refactor(knowledge-retrieval): improve error handling with custom exceptions

- Introduced specific exception classes for various error scenarios in knowledge retrieval nodes.
- Replaced generic ValueError with ModelNotExistError for non-existing model errors.
- Changed ProviderTokenNotInitError to ModelCredentialsNotInitializedError for uninitialized credentials handling.
- Updated ModelCurrentlyNotSupportError to ModelNotSupportedError for unsupported models.
- Used ModelQuotaExceededError in place of QuotaExceededError for exceeded quota situations.
- Added custom exception imports to knowledge retrieval node module.
- Adjusted logger level for KnowledgeRetrievalNodeError from exception to warning.

.devcontainer/post_start_command.sh

@@ -1,3 +1,3 @@
 #!/bin/bash
 
-poetry install -C api
+cd api && poetry install

.github/workflows/api-tests.yml

@@ -7,6 +7,7 @@ on:
     paths:
       - api/**
       - docker/**
+      - .github/workflows/api-tests.yml
 
 concurrency:
   group: api-tests-${{ github.head_ref || github.run_id }}
@@ -27,16 +28,15 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          cache-dependency-path: |
-            api/pyproject.toml
-            api/poetry.lock
-
-      - name: Install Poetry
-        uses: abatilo/actions-poetry@v3
+          cache: poetry
+          cache-dependency-path: api/poetry.lock
 
       - name: Check Poetry lockfile
         run: |
@@ -67,7 +67,7 @@ jobs:
         run: sh .github/workflows/expose_service_ports.sh
 
       - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@v2.0.0
+        uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -77,21 +77,3 @@ jobs:
 
       - name: Run Workflow
         run: poetry run -C api bash dev/pytest/pytest_workflow.sh
-
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch)
-        uses: hoverkraft-tech/compose-action@v2.0.0
-        with:
-          compose-file: |
-            docker/docker-compose.yaml
-          services: |
-            weaviate
-            qdrant
-            etcd
-            minio
-            milvus-standalone
-            pgvecto-rs
-            pgvector
-            chroma
-            elasticsearch
-      - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh

.github/workflows/build-push.yml

@@ -49,7 +49,7 @@ jobs:
           echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}
@@ -114,7 +114,7 @@ jobs:
           merge-multiple: true
 
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ env.DOCKERHUB_USER }}
           password: ${{ env.DOCKERHUB_TOKEN }}

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

@@ -43,7 +43,7 @@ jobs:
           cp middleware.env.example middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@v2.0.0
+        uses: hoverkraft-tech/compose-action@v2.0.2
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml

.github/workflows/expose_service_ports.sh

@@ -7,5 +7,7 @@ yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/dock
 yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml
 yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml
 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
 
-echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch"
+echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch, couchbase"

.github/workflows/style.yml

@@ -24,16 +24,16 @@ jobs:
         with:
           files: api/**
 
+      - name: Install Poetry
+        if: steps.changed-files.outputs.any_changed == 'true'
+        uses: abatilo/actions-poetry@v3
+
       - name: Set up Python
         uses: actions/setup-python@v5
         if: steps.changed-files.outputs.any_changed == 'true'
         with:
           python-version: '3.10'
 
-      - name: Install Poetry
-        if: steps.changed-files.outputs.any_changed == 'true'
-        uses: abatilo/actions-poetry@v3
-
       - name: Python dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
         run: poetry install -C api --only lint

.github/workflows/vdb-tests.yml

@@ -0,0 +1,75 @@
+name: Run VDB Tests
+
+on:
+  pull_request:
+    branches:
+      - main
+    paths:
+      - api/core/rag/datasource/**
+      - docker/**
+      - .github/workflows/vdb-tests.yml
+
+concurrency:
+  group: vdb-tests-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    name: VDB Tests
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.10"
+          - "3.11"
+          - "3.12"
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: poetry
+          cache-dependency-path: api/poetry.lock
+
+      - name: Check Poetry lockfile
+        run: |
+          poetry check -C api --lock
+          poetry show -C api
+
+      - name: Install dependencies
+        run: poetry install -C api --with dev
+
+      - name: Set up dotenvs
+        run: |
+          cp docker/.env.example docker/.env
+          cp docker/middleware.env.example docker/middleware.env
+
+      - name: Expose Service Ports
+        run: sh .github/workflows/expose_service_ports.sh
+
+      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
+        uses: hoverkraft-tech/compose-action@v2.0.2
+        with:
+          compose-file: |
+            docker/docker-compose.yaml
+          services: |
+            weaviate
+            qdrant
+            couchbase-server
+            etcd
+            minio
+            milvus-standalone
+            pgvecto-rs
+            pgvector
+            chroma
+            elasticsearch
+
+      - name: Test Vector Stores
+        run: poetry run -C api bash dev/pytest/pytest_vdb.sh

.gitignore

@@ -173,6 +173,8 @@ docker/volumes/myscale/log/*
 docker/volumes/unstructured/*
 docker/volumes/pgvector/data/*
 docker/volumes/pgvecto_rs/data/*
+docker/volumes/couchbase/*
+docker/volumes/oceanbase/*
 
 docker/nginx/conf.d/default.conf
 docker/nginx/ssl/*
@@ -189,4 +191,4 @@ pyrightconfig.json
 api/.vscode
 
 .idea/
-.vscode
+.vscode

CONTRIBUTING.md

@@ -81,7 +81,7 @@ Dify requires the following dependencies to build, make sure they're installed o
 
 Dify is composed of a backend and a frontend. Navigate to the backend directory by `cd api/`, then follow the [Backend README](api/README.md) to install it. In a separate terminal, navigate to the frontend directory by `cd web/`, then follow the [Frontend README](web/README.md) to install.
 
-Check the [installation FAQ](https://docs.dify.ai/learn-more/faq/self-host-faq) for a list of common issues and steps to troubleshoot.
+Check the [installation FAQ](https://docs.dify.ai/learn-more/faq/install-faq) for a list of common issues and steps to troubleshoot.
 
 ### 5. Visit dify in your browser
 

CONTRIBUTING_VI.md

@@ -79,7 +79,7 @@ Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đ
 
 Dify bao gồm một backend và một frontend. Đi đến thư mục backend bằng lệnh `cd api/`, sau đó làm theo hướng dẫn trong [README của Backend](api/README.md) để cài đặt. Trong một terminal khác, đi đến thư mục frontend bằng lệnh `cd web/`, sau đó làm theo hướng dẫn trong [README của Frontend](web/README.md) để cài đặt.
 
-Kiểm tra [FAQ về cài đặt](https://docs.dify.ai/learn-more/faq/self-host-faq) để xem danh sách các vấn đề thường gặp và các bước khắc phục.
+Kiểm tra [FAQ về cài đặt](https://docs.dify.ai/learn-more/faq/install-faq) để xem danh sách các vấn đề thường gặp và các bước khắc phục.
 
 ### 5. Truy cập Dify trong trình duyệt của bạn
 

README.md

@@ -1,5 +1,9 @@
 ![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
 
+<p align="center">
+  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introducing Dify Workflow File Upload: Recreate Google NotebookLM Podcast</a>
+</p>
+
 <p align="center">
   <a href="https://cloud.dify.ai">Dify Cloud</a> ·
   <a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
@@ -42,9 +46,33 @@
 </p>
 
 
-Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
-</br> </br>
+Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. 
 
+## Quick start
+> Before installing Dify, make sure your machine meets the following minimum system requirements:
+> 
+>- CPU >= 2 Core
+>- RAM >= 4 GiB
+
+</br>
+
+The easiest way to start the Dify server is through [docker compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
+
+```bash
+cd dify
+cd docker
+cp .env.example .env
+docker compose up -d
+```
+
+After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
+
+#### Seeking help
+Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) if you encounter problems setting up Dify. Reach out to [the community and us](#community--contact) if you are still having issues.
+
+> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
+
+## Key features
 **1. Workflow**: 
   Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
 
@@ -75,73 +103,6 @@ Dify is an open-source LLM app development platform. Its intuitive interface com
   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 Features (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
 
 - **Cloud </br>**
@@ -163,28 +124,7 @@ Star Dify on GitHub and be instantly notified of new releases.
 ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
 
 
-
-## Quick start
-> Before installing Dify, make sure your machine meets the following minimum system requirements:
-> 
->- CPU >= 2 Core
->- RAM >= 4 GiB
-
-</br>
-
-The easiest way to start the Dify server is to run our [docker-compose.yml](docker/docker-compose.yaml) file. Before running the installation command, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
-
-```bash
-cd docker
-cp .env.example .env
-docker compose up -d
-```
-
-After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
-
-> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
-
-## Next steps
+## Advanced Setup
 
 If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
@@ -212,12 +152,6 @@ At the same time, please consider supporting Dify by sharing it on social media
 
 > We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
 
-**Contributors**
-
-<a href="https://github.com/langgenius/dify/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
-</a>
-
 ## Community & contact
 
 * [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
@@ -225,6 +159,12 @@ At the same time, please consider supporting Dify by sharing it on social media
 * [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
 * [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
 
+**Contributors**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
 ## Star history
 
 [![Star History Chart](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)

README_CN.md

@@ -154,7 +154,7 @@ Dify 是一个开源的 LLM 应用开发平台。其直观的界面结合了 AI
 我们提供[ Dify 云服务](https://dify.ai)，任何人都可以零设置尝试。它提供了自部署版本的所有功能，并在沙盒计划中包含 200 次免费的 GPT-4 调用。
 
 - **自托管 Dify 社区版</br>**
-使用这个[入门指南](#quick-start)快速在您的环境中运行 Dify。
+使用这个[入门指南](#快速启动)快速在您的环境中运行 Dify。
 使用我们的[文档](https://docs.dify.ai)进行进一步的参考和更深入的说明。
 
