fix: tool info

Co-authored-by: xudong2.zhang <xudong2.zhang@zkh.com>
Co-authored-by: crazywoola <427733928@qq.com>

.devcontainer/post_create_command.sh

@@ -1,11 +1,12 @@
 #!/bin/bash
 
-cd web && npm install
+npm add -g pnpm@9.12.2
+cd web && pnpm install
 pipx install poetry
 
 echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
 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-web="cd /workspaces/dify/web && pnpm 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
 

.github/actions/setup-poetry/action.yml

@@ -8,7 +8,7 @@ inputs:
   poetry-version:
     description: Poetry version to set up
     required: true
-    default: '1.8.4'
+    default: '2.0.1'
   poetry-lockfile:
     description: Path to the Poetry lockfile to restore cache from
     required: true

.github/workflows/api-tests.yml

@@ -26,6 +26,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python ${{ matrix.python-version }}
         uses: ./.github/actions/setup-poetry
@@ -42,19 +45,17 @@ jobs:
         run: poetry install -C api --with dev
 
       - name: Check dependencies in pyproject.toml
-        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+        run: poetry run -P api bash dev/pytest/pytest_artifacts.sh
 
       - name: Run Unit tests
-        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
-
-      - name: Run ModelRuntime
-        run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
+        run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh
 
       - name: Run dify config tests
-        run: poetry run -C api python dev/pytest/pytest_config_tests.py
+        run: poetry run -P 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: |
+          poetry run -C api python -m mypy --install-types --non-interactive .
 
       - name: Set up dotenvs
         run: |
@@ -74,4 +75,4 @@ jobs:
             ssrf_proxy
 
       - name: Run Workflow
-        run: poetry run -C api bash dev/pytest/pytest_workflow.sh
+        run: poetry run -P api bash dev/pytest/pytest_workflow.sh

.github/workflows/build-push.yml

@@ -79,10 +79,12 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}
 
       - name: Export digest
+        env:
+          DIGEST: ${{ steps.build.outputs.digest }}
         run: |
           mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
+          sanitized_digest=${DIGEST#sha256:}
+          touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
         uses: actions/upload-artifact@v4
@@ -132,10 +134,15 @@ jobs:
 
       - name: Create manifest list and push
         working-directory: /tmp/digests
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
         run: |
           docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env[matrix.image_name_env] }}@sha256:%s ' *)
+            $(printf "$IMAGE_NAME@sha256:%s " *)
 
       - name: Inspect image
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
+          IMAGE_VERSION: ${{ steps.meta.outputs.version }}
         run: |
-          docker buildx imagetools inspect ${{ env[matrix.image_name_env] }}:${{ steps.meta.outputs.version }}
+          docker buildx imagetools inspect "$IMAGE_NAME:$IMAGE_VERSION"

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

@@ -4,6 +4,7 @@ on:
   pull_request:
     branches:
       - main
+      - plugins/beta
     paths:
       - api/migrations/**
       - .github/workflows/db-migration-test.yml
@@ -19,6 +20,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python
         uses: ./.github/actions/setup-poetry

.github/workflows/docker-build.yml

@@ -0,0 +1,47 @@
+name: Build docker image
+
+on:
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - api/Dockerfile
+      - web/Dockerfile
+
+concurrency:
+  group: docker-build-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build-docker:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - service_name: "api-amd64"
+            platform: linux/amd64
+            context: "api"
+          - service_name: "api-arm64"
+            platform: linux/arm64
+            context: "api"
+          - service_name: "web-amd64"
+            platform: linux/amd64
+            context: "web"
+          - service_name: "web-arm64"
+            platform: linux/arm64
+            context: "web"
+    steps:
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker Image
+        uses: docker/build-push-action@v6
+        with:
+          push: false
+          context: "{{defaultContext}}:${{ matrix.context }}"
+          platforms: ${{ matrix.platform }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/expose_service_ports.sh

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

.github/workflows/style.yml

@@ -17,6 +17,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -38,12 +41,12 @@ jobs:
         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
+          poetry run -C api ruff check ./
+          poetry run -C api ruff format --check ./
 
       - name: Dotenv check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
+        run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example
 
       - name: Lint hints
         if: failure()
@@ -59,6 +62,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -66,22 +72,58 @@ jobs:
         with:
           files: web/**
 
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+          run_install: false
+
       - name: Setup NodeJS
         uses: actions/setup-node@v4
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           node-version: 20
-          cache: yarn
+          cache: pnpm
           cache-dependency-path: ./web/package.json
 
       - name: Web dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn run lint
+        run: pnpm run lint
 
+  docker-compose-template:
+    name: Docker Compose Template
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Check changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v45
+        with:
+          files: |
+            docker/generate_docker_compose
+            docker/.env.example
+            docker/docker-compose-template.yaml
+            docker/docker-compose.yaml
+
+      - name: Generate Docker Compose
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: |
+          cd docker
+          ./generate_docker_compose
+
+      - name: Check for changes
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: git diff --exit-code
 
   superlinter:
     name: SuperLinter
@@ -90,6 +132,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files

.github/workflows/tool-test-sdks.yaml

@@ -26,16 +26,19 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Use Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node-version }}
           cache: ''
-          cache-dependency-path: 'yarn.lock'
+          cache-dependency-path: 'pnpm-lock.yaml'
 
       - name: Install Dependencies
-        run: yarn install
+        run: pnpm install --frozen-lockfile
 
       - name: Test
-        run: yarn test
+        run: pnpm test

.github/workflows/translate-i18n-base-on-english.yml

@@ -16,6 +16,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 2 # last 2 commits
+          persist-credentials: false
 
       - name: Check for file changes in i18n/en-US
         id: check_files
@@ -38,11 +39,11 @@ jobs:
 
       - name: Install dependencies
         if: env.FILES_CHANGED == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile
 
       - name: Run npm script
         if: env.FILES_CHANGED == 'true'
-        run: npm run auto-gen-i18n
+        run: pnpm run auto-gen-i18n
 
       - name: Create Pull Request
         if: env.FILES_CHANGED == 'true'

.github/workflows/vdb-tests.yml

@@ -28,6 +28,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python ${{ matrix.python-version }}
         uses: ./.github/actions/setup-poetry
@@ -51,7 +54,15 @@ jobs:
       - name: Expose Service Ports
         run: sh .github/workflows/expose_service_ports.sh
 
-      - name: Set up Vector Stores (TiDB, Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+      - name: Set up Vector Store (TiDB)
+        uses: hoverkraft-tech/compose-action@v2.0.2
+        with:
+          compose-file: docker/tidb/docker-compose.yaml
+          services: |
+            tidb
+            tiflash
+
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
         uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
@@ -67,7 +78,9 @@ jobs:
             pgvector
             chroma
             elasticsearch
-            tidb
+
+      - name: Check TiDB Ready
+        run: poetry run -P api python api/tests/integration_tests/vdb/tidb_vector/check_tiflash_ready.py
 
       - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
+        run: poetry run -P api bash dev/pytest/pytest_vdb.sh

.github/workflows/web-tests.yml

@@ -22,25 +22,34 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
         uses: tj-actions/changed-files@v45
         with:
           files: web/**
+      # to run pnpm, should install package canvas, but it always install failed on amd64 under ubuntu-latest
+      # - name: Install pnpm
+      #   uses: pnpm/action-setup@v4
+      #   with:
+      #     version: 10
+      #     run_install: false
 
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 20
-          cache: yarn
-          cache-dependency-path: ./web/package.json
+      # - name: Setup Node.js
+      #   uses: actions/setup-node@v4
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   with:
+      #     node-version: 20
+      #     cache: pnpm
+      #     cache-dependency-path: ./web/package.json
 
-      - name: Install dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+      # - name: Install dependencies
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   run: pnpm install --frozen-lockfile
 
-      - name: Run tests
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn test
+      # - name: Run tests
+      #   if: steps.changed-files.outputs.any_changed == 'true'
+      #   run: pnpm test

.gitignore

@@ -163,6 +163,7 @@ docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
 docker/volumes/qdrant/*
+docker/tidb/volumes/*
 docker/volumes/etcd/*
 docker/volumes/minio/*
 docker/volumes/milvus/*
@@ -175,6 +176,7 @@ docker/volumes/pgvector/data/*
 docker/volumes/pgvecto_rs/data/*
 docker/volumes/couchbase/*
 docker/volumes/oceanbase/*
+docker/volumes/plugin_daemon/*
 !docker/volumes/oceanbase/init.d
 
 docker/nginx/conf.d/default.conf
@@ -193,3 +195,9 @@ api/.vscode
 
 .idea/
 .vscode
+
+# pnpm
+/.pnpm-store
+
+# plugin migrate
+plugins.jsonl

README.md

@@ -25,6 +25,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -105,6 +108,72 @@ Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-host
 **7. Backend-as-a-Service**: 
   All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
 
+## Feature Comparison
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Feature</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programming Approach</td>
+    <td align="center">API + App-oriented</td>
+    <td align="center">Python Code</td>
+    <td align="center">App-oriented</td>
+    <td align="center">API-oriented</td>
+  </tr>
+  <tr>
+    <td align="center">Supported LLMs</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">Rich Variety</td>
+    <td align="center">OpenAI-only</td>
+  </tr>
+  <tr>
+    <td align="center">RAG Engine</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Workflow</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Observability</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Enterprise Feature (SSO/Access control)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Local Deployment</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
 ## Using Dify
 

README_AR.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

README_CN.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

README_ES.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="seguir en X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="seguir en LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Descargas de Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

README_FR.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="suivre sur X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="suivre sur LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Tirages Docker" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -52,7 +55,7 @@
 Dify est une plateforme de développement d'applications LLM open source. Son interface intuitive combine un flux de travail d'IA, un pipeline RAG, des capacités d'agent, une gestion de modèles, des fonctionnalités d'observabilité, et plus encore, vous permettant de passer rapidement du prototype à la production. Voici une liste des fonctionnalités principales:
 </br> </br>
 
-**1. Flux de travail**: 
+**1. Flux de travail** : 
   Construisez et testez des flux de travail d'IA puissants sur un canevas visuel, en utilisant toutes les fonctionnalités suivantes et plus encore.
 
