):
         description="Lindorm password",
         default=None,
     )
+    DEFAULT_INDEX_TYPE: Optional[str] = Field(
+        description="Lindorm Vector Index Type, hnsw or flat is available in dify",
+        default="hnsw",
+    )
+    DEFAULT_DISTANCE_TYPE: Optional[str] = Field(
+        description="Vector Distance Type, support l2, cosinesimil, innerproduct", default="l2"
+    )
+    USING_UGC_INDEX: Optional[bool] = Field(
+        description="Using UGC index will store the same type of Index in a single index but can retrieve separately.",
+        default=False,
+    )

api/configs/middleware/vdb/myscale_config.py

@@ -1,7 +1,8 @@
-from pydantic import BaseModel, Field, PositiveInt
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
 
 
-class MyScaleConfig(BaseModel):
+class MyScaleConfig(BaseSettings):
     """
     Configuration settings for MyScale vector database
     """

api/configs/middleware/vdb/vikingdb_config.py

@@ -1,9 +1,10 @@
 from typing import Optional
 
-from pydantic import BaseModel, Field
+from pydantic import Field
+from pydantic_settings import BaseSettings
 
 
-class VikingDBConfig(BaseModel):
+class VikingDBConfig(BaseSettings):
     """
     Configuration for connecting to Volcengine VikingDB.
     Refer to the following documentation for details on obtaining credentials:

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.12.1",
+        default="0.14.2",
     )
 
     COMMIT_SHA: str = Field(

api/configs/remote_settings_sources/__init__.py

@@ -0,0 +1,17 @@
+from typing import Optional
+
+from pydantic import Field
+
+from .apollo import ApolloSettingsSourceInfo
+from .base import RemoteSettingsSource
+from .enums import RemoteSettingsSourceName
+
+
+class RemoteSettingsSourceConfig(ApolloSettingsSourceInfo):
+    REMOTE_SETTINGS_SOURCE_NAME: RemoteSettingsSourceName | str = Field(
+        description="name of remote config source",
+        default="",
+    )
+
+
+__all__ = ["RemoteSettingsSource", "RemoteSettingsSourceConfig", "RemoteSettingsSourceName"]

api/configs/remote_settings_sources/apollo/__init__.py

@@ -0,0 +1,55 @@
+from collections.abc import Mapping
+from typing import Any, Optional
+
+from pydantic import Field
+from pydantic.fields import FieldInfo
+from pydantic_settings import BaseSettings
+
+from configs.remote_settings_sources.base import RemoteSettingsSource
+
+from .client import ApolloClient
+
+
+class ApolloSettingsSourceInfo(BaseSettings):
+    """
+    Packaging build information
+    """
+
+    APOLLO_APP_ID: Optional[str] = Field(
+        description="apollo app_id",
+        default=None,
+    )
+
+    APOLLO_CLUSTER: Optional[str] = Field(
+        description="apollo cluster",
+        default=None,
+    )
+
+    APOLLO_CONFIG_URL: Optional[str] = Field(
+        description="apollo config url",
+        default=None,
+    )
+
+    APOLLO_NAMESPACE: Optional[str] = Field(
+        description="apollo namespace",
+        default=None,
+    )
+
+
+class ApolloSettingsSource(RemoteSettingsSource):
+    def __init__(self, configs: Mapping[str, Any]):
+        self.client = ApolloClient(
+            app_id=configs["APOLLO_APP_ID"],
+            cluster=configs["APOLLO_CLUSTER"],
+            config_url=configs["APOLLO_CONFIG_URL"],
+            start_hot_update=False,
+            _notification_map={configs["APOLLO_NAMESPACE"]: -1},
+        )
+        self.namespace = configs["APOLLO_NAMESPACE"]
+        self.remote_configs = self.client.get_all_dicts(self.namespace)
+
+    def get_field_value(self, field: FieldInfo, field_name: str) -> tuple[Any, str, bool]:
+        if not isinstance(self.remote_configs, dict):
+            raise ValueError(f"remote configs is not dict, but {type(self.remote_configs)}")
+        field_value = self.remote_configs.get(field_name)
+        return field_value, field_name, False

api/configs/remote_settings_sources/apollo/client.py

@@ -0,0 +1,304 @@
+import hashlib
+import json
+import logging
+import os
+import threading
+import time
+from collections.abc import Mapping
+from pathlib import Path
+
+from .python_3x import http_request, makedirs_wrapper
+from .utils import (
+    CONFIGURATIONS,
+    NAMESPACE_NAME,
+    NOTIFICATION_ID,
+    get_value_from_dict,
+    init_ip,
+    no_key_cache_key,
+    signature,
+    url_encode_wrapper,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class ApolloClient:
+    def __init__(
+        self,
+        config_url,
+        app_id,
+        cluster="default",
+        secret="",
+        start_hot_update=True,
+        change_listener=None,
+        _notification_map=None,
+    ):
+        # Core routing parameters
+        self.config_url = config_url
+        self.cluster = cluster
+        self.app_id = app_id
+
+        # Non-core parameters
+        self.ip = init_ip()
+        self.secret = secret
+
+        # Check the parameter variables
+
+        # Private control variables
+        self._cycle_time = 5
+        self._stopping = False
+        self._cache = {}
+        self._no_key = {}
+        self._hash = {}
+        self._pull_timeout = 75
+        self._cache_file_path = os.path.expanduser("~") + "/.dify/config/remote-settings/apollo/cache/"
+        self._long_poll_thread = None
+        self._change_listener = change_listener  # "add" "delete" "update"
+        if _notification_map is None:
+            _notification_map = {"application": -1}
+        self._notification_map = _notification_map
+        self.last_release_key = None
+        # Private startup method
+        self._path_checker()
+        if start_hot_update:
+            self._start_hot_update()
+
+        # start the heartbeat thread
+        heartbeat = threading.Thread(target=self._heart_beat)
+        heartbeat.daemon = True
+        heartbeat.start()
+
+    def get_json_from_net(self, namespace="application"):
+        url = "{}/configs/{}/{}/{}?releaseKey={}&ip={}".format(
+            self.config_url, self.app_id, self.cluster, namespace, "", self.ip
+        )
+        try:
+            code, body = http_request(url, timeout=3, headers=self._sign_headers(url))
+            if code == 200:
+                if not body:
+                    logger.error(f"get_json_from_net load configs failed, body is {body}")
+                    return None
+                data = json.loads(body)
+                data = data["configurations"]
+                return_data = {CONFIGURATIONS: data}
+                return return_data
+            else:
+                return None
+        except Exception:
+            logger.exception("an error occurred in get_json_from_net")
+            return None
+
+    def get_value(self, key, default_val=None, namespace="application"):
+        try:
+            # read memory configuration
+            namespace_cache = self._cache.get(namespace)
+            val = get_value_from_dict(namespace_cache, key)
+            if val is not None:
+                return val
+
+            no_key = no_key_cache_key(namespace, key)
+            if no_key in self._no_key:
+                return default_val
+
+            # read the network configuration
+            namespace_data = self.get_json_from_net(namespace)
+            val = get_value_from_dict(namespace_data, key)
+            if val is not None:
+                self._update_cache_and_file(namespace_data, namespace)
+                return val
+
+            # read the file configuration
+            namespace_cache = self._get_local_cache(namespace)
+            val = get_value_from_dict(namespace_cache, key)
+            if val is not None:
+                self._update_cache_and_file(namespace_cache, namespace)
+                return val
+
+            # If all of them are not obtained, the default value is returned
+            # and the local cache is set to None
+            self._set_local_cache_none(namespace, key)
+            return default_val
+        except Exception:
+            logger.exception("get_value has error, [key is %s], [namespace is %s]", key, namespace)
+            return default_val
+
+    # Set the key of a namespace to none, and do not set default val
+    # to ensure the real-time correctness of the function call.
+    # If the user does not have the same default val twice
+    # and the default val is used here, there may be a problem.
+    def _set_local_cache_none(self, namespace, key):
+        no_key = no_key_cache_key(namespace, key)
+        self._no_key[no_key] = key
+
+    def _start_hot_update(self):
+        self._long_poll_thread = threading.Thread(target=self._listener)
+        # When the asynchronous thread is started, the daemon thread will automatically exit
+        # when the main thread is launched.
+        self._long_poll_thread.daemon = True
+        self._long_poll_thread.start()
+
+    def stop(self):
+        self._stopping = True
+        logger.info("Stopping listener...")
+
+    # Call the set callback function, and if it is abnormal, try it out
+    def _call_listener(self, namespace, old_kv, new_kv):
+        if self._change_listener is None:
+            return
+        if old_kv is None:
+            old_kv = {}
+        if new_kv is None:
+            new_kv = {}
+        try:
+            for key in old_kv:
+                new_value = new_kv.get(key)
+                old_value = old_kv.get(key)
+                if new_value is None:
+                    # If newValue is empty, it means key, and the value is deleted.
+                    self._change_listener("delete", namespace, key, old_value)
+                    continue
+                if new_value != old_value:
+                    self._change_listener("update", namespace, key, new_value)
+                    continue
+            for key in new_kv:
+                new_value = new_kv.get(key)
+                old_value = old_kv.get(key)
+                if old_value is None:
+                    self._change_listener("add", namespace, key, new_value)
+        except BaseException as e:
+            logger.warning(str(e))
+
+    def _path_checker(self):
+        if not os.path.isdir(self._cache_file_path):
+            makedirs_wrapper(self._cache_file_path)
+
+    # update the local cache and file cache
+    def _update_cache_and_file(self, namespace_data, namespace="application"):
+        # update the local cache
+        self._cache[namespace] = namespace_data
+        # update the file cache
+        new_string = json.dumps(namespace_data)
+        new_hash = hashlib.md5(new_string.encode("utf-8")).hexdigest()
+        if self._hash.get(namespace) == new_hash:
+            pass
+        else:
+            file_path = Path(self._cache_file_path) / f"{self.app_id}_configuration_{namespace}.txt"
+            file_path.write_text(new_string)
+            self._hash[namespace] = new_hash
+
+    # get the configuration from the local file
+    def _get_local_cache(self, namespace="application"):
+        cache_file_path = os.path.join(self._cache_file_path, f"{self.app_id}_configuration_{namespace}.txt")
+        if os.path.isfile(cache_file_path):
+            with open(cache_file_path) as f:
+                result = json.loads(f.readline())
+            return result
+        return {}
+
+    def _long_poll(self):
+        notifications = []
+        for key in self._cache:
+            namespace_data = self._cache[key]
+            notification_id = -1
+            if NOTIFICATION_ID in namespace_data:
+                notification_id = self._cache[key][NOTIFICATION_ID]
+            notifications.append({NAMESPACE_NAME: key, NOTIFICATION_ID: notification_id})
+        try:
+            # if the length is 0 it is returned directly
+            if len(notifications) == 0:
+                return
+            url = "{}/notifications/v2".format(self.config_url)
+            params = {
+                "appId": self.app_id,
+                "cluster": self.cluster,
+                "notifications": json.dumps(notifications, ensure_ascii=False),
+            }
+            param_str = url_encode_wrapper(params)
+            url = url + "?" + param_str
+            code, body = http_request(url, self._pull_timeout, headers=self._sign_headers(url))
+            http_code = code
+            if http_code == 304:
+                logger.debug("No change, loop...")
+                return
+            if http_code == 200:
+                if not body:
+                    logger.error(f"_long_poll load configs failed,body is {body}")
+                    return
+                data = json.loads(body)
+                for entry in data:
+                    namespace = entry[NAMESPACE_NAME]
+                    n_id = entry[NOTIFICATION_ID]
+                    logger.info("%s has changes: notificationId=%d", namespace, n_id)
+                    self._get_net_and_set_local(namespace, n_id, call_change=True)
+                    return
+            else:
+                logger.warning("Sleep...")
+        except Exception as e:
+            logger.warning(str(e))
+
+    def _get_net_and_set_local(self, namespace, n_id, call_change=False):
+        namespace_data = self.get_json_from_net(namespace)
+        if not namespace_data:
+            return
+        namespace_data[NOTIFICATION_ID] = n_id
+        old_namespace = self._cache.get(namespace)
+        self._update_cache_and_file(namespace_data, namespace)
+        if self._change_listener is not None and call_change and old_namespace:
+            old_kv = old_namespace.get(CONFIGURATIONS)
+            new_kv = namespace_data.get(CONFIGURATIONS)
+            self._call_listener(namespace, old_kv, new_kv)
+
+    def _listener(self):
+        logger.info("start long_poll")
+        while not self._stopping:
+            self._long_poll()
+            time.sleep(self._cycle_time)
+        logger.info("stopped, long_poll")
+
+    # add the need for endorsement to the header
+    def _sign_headers(self, url: str) -> Mapping[str, str]:
+        headers: dict[str, str] = {}
+        if self.secret == "":
+            return headers
+        uri = url[len(self.config_url) : len(url)]
+        time_unix_now = str(int(round(time.time() * 1000)))
+        headers["Authorization"] = "Apollo " + self.app_id + ":" + signature(time_unix_now, uri, self.secret)
+        headers["Timestamp"] = time_unix_now
+        return headers
+
+    def _heart_beat(self):
+        while not self._stopping:
+            for namespace in self._notification_map:
+                self._do_heart_beat(namespace)
+            time.sleep(60 * 10)  # 10分钟
+
+    def _do_heart_beat(self, namespace):
+        url = "{}/configs/{}/{}/{}?ip={}".format(self.config_url, self.app_id, self.cluster, namespace, self.ip)
+        try:
+            code, body = http_request(url, timeout=3, headers=self._sign_headers(url))
+            if code == 200:
+                if not body:
+                    logger.error(f"_do_heart_beat load configs failed,body is {body}")
+                    return None
+                data = json.loads(body)
+                if self.last_release_key == data["releaseKey"]:
+                    return None
+                self.last_release_key = data["releaseKey"]
+                data = data["configurations"]
+                self._update_cache_and_file(data, namespace)
+            else:
+                return None
+        except Exception:
+            logger.exception("an error occurred in _do_heart_beat")
+            return None
+
+    def get_all_dicts(self, namespace):
+        namespace_data = self._cache.get(namespace)
+        if namespace_data is None:
+            net_namespace_data = self.get_json_from_net(namespace)
+            if not net_namespace_data:
+                return namespace_data
+            namespace_data = net_namespace_data.get(CONFIGURATIONS)
+            if namespace_data:
+                self._update_cache_and_file(namespace_data, namespace)
+        return namespace_data