 - **面向企业/组织的 Dify</br>**

README_PT.md

@@ -0,0 +1,241 @@
+![cover-v5-optimized](https://github.com/langgenius/dify/assets/13230914/f9e19af5-61ba-4119-b926-d10c4c06ebab)
+
+<p align="center">
+  📌 <a href="https://dify.ai/blog/introducing-dify-workflow-file-upload-a-demo-on-ai-podcast">Introduzindo o Dify Workflow com Upload de Arquivo: Recrie o Podcast Google NotebookLM</a>
+</p>
+
+<p align="center">
+  <a href="https://cloud.dify.ai">Dify Cloud</a> ·
+  <a href="https://docs.dify.ai/getting-started/install-self-hosted">Auto-hospedagem</a> ·
+  <a href="https://docs.dify.ai">Documentação</a> ·
+  <a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Consultas empresariais</a>
+</p>
+
+<p align="center">
+    <a href="https://dify.ai" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/Product-F04438"></a>
+    <a href="https://dify.ai/pricing" target="_blank">
+        <img alt="Static Badge" src="https://img.shields.io/badge/free-pricing?logo=free&color=%20%23155EEF&label=pricing&labelColor=%20%23528bff"></a>
+    <a href="https://discord.gg/FngNHpbcY7" target="_blank">
+        <img src="https://img.shields.io/discord/1082486657678311454?logo=discord&labelColor=%20%235462eb&logoColor=%20%23f5f5f5&color=%20%235462eb"
+            alt="chat on Discord"></a>
+    <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://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">
+        <img alt="Commits last month" src="https://img.shields.io/github/commit-activity/m/langgenius/dify?labelColor=%20%2332b583&color=%20%2312b76a"></a>
+    <a href="https://github.com/langgenius/dify/" target="_blank">
+        <img alt="Issues closed" src="https://img.shields.io/github/issues-search?query=repo%3Alanggenius%2Fdify%20is%3Aclosed&label=issues%20closed&labelColor=%20%237d89b0&color=%20%235d6b98"></a>
+    <a href="https://github.com/langgenius/dify/discussions/" target="_blank">
+        <img alt="Discussion posts" src="https://img.shields.io/github/discussions/langgenius/dify?labelColor=%20%239b8afb&color=%20%237a5af8"></a>
+</p>
+
+<p align="center">
+  <a href="./README.md"><img alt="README em Inglês" src="https://img.shields.io/badge/English-d9d9d9"></a>
+  <a href="./README_CN.md"><img alt="简体中文版自述文件" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
+  <a href="./README_JA.md"><img alt="日本語のREADME" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
+  <a href="./README_ES.md"><img alt="README em Espanhol" src="https://img.shields.io/badge/Español-d9d9d9"></a>
+  <a href="./README_FR.md"><img alt="README em Francês" src="https://img.shields.io/badge/Français-d9d9d9"></a>
+  <a href="./README_KL.md"><img alt="README tlhIngan Hol" src="https://img.shields.io/badge/Klingon-d9d9d9"></a>
+  <a href="./README_KR.md"><img alt="README em Coreano" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
+  <a href="./README_AR.md"><img alt="README em Árabe" src="https://img.shields.io/badge/العربية-d9d9d9"></a>
+  <a href="./README_TR.md"><img alt="README em Turco" src="https://img.shields.io/badge/Türkçe-d9d9d9"></a>
+  <a href="./README_VI.md"><img alt="README em Vietnamita" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
+  <a href="./README_PT.md"><img alt="README em Português - BR" src="https://img.shields.io/badge/Portugu%C3%AAs-BR?style=flat&label=BR&color=d9d9d9"></a>
+</p>
+
+Dify é uma plataforma de desenvolvimento de aplicativos LLM de código aberto. Sua interface intuitiva combina workflow de IA, pipeline RAG, capacidades de agente, gerenciamento de modelos, recursos de observabilidade e muito mais, permitindo que você vá rapidamente do protótipo à produção. Aqui está uma lista das principais funcionalidades:
+</br> </br>
+
+**1. Workflow**: 
+  Construa e teste workflows poderosos de IA em uma interface visual, aproveitando todos os recursos a seguir e muito mais.
+
+
+  https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
+
+
+
+**2. Suporte abrangente a modelos**: 
+  Integração perfeita com centenas de LLMs proprietários e de código aberto de diversas provedoras e soluções auto-hospedadas, abrangendo GPT, Mistral, Llama3 e qualquer modelo compatível com a API da OpenAI. A lista completa de provedores suportados pode ser encontrada [aqui](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**: 
+  Interface intuitiva para criação de prompts, comparação de desempenho de modelos e adição de recursos como conversão de texto para fala em um aplicativo baseado em chat. 
+
+**4. Pipeline RAG**: 
+  Extensas capacidades de RAG que cobrem desde a ingestão de documentos até a recuperação, com suporte nativo para extração de texto de PDFs, PPTs e outros formatos de documentos comuns.
+
+**5. Capacidades de agente**: 
+  Você pode definir agentes com base em LLM Function Calling ou ReAct e adicionar ferramentas pré-construídas ou personalizadas para o agente. O Dify oferece mais de 50 ferramentas integradas para agentes de IA, como Google Search, DALL·E, Stable Diffusion e WolframAlpha.
+
+**6. LLMOps**: 
+  Monitore e analise os registros e o desempenho do aplicativo ao longo do tempo. É possível melhorar continuamente prompts, conjuntos de dados e modelos com base nos dados de produção e anotações.
+
+**7. Backend como Serviço**: 
+  Todas os recursos do Dify vêm com APIs correspondentes, permitindo que você integre o Dify sem esforço na lógica de negócios da sua empresa.
+
+
+## Comparação de recursos
+<table style="width: 100%;">
+  <tr>
+    <th align="center">Recurso</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">Abordagem de Programação</td>
+    <td align="center">Orientada a API + Aplicativo</td>
+    <td align="center">Código Python</td>
+    <td align="center">Orientada a Aplicativo</td>
+    <td align="center">Orientada a API</td>
+  </tr>
+  <tr>
+    <td align="center">LLMs Suportados</td>
+    <td align="center">Variedade Rica</td>
+    <td align="center">Variedade Rica</td>
+    <td align="center">Variedade Rica</td>
+    <td align="center">Apenas OpenAI</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">Agente</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">Observabilidade</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Recursos Empresariais (SSO/Controle de Acesso)</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+    <td align="center">❌</td>
+  </tr>
+  <tr>
+    <td align="center">Implantação Local</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">✅</td>
+    <td align="center">❌</td>
+  </tr>
+</table>
+
+## Usando o Dify
+
+- **Nuvem </br>**
+Oferecemos o serviço [Dify Cloud](https://dify.ai) para qualquer pessoa experimentar sem nenhuma configuração. Ele fornece todas as funcionalidades da versão auto-hospedada, incluindo 200 chamadas GPT-4 gratuitas no plano sandbox.
+
+- **Auto-hospedagem do Dify Community Edition</br>**
+Configure rapidamente o Dify no seu ambiente com este [guia inicial](#quick-start).
+Use nossa [documentação](https://docs.dify.ai) para referências adicionais e instruções mais detalhadas.
+
+- **Dify para empresas/organizações</br>**
+Oferecemos recursos adicionais voltados para empresas. [Envie suas perguntas através deste chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) ou [envie-nos um e-mail](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) para discutir necessidades empresariais. </br>
+  > Para startups e pequenas empresas que utilizam AWS, confira o [Dify Premium no AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) e implemente no seu próprio AWS VPC com um clique. É uma oferta AMI acessível com a opção de criar aplicativos com logotipo e marca personalizados.
+
+
+## Mantendo-se atualizado
+
+Dê uma estrela no Dify no GitHub e seja notificado imediatamente sobre novos lançamentos.
+
+![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
+
+
+
+## Início rápido
+> Antes de instalar o Dify, certifique-se de que sua máquina atenda aos seguintes requisitos mínimos de sistema:
+> 
+>- CPU >= 2 Núcleos
+>- RAM >= 4 GiB
+
+</br>
+
+A maneira mais fácil de iniciar o servidor Dify é executar nosso arquivo [docker-compose.yml](docker/docker-compose.yaml). Antes de rodar o comando de instalação, certifique-se de que o [Docker](https://docs.docker.com/get-docker/) e o [Docker Compose](https://docs.docker.com/compose/install/) estão instalados na sua máquina:
+
+```bash
+cd docker
+cp .env.example .env
+docker compose up -d
+```
+
+Após a execução, você pode acessar o painel do Dify no navegador em [http://localhost/install](http://localhost/install) e iniciar o processo de inicialização.
+
+> Se você deseja contribuir com o Dify ou fazer desenvolvimento adicional, consulte nosso [guia para implantar a partir do código fonte](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code).
+
+## Próximos passos
+
+Se precisar personalizar a configuração, consulte os comentários no nosso arquivo [.env.example](docker/.env.example) e atualize os valores correspondentes no seu arquivo `.env`. Além disso, talvez seja necessário fazer ajustes no próprio arquivo `docker-compose.yaml`, como alterar versões de imagem, mapeamentos de portas ou montagens de volumes, com base no seu ambiente de implantação específico e nas suas necessidades. Após fazer quaisquer alterações, execute novamente `docker-compose up -d`. Você pode encontrar a lista completa de variáveis de ambiente disponíveis [aqui](https://docs.dify.ai/getting-started/install-self-hosted/environments).
+
+Se deseja configurar uma instalação de alta disponibilidade, há [Helm Charts](https://helm.sh/) e arquivos YAML contribuídos pela comunidade que permitem a implantação do Dify no Kubernetes.
+
+- [Helm Chart de @LeoQuote](https://github.com/douban/charts/tree/master/charts/dify)
+- [Helm Chart de @BorisPolonsky](https://github.com/BorisPolonsky/dify-helm)
+- [Arquivo YAML de @Winson-030](https://github.com/Winson-030/dify-kubernetes)
+
+#### Usando o Terraform para Implantação
+
+Implante o Dify na Plataforma Cloud com um único clique usando [terraform](https://www.terraform.io/)
+
+##### Azure Global
+- [Azure Terraform por @nikawang](https://github.com/nikawang/dify-azure-terraform)
+
+##### Google Cloud
+- [Google Cloud Terraform por @sotazum](https://github.com/DeNA/dify-google-cloud-terraform)
+
+## Contribuindo
+
+Para aqueles que desejam contribuir com código, veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md). 
+Ao mesmo tempo, considere apoiar o Dify compartilhando-o nas redes sociais e em eventos e conferências.
+
+> Estamos buscando contribuidores para ajudar na tradução do Dify para idiomas além de Mandarim e Inglês. Se você tiver interesse em ajudar, consulte o [README i18n](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) para mais informações e deixe-nos um comentário no canal `global-users` em nosso [Servidor da Comunidade no Discord](https://discord.gg/8Tpq4AcN9c).
+
+**Contribuidores**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
+## Comunidade e contato
+
+* [Discussões no GitHub](https://github.com/langgenius/dify/discussions). Melhor para: compartilhar feedback e fazer perguntas.
+* [Problemas no GitHub](https://github.com/langgenius/dify/issues). Melhor para: relatar bugs encontrados no Dify.AI e propor novos recursos. Veja nosso [Guia de Contribuição](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
+* [Discord](https://discord.gg/FngNHpbcY7). Melhor para: compartilhar suas aplicações e interagir com a comunidade.
+* [X(Twitter)](https://twitter.com/dify_ai). Melhor para: compartilhar suas aplicações e interagir com a comunidade.
+
+## Histórico de estrelas
+
+[![Gráfico de Histórico de Estrelas](https://api.star-history.com/svg?repos=langgenius/dify&type=Date)](https://star-history.com/#langgenius/dify&Date)
+
+## Divulgação de segurança
+
+Para proteger sua privacidade, evite postar problemas de segurança no GitHub. Em vez disso, envie suas perguntas para security@dify.ai e forneceremos uma resposta mais detalhada.
+
+## Licença
+
+Este repositório está disponível sob a [Licença de Código Aberto Dify](LICENSE), que é essencialmente Apache 2.0 com algumas restrições adicionais.

api/.env.example

@@ -31,8 +31,17 @@ REDIS_HOST=localhost
 REDIS_PORT=6379
 REDIS_USERNAME=
 REDIS_PASSWORD=difyai123456
+REDIS_USE_SSL=false
 REDIS_DB=0
 
+# redis Sentinel configuration.
+REDIS_USE_SENTINEL=false
+REDIS_SENTINELS=
+REDIS_SENTINEL_SERVICE_NAME=
+REDIS_SENTINEL_USERNAME=
+REDIS_SENTINEL_PASSWORD=
+REDIS_SENTINEL_SOCKET_TIMEOUT=0.1
+
 # PostgreSQL database configuration
 DB_USERNAME=postgres
 DB_PASSWORD=difyai123456
@@ -111,7 +120,8 @@ SUPABASE_URL=your-server-url
 WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, vikingdb, upstash
+
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -127,6 +137,13 @@ QDRANT_CLIENT_TIMEOUT=20
 QDRANT_GRPC_ENABLED=false
 QDRANT_GRPC_PORT=6334
 
+#Couchbase configuration
+COUCHBASE_CONNECTION_STRING=127.0.0.1
+COUCHBASE_USER=Administrator
+COUCHBASE_PASSWORD=password
+COUCHBASE_BUCKET_NAME=Embeddings
+COUCHBASE_SCOPE_NAME=_default
+
 # Milvus configuration
 MILVUS_URI=http://127.0.0.1:19530
 MILVUS_TOKEN=
@@ -186,6 +203,20 @@ TIDB_VECTOR_USER=xxx.root
 TIDB_VECTOR_PASSWORD=xxxxxx
 TIDB_VECTOR_DATABASE=dify
 