 
@@ -60,27 +63,25 @@ Dify est une plateforme de développement d'applications LLM open source. Son in
 
 
 
-**2. Prise en charge complète des modèles**: 
+**2. Prise en charge complète des modèles** : 
   Intégration transparente avec des centaines de LLM propriétaires / open source provenant de dizaines de fournisseurs d'inférence et de solutions auto-hébergées, couvrant GPT, Mistral, Llama3, et tous les modèles compatibles avec l'API OpenAI. Une liste complète des fournisseurs de modèles pris en charge se trouve [ici](https://docs.dify.ai/getting-started/readme/model-providers).
 
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
 
-**3. IDE de prompt**: 
+**3. IDE de prompt** : 
   Interface intuitive pour créer des prompts, comparer les performances des modèles et ajouter des fonctionnalités supplémentaires telles que la synthèse vocale à une application basée sur des chats. 
 
-**4. Pipeline RAG**: 
+**4. Pipeline RAG** : 
   Des capacités RAG étendues qui couvrent tout, de l'ingestion de documents à la récupération, avec un support prêt à l'emploi pour l'extraction de texte à partir de PDF, PPT et autres formats de document courants.
 
-**5. Capac
-
-ités d'agent**: 
+**5. Capacités d'agent** : 
   Vous pouvez définir des agents basés sur l'appel de fonction LLM ou ReAct, et ajouter des outils pré-construits ou personnalisés pour l'agent. Dify fournit plus de 50 outils intégrés pour les agents d'IA, tels que la recherche Google, DALL·E, Stable Diffusion et WolframAlpha.
 
-**6. LLMOps**: 
+**6. LLMOps** : 
   Surveillez et analysez les journaux d'application et les performances au fil du temps. Vous pouvez continuellement améliorer les prompts, les ensembles de données et les modèles en fonction des données de production et des annotations.
 
-**7. Backend-as-a-Service**: 
+**7. Backend-as-a-Service** : 
   Toutes les offres de Dify sont accompagnées d'API correspondantes, vous permettant d'intégrer facilement Dify dans votre propre logique métier.
 
 

README_JA.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="X(Twitter)でフォロー"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="LinkedInでフォロー"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -161,7 +164,7 @@ DifyはオープンソースのLLMアプリケーション開発プラットフ
 
 - **企業/組織向けのDify</br>**
 企業中心の機能を提供しています。[メールを送信](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry)して企業のニーズについて相談してください。 </br>
-  > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングどして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。
+  > AWSを使用しているスタートアップ企業や中小企業の場合は、[AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t23mebxzwjhu6)のDify Premiumをチェックして、ワンクリックで自分のAWS VPCにデプロイできます。さらに、手頃な価格のAMIオファリングとして、ロゴやブランディングをカスタマイズしてアプリケーションを作成するオプションがあります。
 
 
 ## 最新の情報を入手

README_KL.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -84,9 +87,7 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
 
 ## Feature Comparison
 <table style="width: 100%;">
-  <tr
-
->
+  <tr>
     <th align="center">Feature</th>
     <th align="center">Dify.AI</th>
     <th align="center">LangChain</th>

README_KR.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

README_PT.md

@@ -25,6 +25,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

README_SI.md

@@ -22,6 +22,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="follow on X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="follow on LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -103,6 +106,73 @@ Prosimo, glejte naša pogosta vprašanja [FAQ](https://docs.dify.ai/getting-star
 **7. Backend-as-a-Service**: 
   AVse ponudbe Difyja so opremljene z ustreznimi API-ji, tako da lahko Dify brez težav integrirate v svojo poslovno logiko.
 
+## Primerjava Funkcij
+
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Funkcija</th>
+    <th align="center">Dify.AI</th>
+    <th align="center">LangChain</th>
+    <th align="center">Flowise</th>
+    <th align="center">OpenAI Assistants API</th>
+  </tr>
+  <tr>
+    <td align="center">Programski pristop</td>
+    <td align="center">API + usmerjeno v aplikacije</td>
+    <td align="center">Python koda</td>
+    <td align="center">Usmerjeno v aplikacije</td>
+    <td align="center">Usmerjeno v API</td>
+  </tr>
+  <tr>
+    <td align="center">Podprti LLM-ji</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Bogata izbira</td>
+    <td align="center">Samo OpenAI</td>
+  </tr>
+  <tr>
+    <td align="center">RAG pogon</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Agent</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+  </tr>
+  <tr>
+    <td align="center">Potek dela</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Spremljanje</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Funkcija za podjetja (SSO/nadzor dostopa)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Lokalna namestitev</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
 
 ## Uporaba Dify
 
@@ -184,4 +254,4 @@ Zaradi zaščite vaše zasebnosti se izogibajte objavljanju varnostnih vprašanj
 
 ## Licenca
 
-To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.
+To skladišče je na voljo pod [odprtokodno licenco Dify](LICENSE) , ki je v bistvu Apache 2.0 z nekaj dodatnimi omejitvami.

README_TR.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="X(Twitter)'da takip et"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="LinkedIn'da takip et"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Çekmeleri" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">
@@ -62,8 +65,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ![providers-v5](https://github.com/langgenius/dify/assets/13230914/5a17bdbe-097a-4100-8363-40255b70f6e3)
 
 
-Özür dilerim, haklısınız. Daha anlamlı ve akıcı bir çeviri yapmaya çalışayım. İşte güncellenmiş çeviri:
-
 **3. Prompt IDE**: 
   Komut istemlerini oluşturmak, model performansını karşılaştırmak ve sohbet tabanlı uygulamalara metin-konuşma gibi ek özellikler eklemek için kullanıcı dostu bir arayüz.
 
@@ -150,8 +151,6 @@ Görsel bir arayüz üzerinde güçlü AI iş akışları oluşturun ve test edi
 ## Dify'ı Kullanma
 
 - **Cloud </br>**
-İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
-- 
 Herkesin sıfır kurulumla denemesi için bir [Dify Cloud](https://dify.ai) hizmeti sunuyoruz. Bu hizmet, kendi kendine dağıtılan versiyonun tüm yeteneklerini sağlar ve sandbox planında 200 ücretsiz GPT-4 çağrısı içerir.
 
 - **Dify Topluluk Sürümünü Kendi Sunucunuzda Barındırma</br>**
@@ -177,8 +176,6 @@ GitHub'da Dify'a yıldız verin ve yeni sürümlerden anında haberdar olun.
 >- RAM >= 4GB
 