api/configs/remote_settings_sources/apollo/python_3x.py

@@ -0,0 +1,41 @@
+import logging
+import os
+import ssl
+import urllib.request
+from urllib import parse
+from urllib.error import HTTPError
+
+# Create an SSL context that allows for a lower level of security
+ssl_context = ssl.create_default_context()
+ssl_context.set_ciphers("HIGH:!DH:!aNULL")
+ssl_context.check_hostname = False
+ssl_context.verify_mode = ssl.CERT_NONE
+
+# Create an opener object and pass in a custom SSL context
+opener = urllib.request.build_opener(urllib.request.HTTPSHandler(context=ssl_context))
+
+urllib.request.install_opener(opener)
+
+logger = logging.getLogger(__name__)
+
+
+def http_request(url, timeout, headers={}):
+    try:
+        request = urllib.request.Request(url, headers=headers)
+        res = urllib.request.urlopen(request, timeout=timeout)
+        body = res.read().decode("utf-8")
+        return res.code, body
+    except HTTPError as e:
+        if e.code == 304:
+            logger.warning("http_request error,code is 304, maybe you should check secret")
+            return 304, None
+        logger.warning("http_request error,code is %d, msg is %s", e.code, e.msg)
+        raise e
+
+
+def url_encode(params):
+    return parse.urlencode(params)
+
+
+def makedirs_wrapper(path):
+    os.makedirs(path, exist_ok=True)

api/configs/remote_settings_sources/apollo/utils.py

@@ -0,0 +1,51 @@
+import hashlib
+import socket
+
+from .python_3x import url_encode
+
+# define constants
+CONFIGURATIONS = "configurations"
+NOTIFICATION_ID = "notificationId"
+NAMESPACE_NAME = "namespaceName"
+
+
+# add timestamps uris and keys
+def signature(timestamp, uri, secret):
+    import base64
+    import hmac
+
+    string_to_sign = "" + timestamp + "\n" + uri
+    hmac_code = hmac.new(secret.encode(), string_to_sign.encode(), hashlib.sha1).digest()
+    return base64.b64encode(hmac_code).decode()
+
+
+def url_encode_wrapper(params):
+    return url_encode(params)
+
+
+def no_key_cache_key(namespace, key):
+    return "{}{}{}".format(namespace, len(namespace), key)
+
+
+# Returns whether the obtained value is obtained, and None if it does not
+def get_value_from_dict(namespace_cache, key):
+    if namespace_cache:
+        kv_data = namespace_cache.get(CONFIGURATIONS)
+        if kv_data is None:
+            return None
+        if key in kv_data:
+            return kv_data[key]
+    return None
+
+
+def init_ip():
+    ip = ""
+    s = None
+    try:
+        s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        s.connect(("8.8.8.8", 53))
+        ip = s.getsockname()[0]
+    finally:
+        if s:
+            s.close()
+    return ip

api/configs/remote_settings_sources/base.py

@@ -0,0 +1,15 @@
+from collections.abc import Mapping
+from typing import Any
+
+from pydantic.fields import FieldInfo
+
+
+class RemoteSettingsSource:
+    def __init__(self, configs: Mapping[str, Any]):
+        pass
+
+    def get_field_value(self, field: FieldInfo, field_name: str) -> tuple[Any, str, bool]:
+        raise NotImplementedError
+
+    def prepare_field_value(self, field_name: str, field: FieldInfo, value: Any, value_is_complex: bool) -> Any:
+        return value

api/configs/remote_settings_sources/enums.py

@@ -0,0 +1,5 @@
+from enum import StrEnum
+
+
+class RemoteSettingsSourceName(StrEnum):
+    APOLLO = "apollo"

api/constants/__init__.py

@@ -14,11 +14,11 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
 
 
 if dify_config.ETL_TYPE == "Unstructured":
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls"]
+    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
     DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
     if dify_config.UNSTRUCTURED_API_URL:
         DOCUMENT_EXTENSIONS.append("ppt")
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])
 else:
-    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
+    DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls", "docx", "csv"]
     DOCUMENT_EXTENSIONS.extend([ext.upper() for ext in DOCUMENT_EXTENSIONS])

api/constants/languages.py

@@ -18,6 +18,7 @@ language_timezone_mapping = {
     "tr-TR": "Europe/Istanbul",
     "fa-IR": "Asia/Tehran",
     "sl-SI": "Europe/Ljubljana",
+    "th-TH": "Asia/Bangkok",
 }
 
 languages = list(language_timezone_mapping.keys())

api/constants/model_template.py

@@ -1,8 +1,9 @@
 import json
+from collections.abc import Mapping
 
 from models.model import AppMode
 
-default_app_templates = {
+default_app_templates: Mapping[AppMode, Mapping] = {
     # workflow default mode
     AppMode.WORKFLOW: {
         "app": {

api/controllers/common/errors.py

@@ -4,3 +4,8 @@ from werkzeug.exceptions import HTTPException
 class FilenameNotExistsError(HTTPException):
     code = 400
     description = "The specified filename does not exist."
+
+
+class RemoteFileUploadError(HTTPException):
+    code = 400
+    description = "Error uploading remote file."

api/controllers/common/fields.py

@@ -1,4 +1,4 @@
-from flask_restful import fields
+from flask_restful import fields  # type: ignore
 
 parameters__system_parameters = {
     "image_file_size_limit": fields.Integer,

api/controllers/console/__init__.py

@@ -3,6 +3,25 @@ from flask import Blueprint
 from libs.external_api import ExternalApi
 
 from .app.app_import import AppImportApi, AppImportConfirmApi
+from .explore.audio import ChatAudioApi, ChatTextApi
+from .explore.completion import ChatApi, ChatStopApi, CompletionApi, CompletionStopApi
+from .explore.conversation import (
+    ConversationApi,
+    ConversationListApi,
+    ConversationPinApi,
+    ConversationRenameApi,
+    ConversationUnPinApi,
+)
+from .explore.message import (
+    MessageFeedbackApi,
+    MessageListApi,
+    MessageMoreLikeThisApi,
+    MessageSuggestedQuestionApi,
+)
+from .explore.workflow import (
+    InstalledAppWorkflowRunApi,
+    InstalledAppWorkflowTaskStopApi,
+)
 from .files import FileApi, FilePreviewApi, FileSupportTypeApi
 from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
 