+# Tidb on qdrant configuration
+TIDB_ON_QDRANT_URL=http://127.0.0.1
+TIDB_ON_QDRANT_API_KEY=dify
+TIDB_ON_QDRANT_CLIENT_TIMEOUT=20
+TIDB_ON_QDRANT_GRPC_ENABLED=false
+TIDB_ON_QDRANT_GRPC_PORT=6334
+TIDB_PUBLIC_KEY=dify
+TIDB_PRIVATE_KEY=dify
+TIDB_API_URL=http://127.0.0.1
+TIDB_IAM_API_URL=http://127.0.0.1
+TIDB_REGION=regions/aws-us-east-1
+TIDB_PROJECT_ID=dify
+TIDB_SPEND_LIMIT=100
+
 # Chroma configuration
 CHROMA_HOST=127.0.0.1
 CHROMA_PORT=8000
@@ -233,6 +264,20 @@ VIKINGDB_SCHEMA=http
 VIKINGDB_CONNECTION_TIMEOUT=30
 VIKINGDB_SOCKET_TIMEOUT=30
 
+# Lindorm configuration
+LINDORM_URL=http://ld-*******************-proxy-search-pub.lindorm.aliyuncs.com:30070
+LINDORM_USERNAME=admin
+LINDORM_PASSWORD=admin
+
+# OceanBase Vector configuration
+OCEANBASE_VECTOR_HOST=127.0.0.1
+OCEANBASE_VECTOR_PORT=2881
+OCEANBASE_VECTOR_USER=root@test
+OCEANBASE_VECTOR_PASSWORD=
+OCEANBASE_VECTOR_DATABASE=test
+OCEANBASE_MEMORY_LIMIT=6G
+
+
 # Upload configuration
 UPLOAD_FILE_SIZE_LIMIT=15
 UPLOAD_FILE_BATCH_LIMIT=5
@@ -275,13 +320,21 @@ ETL_TYPE=dify
 UNSTRUCTURED_API_URL=
 UNSTRUCTURED_API_KEY=
 
+#ssrf
 SSRF_PROXY_HTTP_URL=
 SSRF_PROXY_HTTPS_URL=
 SSRF_DEFAULT_MAX_RETRIES=3
+SSRF_DEFAULT_TIME_OUT=
+SSRF_DEFAULT_CONNECT_TIME_OUT=
+SSRF_DEFAULT_READ_TIME_OUT=
+SSRF_DEFAULT_WRITE_TIME_OUT=
 
 BATCH_UPLOAD_LIMIT=10
 KEYWORD_DATA_SOURCE_TYPE=database
 
+# Workflow file upload limit
+WORKFLOW_FILE_UPLOAD_LIMIT=10
+
 # CODE EXECUTION CONFIGURATION
 CODE_EXECUTION_ENDPOINT=http://127.0.0.1:8194
 CODE_EXECUTION_API_KEY=dify-sandbox

api/Dockerfile

@@ -55,7 +55,9 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.1-1 \
+    && apt-get install -y --no-install-recommends expat=2.6.3-2 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    # install a chinese font to support the use of tools like matplotlib
+    && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 

api/README.md

@@ -76,13 +76,13 @@
 1. Install dependencies for both the backend and the test environment
 
    ```bash
-   poetry install --with dev
+   poetry install -C api --with dev
    ```
 
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
 
    ```bash
-   cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
 
+

api/commands.py

@@ -278,6 +278,8 @@ def migrate_knowledge_vector_database():
         VectorType.BAIDU,
         VectorType.VIKINGDB,
         VectorType.UPSTASH,
+        VectorType.COUCHBASE,
+        VectorType.OCEANBASE,
     }
     page = 1
     while True:

api/configs/feature/__init__.py

@@ -216,6 +216,11 @@ class FileUploadConfig(BaseSettings):
         default=20,
     )
 
+    WORKFLOW_FILE_UPLOAD_LIMIT: PositiveInt = Field(
+        description="Maximum number of files allowed in a workflow upload operation",
+        default=10,
+    )
+
 
 class HttpConfig(BaseSettings):
     """
@@ -281,6 +286,26 @@ class HttpConfig(BaseSettings):
         default=None,
     )
 
+    SSRF_DEFAULT_TIME_OUT: PositiveFloat = Field(
+        description="The default timeout period used for network requests (SSRF)",
+        default=5,
+    )
+
+    SSRF_DEFAULT_CONNECT_TIME_OUT: PositiveFloat = Field(
+        description="The default connect timeout period used for network requests (SSRF)",
+        default=5,
+    )
+
+    SSRF_DEFAULT_READ_TIME_OUT: PositiveFloat = Field(
+        description="The default read timeout period used for network requests (SSRF)",
+        default=5,
+    )
+
+    SSRF_DEFAULT_WRITE_TIME_OUT: PositiveFloat = Field(
+        description="The default write timeout period used for network requests (SSRF)",
+        default=5,
+    )
+
     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",
@@ -571,6 +596,11 @@ class DataSetConfig(BaseSettings):
         default=False,
     )
 
+    TIDB_SERVERLESS_NUMBER: PositiveInt = Field(
+        description="number of tidb serverless cluster",
+        default=500,
+    )
+
 
 class WorkspaceConfig(BaseSettings):
     """

api/configs/middleware/__init__.py

@@ -16,10 +16,14 @@ from configs.middleware.storage.supabase_storage_config import SupabaseStorageCo
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
+from configs.middleware.vdb.baidu_vector_config import BaiduVectorDBConfig
 from configs.middleware.vdb.chroma_config import ChromaConfig
+from configs.middleware.vdb.couchbase_config import CouchbaseConfig
 from configs.middleware.vdb.elasticsearch_config import ElasticsearchConfig
+from configs.middleware.vdb.lindorm_config import LindormConfig
 from configs.middleware.vdb.milvus_config import MilvusConfig
 from configs.middleware.vdb.myscale_config import MyScaleConfig
+from configs.middleware.vdb.oceanbase_config import OceanBaseVectorConfig
 from configs.middleware.vdb.opensearch_config import OpenSearchConfig
 from configs.middleware.vdb.oracle_config import OracleConfig
 from configs.middleware.vdb.pgvector_config import PGVectorConfig
@@ -27,6 +31,7 @@ from configs.middleware.vdb.pgvectors_config import PGVectoRSConfig
 from configs.middleware.vdb.qdrant_config import QdrantConfig
 from configs.middleware.vdb.relyt_config import RelytConfig
 from configs.middleware.vdb.tencent_vector_config import TencentVectorDBConfig
+from configs.middleware.vdb.tidb_on_qdrant_config import TidbOnQdrantConfig
 from configs.middleware.vdb.tidb_vector_config import TiDBVectorConfig
 from configs.middleware.vdb.upstash_config import UpstashConfig
 from configs.middleware.vdb.vikingdb_config import VikingDBConfig
@@ -54,6 +59,11 @@ class VectorStoreConfig(BaseSettings):
         default=None,
     )
 
+    VECTOR_STORE_WHITELIST_ENABLE: Optional[bool] = Field(
+        description="Enable whitelist for vector store.",
+        default=False,
+    )
+
 
 class KeywordStoreConfig(BaseSettings):
     KEYWORD_STORE: str = Field(
@@ -245,8 +255,13 @@ class MiddlewareConfig(
     TiDBVectorConfig,
     WeaviateConfig,
     ElasticsearchConfig,
+    CouchbaseConfig,
     InternalTestConfig,
     VikingDBConfig,
     UpstashConfig,
+    TidbOnQdrantConfig,
+    LindormConfig,
+    OceanBaseVectorConfig,
+    BaiduVectorDBConfig,
 ):
     pass

api/configs/middleware/vdb/couchbase_config.py

@@ -0,0 +1,34 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class CouchbaseConfig(BaseModel):
+    """
+    Couchbase configs
+    """
+
+    COUCHBASE_CONNECTION_STRING: Optional[str] = Field(
+        description="COUCHBASE connection string",
+        default=None,
+    )
+
+    COUCHBASE_USER: Optional[str] = Field(
+        description="COUCHBASE user",
+        default=None,
+    )
+
+    COUCHBASE_PASSWORD: Optional[str] = Field(
+        description="COUCHBASE password",
+        default=None,
+    )
+
+    COUCHBASE_BUCKET_NAME: Optional[str] = Field(
+        description="COUCHBASE bucket name",
+        default=None,
+    )
+
+    COUCHBASE_SCOPE_NAME: Optional[str] = Field(
+        description="COUCHBASE scope name",
+        default=None,
+    )

api/configs/middleware/vdb/lindorm_config.py

@@ -0,0 +1,23 @@
+from typing import Optional
+
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class LindormConfig(BaseSettings):
+    """
+    Lindorm configs
+    """
+
+    LINDORM_URL: Optional[str] = Field(
+        description="Lindorm url",
+        default=None,
+    )
+    LINDORM_USERNAME: Optional[str] = Field(
+        description="Lindorm user",
+        default=None,
+    )
+    LINDORM_PASSWORD: Optional[str] = Field(
+        description="Lindorm password",
+        default=None,
+    )

api/configs/middleware/vdb/oceanbase_config.py

@@ -0,0 +1,35 @@
+from typing import Optional
+
+from pydantic import Field, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class OceanBaseVectorConfig(BaseSettings):
+    """
+    Configuration settings for OceanBase Vector database
+    """
+
+    OCEANBASE_VECTOR_HOST: Optional[str] = Field(
+        description="Hostname or IP address of the OceanBase Vector server (e.g. 'localhost')",
+        default=None,
+    )
+
+    OCEANBASE_VECTOR_PORT: Optional[PositiveInt] = Field(
+        description="Port number on which the OceanBase Vector server is listening (default is 2881)",
+        default=2881,
+    )
+
+    OCEANBASE_VECTOR_USER: Optional[str] = Field(
+        description="Username for authenticating with the OceanBase Vector database",
+        default=None,
+    )
+
+    OCEANBASE_VECTOR_PASSWORD: Optional[str] = Field(
+        description="Password for authenticating with the OceanBase Vector database",
+        default=None,
+    )
+
+    OCEANBASE_VECTOR_DATABASE: Optional[str] = Field(
+        description="Name of the OceanBase Vector database to connect to",
+        default=None,
+    )

api/configs/middleware/vdb/tidb_on_qdrant_config.py

@@ -0,0 +1,70 @@
+from typing import Optional
+
+from pydantic import Field, NonNegativeInt, PositiveInt
+from pydantic_settings import BaseSettings
+
+
+class TidbOnQdrantConfig(BaseSettings):
+    """
+    Tidb on Qdrant configs
+    """
+
+    TIDB_ON_QDRANT_URL: Optional[str] = Field(
+        description="Tidb on Qdrant url",
+        default=None,
+    )
+
+    TIDB_ON_QDRANT_API_KEY: Optional[str] = Field(
+        description="Tidb on Qdrant api key",
+        default=None,
+    )
+
+    TIDB_ON_QDRANT_CLIENT_TIMEOUT: NonNegativeInt = Field(
+        description="Tidb on Qdrant client timeout in seconds",
+        default=20,
+    )
+
+    TIDB_ON_QDRANT_GRPC_ENABLED: bool = Field(
+        description="whether enable grpc support for Tidb on Qdrant connection",
+        default=False,
+    )
+
+    TIDB_ON_QDRANT_GRPC_PORT: PositiveInt = Field(
+        description="Tidb on Qdrant grpc port",
+        default=6334,
+    )
+
+    TIDB_PUBLIC_KEY: Optional[str] = Field(
+        description="Tidb account public key",
+        default=None,
+    )
+
+    TIDB_PRIVATE_KEY: Optional[str] = Field(
+        description="Tidb account private key",
+        default=None,
+    )
+
+    TIDB_API_URL: Optional[str] = Field(
+        description="Tidb API url",
+        default=None,
+    )
+
+    TIDB_IAM_API_URL: Optional[str] = Field(
+        description="Tidb IAM API url",
+        default=None,
+    )
+
+    TIDB_REGION: Optional[str] = Field(
+        description="Tidb serverless region",
+        default="regions/aws-us-east-1",
+    )
+
+    TIDB_PROJECT_ID: Optional[str] = Field(
+        description="Tidb project id",
+        default=None,
+    )
+
+    TIDB_SPEND_LIMIT: Optional[int] = Field(
+        description="Tidb spend limit",
+        default=100,
+    )