 </br>
-İşte verdiğiniz metnin Türkçe çevirisi, kod bloğu içinde:
-
 Dify sunucusunu başlatmanın en kolay yolu, [docker-compose.yml](docker/docker-compose.yaml) dosyamızı çalıştırmaktır. Kurulum komutunu çalıştırmadan önce, makinenizde [Docker](https://docs.docker.com/get-docker/) ve [Docker Compose](https://docs.docker.com/compose/install/)'un kurulu olduğundan emin olun:
 
 ```bash

README_VI.md

@@ -21,6 +21,9 @@
     <a href="https://twitter.com/intent/follow?screen_name=dify_ai" target="_blank">
         <img src="https://img.shields.io/twitter/follow/dify_ai?logo=X&color=%20%23f5f5f5"
             alt="theo dõi trên X(Twitter)"></a>
+    <a href="https://www.linkedin.com/company/langgenius/" target="_blank">
+        <img src="https://custom-icon-badges.demolab.com/badge/LinkedIn-0A66C2?logo=linkedin-white&logoColor=fff"
+            alt="theo dõi trên LinkedIn"></a>
     <a href="https://hub.docker.com/u/langgenius" target="_blank">
         <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/langgenius/dify-web?labelColor=%20%23FDB062&color=%20%23f79009"></a>
     <a href="https://github.com/langgenius/dify/graphs/commit-activity" target="_blank">

api/.dockerignore

@@ -1,7 +1,10 @@
 .env
 *.env.*
 
+storage/generate_files/*
 storage/privkeys/*
+storage/tools/*
+storage/upload_files/*
 
 # Logs
 logs
@@ -9,6 +12,8 @@ logs
 
 # jetbrains
 .idea
+.mypy_cache
+.ruff_cache
 
 # venv
 .venv

api/.env.example

@@ -23,6 +23,9 @@ FILES_ACCESS_TIMEOUT=300
 # Access token expiration time in minutes
 ACCESS_TOKEN_EXPIRE_MINUTES=60
 
+# Refresh token expiration time in days
+REFRESH_TOKEN_EXPIRE_DAYS=30
+
 # celery configuration
 CELERY_BROKER_URL=redis://:difyai123456@localhost:6379/1
 
@@ -65,7 +68,7 @@ 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
@@ -74,7 +77,7 @@ 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
@@ -88,7 +91,7 @@ ALIYUN_OSS_REGION=your-region
 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
@@ -406,7 +409,6 @@ MAX_VARIABLE_SIZE=204800
 APP_MAX_EXECUTION_TIME=1200
 APP_MAX_ACTIVE_REQUESTS=0
 
-
 # Celery beat configuration
 CELERY_BEAT_SCHEDULER_TIME=1
 
@@ -419,6 +421,22 @@ POSITION_PROVIDER_PINS=
 POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=
 
+# Plugin configuration
+PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
+PLUGIN_DAEMON_URL=http://127.0.0.1:5002
+PLUGIN_REMOTE_INSTALL_PORT=5003
+PLUGIN_REMOTE_INSTALL_HOST=localhost
+PLUGIN_MAX_PACKAGE_SIZE=15728640
+INNER_API_KEY=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
+INNER_API_KEY_FOR_PLUGIN=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
+
+# Marketplace configuration
+MARKETPLACE_ENABLED=true
+MARKETPLACE_API_URL=https://marketplace.dify.ai
+
+# Endpoint configuration
+ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}
+
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
 

api/.ruff.toml

@@ -53,10 +53,12 @@ ignore = [
     "FURB152", # math-constant
     "UP007", # non-pep604-annotation
     "UP032", # f-string
+    "UP045", # non-pep604-annotation-optional
     "B005", # strip-with-multi-characters
     "B006", # mutable-argument-default
     "B007", # unused-loop-control-variable
     "B026", # star-arg-unpacking-after-keyword-arg
+    "B903", # class-as-data-structure
     "B904", # raise-without-from-inside-except
     "B905", # zip-without-explicit-strict
     "N806", # non-lowercase-variable-in-function
@@ -67,7 +69,7 @@ ignore = [
     "SIM105", # suppressible-exception
     "SIM107", # return-in-try-except-finally
     "SIM108", # if-else-block-instead-of-if-exp
-    "SIM113", # eumerate-for-loop
+    "SIM113", # enumerate-for-loop
     "SIM117", # multiple-with-statements
     "SIM210", # if-expr-with-true-false
 ]
@@ -85,11 +87,11 @@ ignore = [
 ]
 "tests/*" = [
     "F811", # redefined-while-unused
-    "F401", # unused-import
 ]
 
 [lint.pyflakes]
-extend-generics = [
+allowed-unused-imports = [
     "_pytest.monkeypatch",
     "tests.integration_tests",
+    "tests.unit_tests",
 ]

api/Dockerfile

@@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api
 
 # Install Poetry
-ENV POETRY_VERSION=1.8.4
+ENV POETRY_VERSION=2.0.1
 
 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -48,16 +48,20 @@ ENV TZ=UTC
 
 WORKDIR /app/api
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-    # if you located in China, you can use aliyun mirror to speed up
-    # && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
-    && 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=5.40.0-8 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 \
+RUN \
+    apt-get update \
+    # Install dependencies
+    && apt-get install -y --no-install-recommends \
+        # basic environment
+        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+        # For Security
+        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        # install a chinese font to support the use of tools like matplotlib
+        fonts-noto-cjk \
+        # install a package to improve the accuracy of guessing mime type and file extension
+        media-types \
+        # install libmagic to support the use of python-magic guess MIMETYPE
+        libmagic1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 
@@ -69,6 +73,10 @@ ENV PATH="${VIRTUAL_ENV}/bin:${PATH}"
 # Download nltk data
 RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
 
+ENV TIKTOKEN_CACHE_DIR=/app/api/.tiktoken_cache
+
+RUN python -c "import tiktoken; tiktoken.encoding_for_model('gpt2')"
+
 # Copy source code
 COPY . /app/api/
 
@@ -76,7 +84,6 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 
-
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}
 

api/README.md

@@ -37,7 +37,13 @@
 
 4. Create environment.
 
-   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. You can execute `poetry shell` to activate the environment.
+   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. First, you need to add the poetry shell plugin, if you don't have it already, in order to run in a virtual environment. [Note: Poetry shell is no longer a native command so you need to install the poetry plugin beforehand]
+
+   ```bash
+   poetry self add poetry-plugin-shell
+   ```
+   
+   Then, You can execute `poetry shell` to activate the environment.
 
 5. Install dependencies
 
@@ -79,5 +85,5 @@
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
 
    ```bash
-   poetry run -C api bash dev/pytest/pytest_all_tests.sh
+   poetry run -P api bash dev/pytest/pytest_all_tests.sh
    ```

api/app.py

@@ -1,12 +1,8 @@
-from libs import version_utils
-
-# preparation before creating app
-version_utils.check_supported_python_version()
+import os
+import sys
 
 
 def is_db_command():
-    import sys
-
     if len(sys.argv) > 1 and sys.argv[0].endswith("flask") and sys.argv[1] == "db":
         return True
     return False
@@ -18,10 +14,25 @@ if is_db_command():
 
     app = create_migrations_app()
 else:
-    from app_factory import create_app
-    from libs import threadings_utils
+    # It seems that JetBrains Python debugger does not work well with gevent,
+    # so we need to disable gevent in debug mode.
+    # If you are using debugpy and set GEVENT_SUPPORT=True, you can debug with gevent.
+    if (flask_debug := os.environ.get("FLASK_DEBUG", "0")) and flask_debug.lower() in {"false", "0", "no"}:
+        from gevent import monkey  # type: ignore
 
-    threadings_utils.apply_gevent_threading_patch()
+        # gevent
+        monkey.patch_all()
+
+        from grpc.experimental import gevent as grpc_gevent  # type: ignore
+
+        # grpc gevent
+        grpc_gevent.init_gevent()
+
+        import psycogreen.gevent  # type: ignore
+
+        psycogreen.gevent.patch_psycopg()
+
+    from app_factory import create_app
 
     app = create_app()
     celery = app.extensions["celery"]

api/commands.py

@@ -25,6 +25,8 @@ from models.dataset import Document as DatasetDocument
 from models.model import Account, App, AppAnnotationSetting, AppMode, Conversation, MessageAnnotation
 from models.provider import Provider, ProviderModel
 from services.account_service import RegisterService, TenantService
+from services.plugin.data_migration import PluginDataMigration
+from services.plugin.plugin_migration import PluginMigration
 
 
 @click.command("reset-password", help="Reset the account password.")
@@ -159,8 +161,7 @@ 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)
             )
@@ -285,8 +286,7 @@ 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)
             )
@@ -450,7 +450,8 @@ 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
@@ -525,7 +526,7 @@ def add_qdrant_doc_id_index(field: str):
                         )
                     )
 
-    except Exception as e:
+    except Exception:
         click.echo(click.style("Failed to create Qdrant client.", fg="red"))
 
     click.echo(click.style(f"Index creation complete. Created {create_count} collection indexes.", fg="green"))
@@ -555,14 +556,20 @@ 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(
@@ -582,13 +589,13 @@ 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()
 
             click.echo(click.style("Database migration successful!", fg="green"))
 
-        except Exception as e:
+        except Exception:
             logging.exception("Failed to execute database migration")
         finally:
             lock.release()
@@ -620,6 +627,10 @@ 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()
@@ -630,7 +641,7 @@ where sites.id is null limit 1000"""
                         account = accounts[0]
                         print("Fixing missing site for app {}".format(app.id))
                         app_was_created.send(app, account=account)
-                except Exception as e:
+                except Exception:
                     failed_app_ids.append(app_id)
                     click.echo(click.style("Failed to fix missing site for app {}".format(app_id), fg="red"))
                     logging.exception(f"Failed to fix app related site missing issue, app_id: {app_id}")
@@ -640,3 +651,69 @@ where sites.id is null limit 1000"""
                 break
 
     click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))
+
+
+@click.command("migrate-data-for-plugin", help="Migrate data for plugin.")
+def migrate_data_for_plugin():
+    """
+    Migrate data for plugin.
+    """
+    click.echo(click.style("Starting migrate data for plugin.", fg="white"))
+
+    PluginDataMigration.migrate()
+
+    click.echo(click.style("Migrate data for plugin completed.", fg="green"))
+
+
+@click.command("extract-plugins", help="Extract plugins.")
+@click.option("--output_file", prompt=True, help="The file to store the extracted plugins.", default="plugins.jsonl")
+@click.option("--workers", prompt=True, help="The number of workers to extract plugins.", default=10)
+def extract_plugins(output_file: str, workers: int):
+    """
+    Extract plugins.
+    """
+    click.echo(click.style("Starting extract plugins.", fg="white"))
+
+    PluginMigration.extract_plugins(output_file, workers)
+
+    click.echo(click.style("Extract plugins completed.", fg="green"))
+
+
+@click.command("extract-unique-identifiers", help="Extract unique identifiers.")
+@click.option(
+    "--output_file",
+    prompt=True,
+    help="The file to store the extracted unique identifiers.",
+    default="unique_identifiers.json",
+)
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+def extract_unique_plugins(output_file: str, input_file: str):
+    """
+    Extract unique plugins.
+    """
+    click.echo(click.style("Starting extract unique plugins.", fg="white"))
+
+    PluginMigration.extract_unique_plugins_to_file(input_file, output_file)
+
+    click.echo(click.style("Extract unique plugins completed.", fg="green"))
+
+
+@click.command("install-plugins", help="Install plugins.")
+@click.option(
+    "--input_file", prompt=True, help="The file to store the extracted unique identifiers.", default="plugins.jsonl"
+)
+@click.option(
+    "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
+)
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_plugins(input_file: str, output_file: str, workers: int):
+    """
+    Install plugins.
+    """
+    click.echo(click.style("Starting install plugins.", fg="white"))
+
+    PluginMigration.install_plugins(input_file, output_file, workers)
+
+    click.echo(click.style("Install plugins completed.", fg="green"))

api/configs/feature/__init__.py

@@ -134,6 +134,60 @@ class CodeExecutionSandboxConfig(BaseSettings):