@@ -66,15 +85,81 @@ from .datasets import (
 
 # Import explore controllers
 from .explore import (
-    audio,
-    completion,
-    conversation,
     installed_app,
-    message,
     parameter,
     recommended_app,
     saved_message,
-    workflow,
+)
+
+# Explore Audio
+api.add_resource(ChatAudioApi, "/installed-apps/<uuid:installed_app_id>/audio-to-text", endpoint="installed_app_audio")
+api.add_resource(ChatTextApi, "/installed-apps/<uuid:installed_app_id>/text-to-audio", endpoint="installed_app_text")
+
+# Explore Completion
+api.add_resource(
+    CompletionApi, "/installed-apps/<uuid:installed_app_id>/completion-messages", endpoint="installed_app_completion"
+)
+api.add_resource(
+    CompletionStopApi,
+    "/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop",
+    endpoint="installed_app_stop_completion",
+)
+api.add_resource(
+    ChatApi, "/installed-apps/<uuid:installed_app_id>/chat-messages", endpoint="installed_app_chat_completion"
+)
+api.add_resource(
+    ChatStopApi,
+    "/installed-apps/<uuid:installed_app_id>/chat-messages/<string:task_id>/stop",
+    endpoint="installed_app_stop_chat_completion",
+)
+
+# Explore Conversation
+api.add_resource(
+    ConversationRenameApi,
+    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/name",
+    endpoint="installed_app_conversation_rename",
+)
+api.add_resource(
+    ConversationListApi, "/installed-apps/<uuid:installed_app_id>/conversations", endpoint="installed_app_conversations"
+)
+api.add_resource(
+    ConversationApi,
+    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>",
+    endpoint="installed_app_conversation",
+)
+api.add_resource(
+    ConversationPinApi,
+    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/pin",
+    endpoint="installed_app_conversation_pin",
+)
+api.add_resource(
+    ConversationUnPinApi,
+    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/unpin",
+    endpoint="installed_app_conversation_unpin",
+)
+
+
+# Explore Message
+api.add_resource(MessageListApi, "/installed-apps/<uuid:installed_app_id>/messages", endpoint="installed_app_messages")
+api.add_resource(
+    MessageFeedbackApi,
+    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/feedbacks",
+    endpoint="installed_app_message_feedback",
+)
+api.add_resource(
+    MessageMoreLikeThisApi,
+    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/more-like-this",
+    endpoint="installed_app_more_like_this",
+)
+api.add_resource(
+    MessageSuggestedQuestionApi,
+    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/suggested-questions",
+    endpoint="installed_app_suggested_question",
+)
+# Explore Workflow
+api.add_resource(InstalledAppWorkflowRunApi, "/installed-apps/<uuid:installed_app_id>/workflows/run")
+api.add_resource(
+    InstalledAppWorkflowTaskStopApi, "/installed-apps/<uuid:installed_app_id>/workflows/tasks/<string:task_id>/stop"
 )
 
 # Import tag controllers

api/controllers/console/admin.py

@@ -1,7 +1,7 @@
 from functools import wraps
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import NotFound, Unauthorized
 
 from configs import dify_config
@@ -31,7 +31,7 @@ def admin_required(view):
         if auth_scheme != "bearer":
             raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
 
-        if dify_config.ADMIN_API_KEY != auth_token:
+        if auth_token != dify_config.ADMIN_API_KEY:
             raise Unauthorized("API key is invalid.")
 
         return view(*args, **kwargs)

api/controllers/console/apikey.py

@@ -1,5 +1,7 @@
-import flask_restful
-from flask_login import current_user
+from typing import Any
+
+import flask_restful  # type: ignore
+from flask_login import current_user  # type: ignore
 from flask_restful import Resource, fields, marshal_with
 from werkzeug.exceptions import Forbidden
 
@@ -35,14 +37,15 @@ def _get_resource(resource_id, tenant_id, resource_model):
 class BaseApiKeyListResource(Resource):
     method_decorators = [account_initialization_required, login_required, setup_required]
 
-    resource_type = None
-    resource_model = None
-    resource_id_field = None
-    token_prefix = None
+    resource_type: str | None = None
+    resource_model: Any = None
+    resource_id_field: str | None = None
+    token_prefix: str | None = None
     max_keys = 10
 
     @marshal_with(api_key_list)
     def get(self, resource_id):
+        assert self.resource_id_field is not None, "resource_id_field must be set"
         resource_id = str(resource_id)
         _get_resource(resource_id, current_user.current_tenant_id, self.resource_model)
         keys = (
@@ -54,6 +57,7 @@ class BaseApiKeyListResource(Resource):
 
     @marshal_with(api_key_fields)
     def post(self, resource_id):
+        assert self.resource_id_field is not None, "resource_id_field must be set"
         resource_id = str(resource_id)
         _get_resource(resource_id, current_user.current_tenant_id, self.resource_model)
         if not current_user.is_editor:
@@ -86,11 +90,12 @@ class BaseApiKeyListResource(Resource):
 class BaseApiKeyResource(Resource):
     method_decorators = [account_initialization_required, login_required, setup_required]
 
-    resource_type = None
-    resource_model = None
-    resource_id_field = None
+    resource_type: str | None = None
+    resource_model: Any = None
+    resource_id_field: str | None = None
 
     def delete(self, resource_id, api_key_id):
+        assert self.resource_id_field is not None, "resource_id_field must be set"
         resource_id = str(resource_id)
         api_key_id = str(api_key_id)
         _get_resource(resource_id, current_user.current_tenant_id, self.resource_model)

api/controllers/console/app/advanced_prompt_template.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required, setup_required

api/controllers/console/app/agent.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/annotation.py

@@ -1,6 +1,6 @@
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
@@ -110,7 +110,7 @@ class AnnotationListApi(Resource):
 
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
-        keyword = request.args.get("keyword", default=None, type=str)
+        keyword = request.args.get("keyword", default="", type=str)
 
         app_id = str(app_id)
         annotation_list, total = AppAnnotationService.get_annotation_list_by_app_id(app_id, page, limit, keyword)

api/controllers/console/app/app.py

@@ -1,8 +1,8 @@
 import uuid
 from typing import cast
 
-from flask_login import current_user
-from flask_restful import Resource, inputs, marshal, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, inputs, marshal, marshal_with, reqparse  # type: ignore
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import BadRequest, Forbidden, abort

api/controllers/console/app/app_import.py

@@ -1,7 +1,7 @@
 from typing import cast
 
-from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
 from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
 

api/controllers/console/app/audio.py

@@ -1,7 +1,7 @@
 import logging
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import InternalServerError
 
 import services

api/controllers/console/app/completion.py

@@ -1,7 +1,7 @@
 import logging
 
-import flask_login
-from flask_restful import Resource, reqparse
+import flask_login  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services

api/controllers/console/app/conversation.py

@@ -1,9 +1,9 @@
 from datetime import UTC, datetime
 
-import pytz
-from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
-from flask_restful.inputs import int_range
+import pytz  # pip install pytz
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 from sqlalchemy import func, or_
 from sqlalchemy.orm import joinedload
 from werkzeug.exceptions import Forbidden, NotFound
@@ -77,8 +77,9 @@ class CompletionConversationApi(Resource):
 
             query = query.where(Conversation.created_at < end_datetime_utc)
 
+        # FIXME, the type ignore in this file
         if args["annotation_status"] == "annotated":
-            query = query.options(joinedload(Conversation.message_annotations)).join(
+            query = query.options(joinedload(Conversation.message_annotations)).join(  # type: ignore
                 MessageAnnotation, MessageAnnotation.conversation_id == Conversation.id
             )
         elif args["annotation_status"] == "not_annotated":
@@ -222,7 +223,7 @@ class ChatConversationApi(Resource):
                     query = query.where(Conversation.created_at <= end_datetime_utc)
 
         if args["annotation_status"] == "annotated":
-            query = query.options(joinedload(Conversation.message_annotations)).join(
+            query = query.options(joinedload(Conversation.message_annotations)).join(  # type: ignore
                 MessageAnnotation, MessageAnnotation.conversation_id == Conversation.id
             )
         elif args["annotation_status"] == "not_annotated":
@@ -234,7 +235,7 @@ class ChatConversationApi(Resource):
 
         if args["message_count_gte"] and args["message_count_gte"] >= 1:
             query = (
-                query.options(joinedload(Conversation.messages))
+                query.options(joinedload(Conversation.messages))  # type: ignore
                 .join(Message, Message.conversation_id == Conversation.id)
                 .group_by(Conversation.id)
                 .having(func.count(Message.id) >= args["message_count_gte"])

api/controllers/console/app/conversation_variables.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
 from sqlalchemy import select
 from sqlalchemy.orm import Session
 

api/controllers/console/app/generator.py

@@ -1,7 +1,7 @@
 import os
 
-from flask_login import current_user
-from flask_restful import Resource, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.error import (

api/controllers/console/app/message.py

@@ -1,8 +1,8 @@
 import logging
 
-from flask_login import current_user
-from flask_restful import Resource, fields, marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, fields, marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 from controllers.console import api

api/controllers/console/app/model_config.py

@@ -1,8 +1,9 @@
 import json
+from typing import cast
 
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
@@ -26,7 +27,9 @@ class ModelConfigResource(Resource):
         """Modify app model config"""
         # validate config
         model_configuration = AppModelConfigService.validate_configuration(
-            tenant_id=current_user.current_tenant_id, config=request.json, app_mode=AppMode.value_of(app_model.mode)
+            tenant_id=current_user.current_tenant_id,
+            config=cast(dict, request.json),
+            app_mode=AppMode.value_of(app_model.mode),
         )
 
         new_app_model_config = AppModelConfig(
@@ -38,9 +41,11 @@ class ModelConfigResource(Resource):
 
         if app_model.mode == AppMode.AGENT_CHAT.value or app_model.is_agent:
             # get original app model config
-            original_app_model_config: AppModelConfig = (
+            original_app_model_config = (
                 db.session.query(AppModelConfig).filter(AppModelConfig.id == app_model.app_model_config_id).first()
             )
+            if original_app_model_config is None:
+                raise ValueError("Original app model config not found")
             agent_mode = original_app_model_config.agent_mode_dict
             # decrypt agent tool parameters if it's secret-input
             parameter_map = {}
@@ -65,7 +70,7 @@ class ModelConfigResource(Resource):
                         provider_type=agent_tool_entity.provider_type,
                         identity_id=f"AGENT.{app_model.id}",
                     )
-                except Exception as e:
+                except Exception:
                     continue
 