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.10.1",
+        default="0.11.0",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/common/errors.py

@@ -0,0 +1,6 @@
+from werkzeug.exceptions import HTTPException
+
+
+class FilenameNotExistsError(HTTPException):
+    code = 400
+    description = "The specified filename does not exist."

api/controllers/common/fields.py

@@ -0,0 +1,24 @@
+from flask_restful import fields
+
+parameters__system_parameters = {
+    "image_file_size_limit": fields.Integer,
+    "video_file_size_limit": fields.Integer,
+    "audio_file_size_limit": fields.Integer,
+    "file_size_limit": fields.Integer,
+    "workflow_file_upload_limit": fields.Integer,
+}
+
+parameters_fields = {
+    "opening_statement": fields.String,
+    "suggested_questions": fields.Raw,
+    "suggested_questions_after_answer": fields.Raw,
+    "speech_to_text": fields.Raw,
+    "text_to_speech": fields.Raw,
+    "retriever_resource": fields.Raw,
+    "annotation_reply": fields.Raw,
+    "more_like_this": fields.Raw,
+    "user_input_form": fields.Raw,
+    "sensitive_word_avoidance": fields.Raw,
+    "file_upload": fields.Raw,
+    "system_parameters": fields.Nested(parameters__system_parameters),
+}

api/controllers/common/helpers.py

@@ -0,0 +1,97 @@
+import mimetypes
+import os
+import re
+import urllib.parse
+from collections.abc import Mapping
+from typing import Any
+from uuid import uuid4
+
+import httpx
+from pydantic import BaseModel
+
+from configs import dify_config
+
+
+class FileInfo(BaseModel):
+    filename: str
+    extension: str
+    mimetype: str
+    size: int
+
+
+def guess_file_info_from_response(response: httpx.Response):
+    url = str(response.url)
+    # Try to extract filename from URL
+    parsed_url = urllib.parse.urlparse(url)
+    url_path = parsed_url.path
+    filename = os.path.basename(url_path)
+
+    # If filename couldn't be extracted, use Content-Disposition header
+    if not filename:
+        content_disposition = response.headers.get("Content-Disposition")
+        if content_disposition:
+            filename_match = re.search(r'filename="?(.+)"?', content_disposition)
+            if filename_match:
+                filename = filename_match.group(1)
+
+    # If still no filename, generate a unique one
+    if not filename:
+        unique_name = str(uuid4())
+        filename = f"{unique_name}"
+
+    # Guess MIME type from filename first, then URL
+    mimetype, _ = mimetypes.guess_type(filename)
+    if mimetype is None:
+        mimetype, _ = mimetypes.guess_type(url)
+    if mimetype is None:
+        # If guessing fails, use Content-Type from response headers
+        mimetype = response.headers.get("Content-Type", "application/octet-stream")
+
+    extension = os.path.splitext(filename)[1]
+
+    # Ensure filename has an extension
+    if not extension:
+        extension = mimetypes.guess_extension(mimetype) or ".bin"
+        filename = f"{filename}{extension}"
+
+    return FileInfo(
+        filename=filename,
+        extension=extension,
+        mimetype=mimetype,
+        size=int(response.headers.get("Content-Length", -1)),
+    )
+
+
+def get_parameters_from_feature_dict(*, features_dict: Mapping[str, Any], user_input_form: list[dict[str, Any]]):
+    return {
+        "opening_statement": features_dict.get("opening_statement"),
+        "suggested_questions": features_dict.get("suggested_questions", []),
+        "suggested_questions_after_answer": features_dict.get("suggested_questions_after_answer", {"enabled": False}),
+        "speech_to_text": features_dict.get("speech_to_text", {"enabled": False}),
+        "text_to_speech": features_dict.get("text_to_speech", {"enabled": False}),
+        "retriever_resource": features_dict.get("retriever_resource", {"enabled": False}),
+        "annotation_reply": features_dict.get("annotation_reply", {"enabled": False}),
+        "more_like_this": features_dict.get("more_like_this", {"enabled": False}),
+        "user_input_form": user_input_form,
+        "sensitive_word_avoidance": features_dict.get(
+            "sensitive_word_avoidance", {"enabled": False, "type": "", "configs": []}
+        ),
+        "file_upload": features_dict.get(
+            "file_upload",
+            {
+                "image": {
+                    "enabled": False,
+                    "number_limits": 3,
+                    "detail": "high",
+                    "transfer_methods": ["remote_url", "local_file"],
+                }
+            },
+        ),
+        "system_parameters": {
+            "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
+            "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
+            "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+            "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
+            "workflow_file_upload_limit": dify_config.WORKFLOW_FILE_UPLOAD_LIMIT,
+        },
+    }

api/controllers/console/__init__.py

@@ -2,9 +2,21 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi, FilePreviewApi, FileSupportTypeApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("console", __name__, url_prefix="/console/api")
 api = ExternalApi(bp)
 
+# File
+api.add_resource(FileApi, "/files/upload")
+api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
+api.add_resource(FileSupportTypeApi, "/files/support-type")
+
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
 # Import other controllers
 from . import admin, apikey, extension, feature, ping, setup, version
 
@@ -43,7 +55,6 @@ from .datasets import (
     datasets_document,
     datasets_segments,
     external,
-    file,
     hit_testing,
     website,
 )

api/controllers/console/apikey.py

@@ -10,8 +10,7 @@ from models.dataset import Dataset
 from models.model import ApiToken, App
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required
+from .wraps import account_initialization_required, setup_required
 
 api_key_fields = {
     "id": fields.String,

api/controllers/console/app/advanced_prompt_template.py

@@ -1,8 +1,7 @@
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.advanced_prompt_template_service import AdvancedPromptTemplateService
 

api/controllers/console/app/agent.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.helper import uuid_value
 from libs.login import login_required
 from models.model import AppMode

api/controllers/console/app/annotation.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import Forbidden
 from controllers.console import api
 from controllers.console.app.error import NoFileUploadedError
 from controllers.console.datasets.error import TooManyFilesError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
     annotation_fields,

api/controllers/console/app/app.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import BadRequest, Forbidden, abort
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.ops.ops_trace_manager import OpsTraceManager
 from fields.app_fields import (
     app_detail_fields,

api/controllers/console/app/audio.py

@@ -18,8 +18,7 @@ from controllers.console.app.error import (
     UnsupportedAudioTypeError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required

api/controllers/console/app/completion.py

@@ -15,8 +15,7 @@ from controllers.console.app.error import (
     ProviderQuotaExceededError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom

api/controllers/console/app/conversation.py

@@ -10,8 +10,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
 from fields.conversation_fields import (

api/controllers/console/app/conversation_variables.py

@@ -4,8 +4,7 @@ from sqlalchemy.orm import Session
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.conversation_variable_fields import paginated_conversation_variable_fields
 from libs.login import login_required

api/controllers/console/app/generator.py

@@ -10,8 +10,7 @@ from controllers.console.app.error import (
     ProviderNotInitializeError,
     ProviderQuotaExceededError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_runtime.errors.invoke import InvokeError

api/controllers/console/app/message.py

@@ -14,8 +14,11 @@ from controllers.console.app.error import (
 )
 from controllers.console.app.wraps import get_app_model
 from controllers.console.explore.error import AppSuggestedQuestionsAfterAnswerDisabledError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
@@ -105,6 +108,8 @@ class ChatMessageListApi(Resource):
             if rest_count > 0:
                 has_more = True
 
+        history_messages = list(reversed(history_messages))
+
         return InfiniteScrollPagination(data=history_messages, limit=args["limit"], has_more=has_more)
 
 

api/controllers/console/app/model_config.py

@@ -6,8 +6,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.agent.entities import AgentToolEntity
 from core.tools.tool_manager import ToolManager
 from core.tools.utils.configuration import ToolParameterConfigurationManager

api/controllers/console/app/ops_trace.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.ops_service import OpsService
 

api/controllers/console/app/site.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.app_fields import app_site_fields
 from libs.login import login_required

api/controllers/console/app/statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/app/workflow.py

@@ -9,8 +9,7 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from factories import variable_factory

api/controllers/console/app/workflow_app_log.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App

api/controllers/console/app/workflow_run.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_run_fields import (
     advanced_chat_workflow_run_pagination_fields,
     workflow_run_detail_fields,

api/controllers/console/app/workflow_statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/auth/data_source_bearer_auth.py

@@ -7,8 +7,7 @@ from controllers.console.auth.error import ApiKeyAuthFailedError
 from libs.login import login_required
 from services.auth.api_key_auth_service import ApiKeyAuthService
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 class ApiKeyAuthDataSource(Resource):

api/controllers/console/auth/data_source_oauth.py

@@ -11,8 +11,7 @@ from controllers.console import api
 from libs.login import login_required
 from libs.oauth_data_source import NotionOAuth
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 def get_oauth_providers():

api/controllers/console/auth/forgot_password.py

@@ -13,7 +13,7 @@ from controllers.console.auth.error import (
     PasswordMismatchError,
 )
 from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip

api/controllers/console/auth/login.py

@@ -20,7 +20,7 @@ from controllers.console.error import (
     NotAllowedCreateWorkspace,
     NotAllowedRegister,
 )
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password

api/controllers/console/billing/billing.py

@@ -2,8 +2,7 @@ from flask_login import current_user
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, only_edition_cloud
+from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required
 from libs.login import login_required
 from services.billing_service import BillingService
 

api/controllers/console/datasets/data_source.py

@@ -7,8 +7,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.extractor.notion_extractor import NotionExtractor

api/controllers/console/datasets/datasets.py

@@ -10,8 +10,7 @@ from controllers.console import api
 from controllers.console.apikey import api_key_fields, api_key_list
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
@@ -102,6 +101,13 @@ class DatasetListApi(Resource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -140,6 +146,7 @@ class DatasetListApi(Resource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=current_user.current_tenant_id,
                 name=args["name"],
+                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=DatasetPermissionEnum.ONLY_ME,
@@ -449,7 +456,7 @@ 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)
@@ -613,6 +620,7 @@ class DatasetRetrievalSettingApi(Resource):
             case (
                 VectorType.MILVUS
                 | VectorType.RELYT
+                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT
@@ -620,6 +628,7 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
+                | VectorType.OCEANBASE
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -631,6 +640,9 @@ class DatasetRetrievalSettingApi(Resource):
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
                 | VectorType.PGVECTOR
+                | VectorType.TIDB_ON_QDRANT
+                | VectorType.LINDORM
+                | VectorType.COUCHBASE
             ):
                 return {
                     "retrieval_method": [
@@ -659,6 +671,7 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.BAIDU
                 | VectorType.VIKINGDB
                 | VectorType.UPSTASH
+                | VectorType.OCEANBASE
             ):
                 return {"retrieval_method": [RetrievalMethod.SEMANTIC_SEARCH.value]}
             case (
@@ -669,7 +682,9 @@ class DatasetRetrievalSettingMockApi(Resource):
                 | VectorType.MYSCALE
                 | VectorType.ORACLE
                 | VectorType.ELASTICSEARCH
+                | VectorType.COUCHBASE
                 | VectorType.PGVECTOR
+                | VectorType.LINDORM
             ):
                 return {
                     "retrieval_method": [

api/controllers/console/datasets/datasets_document.py

@@ -24,8 +24,11 @@ from controllers.console.datasets.error import (
     InvalidActionError,
     InvalidMetadataError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.errors.error import (
     LLMBadRequestError,
     ModelCurrentlyNotSupportError,

api/controllers/console/datasets/datasets_segments.py

@@ -11,11 +11,11 @@ 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.setup import setup_required
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_knowledge_limit_check,
     cloud_edition_billing_resource_check,
+    setup_required,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager

api/controllers/console/datasets/external.py

@@ -6,8 +6,7 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.console import api
 from controllers.console.datasets.error import DatasetNameDuplicateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
 from services.dataset_service import DatasetService

api/controllers/console/datasets/hit_testing.py

@@ -2,8 +2,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 
 

api/controllers/console/datasets/website.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.website_service import WebsiteService
 

api/controllers/console/explore/parameter.py

@@ -1,6 +1,7 @@
-from flask_restful import fields, marshal_with
+from flask_restful import marshal_with
 
-from configs import dify_config
+from controllers.common import fields
+from controllers.common import helpers as controller_helpers
 from controllers.console import api
 from controllers.console.app.error import AppUnavailableError
 from controllers.console.explore.wraps import InstalledAppResource
@@ -11,38 +12,14 @@ from services.app_service import AppService
 class AppParameterApi(InstalledAppResource):
     """Resource for app variables."""
 