     )
 
 
+class PluginConfig(BaseSettings):
+    """
+    Plugin configs
+    """
+
+    PLUGIN_DAEMON_URL: HttpUrl = Field(
+        description="Plugin API URL",
+        default="http://localhost:5002",
+    )
+
+    PLUGIN_DAEMON_KEY: str = Field(
+        description="Plugin API key",
+        default="plugin-api-key",
+    )
+
+    INNER_API_KEY_FOR_PLUGIN: str = Field(description="Inner api key for plugin", default="inner-api-key")
+
+    PLUGIN_REMOTE_INSTALL_HOST: str = Field(
+        description="Plugin Remote Install Host",
+        default="localhost",
+    )
+
+    PLUGIN_REMOTE_INSTALL_PORT: PositiveInt = Field(
+        description="Plugin Remote Install Port",
+        default=5003,
+    )
+
+    PLUGIN_MAX_PACKAGE_SIZE: PositiveInt = Field(
+        description="Maximum allowed size for plugin packages in bytes",
+        default=15728640,
+    )
+
+    PLUGIN_MAX_BUNDLE_SIZE: PositiveInt = Field(
+        description="Maximum allowed size for plugin bundles in bytes",
+        default=15728640 * 12,
+    )
+
+
+class MarketplaceConfig(BaseSettings):
+    """
+    Configuration for marketplace
+    """
+
+    MARKETPLACE_ENABLED: bool = Field(
+        description="Enable or disable marketplace",
+        default=True,
+    )
+
+    MARKETPLACE_API_URL: HttpUrl = Field(
+        description="Marketplace API URL",
+        default="https://marketplace.dify.ai",
+    )
+
+
 class EndpointConfig(BaseSettings):
     """
     Configuration for various application endpoints and URLs
@@ -146,7 +200,7 @@ class EndpointConfig(BaseSettings):
     )
 
     CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
+        description="Base URL for the console web interface,used for frontend references and CORS configuration",
         default="",
     )
 
@@ -160,6 +214,10 @@ class EndpointConfig(BaseSettings):
         default="",
     )
 
+    ENDPOINT_URL_TEMPLATE: str = Field(
+        description="Template url for endpoint plugin", default="http://localhost:5002/e/{hook_id}"
+    )
+
 
 class FileAccessConfig(BaseSettings):
     """
@@ -239,7 +297,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def CONSOLE_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_CONSOLE_CORS_ALLOW_ORIGINS.split(",")
 
@@ -250,7 +307,6 @@ class HttpConfig(BaseSettings):
     )
 
     @computed_field
-    @property
     def WEB_API_CORS_ALLOW_ORIGINS(self) -> list[str]:
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
@@ -317,8 +373,8 @@ class HttpConfig(BaseSettings):
     )
 
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
-        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
-        " to respect X-* headers to redirect clients",
+        description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
+        " when the app is behind a single trusted reverse proxy.",
         default=False,
     )
 
@@ -490,11 +546,21 @@ class AuthConfig(BaseSettings):
         default=60,
     )
 
+    REFRESH_TOKEN_EXPIRE_DAYS: PositiveFloat = Field(
+        description="Expiration time for refresh tokens in days",
+        default=30,
+    )
+
     LOGIN_LOCKOUT_DURATION: PositiveInt = Field(
         description="Time (in seconds) a user must wait before retrying login after exceeding the rate limit.",
         default=86400,
     )
 
+    FORGOT_PASSWORD_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying password reset after exceeding the rate limit.",
+        default=86400,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """
@@ -603,7 +669,7 @@ class RagEtlConfig(BaseSettings):
 
     UNSTRUCTURED_API_KEY: Optional[str] = Field(
         description="API key for Unstructured.io service",
-        default=None,
+        default="",
     )
 
     SCARF_NO_ANALYTICS: Optional[str] = Field(
@@ -669,6 +735,11 @@ class IndexingConfig(BaseSettings):
         default=4000,
     )
 
+    CHILD_CHUNKS_PREVIEW_NUMBER: PositiveInt = Field(
+        description="Maximum number of child chunks to preview",
+        default=50,
+    )
+
 
 class MultiModalTransferConfig(BaseSettings):
     MULTIMODAL_SEND_FORMAT: Literal["base64", "url"] = Field(
@@ -715,27 +786,27 @@ 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() != ""}
 
@@ -767,12 +838,21 @@ class LoginConfig(BaseSettings):
     )
 
 
+class AccountConfig(BaseSettings):
+    ACCOUNT_DELETION_TOKEN_EXPIRY_MINUTES: PositiveInt = Field(
+        description="Duration in minutes for which a account deletion token remains valid",
+        default=5,
+    )
+
+
 class FeatureConfig(
     # place the configs in alphabet order
     AppExecutionConfig,
     AuthConfig,  # Changed from OAuthConfig to AuthConfig
     BillingConfig,
     CodeExecutionSandboxConfig,
+    PluginConfig,
+    MarketplaceConfig,
     DataSetConfig,
     EndpointConfig,
     FileAccessConfig,
@@ -794,6 +874,7 @@ class FeatureConfig(
     WorkflowNodeExecutionConfig,
     WorkspaceConfig,
     LoginConfig,
+    AccountConfig,
     # hosted services config
     HostedServiceConfig,
     CeleryBeatConfig,

api/configs/feature/hosted_service/__init__.py

@@ -1,9 +1,40 @@
 from typing import Optional
 
-from pydantic import Field, NonNegativeInt
+from pydantic import Field, NonNegativeInt, computed_field
 from pydantic_settings import BaseSettings
 
 
+class HostedCreditConfig(BaseSettings):
+    HOSTED_MODEL_CREDIT_CONFIG: str = Field(
+        description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
+        default="",
+    )
+
+    def get_model_credits(self, model_name: str) -> int:
+        """
+        Get credit value for a specific model name.
+        Returns 1 if model is not found in configuration (default credit).
+
+        :param model_name: The name of the model to search for
+        :return: The credit value for the model
+        """
+        if not self.HOSTED_MODEL_CREDIT_CONFIG:
+            return 1
+
+        try:
+            credit_map = dict(
+                item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
+            )
+
+            # Search for matching model pattern
+            for pattern, credit in credit_map.items():
+                if pattern.strip() == model_name:
+                    return int(credit)
+            return 1  # Default quota if no match found
+        except (ValueError, AttributeError):
+            return 1  # Return default quota if parsing fails
+
+
 class HostedOpenAiConfig(BaseSettings):
     """
     Configuration for hosted OpenAI service
@@ -181,7 +212,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
     """
 
     HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
+        description="Mode for fetching app templates: remote, db, or builtin default to remote,",
         default="remote",
     )
 
@@ -202,5 +233,7 @@ class HostedServiceConfig(
     HostedZhipuAIConfig,
     # moderation
     HostedModerationConfig,
+    # credit config
+    HostedCreditConfig,
 ):
     pass

api/configs/middleware/__init__.py

@@ -1,3 +1,4 @@
+import os
 from typing import Any, Literal, Optional
 from urllib.parse import quote_plus
 
@@ -130,7 +131,6 @@ class DatabaseConfig(BaseSettings):
     )
 
     @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
@@ -167,8 +167,12 @@ class DatabaseConfig(BaseSettings):
         default=False,
     )
 
+    RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
+        description="Number of processes for the retrieval service, default to CPU cores.",
+        default=os.cpu_count(),
+    )
+
     @computed_field
-    @property
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {
             "pool_size": self.SQLALCHEMY_POOL_SIZE,
@@ -206,7 +210,6 @@ class CeleryConfig(DatabaseConfig):
     )
 
     @computed_field
-    @property
     def CELERY_RESULT_BACKEND(self) -> str | None:
         return (
             "db+{}".format(self.SQLALCHEMY_DATABASE_URI)
@@ -214,7 +217,6 @@ 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

api/configs/middleware/vdb/milvus_config.py

@@ -33,3 +33,9 @@ class MilvusConfig(BaseSettings):
         description="Name of the Milvus database to connect to (default is 'default')",
         default="default",
     )
+
+    MILVUS_ENABLE_HYBRID_SEARCH: bool = Field(
+        description="Enable hybrid search features (requires Milvus >= 2.5.0). Set to false for compatibility with "
+        "older versions",
+        default=True,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.14.1",
+        default="1.0.0",
     )
 
     COMMIT_SHA: str = Field(

api/configs/remote_settings_sources/apollo/client.py

@@ -4,6 +4,7 @@ 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
@@ -255,8 +256,8 @@ class ApolloClient:
         logger.info("stopped, long_poll")
 
     # add the need for endorsement to the header
-    def _sign_headers(self, url):
-        headers = {}
+    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)]

api/constants/__init__.py

@@ -15,7 +15,7 @@ AUDIO_EXTENSIONS.extend([ext.upper() for ext in AUDIO_EXTENSIONS])
 
 if dify_config.ETL_TYPE == "Unstructured":
     DOCUMENT_EXTENSIONS = ["txt", "markdown", "md", "mdx", "pdf", "html", "htm", "xlsx", "xls"]
-    DOCUMENT_EXTENSIONS.extend(("docx", "csv", "eml", "msg", "pptx", "xml", "epub"))
+    DOCUMENT_EXTENSIONS.extend(("doc", "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])

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/contexts/__init__.py

@@ -1,9 +1,19 @@
 from contextvars import ContextVar
+from threading import Lock
 from typing import TYPE_CHECKING
 
 if TYPE_CHECKING:
+    from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
+    from core.tools.plugin_tool.provider import PluginToolProviderController
     from core.workflow.entities.variable_pool import VariablePool
 
+
 tenant_id: ContextVar[str] = ContextVar("tenant_id")
 
 workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
+
+plugin_tool_providers: ContextVar[dict[str, "PluginToolProviderController"]] = ContextVar("plugin_tool_providers")
+plugin_tool_providers_lock: ContextVar[Lock] = ContextVar("plugin_tool_providers_lock")
+
+plugin_model_providers: ContextVar[list["PluginModelProviderEntity"] | None] = ContextVar("plugin_model_providers")
+plugin_model_providers_lock: ContextVar[Lock] = ContextVar("plugin_model_providers_lock")

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/common/helpers.py

@@ -1,12 +1,32 @@
 import mimetypes
 import os
+import platform
 import re
 import urllib.parse
+import warnings
 from collections.abc import Mapping
 from typing import Any
 from uuid import uuid4
 
 import httpx
+
+try:
+    import magic
+except ImportError:
+    if platform.system() == "Windows":
+        warnings.warn(
+            "To use python-magic guess MIMETYPE, you need to run `pip install python-magic-bin`", stacklevel=2
+        )
+    elif platform.system() == "Darwin":
+        warnings.warn("To use python-magic guess MIMETYPE, you need to run `brew install libmagic`", stacklevel=2)
+    elif platform.system() == "Linux":
+        warnings.warn(
+            "To use python-magic guess MIMETYPE, you need to run `sudo apt-get install libmagic1`", stacklevel=2
+        )
+    else:
+        warnings.warn("To use python-magic guess MIMETYPE, you need to install `libmagic`", stacklevel=2)
+    magic = None  # type: ignore
+
 from pydantic import BaseModel
 
 from configs import dify_config
@@ -47,6 +67,13 @@ def guess_file_info_from_response(response: httpx.Response):
         # If guessing fails, use Content-Type from response headers
         mimetype = response.headers.get("Content-Type", "application/octet-stream")
 
+    # Use python-magic to guess MIME type if still unknown or generic
+    if mimetype == "application/octet-stream" and magic is not None:
+        try:
+            mimetype = magic.from_buffer(response.content[:1024], mime=True)
+        except magic.MagicException:
+            pass
+
     extension = os.path.splitext(filename)[1]
 
     # Ensure filename has an extension

api/controllers/console/__init__.py

@@ -2,7 +2,26 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
-from .app.app_import import AppImportApi, AppImportConfirmApi
+from .app.app_import import AppImportApi, AppImportCheckDependenciesApi, 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
 
@@ -21,6 +40,7 @@ api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
 # Import App
 api.add_resource(AppImportApi, "/apps/imports")
 api.add_resource(AppImportConfirmApi, "/apps/imports/<string:import_id>/confirm")