                 # get decrypted parameters
@@ -97,7 +102,7 @@ class ModelConfigResource(Resource):
                             app_id=app_model.id,
                             agent_tool=agent_tool_entity,
                         )
-                    except Exception as e:
+                    except Exception:
                         continue
 
                 manager = ToolParameterConfigurationManager(

api/controllers/console/app/ops_trace.py

@@ -1,4 +1,5 @@
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
+from werkzeug.exceptions import BadRequest
 
 from controllers.console import api
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
@@ -26,7 +27,7 @@ class TraceAppConfigApi(Resource):
                 return {"has_not_configured": True}
             return trace_config
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -48,7 +49,7 @@ class TraceAppConfigApi(Resource):
                 raise TracingConfigCheckError()
             return result
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -68,7 +69,7 @@ class TraceAppConfigApi(Resource):
                 raise TracingConfigNotExist()
             return {"result": "success"}
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
     @setup_required
     @login_required
@@ -85,7 +86,7 @@ class TraceAppConfigApi(Resource):
                 raise TracingConfigNotExist()
             return {"result": "success"}
         except Exception as e:
-            raise e
+            raise BadRequest(str(e))
 
 
 api.add_resource(TraceAppConfigApi, "/apps/<uuid:app_id>/trace-config")

api/controllers/console/app/site.py

@@ -1,7 +1,7 @@
 from datetime import UTC, datetime
 
-from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, NotFound
 
 from constants.languages import supported_language
@@ -50,7 +50,7 @@ class AppSite(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
-        site = db.session.query(Site).filter(Site.app_id == app_model.id).one_or_404()
+        site = Site.query.filter(Site.app_id == app_model.id).one_or_404()
 
         for attr_name in [
             "title",

api/controllers/console/app/statistic.py

@@ -3,8 +3,8 @@ from decimal import Decimal
 
 import pytz
 from flask import jsonify
-from flask_login import current_user
-from flask_restful import Resource, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/workflow.py

@@ -2,10 +2,11 @@ import json
 import logging
 
 from flask import abort, request
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
+from configs import dify_config
 from controllers.console import api
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
 from controllers.console.app.wraps import get_app_model
@@ -100,11 +101,11 @@ class DraftWorkflowApi(Resource):
         try:
             environment_variables_list = args.get("environment_variables") or []
             environment_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in environment_variables_list
+                variable_factory.build_environment_variable_from_mapping(obj) for obj in environment_variables_list
             ]
             conversation_variables_list = args.get("conversation_variables") or []
             conversation_variables = [
-                variable_factory.build_variable_from_mapping(obj) for obj in conversation_variables_list
+                variable_factory.build_conversation_variable_from_mapping(obj) for obj in conversation_variables_list
             ]
             workflow = workflow_service.sync_draft_workflow(
                 app_model=app_model,
@@ -382,7 +383,7 @@ class DefaultBlockConfigApi(Resource):
         filters = None
         if args.get("q"):
             try:
-                filters = json.loads(args.get("q"))
+                filters = json.loads(args.get("q", ""))
             except json.JSONDecodeError:
                 raise ValueError("Invalid filters")
 
@@ -426,7 +427,46 @@ class ConvertToWorkflowApi(Resource):
         }
 
 
+class WorkflowConfigApi(Resource):
+    """Resource for workflow configuration."""
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    def get(self, app_model: App):
+        return {
+            "parallel_depth_limit": dify_config.WORKFLOW_PARALLEL_DEPTH_LIMIT,
+        }
+
+
+class DraftWorkflowNodeRetriableApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_run_node_execution_fields)
+    def post(self, app_model: App, node_id: str):
+        """
+        Run draft workflow node
+        """
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        workflow_service = WorkflowService()
+        workflow_node_execution = workflow_service.run_retriable_draft_workflow_node(
+            app_model=app_model, node_id=node_id, user_inputs=args.get("inputs", {}), account=current_user
+        )
+
+        return workflow_node_execution
+
+
 api.add_resource(DraftWorkflowApi, "/apps/<uuid:app_id>/workflows/draft")
+api.add_resource(WorkflowConfigApi, "/apps/<uuid:app_id>/workflows/draft/config")
 api.add_resource(AdvancedChatDraftWorkflowRunApi, "/apps/<uuid:app_id>/advanced-chat/workflows/draft/run")
 api.add_resource(DraftWorkflowRunApi, "/apps/<uuid:app_id>/workflows/draft/run")
 api.add_resource(WorkflowTaskStopApi, "/apps/<uuid:app_id>/workflow-runs/tasks/<string:task_id>/stop")
@@ -444,3 +484,4 @@ api.add_resource(
     DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"
 )
 api.add_resource(ConvertToWorkflowApi, "/apps/<uuid:app_id>/convert-to-workflow")
+api.add_resource(DraftWorkflowNodeRetriableApi, "/apps/<uuid:app_id>/workflows/draft/retry/nodes/<string:node_id>/run")

api/controllers/console/app/workflow_app_log.py

@@ -1,5 +1,5 @@
-from flask_restful import Resource, marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/workflow_run.py

@@ -1,5 +1,5 @@
-from flask_restful import Resource, marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/workflow_statistic.py

@@ -3,8 +3,8 @@ from decimal import Decimal
 
 import pytz
 from flask import jsonify
-from flask_login import current_user
-from flask_restful import Resource, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model

api/controllers/console/app/wraps.py

@@ -5,11 +5,10 @@ from typing import Optional, Union
 from controllers.console.app.error import AppNotFoundError
 from extensions.ext_database import db
 from libs.login import current_user
-from models import App
-from models.model import AppMode
+from models import App, AppMode
 
 
-def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode]] = None):
+def get_app_model(view: Optional[Callable] = None, *, mode: Union[AppMode, list[AppMode], None] = None):
     def decorator(view_func):
         @wraps(view_func)
         def decorated_view(*args, **kwargs):

api/controllers/console/auth/activate.py

@@ -1,14 +1,14 @@
 import datetime
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.error import AlreadyActivateError
 from extensions.ext_database import db
 from libs.helper import StrLen, email, extract_remote_ip, timezone
-from models.account import AccountStatus, Tenant
+from models.account import AccountStatus
 from services.account_service import AccountService, RegisterService
 
 
@@ -27,7 +27,7 @@ class ActivateCheckApi(Resource):
         invitation = RegisterService.get_invitation_if_token_valid(workspaceId, reg_email, token)
         if invitation:
             data = invitation.get("data", {})
-            tenant: Tenant = invitation.get("tenant", None)
+            tenant = invitation.get("tenant", None)
             workspace_name = tenant.name if tenant else None
             workspace_id = tenant.id if tenant else None
             invitee_email = data.get("email") if data else None

api/controllers/console/auth/data_source_bearer_auth.py

@@ -1,5 +1,5 @@
-from flask_login import current_user
-from flask_restful import Resource, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api

api/controllers/console/auth/data_source_oauth.py

@@ -2,8 +2,8 @@ import logging
 
 import requests
 from flask import current_app, redirect, request
-from flask_login import current_user
-from flask_restful import Resource
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource  # type: ignore
 from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
@@ -17,8 +17,8 @@ from ..wraps import account_initialization_required, setup_required
 def get_oauth_providers():
     with current_app.app_context():
         notion_oauth = NotionOAuth(
-            client_id=dify_config.NOTION_CLIENT_ID,
-            client_secret=dify_config.NOTION_CLIENT_SECRET,
+            client_id=dify_config.NOTION_CLIENT_ID or "",
+            client_secret=dify_config.NOTION_CLIENT_SECRET or "",
             redirect_uri=dify_config.CONSOLE_API_URL + "/console/api/oauth/data-source/callback/notion",
         )
 
@@ -34,7 +34,6 @@ class OAuthDataSource(Resource):
         OAUTH_DATASOURCE_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_DATASOURCE_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
         if dify_config.NOTION_INTEGRATION_TYPE == "internal":

api/controllers/console/auth/forgot_password.py

@@ -2,7 +2,7 @@ import base64
 import secrets
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 from constants.languages import languages
 from controllers.console import api
@@ -122,8 +122,8 @@ class ForgotPasswordResetApi(Resource):
         else:
             try:
                 account = AccountService.create_account_and_tenant(
-                    email=reset_data.get("email"),
-                    name=reset_data.get("email"),
+                    email=reset_data.get("email", ""),
+                    name=reset_data.get("email", ""),
                     password=password_confirm,
                     interface_language=languages[0],
                 )

api/controllers/console/auth/login.py

@@ -1,8 +1,8 @@
 from typing import cast
 
-import flask_login
+import flask_login  # type: ignore
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 import services
 from constants.languages import languages

api/controllers/console/auth/oauth.py

@@ -4,7 +4,7 @@ from typing import Optional
 
 import requests
 from flask import current_app, redirect, request
-from flask_restful import Resource
+from flask_restful import Resource  # type: ignore
 from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
@@ -52,7 +52,6 @@ class OAuthLogin(Resource):
         OAUTH_PROVIDERS = get_oauth_providers()
         with current_app.app_context():
             oauth_provider = OAUTH_PROVIDERS.get(provider)
-            print(vars(oauth_provider))
         if not oauth_provider:
             return {"error": "Invalid provider"}, 400
 