-    variable_fields = {
-        "key": fields.String,
-        "name": fields.String,
-        "description": fields.String,
-        "type": fields.String,
-        "default": fields.String,
-        "max_length": fields.Integer,
-        "options": fields.List(fields.String),
-    }
-
-    system_parameters_fields = {"image_file_size_limit": fields.String}
-
-    parameters_fields = {
-        "opening_statement": fields.String,
-        "suggested_questions": fields.Raw,
-        "suggested_questions_after_answer": fields.Raw,
-        "speech_to_text": fields.Raw,
-        "text_to_speech": fields.Raw,
-        "retriever_resource": fields.Raw,
-        "annotation_reply": fields.Raw,
-        "more_like_this": fields.Raw,
-        "user_input_form": fields.Raw,
-        "sensitive_word_avoidance": fields.Raw,
-        "file_upload": fields.Raw,
-        "system_parameters": fields.Nested(system_parameters_fields),
-    }
-
-    @marshal_with(parameters_fields)
+    @marshal_with(fields.parameters_fields)
     def get(self, installed_app: InstalledApp):
         """Retrieve app parameters."""
         app_model = installed_app.app
 
+        if app_model is None:
+            raise AppUnavailableError()
+
         if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
             workflow = app_model.workflow
             if workflow is None:
@@ -52,38 +29,16 @@ class AppParameterApi(InstalledAppResource):
             user_input_form = workflow.user_input_form(to_old_structure=True)
         else:
             app_model_config = app_model.app_model_config
+            if app_model_config is None:
+                raise AppUnavailableError()
+
             features_dict = app_model_config.to_dict()
 
             user_input_form = features_dict.get("user_input_form", [])
 
-        return {
-            "opening_statement": features_dict.get("opening_statement"),
-            "suggested_questions": features_dict.get("suggested_questions", []),
-            "suggested_questions_after_answer": features_dict.get(
-                "suggested_questions_after_answer", {"enabled": False}
-            ),
-            "speech_to_text": features_dict.get("speech_to_text", {"enabled": False}),
-            "text_to_speech": features_dict.get("text_to_speech", {"enabled": False}),
-            "retriever_resource": features_dict.get("retriever_resource", {"enabled": False}),
-            "annotation_reply": features_dict.get("annotation_reply", {"enabled": False}),
-            "more_like_this": features_dict.get("more_like_this", {"enabled": False}),
-            "user_input_form": user_input_form,
-            "sensitive_word_avoidance": features_dict.get(
-                "sensitive_word_avoidance", {"enabled": False, "type": "", "configs": []}
-            ),
-            "file_upload": features_dict.get(
-                "file_upload",
-                {
-                    "image": {
-                        "enabled": False,
-                        "number_limits": 3,
-                        "detail": "high",
-                        "transfer_methods": ["remote_url", "local_file"],
-                    }
-                },
-            ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
-        }
+        return controller_helpers.get_parameters_from_feature_dict(
+            features_dict=features_dict, user_input_form=user_input_form
+        )
 
 
 class ExploreAppMetaApi(InstalledAppResource):

api/controllers/console/extension.py

@@ -3,8 +3,7 @@ from flask_restful import Resource, marshal_with, reqparse
 
 from constants import HIDDEN_VALUE
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.api_based_extension_fields import api_based_extension_fields
 from libs.login import login_required
 from models.api_based_extension import APIBasedExtension

api/controllers/console/feature.py

@@ -5,8 +5,7 @@ from libs.login import login_required
 from services.feature_service import FeatureService
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required, cloud_utm_record
+from .wraps import account_initialization_required, cloud_utm_record, setup_required
 
 
 class FeatureApi(Resource):

api/controllers/console/files/__init__.py

@@ -1,25 +1,26 @@
-import urllib.parse
-
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with
 
 import services
 from configs import dify_config
 from constants import DOCUMENT_EXTENSIONS
-from controllers.console import api
-from controllers.console.datasets.error import (
+from controllers.common.errors import FilenameNotExistsError
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
+from fields.file_fields import file_fields, upload_config_fields
+from libs.login import login_required
+from services.file_service import FileService
+
+from .errors import (
     FileTooLargeError,
     NoFileUploadedError,
     TooManyFilesError,
     UnsupportedFileTypeError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
-from libs.login import login_required
-from services.file_service import FileService
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -36,6 +37,7 @@ class FileApi(Resource):
             "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
             "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
             "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+            "workflow_file_upload_limit": dify_config.WORKFLOW_FILE_UPLOAD_LIMIT,
         }, 200
 
     @setup_required
@@ -44,21 +46,29 @@ class FileApi(Resource):
     @marshal_with(file_fields)
     @cloud_edition_billing_resource_check("documents")
     def post(self):
-        # get file from request
         file = request.files["file"]
+        source = request.form.get("source")
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
 
         if len(request.files) > 1:
             raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user, source=source)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source=source,
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:
@@ -83,23 +93,3 @@ class FileSupportTypeApi(Resource):
     @account_initialization_required
     def get(self):
         return {"allowed_extensions": DOCUMENT_EXTENSIONS}
-
-
-class RemoteFileInfoApi(Resource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", 0)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
-api.add_resource(FileSupportTypeApi, "/files/support-type")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/console/files/errors.py

@@ -0,0 +1,25 @@
+from libs.exception import BaseHTTPException
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = "file_too_large"
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = "too_many_files"
+    description = "Only one file is allowed."
+    code = 400
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = "no_file_uploaded"
+    description = "Please upload your file."
+    code = 400

api/controllers/console/remote_files.py

@@ -0,0 +1,71 @@
+import urllib.parse
+from typing import cast
+
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+
+from controllers.common import helpers
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from models.account import Account
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(Resource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", 0)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(Resource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            user = cast(Account, current_user)
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=user,
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/controllers/console/setup.py

@@ -1,5 +1,3 @@
-from functools import wraps
-
 from flask import request
 from flask_restful import Resource, reqparse
 
@@ -10,7 +8,7 @@ from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
 
 from . import api
-from .error import AlreadySetupError, NotInitValidateError, NotSetupError
+from .error import AlreadySetupError, NotInitValidateError
 from .init_validate import get_init_validate_status
 from .wraps import only_edition_self_hosted
 
@@ -52,26 +50,10 @@ class SetupApi(Resource):
         return {"result": "success"}, 201
 
 
-def setup_required(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        # check setup
-        if not get_init_validate_status():
-            raise NotInitValidateError()
-
-        elif not get_setup_status():
-            raise NotSetupError()
-
-        return view(*args, **kwargs)
-
-    return decorated
-
-
 def get_setup_status():
     if dify_config.EDITION == "SELF_HOSTED":
         return DifySetup.query.first()
-    else:
-        return True
+    return True
 
 
 api.add_resource(SetupApi, "/setup")

api/controllers/console/tag/tags.py

@@ -4,8 +4,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.tag_fields import tag_fields
 from libs.login import login_required
 from models.model import Tag

api/controllers/console/version.py

@@ -3,6 +3,7 @@ import logging
 
 import requests
 from flask_restful import Resource, reqparse
+from packaging import version
 
 from configs import dify_config
 
@@ -47,43 +48,15 @@ class VersionApi(Resource):
 
 
 def _has_new_version(*, latest_version: str, current_version: str) -> bool:
-    def parse_version(version: str) -> tuple:
-        # Split version into parts and pre-release suffix if any
-        parts = version.split("-")
-        version_parts = parts[0].split(".")
-        pre_release = parts[1] if len(parts) > 1 else None
+    try:
+        latest = version.parse(latest_version)
+        current = version.parse(current_version)
 
-        # Validate version format
-        if len(version_parts) != 3:
-            raise ValueError(f"Invalid version format: {version}")
-
-        try:
-            # Convert version parts to integers
-            major, minor, patch = map(int, version_parts)
-            return (major, minor, patch, pre_release)
-        except ValueError:
-            raise ValueError(f"Invalid version format: {version}")
-
-    latest = parse_version(latest_version)
-    current = parse_version(current_version)
-
-    # Compare major, minor, and patch versions
-    for latest_part, current_part in zip(latest[:3], current[:3]):
-        if latest_part > current_part:
-            return True
-        elif latest_part < current_part:
-            return False
-
-    # If versions are equal, check pre-release suffixes
-    if latest[3] is None and current[3] is not None:
-        return True
-    elif latest[3] is not None and current[3] is None:
+        # Compare versions
+        return latest > current
+    except version.InvalidVersion:
+        logging.warning(f"Invalid version format: latest={latest_version}, current={current_version}")
         return False
-    elif latest[3] is not None and current[3] is not None:
-        # Simple string comparison for pre-release versions
-        return latest[3] > current[3]
-
-    return False
 
 
 api.add_resource(VersionApi, "/version")

api/controllers/console/workspace/account.py

@@ -8,14 +8,13 @@ from flask_restful import Resource, fields, marshal_with, reqparse
 from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
-from controllers.console.setup import setup_required
 from controllers.console.workspace.error import (
     AccountAlreadyInitedError,
     CurrentPasswordIncorrectError,
     InvalidInvitationCodeError,
     RepeatPasswordNotMatchError,
 )
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.member_fields import account_fields
 from libs.helper import TimestampField, timezone

api/controllers/console/workspace/load_balancing_config.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from libs.login import current_user, login_required

api/controllers/console/workspace/members.py

@@ -4,8 +4,11 @@ from flask_restful import Resource, abort, marshal_with, reqparse
 import services
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from fields.member_fields import account_with_role_list_fields
 from libs.login import login_required

api/controllers/console/workspace/model_providers.py

@@ -6,8 +6,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/models.py

@@ -5,8 +5,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/tool_providers.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import alphanumeric, uuid_value
 from libs.login import login_required

api/controllers/console/workspace/workspace.py

@@ -6,6 +6,7 @@ from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqpa
 from werkzeug.exceptions import Unauthorized
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.console import api
 from controllers.console.admin import admin_required
 from controllers.console.datasets.error import (
@@ -15,8 +16,11 @@ from controllers.console.datasets.error import (
     UnsupportedFileTypeError,
 )
 from controllers.console.error import AccountNotLinkTenantError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from libs.helper import TimestampField
 from libs.login import login_required
@@ -193,12 +197,20 @@ class WebappLogoWorkspaceApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         extension = file.filename.split(".")[-1]
         if extension.lower() not in {"svg", "png"}:
             raise UnsupportedFileTypeError()
 