+api.add_resource(AppImportCheckDependenciesApi, "/apps/imports/<string:app_id>/check-dependencies")
 
 # Import other controllers
 from . import admin, apikey, extension, feature, ping, setup, version
@@ -66,19 +86,96 @@ 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
 from .tag import tags
 
 # Import workspace controllers
-from .workspace import account, load_balancing_config, members, model_providers, models, tool_providers, workspace
+from .workspace import (
+    account,
+    agent_providers,
+    endpoint,
+    load_balancing_config,
+    members,
+    model_providers,
+    models,
+    plugin,
+    tool_providers,
+    workspace,
+)

api/controllers/console/admin.py

@@ -1,7 +1,9 @@
 from functools import wraps
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
+from sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound, Unauthorized
 
 from configs import dify_config
@@ -54,9 +56,10 @@ class InsertExploreAppListApi(Resource):
         parser.add_argument("position", type=int, required=True, nullable=False, location="json")
         args = parser.parse_args()
 
-        app = App.query.filter(App.id == args["app_id"]).first()
+        with Session(db.engine) as session:
+            app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
         if not app:
-            raise NotFound(f'App \'{args["app_id"]}\' is not found')
+            raise NotFound(f"App '{args['app_id']}' is not found")
 
         site = app.site
         if not site:
@@ -70,7 +73,10 @@ class InsertExploreAppListApi(Resource):
             privacy_policy = site.privacy_policy or args["privacy_policy"] or ""
             custom_disclaimer = site.custom_disclaimer or args["custom_disclaimer"] or ""
 
-        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == args["app_id"]).first()
+        with Session(db.engine) as session:
+            recommended_app = session.execute(
+                select(RecommendedApp).filter(RecommendedApp.app_id == args["app_id"])
+            ).scalar_one_or_none()
 
         if not recommended_app:
             recommended_app = RecommendedApp(
@@ -110,17 +116,27 @@ class InsertExploreAppApi(Resource):
     @only_edition_cloud
     @admin_required
     def delete(self, app_id):
-        recommended_app = RecommendedApp.query.filter(RecommendedApp.app_id == str(app_id)).first()
+        with Session(db.engine) as session:
+            recommended_app = session.execute(
+                select(RecommendedApp).filter(RecommendedApp.app_id == str(app_id))
+            ).scalar_one_or_none()
+
         if not recommended_app:
             return {"result": "success"}, 204
 
-        app = App.query.filter(App.id == recommended_app.app_id).first()
+        with Session(db.engine) as session:
+            app = session.execute(select(App).filter(App.id == recommended_app.app_id)).scalar_one_or_none()
+
         if app:
             app.is_public = False
 
-        installed_apps = InstalledApp.query.filter(
-            InstalledApp.app_id == recommended_app.app_id, InstalledApp.tenant_id != InstalledApp.app_owner_tenant_id
-        ).all()
+        with Session(db.engine) as session:
+            installed_apps = session.execute(
+                select(InstalledApp).filter(
+                    InstalledApp.app_id == recommended_app.app_id,
+                    InstalledApp.tenant_id != InstalledApp.app_owner_tenant_id,
+                )
+            ).all()
 
         for installed_app in installed_apps:
             db.session.delete(installed_app)

api/controllers/console/apikey.py

@@ -1,6 +1,10 @@
-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 sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden
 
 from extensions.ext_database import db
@@ -24,7 +28,16 @@ api_key_list = {"data": fields.List(fields.Nested(api_key_fields), attribute="it
 
 
 def _get_resource(resource_id, tenant_id, resource_model):
-    resource = resource_model.query.filter_by(id=resource_id, tenant_id=tenant_id).first()
+    if resource_model == App:
+        with Session(db.engine) as session:
+            resource = session.execute(
+                select(resource_model).filter_by(id=resource_id, tenant_id=tenant_id)
+            ).scalar_one_or_none()
+    else:
+        with Session(db.engine) as session:
+            resource = session.execute(
+                select(resource_model).filter_by(id=resource_id, tenant_id=tenant_id)
+            ).scalar_one_or_none()
 
     if resource is None:
         flask_restful.abort(404, message=f"{resource_model.__name__} not found.")
@@ -35,14 +48,15 @@ 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 +68,7 @@ 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 +101,12 @@ 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
@@ -57,12 +57,13 @@ class AppListApi(Resource):
         )
         parser.add_argument("name", type=str, location="args", required=False)
         parser.add_argument("tag_ids", type=uuid_list, location="args", required=False)
+        parser.add_argument("is_created_by_me", type=inputs.boolean, location="args", required=False)
 
         args = parser.parse_args()
 
         # get app list
         app_service = AppService()
-        app_pagination = app_service.get_paginate_apps(current_user.current_tenant_id, args)
+        app_pagination = app_service.get_paginate_apps(current_user.id, current_user.current_tenant_id, args)
         if not app_pagination:
             return {"data": [], "total": 0, "page": 1, "limit": 20, "has_more": False}
 

api/controllers/console/app/app_import.py

@@ -1,18 +1,20 @@
 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
 
+from controllers.console.app.wraps import get_app_model
 from controllers.console.wraps import (
     account_initialization_required,
     setup_required,
 )
 from extensions.ext_database import db
-from fields.app_fields import app_import_fields
+from fields.app_fields import app_import_check_dependencies_fields, app_import_fields
 from libs.login import login_required
 from models import Account
+from models.model import App
 from services.app_dsl_service import AppDslService, ImportStatus
 
 
@@ -88,3 +90,20 @@ class AppImportConfirmApi(Resource):
         if result.status == ImportStatus.FAILED.value:
             return result.model_dump(mode="json"), 400
         return result.model_dump(mode="json"), 200
+
+
+class AppImportCheckDependenciesApi(Resource):
+    @setup_required
+    @login_required
+    @get_app_model
+    @account_initialization_required
+    @marshal_with(app_import_check_dependencies_fields)
+    def get(self, app_model: App):
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        with Session(db.engine) as session:
+            import_service = AppDslService(session)
+            result = import_service.check_dependencies(app_model=app_model)
+
+        return result.model_dump(mode="json"), 200

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
@@ -22,7 +22,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
-from models.model import AppMode
+from models import App, AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
     AudioTooLargeServiceError,
@@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
     @login_required
     @account_initialization_required
     @get_app_model
-    def post(self, app_model):
+    def post(self, app_model: App):
         from werkzeug.exceptions import InternalServerError
 
         try:
@@ -98,9 +98,13 @@ class ChatMessageTextApi(Resource):
                 and app_model.workflow.features_dict
             ):
                 text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
+                if text_to_speech is None:
+                    raise ValueError("TTS is not enabled")
                 voice = args.get("voice") or text_to_speech.get("voice")
             else:
                 try:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                     voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                 except Exception:
                     voice = None

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
@@ -20,7 +20,6 @@ from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpErr
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import (
-    AppInvokeQuotaExceededError,
     ModelCurrentlyNotSupportError,
     ProviderTokenNotInitError,
     QuotaExceededError,
@@ -76,7 +75,7 @@ class CompletionMessageApi(Resource):
             raise ProviderModelCurrentlyNotSupportError()
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")
@@ -141,7 +140,7 @@ class ChatMessageApi(Resource):
             raise InvokeRateLimitHttpError(ex.description)
         except InvokeError as e:
             raise CompletionRequestError(e.description)
-        except (ValueError, AppInvokeQuotaExceededError) as e:
+        except ValueError as e:
             raise e
         except Exception as e:
             logging.exception("internal server error.")

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 = {}

api/controllers/console/app/ops_trace.py

@@ -1,4 +1,4 @@
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import BadRequest
 
 from controllers.console import api

api/controllers/console/app/site.py

@@ -1,7 +1,8 @@
 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 sqlalchemy.orm import Session
 from werkzeug.exceptions import Forbidden, NotFound
 
 from constants.languages import supported_language
@@ -50,33 +51,37 @@ 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()
+        with Session(db.engine) as session:
+            site = session.query(Site).filter(Site.app_id == app_model.id).first()
 
-        for attr_name in [
-            "title",
-            "icon_type",
-            "icon",
-            "icon_background",
-            "description",
-            "default_language",
-            "chat_color_theme",
-            "chat_color_theme_inverted",
-            "customize_domain",
-            "copyright",
-            "privacy_policy",
-            "custom_disclaimer",
-            "customize_token_strategy",
-            "prompt_public",
-            "show_workflow_steps",
-            "use_icon_as_answer_icon",
-        ]:
-            value = args.get(attr_name)
-            if value is not None:
-                setattr(site, attr_name, value)
+            if not site:
+                raise NotFound
 
-        site.updated_by = current_user.id
-        site.updated_at = datetime.now(UTC).replace(tzinfo=None)
-        db.session.commit()
+            for attr_name in [
+                "title",
+                "icon_type",
+                "icon",
+                "icon_background",
+                "description",
+                "default_language",
+                "chat_color_theme",
+                "chat_color_theme_inverted",
+                "customize_domain",
+                "copyright",
+                "privacy_policy",
+                "custom_disclaimer",
+                "customize_token_strategy",
+                "prompt_public",
+                "show_workflow_steps",
+                "use_icon_as_answer_icon",
+            ]:
+                value = args.get(attr_name)
+                if value is not None:
+                    setattr(site, attr_name, value)
+
+            site.updated_by = current_user.id
+            site.updated_at = datetime.now(UTC).replace(tzinfo=None)
+            session.commit()
 
         return site
 

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
@@ -273,8 +273,7 @@ FROM
             messages m
             ON c.id = m.conversation_id
         WHERE
-            c.override_model_configs IS NULL
-            AND c.app_id = :app_id"""
+            c.app_id = :app_id"""
         arg_dict = {"tz": account.timezone, "app_id": app_model.id}
 
         timezone = pytz.timezone(account.timezone)

api/controllers/console/app/workflow.py

@@ -2,7 +2,7 @@ import json
 import logging
 
 from flask import abort, request
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, inputs, marshal_with, reqparse  # type: ignore
 from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 
 import services
@@ -14,12 +14,13 @@ from controllers.console.wraps import account_initialization_required, setup_req
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from factories import variable_factory
-from fields.workflow_fields import workflow_fields
+from fields.workflow_fields import workflow_fields, workflow_pagination_fields
 from fields.workflow_run_fields import workflow_run_node_execution_fields