@@ -77,8 +76,9 @@ class OAuthCallback(Resource):
         try:
             token = oauth_provider.get_access_token(code)
             user_info = oauth_provider.get_user_info(token)
-        except requests.exceptions.HTTPError as e:
-            logging.exception(f"An error occurred during the OAuth process with {provider}: {e.response.text}")
+        except requests.exceptions.RequestException as e:
+            error_text = e.response.text if e.response else str(e)
+            logging.exception(f"An error occurred during the OAuth process with {provider}: {error_text}")
             return {"error": "OAuth process failed"}, 400
 
         if invite_token and RegisterService.is_valid_invite_token(invite_token):
@@ -130,7 +130,7 @@ class OAuthCallback(Resource):
 
 
 def _get_account_by_openid_or_email(provider: str, user_info: OAuthUserInfo) -> Optional[Account]:
-    account = Account.get_by_openid(provider, user_info.id)
+    account: Optional[Account] = Account.get_by_openid(provider, user_info.id)
 
     if not account:
         account = Account.query.filter_by(email=user_info.email).first()

api/controllers/console/billing/billing.py

@@ -1,5 +1,5 @@
-from flask_login import current_user
-from flask_restful import Resource, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required

api/controllers/console/datasets/data_source.py

@@ -2,8 +2,8 @@ import datetime
 import json
 
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
@@ -218,7 +218,7 @@ class DataSourceNotionApi(Resource):
             args["doc_form"],
             args["doc_language"],
         )
-        return response, 200
+        return response.model_dump(), 200
 
 
 class DataSourceNotionDatasetSyncApi(Resource):

api/controllers/console/datasets/datasets.py

@@ -1,7 +1,7 @@
-import flask_restful
+import flask_restful  # type: ignore
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal, marshal_with, reqparse
+from flask_login import current_user  # type: ignore  # type: ignore
+from flask_restful import Resource, marshal, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -464,7 +464,7 @@ class DatasetIndexingEstimateApi(Resource):
         except Exception as e:
             raise IndexingEstimateError(str(e))
 
-        return response, 200
+        return response.model_dump(), 200
 
 
 class DatasetRelatedAppListApi(Resource):
@@ -733,6 +733,18 @@ class DatasetPermissionUserListApi(Resource):
         }, 200
 
 
+class DatasetAutoDisableLogApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        return DatasetService.get_dataset_auto_disable_logs(dataset_id_str), 200
+
+
 api.add_resource(DatasetListApi, "/datasets")
 api.add_resource(DatasetApi, "/datasets/<uuid:dataset_id>")
 api.add_resource(DatasetUseCheckApi, "/datasets/<uuid:dataset_id>/use-check")
@@ -747,3 +759,4 @@ api.add_resource(DatasetApiBaseUrlApi, "/datasets/api-base-info")
 api.add_resource(DatasetRetrievalSettingApi, "/datasets/retrieval-setting")
 api.add_resource(DatasetRetrievalSettingMockApi, "/datasets/retrieval-setting/<string:vector_type>")
 api.add_resource(DatasetPermissionUserListApi, "/datasets/<uuid:dataset_id>/permission-part-users")
+api.add_resource(DatasetAutoDisableLogApi, "/datasets/<uuid:dataset_id>/auto-disable-logs")

api/controllers/console/datasets/datasets_document.py

@@ -1,12 +1,13 @@
 import logging
 from argparse import ArgumentTypeError
 from datetime import UTC, datetime
+from typing import cast
 
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, fields, marshal, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, fields, marshal, marshal_with, reqparse  # type: ignore
 from sqlalchemy import asc, desc
-from transformers.hf_argparser import string_to_bool
+from transformers.hf_argparser import string_to_bool  # type: ignore
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -51,6 +52,7 @@ from fields.document_fields import (
 from libs.login import login_required
 from models import Dataset, DatasetProcessRule, Document, DocumentSegment, UploadFile
 from services.dataset_service import DatasetService, DocumentService
+from services.entities.knowledge_entities.knowledge_entities import KnowledgeConfig
 from tasks.add_document_to_index_task import add_document_to_index_task
 from tasks.remove_document_from_index_task import remove_document_from_index_task
 
@@ -106,6 +108,7 @@ class GetProcessRuleApi(Resource):
         # get default rules
         mode = DocumentService.DEFAULT_RULES["mode"]
         rules = DocumentService.DEFAULT_RULES["rules"]
+        limits = DocumentService.DEFAULT_RULES["limits"]
         if document_id:
             # get the latest process rule
             document = Document.query.get_or_404(document_id)
@@ -132,7 +135,7 @@ class GetProcessRuleApi(Resource):
                 mode = dataset_process_rule.mode
                 rules = dataset_process_rule.rules_dict
 
-        return {"mode": mode, "rules": rules}
+        return {"mode": mode, "rules": rules, "limits": limits}
 
 
 class DatasetDocumentListApi(Resource):
@@ -253,20 +256,22 @@ class DatasetDocumentListApi(Resource):
         parser.add_argument("duplicate", type=bool, default=True, nullable=False, location="json")
         parser.add_argument("original_document_id", type=str, required=False, location="json")
         parser.add_argument("doc_form", type=str, default="text_model", required=False, nullable=False, location="json")
+        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+
         parser.add_argument(
             "doc_language", type=str, default="English", required=False, nullable=False, location="json"
         )
-        parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
         args = parser.parse_args()
+        knowledge_config = KnowledgeConfig(**args)
 
-        if not dataset.indexing_technique and not args["indexing_technique"]:
+        if not dataset.indexing_technique and not knowledge_config.indexing_technique:
             raise ValueError("indexing_technique is required.")
 
         # validate args
-        DocumentService.document_create_args_validate(args)
+        DocumentService.document_create_args_validate(knowledge_config)
 
         try:
-            documents, batch = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
+            documents, batch = DocumentService.save_document_with_dataset_id(dataset, knowledge_config, current_user)
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
         except QuotaExceededError:
@@ -276,6 +281,25 @@ class DatasetDocumentListApi(Resource):
 
         return {"documents": documents, "batch": batch}
 
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id):
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+
+        try:
+            document_ids = request.args.getlist("document_id")
+            DocumentService.delete_documents(dataset, document_ids)
+        except services.errors.document.DocumentIndexingError:
+            raise DocumentIndexingError("Cannot delete document during indexing.")
+
+        return {"result": "success"}, 204
+
 
 class DatasetInitApi(Resource):
     @setup_required
@@ -311,9 +335,9 @@ class DatasetInitApi(Resource):
         # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
         if not current_user.is_dataset_editor:
             raise Forbidden()
-
-        if args["indexing_technique"] == "high_quality":
-            if args["embedding_model"] is None or args["embedding_model_provider"] is None:
+        knowledge_config = KnowledgeConfig(**args)
+        if knowledge_config.indexing_technique == "high_quality":
+            if knowledge_config.embedding_model is None or knowledge_config.embedding_model_provider is None:
                 raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
             try:
                 model_manager = ModelManager()
@@ -332,11 +356,11 @@ class DatasetInitApi(Resource):
                 raise ProviderNotInitializeError(ex.description)
 
         # validate args
-        DocumentService.document_create_args_validate(args)
+        DocumentService.document_create_args_validate(knowledge_config)
 
         try:
             dataset, documents, batch = DocumentService.save_document_without_dataset_id(
-                tenant_id=current_user.current_tenant_id, document_data=args, account=current_user
+                tenant_id=current_user.current_tenant_id, knowledge_config=knowledge_config, account=current_user
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
@@ -389,7 +413,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
                 indexing_runner = IndexingRunner()
 
                 try:
-                    response = indexing_runner.indexing_estimate(
+                    estimate_response = indexing_runner.indexing_estimate(
                         current_user.current_tenant_id,
                         [extract_setting],
                         data_process_rule_dict,
@@ -397,6 +421,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
                         "English",
                         dataset_id,
                     )
+                    return estimate_response.model_dump(), 200
                 except LLMBadRequestError:
                     raise ProviderNotInitializeError(
                         "No Embedding Model available. Please configure a valid provider "
@@ -407,7 +432,7 @@ class DocumentIndexingEstimateApi(DocumentResource):
                 except Exception as e:
                     raise IndexingEstimateError(str(e))
 
-        return response
+        return response, 200
 
 
 class DocumentBatchIndexingEstimateApi(DocumentResource):
@@ -418,9 +443,8 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
         dataset_id = str(dataset_id)
         batch = str(batch)
         documents = self.get_batch_documents(dataset_id, batch)
-        response = {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}
         if not documents:
-            return response
+            return {"tokens": 0, "total_price": 0, "currency": "USD", "total_segments": 0, "preview": []}, 200
         data_process_rule = documents[0].dataset_process_rule
         data_process_rule_dict = data_process_rule.to_dict()
         info_list = []
@@ -498,6 +522,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                     "English",
                     dataset_id,
                 )
+                return response.model_dump(), 200
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
                     "No Embedding Model available. Please configure a valid provider "
@@ -507,7 +532,6 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                 raise ProviderNotInitializeError(ex.description)
             except Exception as e:
                 raise IndexingEstimateError(str(e))
-        return response
 
 
 class DocumentBatchIndexingStatusApi(DocumentResource):
@@ -580,7 +604,8 @@ class DocumentDetailApi(DocumentResource):
         if metadata == "only":
             response = {"id": document.id, "doc_type": document.doc_type, "doc_metadata": document.doc_metadata}
         elif metadata == "without":
-            process_rules = DatasetService.get_process_rules(dataset_id)
+            dataset_process_rules = DatasetService.get_process_rules(dataset_id)
+            document_process_rules = document.dataset_process_rule.to_dict()
             data_source_info = document.data_source_detail_dict
             response = {
                 "id": document.id,
@@ -588,7 +613,8 @@ class DocumentDetailApi(DocumentResource):
                 "data_source_type": document.data_source_type,
                 "data_source_info": data_source_info,
                 "dataset_process_rule_id": document.dataset_process_rule_id,
-                "dataset_process_rule": process_rules,
+                "dataset_process_rule": dataset_process_rules,
+                "document_process_rule": document_process_rules,
                 "name": document.name,
                 "created_from": document.created_from,
                 "created_by": document.created_by,
@@ -611,7 +637,8 @@ class DocumentDetailApi(DocumentResource):
                 "doc_language": document.doc_language,
             }
         else:
-            process_rules = DatasetService.get_process_rules(dataset_id)
+            dataset_process_rules = DatasetService.get_process_rules(dataset_id)
+            document_process_rules = document.dataset_process_rule.to_dict()
             data_source_info = document.data_source_detail_dict
             response = {
                 "id": document.id,
@@ -619,7 +646,8 @@ class DocumentDetailApi(DocumentResource):
                 "data_source_type": document.data_source_type,
                 "data_source_info": data_source_info,
                 "dataset_process_rule_id": document.dataset_process_rule_id,
-                "dataset_process_rule": process_rules,
+                "dataset_process_rule": dataset_process_rules,
+                "document_process_rule": document_process_rules,
                 "name": document.name,
                 "created_from": document.created_from,
                 "created_by": document.created_by,
@@ -732,8 +760,7 @@ class DocumentMetadataApi(DocumentResource):
 
         if not isinstance(doc_metadata, dict):
             raise ValueError("doc_metadata must be a dictionary.")
-
-        metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[doc_type]
+        metadata_schema: dict = cast(dict, DocumentService.DOCUMENT_METADATA_SCHEMA[doc_type])
 
         document.doc_metadata = {}
         if doc_type == "others":
@@ -756,9 +783,8 @@ class DocumentStatusApi(DocumentResource):
     @login_required
     @account_initialization_required
     @cloud_edition_billing_resource_check("vector_space")
-    def patch(self, dataset_id, document_id, action):
+    def patch(self, dataset_id, action):
         dataset_id = str(dataset_id)
-        document_id = str(document_id)
         dataset = DatasetService.get_dataset(dataset_id)
         if dataset is None:
             raise NotFound("Dataset not found.")
@@ -773,84 +799,79 @@ class DocumentStatusApi(DocumentResource):
         # check user's permission
         DatasetService.check_dataset_permission(dataset, current_user)
 