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+            )
 
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)

api/controllers/console/wraps.py

@@ -1,4 +1,5 @@
 import json
+import os
 from functools import wraps
 
 from flask import abort, request
@@ -6,9 +7,12 @@ from flask_login import current_user
 
 from configs import dify_config
 from controllers.console.workspace.error import AccountNotInitializedError
+from models.model import DifySetup
 from services.feature_service import FeatureService
 from services.operation_service import OperationService
 
+from .error import NotInitValidateError, NotSetupError
+
 
 def account_initialization_required(view):
     @wraps(view)
@@ -124,3 +128,17 @@ def cloud_utm_record(view):
         return view(*args, **kwargs)
 
     return decorated
+
+
+def setup_required(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        # check setup
+        if dify_config.EDITION == "SELF_HOSTED" and os.environ.get("INIT_PASSWORD") and not DifySetup.query.first():
+            raise NotInitValidateError()
+        elif dify_config.EDITION == "SELF_HOSTED" and not DifySetup.query.first():
+            raise NotSetupError()
+
+        return view(*args, **kwargs)
+
+    return decorated

api/controllers/inner_api/workspace/workspace.py

@@ -1,6 +1,6 @@
 from flask_restful import Resource, reqparse
 
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from controllers.inner_api import api
 from controllers.inner_api.wraps import inner_api_only
 from events.tenant_event import tenant_was_created
@@ -21,7 +21,7 @@ class EnterpriseWorkspace(Resource):
         if account is None:
             return {"message": "owner account not found."}, 404
 
-        tenant = TenantService.create_tenant(args["name"])
+        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
         TenantService.create_tenant_member(tenant, account, role="owner")
 
         tenant_was_created.send(tenant)

api/controllers/service_api/app/app.py

@@ -1,6 +1,7 @@
-from flask_restful import Resource, fields, marshal_with
+from flask_restful import Resource, marshal_with
 
-from configs import dify_config
+from controllers.common import fields
+from controllers.common import helpers as controller_helpers
 from controllers.service_api import api
 from controllers.service_api.app.error import AppUnavailableError
 from controllers.service_api.wraps import validate_app_token
@@ -11,35 +12,8 @@ from services.app_service import AppService
 class AppParameterApi(Resource):
     """Resource for app variables."""
 
-    variable_fields = {
-        "key": fields.String,
-        "name": fields.String,
-        "description": fields.String,
-        "type": fields.String,
-        "default": fields.String,
-        "max_length": fields.Integer,
-        "options": fields.List(fields.String),
-    }
-
-    system_parameters_fields = {"image_file_size_limit": fields.String}
-
-    parameters_fields = {
-        "opening_statement": fields.String,
-        "suggested_questions": fields.Raw,
-        "suggested_questions_after_answer": fields.Raw,
-        "speech_to_text": fields.Raw,
-        "text_to_speech": fields.Raw,
-        "retriever_resource": fields.Raw,
-        "annotation_reply": fields.Raw,
-        "more_like_this": fields.Raw,
-        "user_input_form": fields.Raw,
-        "sensitive_word_avoidance": fields.Raw,
-        "file_upload": fields.Raw,
-        "system_parameters": fields.Nested(system_parameters_fields),
-    }
-
     @validate_app_token
-    @marshal_with(parameters_fields)
+    @marshal_with(fields.parameters_fields)
     def get(self, app_model: App):
         """Retrieve app parameters."""
         if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
@@ -51,38 +25,16 @@ class AppParameterApi(Resource):
             user_input_form = workflow.user_input_form(to_old_structure=True)
         else:
             app_model_config = app_model.app_model_config
+            if app_model_config is None:
+                raise AppUnavailableError()
+
             features_dict = app_model_config.to_dict()
 
             user_input_form = features_dict.get("user_input_form", [])
 
-        return {
-            "opening_statement": features_dict.get("opening_statement"),
-            "suggested_questions": features_dict.get("suggested_questions", []),
-            "suggested_questions_after_answer": features_dict.get(
-                "suggested_questions_after_answer", {"enabled": False}
-            ),
-            "speech_to_text": features_dict.get("speech_to_text", {"enabled": False}),
-            "text_to_speech": features_dict.get("text_to_speech", {"enabled": False}),
-            "retriever_resource": features_dict.get("retriever_resource", {"enabled": False}),
-            "annotation_reply": features_dict.get("annotation_reply", {"enabled": False}),
-            "more_like_this": features_dict.get("more_like_this", {"enabled": False}),
-            "user_input_form": user_input_form,
-            "sensitive_word_avoidance": features_dict.get(
-                "sensitive_word_avoidance", {"enabled": False, "type": "", "configs": []}
-            ),
-            "file_upload": features_dict.get(
-                "file_upload",
-                {
-                    "image": {
-                        "enabled": False,
-                        "number_limits": 3,
-                        "detail": "high",
-                        "transfer_methods": ["remote_url", "local_file"],
-                    }
-                },
-            ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
-        }
+        return controller_helpers.get_parameters_from_feature_dict(
+            features_dict=features_dict, user_input_form=user_input_form
+        )
 
 
 class AppMetaApi(Resource):

api/controllers/service_api/app/file.py

@@ -2,6 +2,7 @@ from flask import request
 from flask_restful import Resource, marshal_with
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import (
     FileTooLargeError,
@@ -31,8 +32,16 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         try:
-            upload_file = FileService.upload_file(file, end_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:

api/controllers/service_api/dataset/dataset.py

@@ -66,6 +66,13 @@ class DatasetListApi(DatasetApiResource):
             help="type is required. Name must be between 1 to 40 characters.",
             type=_validate_name,
         )
+        parser.add_argument(
+            "description",
+            type=str,
+            nullable=True,
+            required=False,
+            default="",
+        )
         parser.add_argument(
             "indexing_technique",
             type=str,
@@ -108,6 +115,7 @@ class DatasetListApi(DatasetApiResource):
             dataset = DatasetService.create_empty_dataset(
                 tenant_id=tenant_id,
                 name=args["name"],
+                description=args["description"],
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=args["permission"],

api/controllers/service_api/dataset/document.py

@@ -6,6 +6,7 @@ from sqlalchemy import desc
 from werkzeug.exceptions import NotFound
 
 import services.dataset_service
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.dataset.error import (
@@ -55,7 +56,12 @@ class DocumentAddByTextApi(DatasetApiResource):
         if not dataset.indexing_technique and not args["indexing_technique"]:
             raise ValueError("indexing_technique is required.")
 
-        upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+        text = args.get("text")
+        name = args.get("name")
+        if text is None or name is None:
+            raise ValueError("Both 'text' and 'name' must be non-null values.")
+
+        upload_file = FileService.upload_text(text=str(text), text_name=str(name))
         data_source = {
             "type": "upload_file",
             "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -104,7 +110,11 @@ class DocumentUpdateByTextApi(DatasetApiResource):
             raise ValueError("Dataset is not exist.")
 
         if args["text"]:
-            upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+            text = args.get("text")
+            name = args.get("name")
+            if text is None or name is None:
+                raise ValueError("Both text and name must be strings.")
+            upload_file = FileService.upload_text(text=str(text), text_name=str(name))
             data_source = {
                 "type": "upload_file",
                 "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -163,7 +173,16 @@ class DocumentAddByFileApi(DatasetApiResource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
-        upload_file = FileService.upload_file(file, current_user)
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        upload_file = FileService.upload_file(
+            filename=file.filename,
+            content=file.read(),
+            mimetype=file.mimetype,
+            user=current_user,
+            source="datasets",
+        )
         data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
         args["data_source"] = data_source
         # validate args
@@ -212,7 +231,16 @@ class DocumentUpdateByFileApi(DatasetApiResource):
             if len(request.files) > 1:
                 raise TooManyFilesError()
 
-            upload_file = FileService.upload_file(file, current_user)
+            if not file.filename:
+                raise FilenameNotExistsError
+
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source="datasets",
+            )
             data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
             args["data_source"] = data_source
         # validate args
@@ -230,7 +258,7 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         except ProviderTokenNotInitError as ex:
             raise ProviderNotInitializeError(ex.description)
         document = documents[0]
-        documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": batch}
+        documents_and_batch_fields = {"document": marshal(document, document_fields), "batch": document.batch}
         return documents_and_batch_fields, 200
 
 
@@ -331,10 +359,26 @@ class DocumentIndexingStatusApi(DatasetApiResource):
         return data
 
 
-api.add_resource(DocumentAddByTextApi, "/datasets/<uuid:dataset_id>/document/create_by_text")
-api.add_resource(DocumentAddByFileApi, "/datasets/<uuid:dataset_id>/document/create_by_file")
-api.add_resource(DocumentUpdateByTextApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text")
-api.add_resource(DocumentUpdateByFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file")
+api.add_resource(
+    DocumentAddByTextApi,
+    "/datasets/<uuid:dataset_id>/document/create_by_text",
+    "/datasets/<uuid:dataset_id>/document/create-by-text",
+)
+api.add_resource(
+    DocumentAddByFileApi,
+    "/datasets/<uuid:dataset_id>/document/create_by_file",
+    "/datasets/<uuid:dataset_id>/document/create-by-file",
+)
+api.add_resource(
+    DocumentUpdateByTextApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_text",
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-text",
+)
+api.add_resource(
+    DocumentUpdateByFileApi,
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update_by_file",
+    "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/update-by-file",
+)
 api.add_resource(DocumentDeleteApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>")
 api.add_resource(DocumentListApi, "/datasets/<uuid:dataset_id>/documents")
 api.add_resource(DocumentIndexingStatusApi, "/datasets/<uuid:dataset_id>/documents/<string:batch>/indexing-status")

api/controllers/service_api/dataset/hit_testing.py

@@ -14,4 +14,4 @@ class HitTestingApi(DatasetApiResource, DatasetsHitTestingBase):
         return self.perform_hit_testing(dataset, args)
 
 
-api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing")
+api.add_resource(HitTestingApi, "/datasets/<uuid:dataset_id>/hit-testing", "/datasets/<uuid:dataset_id>/retrieve")

api/controllers/web/__init__.py

@@ -2,8 +2,17 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("web", __name__, url_prefix="/api")
 api = ExternalApi(bp)
 
+# Files
+api.add_resource(FileApi, "/files/upload")
 
-from . import app, audio, completion, conversation, feature, file, message, passport, saved_message, site, workflow
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
+from . import app, audio, completion, conversation, feature, message, passport, saved_message, site, workflow

api/controllers/web/app.py

@@ -1,6 +1,7 @@
-from flask_restful import fields, marshal_with
+from flask_restful import marshal_with
 
-from configs import dify_config
+from controllers.common import fields
+from controllers.common import helpers as controller_helpers
 from controllers.web import api
 from controllers.web.error import AppUnavailableError
 from controllers.web.wraps import WebApiResource
@@ -11,34 +12,7 @@ from services.app_service import AppService
 class AppParameterApi(WebApiResource):
     """Resource for app variables."""
 