 from libs import helper
 from libs.helper import TimestampField, uuid_value
 from libs.login import current_user, login_required
 from models import App
+from models.account import Account
 from models.model import AppMode
 from services.app_generate_service import AppGenerateService
 from services.errors.app import WorkflowHashNotEqualError
@@ -96,6 +97,9 @@ class DraftWorkflowApi(Resource):
         else:
             abort(415)
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         workflow_service = WorkflowService()
 
         try:
@@ -139,6 +143,9 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         parser = reqparse.RequestParser()
         parser.add_argument("inputs", type=dict, location="json")
         parser.add_argument("query", type=str, required=True, location="json", default="")
@@ -160,7 +167,7 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
             raise ConversationCompletedError()
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 
@@ -178,38 +185,7 @@ class AdvancedChatDraftRunIterationNodeApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("inputs", type=dict, location="json")
-        args = parser.parse_args()
-
-        try:
-            response = AppGenerateService.generate_single_iteration(
-                app_model=app_model, user=current_user, node_id=node_id, args=args, streaming=True
-            )
-
-            return helper.compact_generate_response(response)
-        except services.errors.conversation.ConversationNotExistsError:
-            raise NotFound("Conversation Not Exists.")
-        except services.errors.conversation.ConversationCompletedError:
-            raise ConversationCompletedError()
-        except ValueError as e:
-            raise e
-        except Exception as e:
-            logging.exception("internal server error.")
-            raise InternalServerError()
-
-
-class WorkflowDraftRunIterationNodeApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    @get_app_model(mode=[AppMode.WORKFLOW])
-    def post(self, app_model: App, node_id: str):
-        """
-        Run draft workflow iteration node
-        """
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
+        if not isinstance(current_user, Account):
             raise Forbidden()
 
         parser = reqparse.RequestParser()
@@ -228,7 +204,44 @@ class WorkflowDraftRunIterationNodeApi(Resource):
             raise ConversationCompletedError()
         except ValueError as e:
             raise e
-        except Exception as e:
+        except Exception:
+            logging.exception("internal server error.")
+            raise InternalServerError()
+
+
+class WorkflowDraftRunIterationNodeApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.WORKFLOW])
+    def post(self, app_model: App, node_id: str):
+        """
+        Run draft workflow iteration 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()
+
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("inputs", type=dict, location="json")
+        args = parser.parse_args()
+
+        try:
+            response = AppGenerateService.generate_single_iteration(
+                app_model=app_model, user=current_user, node_id=node_id, args=args, streaming=True
+            )
+
+            return helper.compact_generate_response(response)
+        except services.errors.conversation.ConversationNotExistsError:
+            raise NotFound("Conversation Not Exists.")
+        except services.errors.conversation.ConversationCompletedError:
+            raise ConversationCompletedError()
+        except ValueError as e:
+            raise e
+        except Exception:
             logging.exception("internal server error.")
             raise InternalServerError()
 
@@ -246,6 +259,9 @@ class DraftWorkflowRunApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         parser = reqparse.RequestParser()
         parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
         parser.add_argument("files", type=list, required=False, location="json")
@@ -294,13 +310,20 @@ class DraftWorkflowNodeRunApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         parser = reqparse.RequestParser()
         parser.add_argument("inputs", type=dict, required=True, nullable=False, location="json")
         args = parser.parse_args()
 
+        inputs = args.get("inputs")
+        if inputs == None:
+            raise ValueError("missing inputs")
+
         workflow_service = WorkflowService()
         workflow_node_execution = workflow_service.run_draft_workflow_node(
-            app_model=app_model, node_id=node_id, user_inputs=args.get("inputs"), account=current_user
+            app_model=app_model, node_id=node_id, user_inputs=inputs, account=current_user
         )
 
         return workflow_node_execution
@@ -339,6 +362,9 @@ class PublishedWorkflowApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         workflow_service = WorkflowService()
         workflow = workflow_service.publish_workflow(app_model=app_model, account=current_user)
 
@@ -376,12 +402,17 @@ class DefaultBlockConfigApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         parser = reqparse.RequestParser()
         parser.add_argument("q", type=str, location="args")
         args = parser.parse_args()
 
+        q = args.get("q")
+
         filters = None
-        if args.get("q"):
+        if q:
             try:
                 filters = json.loads(args.get("q", ""))
             except json.JSONDecodeError:
@@ -407,6 +438,9 @@ class ConvertToWorkflowApi(Resource):
         if not current_user.is_editor:
             raise Forbidden()
 
+        if not isinstance(current_user, Account):
+            raise Forbidden()
+
         if request.data:
             parser = reqparse.RequestParser()
             parser.add_argument("name", type=str, required=False, nullable=True, location="json")
@@ -440,6 +474,31 @@ class WorkflowConfigApi(Resource):
         }
 
 
+class PublishedAllWorkflowApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @get_app_model(mode=[AppMode.ADVANCED_CHAT, AppMode.WORKFLOW])
+    @marshal_with(workflow_pagination_fields)
+    def get(self, app_model: App):
+        """
+        Get published workflows
+        """
+        if not current_user.is_editor:
+            raise Forbidden()
+
+        parser = reqparse.RequestParser()
+        parser.add_argument("page", type=inputs.int_range(1, 99999), required=False, default=1, location="args")
+        parser.add_argument("limit", type=inputs.int_range(1, 100), required=False, default=20, location="args")
+        args = parser.parse_args()
+        page = args.get("page")
+        limit = args.get("limit")
+        workflow_service = WorkflowService()
+        workflows, has_more = workflow_service.get_all_published_workflow(app_model=app_model, page=page, limit=limit)
+
+        return {"items": workflows, "page": page, "limit": limit, "has_more": has_more}
+
+
 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")
@@ -454,6 +513,7 @@ api.add_resource(
     WorkflowDraftRunIterationNodeApi, "/apps/<uuid:app_id>/workflows/draft/iteration/nodes/<string:node_id>/run"
 )
 api.add_resource(PublishedWorkflowApi, "/apps/<uuid:app_id>/workflows/publish")
+api.add_resource(PublishedAllWorkflowApi, "/apps/<uuid:app_id>/workflows")
 api.add_resource(DefaultBlockConfigsApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs")
 api.add_resource(
     DefaultBlockConfigApi, "/apps/<uuid:app_id>/workflows/default-workflow-block-configs/<string:block_type>"

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

@@ -8,7 +8,7 @@ from libs.login import current_user
 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",
         )
 

api/controllers/console/auth/error.py

@@ -53,3 +53,15 @@ class EmailCodeLoginRateLimitExceededError(BaseHTTPException):
     error_code = "email_code_login_rate_limit_exceeded"
     description = "Too many login emails have been sent. Please try again in 5 minutes."
     code = 429
+
+
+class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
+    error_code = "email_code_account_deletion_rate_limit_exceeded"
+    description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
+    code = 429
+
+
+class EmailPasswordResetLimitError(BaseHTTPException):
+    error_code = "email_password_reset_limit"
+    description = "Too many failed password reset attempts. Please try again in 24 hours."
+    code = 429

api/controllers/console/auth/forgot_password.py

@@ -2,17 +2,20 @@ import base64
 import secrets
 
 from flask import request
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
+from sqlalchemy import select
+from sqlalchemy.orm import Session
 
 from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
     EmailCodeError,
+    EmailPasswordResetLimitError,
     InvalidEmailError,
     InvalidTokenError,
     PasswordMismatchError,
 )
-from controllers.console.error import AccountNotFound, EmailSendIpLimitError
+from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
 from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
@@ -20,6 +23,7 @@ from libs.helper import email, extract_remote_ip
 from libs.password import hash_password, valid_password
 from models.account import Account
 from services.account_service import AccountService, TenantService
+from services.errors.account import AccountRegisterError
 from services.errors.workspace import WorkSpaceNotAllowedCreateError
 from services.feature_service import FeatureService
 
@@ -41,7 +45,8 @@ class ForgotPasswordSendEmailApi(Resource):
         else:
             language = "en-US"
 
-        account = Account.query.filter_by(email=args["email"]).first()
+        with Session(db.engine) as session:
+            account = session.execute(select(Account).filter_by(email=args["email"])).scalar_one_or_none()
         token = None
         if account is None:
             if FeatureService.get_system_features().is_allow_register:
@@ -66,6 +71,10 @@ class ForgotPasswordCheckApi(Resource):
 
         user_email = args["email"]
 
+        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
+        if is_forgot_password_error_rate_limit:
+            raise EmailPasswordResetLimitError()
+
         token_data = AccountService.get_reset_password_data(args["token"])
         if token_data is None:
             raise InvalidTokenError()
@@ -74,8 +83,10 @@ class ForgotPasswordCheckApi(Resource):
             raise InvalidEmailError()
 
         if args["code"] != token_data.get("code"):
+            AccountService.add_forgot_password_error_rate_limit(args["email"])
             raise EmailCodeError()
 
+        AccountService.reset_forgot_password_error_rate_limit(args["email"])
         return {"is_valid": True, "email": token_data.get("email")}
 
 
@@ -108,7 +119,8 @@ class ForgotPasswordResetApi(Resource):
         password_hashed = hash_password(new_password, salt)
         base64_password_hashed = base64.b64encode(password_hashed).decode()
 
-        account = Account.query.filter_by(email=reset_data.get("email")).first()
+        with Session(db.engine) as session:
+            account = session.execute(select(Account).filter_by(email=reset_data.get("email"))).scalar_one_or_none()
         if account:
             account.password = base64_password_hashed
             account.password_salt = base64_salt
@@ -122,13 +134,15 @@ 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],
                 )
             except WorkSpaceNotAllowedCreateError:
                 pass
+            except AccountRegisterError:
+                raise AccountInFreezeError()
 
         return {"result": "success"}
 

api/controllers/console/auth/login.py

@@ -1,10 +1,11 @@
 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 configs import dify_config
 from constants.languages import languages
 from controllers.console import api
 from controllers.console.auth.error import (
@@ -16,6 +17,7 @@ from controllers.console.auth.error import (
 )
 from controllers.console.error import (
     AccountBannedError,
+    AccountInFreezeError,
     AccountNotFound,
     EmailSendIpLimitError,
     NotAllowedCreateWorkspace,
@@ -26,6 +28,8 @@ from libs.helper import email, extract_remote_ip
 from libs.password import valid_password
 from models.account import Account
 from services.account_service import AccountService, RegisterService, TenantService
+from services.billing_service import BillingService
+from services.errors.account import AccountRegisterError