-        document = self.get_document(dataset_id, document_id)
+        document_ids = request.args.getlist("document_id")
+        for document_id in document_ids:
+            document = self.get_document(dataset_id, document_id)
 
-        indexing_cache_key = "document_{}_indexing".format(document.id)
-        cache_result = redis_client.get(indexing_cache_key)
-        if cache_result is not None:
-            raise InvalidActionError("Document is being indexed, please try again later")
+            indexing_cache_key = "document_{}_indexing".format(document.id)
+            cache_result = redis_client.get(indexing_cache_key)
+            if cache_result is not None:
+                raise InvalidActionError(f"Document:{document.name} is being indexed, please try again later")
 
-        if action == "enable":
-            if document.enabled:
-                raise InvalidActionError("Document already enabled.")
+            if action == "enable":
+                if document.enabled:
+                    continue
+                document.enabled = True
+                document.disabled_at = None
+                document.disabled_by = None
+                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
+                db.session.commit()
 
-            document.enabled = True
-            document.disabled_at = None
-            document.disabled_by = None
-            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-            db.session.commit()
+                # Set cache to prevent indexing the same document multiple times
+                redis_client.setex(indexing_cache_key, 600, 1)
 
-            # Set cache to prevent indexing the same document multiple times
-            redis_client.setex(indexing_cache_key, 600, 1)
+                add_document_to_index_task.delay(document_id)
 
-            add_document_to_index_task.delay(document_id)
+            elif action == "disable":
+                if not document.completed_at or document.indexing_status != "completed":
+                    raise InvalidActionError(f"Document: {document.name} is not completed.")
+                if not document.enabled:
+                    continue
 
-            return {"result": "success"}, 200
+                document.enabled = False
+                document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
+                document.disabled_by = current_user.id
+                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
+                db.session.commit()
 
-        elif action == "disable":
-            if not document.completed_at or document.indexing_status != "completed":
-                raise InvalidActionError("Document is not completed.")
-            if not document.enabled:
-                raise InvalidActionError("Document already disabled.")
-
-            document.enabled = False
-            document.disabled_at = datetime.now(UTC).replace(tzinfo=None)
-            document.disabled_by = current_user.id
-            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-            db.session.commit()
-
-            # Set cache to prevent indexing the same document multiple times
-            redis_client.setex(indexing_cache_key, 600, 1)
-
-            remove_document_from_index_task.delay(document_id)
-
-            return {"result": "success"}, 200
-
-        elif action == "archive":
-            if document.archived:
-                raise InvalidActionError("Document already archived.")
-
-            document.archived = True
-            document.archived_at = datetime.now(UTC).replace(tzinfo=None)
-            document.archived_by = current_user.id
-            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-            db.session.commit()
-
-            if document.enabled:
                 # Set cache to prevent indexing the same document multiple times
                 redis_client.setex(indexing_cache_key, 600, 1)
 
                 remove_document_from_index_task.delay(document_id)
 
-            return {"result": "success"}, 200
-        elif action == "un_archive":
-            if not document.archived:
-                raise InvalidActionError("Document is not archived.")
+            elif action == "archive":
+                if document.archived:
+                    continue
 
-            document.archived = False
-            document.archived_at = None
-            document.archived_by = None
-            document.updated_at = datetime.now(UTC).replace(tzinfo=None)
-            db.session.commit()
+                document.archived = True
+                document.archived_at = datetime.now(UTC).replace(tzinfo=None)
+                document.archived_by = current_user.id
+                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
+                db.session.commit()
 
-            # Set cache to prevent indexing the same document multiple times
-            redis_client.setex(indexing_cache_key, 600, 1)
+                if document.enabled:
+                    # Set cache to prevent indexing the same document multiple times
+                    redis_client.setex(indexing_cache_key, 600, 1)
 
-            add_document_to_index_task.delay(document_id)
+                    remove_document_from_index_task.delay(document_id)
 
-            return {"result": "success"}, 200
-        else:
-            raise InvalidActionError()
+            elif action == "un_archive":
+                if not document.archived:
+                    continue
+                document.archived = False
+                document.archived_at = None
+                document.archived_by = None
+                document.updated_at = datetime.now(UTC).replace(tzinfo=None)
+                db.session.commit()
+
+                # Set cache to prevent indexing the same document multiple times
+                redis_client.setex(indexing_cache_key, 600, 1)
+
+                add_document_to_index_task.delay(document_id)
+
+            else:
+                raise InvalidActionError()
+        return {"result": "success"}, 200
 
 
 class DocumentPauseApi(DocumentResource):
@@ -947,7 +968,7 @@ class DocumentRetryApi(DocumentResource):
                 if document.indexing_status == "completed":
                     raise DocumentAlreadyFinishedError()
                 retry_documents.append(document)
-            except Exception as e:
+            except Exception:
                 logging.exception(f"Failed to retry document, document id: {document_id}")
                 continue
         # retry document
@@ -1021,7 +1042,7 @@ api.add_resource(
 )
 api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
 api.add_resource(DocumentMetadataApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/metadata")
-api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/status/<string:action>")
+api.add_resource(DocumentStatusApi, "/datasets/<uuid:dataset_id>/documents/status/<string:action>/batch")
 api.add_resource(DocumentPauseApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/pause")
 api.add_resource(DocumentRecoverApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/processing/resume")
 api.add_resource(DocumentRetryApi, "/datasets/<uuid:dataset_id>/retry")

api/controllers/console/datasets/datasets_segments.py

@@ -1,16 +1,21 @@
 import uuid
-from datetime import UTC, datetime
 
 import pandas as pd
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, NotFound
 
 import services
 from controllers.console import api
 from controllers.console.app.error import ProviderNotInitializeError
-from controllers.console.datasets.error import InvalidActionError, NoFileUploadedError, TooManyFilesError
+from controllers.console.datasets.error import (
+    ChildChunkDeleteIndexError,
+    ChildChunkIndexingError,
+    InvalidActionError,
+    NoFileUploadedError,
+    TooManyFilesError,
+)
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_knowledge_limit_check,
@@ -20,15 +25,15 @@ from controllers.console.wraps import (
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
-from extensions.ext_database import db
 from extensions.ext_redis import redis_client
-from fields.segment_fields import segment_fields
+from fields.segment_fields import child_chunk_fields, segment_fields
 from libs.login import login_required
-from models import DocumentSegment
+from models.dataset import ChildChunk, DocumentSegment
 from services.dataset_service import DatasetService, DocumentService, SegmentService
+from services.entities.knowledge_entities.knowledge_entities import ChildChunkUpdateArgs, SegmentUpdateArgs
+from services.errors.chunk import ChildChunkDeleteIndexError as ChildChunkDeleteIndexServiceError
+from services.errors.chunk import ChildChunkIndexingError as ChildChunkIndexingServiceError
 from tasks.batch_create_segment_to_index_task import batch_create_segment_to_index_task
-from tasks.disable_segment_from_index_task import disable_segment_from_index_task
-from tasks.enable_segment_to_index_task import enable_segment_to_index_task
 
 
 class DatasetDocumentSegmentListApi(Resource):
@@ -53,15 +58,16 @@ class DatasetDocumentSegmentListApi(Resource):
             raise NotFound("Document not found.")
 
         parser = reqparse.RequestParser()
-        parser.add_argument("last_id", type=str, default=None, location="args")
         parser.add_argument("limit", type=int, default=20, location="args")
         parser.add_argument("status", type=str, action="append", default=[], location="args")
         parser.add_argument("hit_count_gte", type=int, default=None, location="args")
         parser.add_argument("enabled", type=str, default="all", location="args")
         parser.add_argument("keyword", type=str, default=None, location="args")
+        parser.add_argument("page", type=int, default=1, location="args")
+
         args = parser.parse_args()
 
-        last_id = args["last_id"]
+        page = args["page"]
         limit = min(args["limit"], 100)
         status_list = args["status"]
         hit_count_gte = args["hit_count_gte"]
@@ -69,14 +75,7 @@ class DatasetDocumentSegmentListApi(Resource):
 
         query = DocumentSegment.query.filter(
             DocumentSegment.document_id == str(document_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        )
-
-        if last_id is not None:
-            last_segment = db.session.get(DocumentSegment, str(last_id))
-            if last_segment:
-                query = query.filter(DocumentSegment.position > last_segment.position)
-            else:
-                return {"data": [], "has_more": False, "limit": limit}, 200
+        ).order_by(DocumentSegment.position.asc())
 
         if status_list:
             query = query.filter(DocumentSegment.status.in_(status_list))
@@ -93,21 +92,44 @@ class DatasetDocumentSegmentListApi(Resource):
             elif args["enabled"].lower() == "false":
                 query = query.filter(DocumentSegment.enabled == False)
 
-        total = query.count()
-        segments = query.order_by(DocumentSegment.position).limit(limit + 1).all()
+        segments = query.paginate(page=page, per_page=limit, max_per_page=100, error_out=False)
 