-    variable_fields = {
-        "key": fields.String,
-        "name": fields.String,
-        "description": fields.String,
-        "type": fields.String,
-        "default": fields.String,
-        "max_length": fields.Integer,
-        "options": fields.List(fields.String),
-    }
-
-    system_parameters_fields = {"image_file_size_limit": fields.String}
-
-    parameters_fields = {
-        "opening_statement": fields.String,
-        "suggested_questions": fields.Raw,
-        "suggested_questions_after_answer": fields.Raw,
-        "speech_to_text": fields.Raw,
-        "text_to_speech": fields.Raw,
-        "retriever_resource": fields.Raw,
-        "annotation_reply": fields.Raw,
-        "more_like_this": fields.Raw,
-        "user_input_form": fields.Raw,
-        "sensitive_word_avoidance": fields.Raw,
-        "file_upload": fields.Raw,
-        "system_parameters": fields.Nested(system_parameters_fields),
-    }
-
-    @marshal_with(parameters_fields)
+    @marshal_with(fields.parameters_fields)
     def get(self, app_model: App, end_user):
         """Retrieve app parameters."""
         if app_model.mode in {AppMode.ADVANCED_CHAT.value, AppMode.WORKFLOW.value}:
@@ -50,38 +24,16 @@ class AppParameterApi(WebApiResource):
             user_input_form = workflow.user_input_form(to_old_structure=True)
         else:
             app_model_config = app_model.app_model_config
+            if app_model_config is None:
+                raise AppUnavailableError()
+
             features_dict = app_model_config.to_dict()
 
             user_input_form = features_dict.get("user_input_form", [])
 
-        return {
-            "opening_statement": features_dict.get("opening_statement"),
-            "suggested_questions": features_dict.get("suggested_questions", []),
-            "suggested_questions_after_answer": features_dict.get(
-                "suggested_questions_after_answer", {"enabled": False}
-            ),
-            "speech_to_text": features_dict.get("speech_to_text", {"enabled": False}),
-            "text_to_speech": features_dict.get("text_to_speech", {"enabled": False}),
-            "retriever_resource": features_dict.get("retriever_resource", {"enabled": False}),
-            "annotation_reply": features_dict.get("annotation_reply", {"enabled": False}),
-            "more_like_this": features_dict.get("more_like_this", {"enabled": False}),
-            "user_input_form": user_input_form,
-            "sensitive_word_avoidance": features_dict.get(
-                "sensitive_word_avoidance", {"enabled": False, "type": "", "configs": []}
-            ),
-            "file_upload": features_dict.get(
-                "file_upload",
-                {
-                    "image": {
-                        "enabled": False,
-                        "number_limits": 3,
-                        "detail": "high",
-                        "transfer_methods": ["remote_url", "local_file"],
-                    }
-                },
-            ),
-            "system_parameters": {"image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT},
-        }
+        return controller_helpers.get_parameters_from_feature_dict(
+            features_dict=features_dict, user_input_form=user_input_form
+        )
 
 
 class AppMeta(WebApiResource):

api/controllers/web/file.py

@@ -1,56 +0,0 @@
-import urllib.parse
-
-from flask import request
-from flask_restful import marshal_with, reqparse
-
-import services
-from controllers.web import api
-from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
-from controllers.web.wraps import WebApiResource
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields
-from services.file_service import FileService
-
-
-class FileApi(WebApiResource):
-    @marshal_with(file_fields)
-    def post(self, app_model, end_user):
-        # get file from request
-        file = request.files["file"]
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
-        if "file" not in request.files:
-            raise NoFileUploadedError()
-
-        if len(request.files) > 1:
-            raise TooManyFilesError()
-        try:
-            upload_file = FileService.upload_file(file=file, user=end_user, source=source)
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
-
-        return upload_file, 201
-
-
-class RemoteFileInfoApi(WebApiResource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", -1)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/web/files.py

@@ -0,0 +1,43 @@
+from flask import request
+from flask_restful import marshal_with
+
+import services
+from controllers.common.errors import FilenameNotExistsError
+from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
+from controllers.web.wraps import WebApiResource
+from fields.file_fields import file_fields
+from services.file_service import FileService
+
+
+class FileApi(WebApiResource):
+    @marshal_with(file_fields)
+    def post(self, app_model, end_user):
+        file = request.files["file"]
+        source = request.form.get("source")
+
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+                source=source,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201

api/controllers/web/remote_files.py

@@ -0,0 +1,68 @@
+import urllib.parse
+
+from flask_restful import marshal_with, reqparse
+
+from controllers.common import helpers
+from controllers.web.wraps import WebApiResource
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(WebApiResource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", -1)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(WebApiResource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self, app_model, end_user):  # Add app_model and end_user parameters
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=end_user,  # Use end_user instead of current_user
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/core/agent/base_agent_runner.py

@@ -165,6 +165,12 @@ class BaseAgentRunner(AppRunner):
                 continue
 
             parameter_type = parameter.type.as_normal_type()
+            if parameter.type in {
+                ToolParameter.ToolParameterType.SYSTEM_FILES,
+                ToolParameter.ToolParameterType.FILE,
+                ToolParameter.ToolParameterType.FILES,
+            }:
+                continue
             enum = []
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options]
@@ -250,6 +256,12 @@ class BaseAgentRunner(AppRunner):
                 continue
 
             parameter_type = parameter.type.as_normal_type()
+            if parameter.type in {
+                ToolParameter.ToolParameterType.SYSTEM_FILES,
+                ToolParameter.ToolParameterType.FILE,
+                ToolParameter.ToolParameterType.FILES,
+            }:
+                continue
             enum = []
             if parameter.type == ToolParameter.ToolParameterType.SELECT:
                 enum = [option.value for option in parameter.options]

api/core/app/app_config/features/file_upload/manager.py

@@ -1,8 +1,7 @@
 from collections.abc import Mapping
 from typing import Any
 
-from core.file.models import FileExtraConfig
-from models import FileUploadConfig
+from core.file import FileExtraConfig
 
 
 class FileUploadConfigManager:
@@ -43,6 +42,6 @@ class FileUploadConfigManager:
         if not config.get("file_upload"):
             config["file_upload"] = {}
         else:
-            FileUploadConfig.model_validate(config["file_upload"])
+            FileExtraConfig.model_validate(config["file_upload"])
 
         return config, ["file_upload"]

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -20,6 +20,7 @@ from core.app.entities.queue_entities import (
     QueueIterationStartEvent,
     QueueMessageReplaceEvent,
     QueueNodeFailedEvent,
+    QueueNodeInIterationFailedEvent,
     QueueNodeStartedEvent,
     QueueNodeSucceededEvent,
     QueueParallelBranchRunFailedEvent,
@@ -314,7 +315,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
 
                 if response:
                     yield response
-            elif isinstance(event, QueueNodeFailedEvent):
+            elif isinstance(event, QueueNodeFailedEvent | QueueNodeInIterationFailedEvent):
                 workflow_node_execution = self._handle_workflow_node_execution_failed(event)
 
                 response = self._workflow_node_finish_to_stream_response(

api/core/app/apps/base_app_generator.py

@@ -22,7 +22,10 @@ class BaseAppGenerator:
         user_inputs = user_inputs or {}
         # Filter input variables from form configuration, handle required fields, default values, and option values
         variables = app_config.variables
-        user_inputs = {var.variable: self._validate_input(inputs=user_inputs, var=var) for var in variables}
+        user_inputs = {
+            var.variable: self._validate_inputs(value=user_inputs.get(var.variable), variable_entity=var)
+            for var in variables
+        }
         user_inputs = {k: self._sanitize_value(v) for k, v in user_inputs.items()}
         # Convert files in inputs to File
         entity_dictionary = {item.variable: item for item in app_config.variables}
@@ -74,50 +77,66 @@ class BaseAppGenerator:
 
         return user_inputs
 
-    def _validate_input(self, *, inputs: Mapping[str, Any], var: "VariableEntity"):
-        user_input_value = inputs.get(var.variable)
-        if not user_input_value:
-            if var.required:
-                raise ValueError(f"{var.variable} is required in input form")
-            else:
-                return None
+    def _validate_inputs(
+        self,
+        *,
+        variable_entity: "VariableEntity",
+        value: Any,
+    ):
+        if value is None:
+            if variable_entity.required:
+                raise ValueError(f"{variable_entity.variable} is required in input form")
+            return value
 
-        if var.type in {
+        if variable_entity.type in {
             VariableEntityType.TEXT_INPUT,
             VariableEntityType.SELECT,
             VariableEntityType.PARAGRAPH,
-        } and not isinstance(user_input_value, str):
-            raise ValueError(f"(type '{var.type}') {var.variable} in input form must be a string")
-        if var.type == VariableEntityType.NUMBER and isinstance(user_input_value, str):
+        } and not isinstance(value, str):
+            raise ValueError(
+                f"(type '{variable_entity.type}') {variable_entity.variable} in input form must be a string"
+            )
+
+        if variable_entity.type == VariableEntityType.NUMBER and isinstance(value, str):
             # may raise ValueError if user_input_value is not a valid number
             try:
-                if "." in user_input_value:
-                    return float(user_input_value)
+                if "." in value:
+                    return float(value)
                 else:
-                    return int(user_input_value)
+                    return int(value)
             except ValueError:
-                raise ValueError(f"{var.variable} in input form must be a valid number")
-        if var.type == VariableEntityType.SELECT:
-            options = var.options
-            if user_input_value not in options:
-                raise ValueError(f"{var.variable} in input form must be one of the following: {options}")
-        elif var.type in {VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH}:
-            if var.max_length and len(user_input_value) > var.max_length:
-                raise ValueError(f"{var.variable} in input form must be less than {var.max_length} characters")
-        elif var.type == VariableEntityType.FILE:
-            if not isinstance(user_input_value, dict) and not isinstance(user_input_value, File):
-                raise ValueError(f"{var.variable} in input form must be a file")
-        elif var.type == VariableEntityType.FILE_LIST:
-            if not (
-                isinstance(user_input_value, list)
-                and (
-                    all(isinstance(item, dict) for item in user_input_value)
-                    or all(isinstance(item, File) for item in user_input_value)
-                )
-            ):
-                raise ValueError(f"{var.variable} in input form must be a list of files")
+                raise ValueError(f"{variable_entity.variable} in input form must be a valid number")
 
-        return user_input_value
+        match variable_entity.type:
+            case VariableEntityType.SELECT:
+                if value not in variable_entity.options:
+                    raise ValueError(
+                        f"{variable_entity.variable} in input form must be one of the following: "
+                        f"{variable_entity.options}"
+                    )
+            case VariableEntityType.TEXT_INPUT | VariableEntityType.PARAGRAPH:
+                if variable_entity.max_length and len(value) > variable_entity.max_length:
+                    raise ValueError(
+                        f"{variable_entity.variable} in input form must be less than {variable_entity.max_length} "
+                        "characters"
+                    )
+            case VariableEntityType.FILE:
+                if not isinstance(value, dict) and not isinstance(value, File):
+                    raise ValueError(f"{variable_entity.variable} in input form must be a file")
+            case VariableEntityType.FILE_LIST:
+                # if number of files exceeds the limit, raise ValueError
+                if not (
+                    isinstance(value, list)
+                    and (all(isinstance(item, dict) for item in value) or all(isinstance(item, File) for item in value))
+                ):
+                    raise ValueError(f"{variable_entity.variable} in input form must be a list of files")
+
+                if variable_entity.max_length and len(value) > variable_entity.max_length:
+                    raise ValueError(
+                        f"{variable_entity.variable} in input form must be less than {variable_entity.max_length} files"
+                    )
+
+        return value
 
     def _sanitize_value(self, value: Any) -> Any:
         if isinstance(value, str):