 from services.errors.workspace import WorkSpaceNotAllowedCreateError
 from services.feature_service import FeatureService
 
@@ -44,6 +48,9 @@ class LoginApi(Resource):
         parser.add_argument("language", type=str, required=False, default="en-US", location="json")
         args = parser.parse_args()
 
+        if dify_config.BILLING_ENABLED and BillingService.is_email_in_freeze(args["email"]):
+            raise AccountInFreezeError()
+
         is_login_error_rate_limit = AccountService.is_login_error_rate_limit(args["email"])
         if is_login_error_rate_limit:
             raise EmailPasswordLoginLimitError()
@@ -113,8 +120,10 @@ class ResetPasswordSendEmailApi(Resource):
             language = "zh-Hans"
         else:
             language = "en-US"
-
-        account = AccountService.get_user_through_email(args["email"])
+        try:
+            account = AccountService.get_user_through_email(args["email"])
+        except AccountRegisterError as are:
+            raise AccountInFreezeError()
         if account is None:
             if FeatureService.get_system_features().is_allow_register:
                 token = AccountService.send_reset_password_email(email=args["email"], language=language)
@@ -142,8 +151,11 @@ class EmailCodeLoginSendEmailApi(Resource):
             language = "zh-Hans"
         else:
             language = "en-US"
+        try:
+            account = AccountService.get_user_through_email(args["email"])
+        except AccountRegisterError as are:
+            raise AccountInFreezeError()
 
-        account = AccountService.get_user_through_email(args["email"])
         if account is None:
             if FeatureService.get_system_features().is_allow_register:
                 token = AccountService.send_email_code_login_email(email=args["email"], language=language)
@@ -177,7 +189,10 @@ class EmailCodeLoginApi(Resource):
             raise EmailCodeError()
 
         AccountService.revoke_email_code_login_token(args["token"])
-        account = AccountService.get_user_through_email(user_email)
+        try:
+            account = AccountService.get_user_through_email(user_email)
+        except AccountRegisterError as are:
+            raise AccountInFreezeError()
         if account:
             tenant = TenantService.get_join_tenants(account)
             if not tenant:
@@ -196,6 +211,8 @@ class EmailCodeLoginApi(Resource):
                 )
             except WorkSpaceNotAllowedCreateError:
                 return NotAllowedCreateWorkspace()
+            except AccountRegisterError as are:
+                raise AccountInFreezeError()
         token_pair = AccountService.login(account, ip_address=extract_remote_ip(request))
         AccountService.reset_login_error_rate_limit(args["email"])
         return {"result": "success", "data": token_pair.model_dump()}

api/controllers/console/auth/oauth.py

@@ -4,7 +4,9 @@ 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 sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import Unauthorized
 
 from configs import dify_config
@@ -16,7 +18,7 @@ from libs.oauth import GitHubOAuth, GoogleOAuth, OAuthUserInfo
 from models import Account
 from models.account import AccountStatus
 from services.account_service import AccountService, RegisterService, TenantService
-from services.errors.account import AccountNotFoundError
+from services.errors.account import AccountNotFoundError, AccountRegisterError
 from services.errors.workspace import WorkSpaceNotAllowedCreateError, WorkSpaceNotFoundError
 from services.feature_service import FeatureService
 
@@ -76,8 +78,9 @@ 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):
@@ -98,6 +101,8 @@ class OAuthCallback(Resource):
                 f"{dify_config.CONSOLE_WEB_URL}/signin"
                 "?message=Workspace not found, please contact system admin to invite you to join in a workspace."
             )
+        except AccountRegisterError as e:
+            return redirect(f"{dify_config.CONSOLE_WEB_URL}/signin?message={e.description}")
 
         # Check account status
         if account.status == AccountStatus.BANNED.value:
@@ -129,10 +134,11 @@ 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()
+        with Session(db.engine) as session:
+            account = session.execute(select(Account).filter_by(email=user_info.email)).scalar_one_or_none()
 
     return account
 

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 +2,10 @@ 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 sqlalchemy import select
+from sqlalchemy.orm import Session
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
@@ -76,7 +78,10 @@ class DataSourceApi(Resource):
     def patch(self, binding_id, action):
         binding_id = str(binding_id)
         action = str(action)
-        data_source_binding = DataSourceOauthBinding.query.filter_by(id=binding_id).first()
+        with Session(db.engine) as session:
+            data_source_binding = session.execute(
+                select(DataSourceOauthBinding).filter_by(id=binding_id)
+            ).scalar_one_or_none()
         if data_source_binding is None:
             raise NotFound("Data source binding not found.")
         # enable binding
@@ -108,47 +113,53 @@ class DataSourceNotionListApi(Resource):
     def get(self):
         dataset_id = request.args.get("dataset_id", default=None, type=str)
         exist_page_ids = []
-        # import notion in the exist dataset
-        if dataset_id:
-            dataset = DatasetService.get_dataset(dataset_id)
-            if not dataset:
-                raise NotFound("Dataset not found.")
-            if dataset.data_source_type != "notion_import":
-                raise ValueError("Dataset is not notion type.")
-            documents = Document.query.filter_by(
-                dataset_id=dataset_id,
-                tenant_id=current_user.current_tenant_id,
-                data_source_type="notion_import",
-                enabled=True,
+        with Session(db.engine) as session:
+            # import notion in the exist dataset
+            if dataset_id:
+                dataset = DatasetService.get_dataset(dataset_id)
+                if not dataset:
+                    raise NotFound("Dataset not found.")
+                if dataset.data_source_type != "notion_import":
+                    raise ValueError("Dataset is not notion type.")
+
+                documents = session.execute(
+                    select(Document).filter_by(
+                        dataset_id=dataset_id,
+                        tenant_id=current_user.current_tenant_id,
+                        data_source_type="notion_import",
+                        enabled=True,
+                    )
+                ).all()
+                if documents:
+                    for document in documents:
+                        data_source_info = json.loads(document.data_source_info)
+                        exist_page_ids.append(data_source_info["notion_page_id"])
+            # get all authorized pages
+            data_source_bindings = session.scalars(
+                select(DataSourceOauthBinding).filter_by(
+                    tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
+                )
             ).all()
-            if documents:
-                for document in documents:
-                    data_source_info = json.loads(document.data_source_info)
-                    exist_page_ids.append(data_source_info["notion_page_id"])
-        # get all authorized pages
-        data_source_bindings = DataSourceOauthBinding.query.filter_by(
-            tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
-        ).all()
-        if not data_source_bindings:
-            return {"notion_info": []}, 200
-        pre_import_info_list = []
-        for data_source_binding in data_source_bindings:
-            source_info = data_source_binding.source_info
-            pages = source_info["pages"]
-            # Filter out already bound pages
-            for page in pages:
-                if page["page_id"] in exist_page_ids:
-                    page["is_bound"] = True
-                else:
-                    page["is_bound"] = False
-            pre_import_info = {
-                "workspace_name": source_info["workspace_name"],
-                "workspace_icon": source_info["workspace_icon"],
-                "workspace_id": source_info["workspace_id"],
-                "pages": pages,
-            }
-            pre_import_info_list.append(pre_import_info)
-        return {"notion_info": pre_import_info_list}, 200
+            if not data_source_bindings:
+                return {"notion_info": []}, 200
+            pre_import_info_list = []
+            for data_source_binding in data_source_bindings:
+                source_info = data_source_binding.source_info
+                pages = source_info["pages"]
+                # Filter out already bound pages
+                for page in pages:
+                    if page["page_id"] in exist_page_ids:
+                        page["is_bound"] = True
+                    else:
+                        page["is_bound"] = False
+                pre_import_info = {
+                    "workspace_name": source_info["workspace_name"],
+                    "workspace_icon": source_info["workspace_icon"],
+                    "workspace_id": source_info["workspace_id"],
+                    "pages": pages,
+                }
+                pre_import_info_list.append(pre_import_info)
+            return {"notion_info": pre_import_info_list}, 200
 
 
 class DataSourceNotionApi(Resource):
@@ -158,14 +169,17 @@ class DataSourceNotionApi(Resource):
     def get(self, workspace_id, page_id, page_type):
         workspace_id = str(workspace_id)
         page_id = str(page_id)
-        data_source_binding = DataSourceOauthBinding.query.filter(
-            db.and_(
-                DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
-                DataSourceOauthBinding.provider == "notion",
-                DataSourceOauthBinding.disabled == False,
-                DataSourceOauthBinding.source_info["workspace_id"] == f'"{workspace_id}"',
-            )
-        ).first()
+        with Session(db.engine) as session:
+            data_source_binding = session.execute(
+                select(DataSourceOauthBinding).filter(
+                    db.and_(
+                        DataSourceOauthBinding.tenant_id == current_user.current_tenant_id,
+                        DataSourceOauthBinding.provider == "notion",
+                        DataSourceOauthBinding.disabled == False,
+                        DataSourceOauthBinding.source_info["workspace_id"] == f'"{workspace_id}"',
+                    )
+                )
+            ).scalar_one_or_none()
         if not data_source_binding:
             raise NotFound("Data source binding not found.")
 
@@ -218,7 +232,7 @@ 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
@@ -14,6 +14,7 @@ from controllers.console.wraps import account_initialization_required, enterpris
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
+from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -52,12 +53,12 @@ class DatasetListApi(Resource):
         # provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
-
+        include_all = request.args.get("include_all", default="false").lower() == "true"
         if ids:
             datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
         else:
             datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
             )
 
         # check embedding setting
@@ -72,7 +73,9 @@ class DatasetListApi(Resource):
 
         data = marshal(datasets, dataset_detail_fields)
         for item in data:
+            # convert embedding_model_provider to plugin standard format
             if item["indexing_technique"] == "high_quality":
+                item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                 item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                 if item_model in model_names:
                     item["embedding_available"] = True
@@ -457,14 +460,14 @@ class DatasetIndexingEstimateApi(Resource):
             )
         except LLMBadRequestError:
             raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
             )
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
         except Exception as e:
             raise IndexingEstimateError(str(e))
 
-        return response, 200