-        has_more = False
-        if len(segments) > limit:
-            has_more = True
-            segments = segments[:-1]
-
-        return {
-            "data": marshal(segments, segment_fields),
-            "doc_form": document.doc_form,
-            "has_more": has_more,
+        response = {
+            "data": marshal(segments.items, segment_fields),
             "limit": limit,
-            "total": total,
-        }, 200
+            "total": segments.total,
+            "total_pages": segments.pages,
+            "page": page,
+        }
+        return response, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        segment_ids = request.args.getlist("segment_id")
+
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        SegmentService.delete_segments(segment_ids, document, dataset)
+        return {"result": "success"}, 200
 
 
 class DatasetDocumentSegmentApi(Resource):
@@ -115,11 +137,15 @@ class DatasetDocumentSegmentApi(Resource):
     @login_required
     @account_initialization_required
     @cloud_edition_billing_resource_check("vector_space")
-    def patch(self, dataset_id, segment_id, action):
+    def patch(self, dataset_id, document_id, action):
         dataset_id = str(dataset_id)
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound("Dataset not found.")
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
         # check user's model setting
         DatasetService.check_dataset_model_setting(dataset)
         # The role of the current user in the ta table must be admin, owner, or editor
@@ -147,59 +173,17 @@ class DatasetDocumentSegmentApi(Resource):
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
+        segment_ids = request.args.getlist("segment_id")
 
-        segment = DocumentSegment.query.filter(
-            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
-        ).first()
-
-        if not segment:
-            raise NotFound("Segment not found.")
-
-        if segment.status != "completed":
-            raise NotFound("Segment is not completed, enable or disable function is not allowed")
-
-        document_indexing_cache_key = "document_{}_indexing".format(segment.document_id)
+        document_indexing_cache_key = "document_{}_indexing".format(document.id)
         cache_result = redis_client.get(document_indexing_cache_key)
         if cache_result is not None:
             raise InvalidActionError("Document is being indexed, please try again later")
-
-        indexing_cache_key = "segment_{}_indexing".format(segment.id)
-        cache_result = redis_client.get(indexing_cache_key)
-        if cache_result is not None:
-            raise InvalidActionError("Segment is being indexed, please try again later")
-
-        if action == "enable":
-            if segment.enabled:
-                raise InvalidActionError("Segment is already enabled.")
-
-            segment.enabled = True
-            segment.disabled_at = None
-            segment.disabled_by = None
-            db.session.commit()
-
-            # Set cache to prevent indexing the same segment multiple times
-            redis_client.setex(indexing_cache_key, 600, 1)
-
-            enable_segment_to_index_task.delay(segment.id)
-
-            return {"result": "success"}, 200
-        elif action == "disable":
-            if not segment.enabled:
-                raise InvalidActionError("Segment is already disabled.")
-
-            segment.enabled = False
-            segment.disabled_at = datetime.now(UTC).replace(tzinfo=None)
-            segment.disabled_by = current_user.id
-            db.session.commit()
-
-            # Set cache to prevent indexing the same segment multiple times
-            redis_client.setex(indexing_cache_key, 600, 1)
-
-            disable_segment_from_index_task.delay(segment.id)
-
-            return {"result": "success"}, 200
-        else:
-            raise InvalidActionError()
+        try:
+            SegmentService.update_segments_status(segment_ids, action, dataset, document)
+        except Exception as e:
+            raise InvalidActionError(str(e))
+        return {"result": "success"}, 200
 
 
 class DatasetDocumentSegmentAddApi(Resource):
@@ -307,9 +291,12 @@ class DatasetDocumentSegmentUpdateApi(Resource):
         parser.add_argument("content", type=str, required=True, nullable=False, location="json")
         parser.add_argument("answer", type=str, required=False, nullable=True, location="json")
         parser.add_argument("keywords", type=list, required=False, nullable=True, location="json")
+        parser.add_argument(
+            "regenerate_child_chunks", type=bool, required=False, nullable=True, default=False, location="json"
+        )
         args = parser.parse_args()
         SegmentService.segment_create_args_validate(args, document)
-        segment = SegmentService.update_segment(args, segment, document, dataset)
+        segment = SegmentService.update_segment(SegmentUpdateArgs(**args), segment, document, dataset)
         return {"data": marshal(segment, segment_fields), "doc_form": document.doc_form}, 200
 
     @setup_required
@@ -412,8 +399,248 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
         return {"job_id": job_id, "job_status": cache_result.decode()}, 200
 
 
+class ChildChunkAddApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    @cloud_edition_billing_knowledge_limit_check("add_segment")
+    def post(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        if not current_user.is_editor:
+            raise Forbidden()
+        # check embedding model setting
+        if dataset.indexing_technique == "high_quality":
+            try:
+                model_manager = ModelManager()
+                model_manager.get_model_instance(
+                    tenant_id=current_user.current_tenant_id,
+                    provider=dataset.embedding_model_provider,
+                    model_type=ModelType.TEXT_EMBEDDING,
+                    model=dataset.embedding_model,
+                )
+            except LLMBadRequestError:
+                raise ProviderNotInitializeError(
+                    "No Embedding Model available. Please configure a valid provider "
+                    "in the Settings -> Model Provider."
+                )
+            except ProviderTokenNotInitError as ex:
+                raise ProviderNotInitializeError(ex.description)
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            child_chunk = SegmentService.create_child_chunk(args.get("content"), segment, document, dataset)
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunk, child_chunk_fields)}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        parser = reqparse.RequestParser()
+        parser.add_argument("limit", type=int, default=20, location="args")
+        parser.add_argument("keyword", type=str, default=None, location="args")
+        parser.add_argument("page", type=int, default=1, location="args")
+
+        args = parser.parse_args()
+
+        page = args["page"]
+        limit = min(args["limit"], 100)
+        keyword = args["keyword"]
+
+        child_chunks = SegmentService.get_child_chunks(segment_id, document_id, dataset_id, page, limit, keyword)
+        return {
+            "data": marshal(child_chunks.items, child_chunk_fields),
+            "total": child_chunks.total,
+            "total_pages": child_chunks.pages,
+            "page": page,
+            "limit": limit,
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, segment_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+            # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # The role of the current user in the ta table must be admin, owner, or editor
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("chunks", type=list, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            chunks = [ChildChunkUpdateArgs(**chunk) for chunk in args.get("chunks")]
+            child_chunks = SegmentService.update_child_chunks(chunks, segment, document, dataset)
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunks, child_chunk_fields)}, 200
+
+
+class ChildChunkUpdateApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def delete(self, dataset_id, document_id, segment_id, child_chunk_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # check child chunk
+        child_chunk_id = str(child_chunk_id)
+        child_chunk = ChildChunk.query.filter(
+            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not child_chunk:
+            raise NotFound("Child chunk not found.")
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        try:
+            SegmentService.delete_child_chunk(child_chunk, dataset)
+        except ChildChunkDeleteIndexServiceError as e:
+            raise ChildChunkDeleteIndexError(str(e))
+        return {"result": "success"}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @cloud_edition_billing_resource_check("vector_space")
+    def patch(self, dataset_id, document_id, segment_id, child_chunk_id):
+        # check dataset
+        dataset_id = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check user's model setting
+        DatasetService.check_dataset_model_setting(dataset)
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset_id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+            # check segment
+        segment_id = str(segment_id)
+        segment = DocumentSegment.query.filter(
+            DocumentSegment.id == str(segment_id), DocumentSegment.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not segment:
+            raise NotFound("Segment not found.")
+        # check child chunk
+        child_chunk_id = str(child_chunk_id)
+        child_chunk = ChildChunk.query.filter(
+            ChildChunk.id == str(child_chunk_id), ChildChunk.tenant_id == current_user.current_tenant_id
+        ).first()
+        if not child_chunk:
+            raise NotFound("Child chunk not found.")
+        # The role of the current user in the ta table must be admin or owner
+        if not current_user.is_editor:
+            raise Forbidden()
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+        # validate args
+        parser = reqparse.RequestParser()
+        parser.add_argument("content", type=str, required=True, nullable=False, location="json")
+        args = parser.parse_args()
+        try:
+            child_chunk = SegmentService.update_child_chunk(
+                args.get("content"), child_chunk, segment, document, dataset
+            )
+        except ChildChunkIndexingServiceError as e:
+            raise ChildChunkIndexingError(str(e))
+        return {"data": marshal(child_chunk, child_chunk_fields)}, 200
+
+
 api.add_resource(DatasetDocumentSegmentListApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments")
-api.add_resource(DatasetDocumentSegmentApi, "/datasets/<uuid:dataset_id>/segments/<uuid:segment_id>/<string:action>")
+api.add_resource(
+    DatasetDocumentSegmentApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment/<string:action>"
+)
 api.add_resource(DatasetDocumentSegmentAddApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segment")
 api.add_resource(
     DatasetDocumentSegmentUpdateApi,
@@ -424,3 +651,11 @@ api.add_resource(
     "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/batch_import",
     "/datasets/batch_import_status/<uuid:job_id>",
 )
+api.add_resource(
+    ChildChunkAddApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks",
+)
+api.add_resource(
+    ChildChunkUpdateApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/segments/<uuid:segment_id>/child_chunks/<uuid:child_chunk_id>",
+)

api/controllers/console/datasets/error.py

@@ -89,3 +89,15 @@ class IndexingEstimateError(BaseHTTPException):
     error_code = "indexing_estimate_error"
     description = "Knowledge indexing estimate failed: {message}"
     code = 500
+
+
+class ChildChunkIndexingError(BaseHTTPException):
+    error_code = "child_chunk_indexing_error"
+    description = "Create child chunk index failed: {message}"
+    code = 500
+
+
+class ChildChunkDeleteIndexError(BaseHTTPException):
+    error_code = "child_chunk_delete_index_error"
+    description = "Delete child chunk index failed: {message}"
+    code = 500

api/controllers/console/datasets/external.py

@@ -1,6 +1,6 @@
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services

api/controllers/console/datasets/hit_testing.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource
+from flask_restful import Resource  # type: ignore
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase

api/controllers/console/datasets/hit_testing_base.py

@@ -1,7 +1,7 @@
 import logging
 
-from flask_login import current_user
-from flask_restful import marshal, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import marshal, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services.dataset_service

api/controllers/console/datasets/website.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError

api/controllers/console/explore/audio.py

@@ -4,7 +4,6 @@ from flask import request
 from werkzeug.exceptions import InternalServerError
 
 import services
-from controllers.console import api
 from controllers.console.app.error import (
     AppUnavailableError,
     AudioTooLargeError,
@@ -67,7 +66,7 @@ class ChatAudioApi(InstalledAppResource):
 
 class ChatTextApi(InstalledAppResource):
     def post(self, installed_app):
-        from flask_restful import reqparse
+        from flask_restful import reqparse  # type: ignore
 
         app_model = installed_app.app
         try:
@@ -118,9 +117,3 @@ class ChatTextApi(InstalledAppResource):
         except Exception as e:
             logging.exception("internal server error.")
             raise InternalServerError()
-
-
-api.add_resource(ChatAudioApi, "/installed-apps/<uuid:installed_app_id>/audio-to-text", endpoint="installed_app_audio")
-api.add_resource(ChatTextApi, "/installed-apps/<uuid:installed_app_id>/text-to-audio", endpoint="installed_app_text")
-# api.add_resource(ChatTextApiWithMessageId, '/installed-apps/<uuid:installed_app_id>/text-to-audio/message-id',
-#                  endpoint='installed_app_text_with_message_id')

api/controllers/console/explore/completion.py

@@ -1,12 +1,11 @@
 import logging
 from datetime import UTC, datetime
 
-from flask_login import current_user
-from flask_restful import reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import reqparse  # type: ignore
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
-from controllers.console import api
 from controllers.console.app.error import (
     AppUnavailableError,
     CompletionRequestError,
@@ -147,21 +146,3 @@ class ChatStopApi(InstalledAppResource):
         AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
 
         return {"result": "success"}, 200
-
-
-api.add_resource(
-    CompletionApi, "/installed-apps/<uuid:installed_app_id>/completion-messages", endpoint="installed_app_completion"
-)
-api.add_resource(
-    CompletionStopApi,
-    "/installed-apps/<uuid:installed_app_id>/completion-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_completion",
-)
-api.add_resource(
-    ChatApi, "/installed-apps/<uuid:installed_app_id>/chat-messages", endpoint="installed_app_chat_completion"
-)
-api.add_resource(
-    ChatStopApi,
-    "/installed-apps/<uuid:installed_app_id>/chat-messages/<string:task_id>/stop",
-    endpoint="installed_app_stop_chat_completion",
-)

api/controllers/console/explore/conversation.py

@@ -1,12 +1,13 @@
-from flask_login import current_user
-from flask_restful import marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_login import current_user  # type: ignore
+from flask_restful import marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
-from controllers.console import api
 from controllers.console.explore.error import NotChatAppError
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.entities.app_invoke_entities import InvokeFrom
+from extensions.ext_database import db
 from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import uuid_value
 from models.model import AppMode
@@ -34,14 +35,16 @@ class ConversationListApi(InstalledAppResource):
             pinned = True if args["pinned"] == "true" else False
 
         try:
-            return WebConversationService.pagination_by_last_id(
-                app_model=app_model,
-                user=current_user,
-                last_id=args["last_id"],
-                limit=args["limit"],
-                invoke_from=InvokeFrom.EXPLORE,
-                pinned=pinned,
-            )
+            with Session(db.engine) as session:
+                return WebConversationService.pagination_by_last_id(
+                    session=session,
+                    app_model=app_model,
+                    user=current_user,
+                    last_id=args["last_id"],
+                    limit=args["limit"],
+                    invoke_from=InvokeFrom.EXPLORE,
+                    pinned=pinned,
+                )
         except LastConversationNotExistsError:
             raise NotFound("Last Conversation Not Exists.")
 
@@ -114,28 +117,3 @@ class ConversationUnPinApi(InstalledAppResource):
         WebConversationService.unpin(app_model, conversation_id, current_user)
 
         return {"result": "success"}
-
-
-api.add_resource(
-    ConversationRenameApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/name",
-    endpoint="installed_app_conversation_rename",
-)
-api.add_resource(
-    ConversationListApi, "/installed-apps/<uuid:installed_app_id>/conversations", endpoint="installed_app_conversations"
-)
-api.add_resource(
-    ConversationApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>",
-    endpoint="installed_app_conversation",
-)
-api.add_resource(
-    ConversationPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/pin",
-    endpoint="installed_app_conversation_pin",
-)
-api.add_resource(
-    ConversationUnPinApi,
-    "/installed-apps/<uuid:installed_app_id>/conversations/<uuid:c_id>/unpin",
-    endpoint="installed_app_conversation_unpin",
-)

api/controllers/console/explore/installed_app.py

@@ -1,7 +1,9 @@
 from datetime import UTC, datetime
+from typing import Any
 
-from flask_login import current_user
-from flask_restful import Resource, inputs, marshal_with, reqparse
+from flask import request
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
 from sqlalchemy import and_
 from werkzeug.exceptions import BadRequest, Forbidden, NotFound
 
@@ -20,11 +22,20 @@ class InstalledAppsListApi(Resource):
     @account_initialization_required
     @marshal_with(installed_app_list_fields)
     def get(self):
+        app_id = request.args.get("app_id", default=None, type=str)
         current_tenant_id = current_user.current_tenant_id
-        installed_apps = db.session.query(InstalledApp).filter(InstalledApp.tenant_id == current_tenant_id).all()
+
+        if app_id:
+            installed_apps = (
+                db.session.query(InstalledApp)
+                .filter(and_(InstalledApp.tenant_id == current_tenant_id, InstalledApp.app_id == app_id))
+                .all()
+            )
+        else:
+            installed_apps = db.session.query(InstalledApp).filter(InstalledApp.tenant_id == current_tenant_id).all()
 
         current_user.role = TenantService.get_user_role(current_user, current_user.current_tenant)
-        installed_apps = [
+        installed_app_list: list[dict[str, Any]] = [
             {
                 "id": installed_app.id,
                 "app": installed_app.app,
@@ -37,7 +48,7 @@ class InstalledAppsListApi(Resource):
             for installed_app in installed_apps
             if installed_app.app is not None
         ]
-        installed_apps.sort(
+        installed_app_list.sort(
             key=lambda app: (
                 -app["is_pinned"],
                 app["last_used_at"] is None,
@@ -45,7 +56,7 @@ class InstalledAppsListApi(Resource):
             )
         )
 
-        return {"installed_apps": installed_apps}
+        return {"installed_apps": installed_app_list}
 
     @login_required
     @account_initialization_required

api/controllers/console/explore/message.py

@@ -1,12 +1,11 @@
 import logging
 
-from flask_login import current_user
-from flask_restful import marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_login import current_user  # type: ignore
+from flask_restful import marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 from werkzeug.exceptions import InternalServerError, NotFound
 
 import services
-from controllers.console import api
 from controllers.console.app.error import (
     AppMoreLikeThisDisabledError,
     CompletionRequestError,
@@ -70,7 +69,7 @@ class MessageFeedbackApi(InstalledAppResource):
         args = parser.parse_args()
 
         try:
-            MessageService.create_feedback(app_model, message_id, current_user, args["rating"])
+            MessageService.create_feedback(app_model, message_id, current_user, args.get("rating"), args.get("content"))
         except services.errors.message.MessageNotExistsError:
             raise NotFound("Message Not Exists.")
 
@@ -153,21 +152,3 @@ class MessageSuggestedQuestionApi(InstalledAppResource):
             raise InternalServerError()
 
         return {"data": questions}
-
-
-api.add_resource(MessageListApi, "/installed-apps/<uuid:installed_app_id>/messages", endpoint="installed_app_messages")
-api.add_resource(
-    MessageFeedbackApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/feedbacks",
-    endpoint="installed_app_message_feedback",
-)
-api.add_resource(
-    MessageMoreLikeThisApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/more-like-this",
-    endpoint="installed_app_more_like_this",
-)
-api.add_resource(
-    MessageSuggestedQuestionApi,
-    "/installed-apps/<uuid:installed_app_id>/messages/<uuid:message_id>/suggested-questions",
-    endpoint="installed_app_suggested_question",
-)

api/controllers/console/explore/parameter.py

@@ -1,4 +1,4 @@
-from flask_restful import marshal_with
+from flask_restful import marshal_with  # type: ignore
 
 from controllers.common import fields
 from controllers.common import helpers as controller_helpers

api/controllers/console/explore/recommended_app.py

@@ -1,9 +1,10 @@
-from flask_login import current_user
-from flask_restful import Resource, fields, marshal_with, reqparse
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, fields, marshal_with, reqparse  # type: ignore
 
 from constants.languages import languages
 from controllers.console import api
 from controllers.console.wraps import account_initialization_required
+from libs.helper import AppIconUrlField
 from libs.login import login_required
 from services.recommended_app_service import RecommendedAppService
 
@@ -12,6 +13,8 @@ app_fields = {
     "name": fields.String,
     "mode": fields.String,
     "icon": fields.String,
+    "icon_type": fields.String,
+    "icon_url": AppIconUrlField,
     "icon_background": fields.String,
 }
 

api/controllers/console/explore/saved_message.py

@@ -1,6 +1,6 @@
-from flask_login import current_user
-from flask_restful import fields, marshal_with, reqparse
-from flask_restful.inputs import int_range
+from flask_login import current_user  # type: ignore
+from flask_restful import fields, marshal_with, reqparse  # type: ignore
+from flask_restful.inputs import int_range  # type: ignore
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api

api/controllers/console/explore/workflow.py

@@ -1,9 +1,8 @@
 import logging
 
-from flask_restful import reqparse
+from flask_restful import reqparse  # type: ignore
 from werkzeug.exceptions import InternalServerError
 
-from controllers.console import api
 from controllers.console.app.error import (
     CompletionRequestError,
     ProviderModelCurrentlyNotSupportError,
@@ -73,9 +72,3 @@ class InstalledAppWorkflowTaskStopApi(InstalledAppResource):
         AppQueueManager.set_stop_flag(task_id, InvokeFrom.EXPLORE, current_user.id)
 
         return {"result": "success"}
-
-
-api.add_resource(InstalledAppWorkflowRunApi, "/installed-apps/<uuid:installed_app_id>/workflows/run")
-api.add_resource(
-    InstalledAppWorkflowTaskStopApi, "/installed-apps/<uuid:installed_app_id>/workflows/tasks/<string:task_id>/stop"
-)