+        return response.model_dump(), 200
 
 
 class DatasetRelatedAppListApi(Resource):
@@ -619,9 +622,7 @@ class DatasetRetrievalSettingApi(Resource):
         vector_type = dify_config.VECTOR_STORE
         match vector_type:
             case (
-                VectorType.MILVUS
-                | VectorType.RELYT
-                | VectorType.PGVECTOR
+                VectorType.RELYT
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT
@@ -640,10 +641,12 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.ELASTICSEARCH_JA
                 | VectorType.PGVECTOR
                 | VectorType.TIDB_ON_QDRANT
                 | VectorType.LINDORM
                 | VectorType.COUCHBASE
+                | VectorType.MILVUS
             ):
                 return {
                     "retrieval_method": [
@@ -683,6 +686,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.ELASTICSEARCH_JA
                 | VectorType.COUCHBASE
                 | VectorType.PGVECTOR
                 | VectorType.LINDORM
@@ -733,6 +737,18 @@ 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 +763,4 @@ 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 +1,12 @@
 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 werkzeug.exceptions import Forbidden, NotFound
 
 import services
@@ -39,6 +39,7 @@ from core.indexing_runner import IndexingRunner
 from core.model_manager import ModelManager
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.invoke import InvokeAuthorizationError
+from core.plugin.manager.exc import PluginDaemonClientSideError
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
@@ -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
 
@@ -148,8 +150,20 @@ class DatasetDocumentListApi(Resource):
         sort = request.args.get("sort", default="-created_at", type=str)
         # "yes", "true", "t", "y", "1" convert to True, while others convert to False.
         try:
-            fetch = string_to_bool(request.args.get("fetch", default="false"))
-        except (ArgumentTypeError, ValueError, Exception) as e:
+            fetch_val = request.args.get("fetch", default="false")
+            if isinstance(fetch_val, bool):
+                fetch = fetch_val
+            else:
+                if fetch_val.lower() in ("yes", "true", "t", "y", "1"):
+                    fetch = True
+                elif fetch_val.lower() in ("no", "false", "f", "n", "0"):
+                    fetch = False
+                else:
+                    raise ArgumentTypeError(
+                        f"Truthy value expected: got {fetch_val} but expected one of yes/no, true/false, t/f, y/n, 1/0 "
+                        f"(case insensitive)."
+                    )
+        except (ArgumentTypeError, ValueError, Exception):
             fetch = False
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
@@ -254,20 +268,23 @@ 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("embedding_model", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("embedding_model_provider", type=str, required=False, nullable=True, 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:
@@ -277,6 +294,25 @@ 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
@@ -312,9 +348,9 @@ 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()
@@ -326,18 +362,17 @@ class DatasetInitApi(Resource):
                 )
             except InvokeAuthorizationError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 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)
@@ -390,7 +425,7 @@ 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,
@@ -398,6 +433,7 @@ 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 "
@@ -405,10 +441,12 @@ class DocumentIndexingEstimateApi(DocumentResource):
                     )
                 except ProviderTokenNotInitError as ex:
                     raise ProviderNotInitializeError(ex.description)
+                except PluginDaemonClientSideError as ex:
+                    raise ProviderNotInitializeError(ex.description)
                 except Exception as e:
                     raise IndexingEstimateError(str(e))
 
-        return response
+        return response, 200
 
 
 class DocumentBatchIndexingEstimateApi(DocumentResource):
@@ -419,9 +457,8 @@ 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 = []
@@ -499,16 +536,17 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                     "English",
                     dataset_id,
                 )
+                return response.model_dump(), 200
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
+            except PluginDaemonClientSideError as ex:
+                raise ProviderNotInitializeError(ex.description)
             except Exception as e:
                 raise IndexingEstimateError(str(e))
-        return response
 
 
 class DocumentBatchIndexingStatusApi(DocumentResource):
@@ -581,7 +619,8 @@ 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,
@@ -589,7 +628,8 @@ 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,
@@ -612,7 +652,8 @@ 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,
@@ -620,7 +661,8 @@ 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,
@@ -733,8 +775,7 @@ 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":
@@ -757,9 +798,8 @@ 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.")
@@ -774,84 +814,79 @@ 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):
@@ -1022,7 +1057,7 @@ 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
@@ -142,64 +168,21 @@ class DatasetDocumentSegmentApi(Resource):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             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):
@@ -233,8 +216,7 @@ class DatasetDocumentSegmentAddApi(Resource):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -283,8 +265,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                 )
             except LLMBadRequestError:
                 raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                 )
             except ProviderTokenNotInitError as ex:
                 raise ProviderNotInitializeError(ex.description)
@@ -307,9 +288,12 @@ 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
@@ -381,9 +365,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
             result = []
             for index, row in df.iterrows():
                 if document.doc_form == "qa_model":
-                    data = {"content": row[0], "answer": row[1]}
+                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
                 else:
-                    data = {"content": row[0]}
+                    data = {"content": row.iloc[0]}
                 result.append(data)
             if len(result) == 0:
                 raise ValueError("The CSV file is empty.")
@@ -412,8 +396,247 @@ 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 +647,11 @@ 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/error.py

@@ -92,3 +92,12 @@ class UnauthorizedAndForceLogout(BaseHTTPException):
     error_code = "unauthorized_and_force_logout"
     description = "Unauthorized and force logout."
     code = 401
+
+
+class AccountInFreezeError(BaseHTTPException):
+    error_code = "account_in_freeze"
+    code = 400
+    description = (
+        "This email account has been deleted within the past 30 days"
+        "and is temporarily unavailable for new account registration."
+    )

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,
@@ -19,7 +18,11 @@ from controllers.console.explore.error import NotChatAppError, NotCompletionAppE
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from extensions.ext_database import db
 from libs import helper
@@ -147,21 +150,3 @@ 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
@@ -31,17 +32,19 @@ class ConversationListApi(InstalledAppResource):
 
         pinned = None
         if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"
 
         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

@@ -1,8 +1,9 @@
 from datetime import UTC, datetime
+from typing import Any
 
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, inputs, marshal_with, reqparse
+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
 
@@ -34,7 +35,7 @@ class InstalledAppsListApi(Resource):
             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,
@@ -47,7 +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,
@@ -55,7 +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,
@@ -51,7 +50,7 @@ class MessageListApi(InstalledAppResource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")
@@ -67,10 +66,17 @@ class MessageFeedbackApi(InstalledAppResource):
 
         parser = reqparse.RequestParser()
         parser.add_argument("rating", type=str, choices=["like", "dislike", None], location="json")
+        parser.add_argument("content", type=str, location="json")
         args = parser.parse_args()
 
         try:
-            MessageService.create_feedback(app_model, message_id, current_user, args["rating"])
+            MessageService.create_feedback(
+                app_model=app_model,
+                message_id=message_id,
+                user=current_user,
+                rating=args.get("rating"),
+                content=args.get("content"),
+            )
         except services.errors.message.MessageNotExistsError:
             raise NotFound("Message Not Exists.")
 
@@ -153,21 +159,3 @@ 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

@@ -1,5 +1,5 @@
-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

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,
@@ -14,7 +13,11 @@ from controllers.console.explore.error import NotWorkflowAppError
 from controllers.console.explore.wraps import InstalledAppResource
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
-from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
+from core.errors.error import (
+    ModelCurrentlyNotSupportError,
+    ProviderTokenNotInitError,
+    QuotaExceededError,
+)
 from core.model_runtime.errors.invoke import InvokeError
 from libs import helper
 from libs.login import current_user
@@ -73,9 +76,3 @@ 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"
-)

api/controllers/console/explore/wraps.py

@@ -1,7 +1,7 @@
 from functools import wraps
 
-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 NotFound
 
 from controllers.console.wraps import account_initialization_required

api/controllers/console/extension.py

@@ -1,5 +1,5 @@
-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 constants import HIDDEN_VALUE
 from controllers.console import api

api/controllers/console/feature.py

@@ -1,5 +1,5 @@
-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 libs.login import login_required
 from services.feature_service import FeatureService

api/controllers/console/files.py

@@ -1,6 +1,8 @@
+from typing import Literal
+
 from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal_with
+from flask_login import current_user  # type: ignore
+from flask_restful import Resource, marshal_with  # type: ignore
 from werkzeug.exceptions import Forbidden
 
 import services
@@ -48,7 +50,8 @@ class FileApi(Resource):
     @cloud_edition_billing_resource_check("documents")
     def post(self):
         file = request.files["file"]
-        source = request.form.get("source")
+        source_str = request.form.get("source")
+        source: Literal["datasets"] | None = "datasets" if source_str == "datasets" else None
 
         if "file" not in request.files:
             raise NoFileUploadedError()

api/controllers/console/init_validate.py

@@ -1,9 +1,12 @@
 import os
 
 from flask import session
-from flask_restful import Resource, reqparse
+from flask_restful import Resource, reqparse  # type: ignore
+from sqlalchemy import select
+from sqlalchemy.orm import Session
 
 from configs import dify_config
+from extensions.ext_database import db
 from libs.helper import StrLen
 from models.model import DifySetup
 from services.account_service import TenantService
@@ -42,7 +45,11 @@ class InitValidateAPI(Resource):
 def get_init_validate_status():
     if dify_config.EDITION == "SELF_HOSTED":
         if os.environ.get("INIT_PASSWORD"):
-            return session.get("is_init_validated") or DifySetup.query.first()
+            if session.get("is_init_validated"):
+                return True
+
+            with Session(db.engine) as db_session:
+                return db_session.execute(select(DifySetup)).scalar_one_or_none()
 
     return True
 

api/controllers/console/ping.py

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