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -16,6 +16,7 @@ from core.app.entities.queue_entities import (
     QueueIterationNextEvent,
     QueueIterationStartEvent,
     QueueNodeFailedEvent,
+    QueueNodeInIterationFailedEvent,
     QueueNodeStartedEvent,
     QueueNodeSucceededEvent,
     QueueParallelBranchRunFailedEvent,
@@ -275,7 +276,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
 
                 if response:
                     yield response
-            elif isinstance(event, QueueNodeFailedEvent):
+            elif isinstance(event, QueueNodeFailedEvent | QueueNodeInIterationFailedEvent):
                 workflow_node_execution = self._handle_workflow_node_execution_failed(event)
 
                 response = self._workflow_node_finish_to_stream_response(

api/core/app/apps/workflow_app_runner.py

@@ -9,6 +9,7 @@ from core.app.entities.queue_entities import (
     QueueIterationNextEvent,
     QueueIterationStartEvent,
     QueueNodeFailedEvent,
+    QueueNodeInIterationFailedEvent,
     QueueNodeStartedEvent,
     QueueNodeSucceededEvent,
     QueueParallelBranchRunFailedEvent,
@@ -30,6 +31,7 @@ from core.workflow.graph_engine.entities.event import (
     IterationRunNextEvent,
     IterationRunStartedEvent,
     IterationRunSucceededEvent,
+    NodeInIterationFailedEvent,
     NodeRunFailedEvent,
     NodeRunRetrieverResourceEvent,
     NodeRunStartedEvent,
@@ -193,6 +195,7 @@ class WorkflowBasedAppRunner(AppRunner):
                     node_run_index=event.route_node_state.index,
                     predecessor_node_id=event.predecessor_node_id,
                     in_iteration_id=event.in_iteration_id,
+                    parallel_mode_run_id=event.parallel_mode_run_id,
                 )
             )
         elif isinstance(event, NodeRunSucceededEvent):
@@ -246,9 +249,40 @@ class WorkflowBasedAppRunner(AppRunner):
                     error=event.route_node_state.node_run_result.error
                     if event.route_node_state.node_run_result and event.route_node_state.node_run_result.error
                     else "Unknown error",
+                    execution_metadata=event.route_node_state.node_run_result.metadata
+                    if event.route_node_state.node_run_result
+                    else {},
                     in_iteration_id=event.in_iteration_id,
                 )
             )
+        elif isinstance(event, NodeInIterationFailedEvent):
+            self._publish_event(
+                QueueNodeInIterationFailedEvent(
+                    node_execution_id=event.id,
+                    node_id=event.node_id,
+                    node_type=event.node_type,
+                    node_data=event.node_data,
+                    parallel_id=event.parallel_id,
+                    parallel_start_node_id=event.parallel_start_node_id,
+                    parent_parallel_id=event.parent_parallel_id,
+                    parent_parallel_start_node_id=event.parent_parallel_start_node_id,
+                    start_at=event.route_node_state.start_at,
+                    inputs=event.route_node_state.node_run_result.inputs
+                    if event.route_node_state.node_run_result
+                    else {},
+                    process_data=event.route_node_state.node_run_result.process_data
+                    if event.route_node_state.node_run_result
+                    else {},
+                    outputs=event.route_node_state.node_run_result.outputs
+                    if event.route_node_state.node_run_result
+                    else {},
+                    execution_metadata=event.route_node_state.node_run_result.metadata
+                    if event.route_node_state.node_run_result
+                    else {},
+                    in_iteration_id=event.in_iteration_id,
+                    error=event.error,
+                )
+            )
         elif isinstance(event, NodeRunStreamChunkEvent):
             self._publish_event(
                 QueueTextChunkEvent(
@@ -326,6 +360,7 @@ class WorkflowBasedAppRunner(AppRunner):
                     index=event.index,
                     node_run_index=workflow_entry.graph_engine.graph_runtime_state.node_run_steps,
                     output=event.pre_iteration_output,
+                    parallel_mode_run_id=event.parallel_mode_run_id,
                 )
             )
         elif isinstance(event, (IterationRunSucceededEvent | IterationRunFailedEvent)):

api/core/app/entities/queue_entities.py

@@ -107,7 +107,8 @@ class QueueIterationNextEvent(AppQueueEvent):
     """parent parallel id if node is in parallel"""
     parent_parallel_start_node_id: Optional[str] = None
     """parent parallel start node id if node is in parallel"""
-
+    parallel_mode_run_id: Optional[str] = None
+    """iteratoin run in parallel mode run id"""
     node_run_index: int
     output: Optional[Any] = None  # output for the current iteration
 
@@ -273,6 +274,8 @@ class QueueNodeStartedEvent(AppQueueEvent):
     in_iteration_id: Optional[str] = None
     """iteration id if node is in iteration"""
     start_at: datetime
+    parallel_mode_run_id: Optional[str] = None
+    """iteratoin run in parallel mode run id"""
 
 
 class QueueNodeSucceededEvent(AppQueueEvent):
@@ -306,6 +309,37 @@ class QueueNodeSucceededEvent(AppQueueEvent):
     error: Optional[str] = None
 
 
+class QueueNodeInIterationFailedEvent(AppQueueEvent):
+    """
+    QueueNodeInIterationFailedEvent entity
+    """
+
+    event: QueueEvent = QueueEvent.NODE_FAILED
+
+    node_execution_id: str
+    node_id: str
+    node_type: NodeType
+    node_data: BaseNodeData
+    parallel_id: Optional[str] = None
+    """parallel id if node is in parallel"""
+    parallel_start_node_id: Optional[str] = None
+    """parallel start node id if node is in parallel"""
+    parent_parallel_id: Optional[str] = None
+    """parent parallel id if node is in parallel"""
+    parent_parallel_start_node_id: Optional[str] = None
+    """parent parallel start node id if node is in parallel"""
+    in_iteration_id: Optional[str] = None
+    """iteration id if node is in iteration"""
+    start_at: datetime
+
+    inputs: Optional[dict[str, Any]] = None
+    process_data: Optional[dict[str, Any]] = None
+    outputs: Optional[dict[str, Any]] = None
+    execution_metadata: Optional[dict[NodeRunMetadataKey, Any]] = None
+
+    error: str
+
+
 class QueueNodeFailedEvent(AppQueueEvent):
     """
     QueueNodeFailedEvent entity
@@ -332,6 +366,7 @@ class QueueNodeFailedEvent(AppQueueEvent):
     inputs: Optional[dict[str, Any]] = None
     process_data: Optional[dict[str, Any]] = None
     outputs: Optional[dict[str, Any]] = None
+    execution_metadata: Optional[dict[NodeRunMetadataKey, Any]] = None
 
     error: str
 

api/core/app/entities/task_entities.py

@@ -244,6 +244,7 @@ class NodeStartStreamResponse(StreamResponse):
         parent_parallel_id: Optional[str] = None
         parent_parallel_start_node_id: Optional[str] = None
         iteration_id: Optional[str] = None
+        parallel_run_id: Optional[str] = None
 
     event: StreamEvent = StreamEvent.NODE_STARTED
     workflow_run_id: str
@@ -432,6 +433,7 @@ class IterationNodeNextStreamResponse(StreamResponse):
         extras: dict = {}
         parallel_id: Optional[str] = None
         parallel_start_node_id: Optional[str] = None
+        parallel_mode_run_id: Optional[str] = None
 
     event: StreamEvent = StreamEvent.ITERATION_NEXT
     workflow_run_id: str

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -12,6 +12,7 @@ from core.app.entities.queue_entities import (
     QueueIterationNextEvent,
     QueueIterationStartEvent,
     QueueNodeFailedEvent,
+    QueueNodeInIterationFailedEvent,
     QueueNodeStartedEvent,
     QueueNodeSucceededEvent,
     QueueParallelBranchRunFailedEvent,
@@ -35,6 +36,7 @@ from core.model_runtime.utils.encoders import jsonable_encoder
 from core.ops.entities.trace_entity import TraceTaskName
 from core.ops.ops_trace_manager import TraceQueueManager, TraceTask
 from core.tools.tool_manager import ToolManager
+from core.workflow.entities.node_entities import NodeRunMetadataKey
 from core.workflow.enums import SystemVariableKey
 from core.workflow.nodes import NodeType
 from core.workflow.nodes.tool.entities import ToolNodeData
@@ -251,6 +253,12 @@ class WorkflowCycleManage:
             workflow_node_execution.status = WorkflowNodeExecutionStatus.RUNNING.value
             workflow_node_execution.created_by_role = workflow_run.created_by_role
             workflow_node_execution.created_by = workflow_run.created_by
+            workflow_node_execution.execution_metadata = json.dumps(
+                {
+                    NodeRunMetadataKey.PARALLEL_MODE_RUN_ID: event.parallel_mode_run_id,
+                    NodeRunMetadataKey.ITERATION_ID: event.in_iteration_id,
+                }
+            )
             workflow_node_execution.created_at = datetime.now(timezone.utc).replace(tzinfo=None)
 
             session.add(workflow_node_execution)
@@ -305,7 +313,9 @@ class WorkflowCycleManage:
 
         return workflow_node_execution
 
-    def _handle_workflow_node_execution_failed(self, event: QueueNodeFailedEvent) -> WorkflowNodeExecution:
+    def _handle_workflow_node_execution_failed(
+        self, event: QueueNodeFailedEvent | QueueNodeInIterationFailedEvent
+    ) -> WorkflowNodeExecution:
         """
         Workflow node execution failed
         :param event: queue node failed event
@@ -318,16 +328,19 @@ class WorkflowCycleManage:
         outputs = WorkflowEntry.handle_special_values(event.outputs)
         finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
         elapsed_time = (finished_at - event.start_at).total_seconds()
-
+        execution_metadata = (
+            json.dumps(jsonable_encoder(event.execution_metadata)) if event.execution_metadata else None
+        )
         db.session.query(WorkflowNodeExecution).filter(WorkflowNodeExecution.id == workflow_node_execution.id).update(
             {
                 WorkflowNodeExecution.status: WorkflowNodeExecutionStatus.FAILED.value,
                 WorkflowNodeExecution.error: event.error,
                 WorkflowNodeExecution.inputs: json.dumps(inputs) if inputs else None,
-                WorkflowNodeExecution.process_data: json.dumps(process_data) if event.process_data else None,
+                WorkflowNodeExecution.process_data: json.dumps(event.process_data) if event.process_data else None,
                 WorkflowNodeExecution.outputs: json.dumps(outputs) if outputs else None,
                 WorkflowNodeExecution.finished_at: finished_at,
                 WorkflowNodeExecution.elapsed_time: elapsed_time,
+                WorkflowNodeExecution.execution_metadata: execution_metadata,
             }
         )
 
@@ -342,6 +355,7 @@ class WorkflowCycleManage:
         workflow_node_execution.outputs = json.dumps(outputs) if outputs else None
         workflow_node_execution.finished_at = finished_at
         workflow_node_execution.elapsed_time = elapsed_time
+        workflow_node_execution.execution_metadata = execution_metadata
 
         self._wip_workflow_node_executions.pop(workflow_node_execution.node_execution_id)
 
@@ -448,6 +462,7 @@ class WorkflowCycleManage:
                 parent_parallel_id=event.parent_parallel_id,
                 parent_parallel_start_node_id=event.parent_parallel_start_node_id,
                 iteration_id=event.in_iteration_id,
+                parallel_run_id=event.parallel_mode_run_id,
             ),
         )
 
@@ -464,7 +479,7 @@ class WorkflowCycleManage:
 
     def _workflow_node_finish_to_stream_response(
         self,
-        event: QueueNodeSucceededEvent | QueueNodeFailedEvent,
+        event: QueueNodeSucceededEvent | QueueNodeFailedEvent | QueueNodeInIterationFailedEvent,
         task_id: str,
         workflow_node_execution: WorkflowNodeExecution,
     ) -> Optional[NodeFinishStreamResponse]:
@@ -608,6 +623,7 @@ class WorkflowCycleManage:
                 extras={},
                 parallel_id=event.parallel_id,
                 parallel_start_node_id=event.parallel_start_node_id,
+                parallel_mode_run_id=event.parallel_mode_run_id,
             ),
         )
 
@@ -633,7 +649,9 @@ class WorkflowCycleManage:
                 created_at=int(time.time()),
                 extras={},
                 inputs=event.inputs or {},
-                status=WorkflowNodeExecutionStatus.SUCCEEDED,
+                status=WorkflowNodeExecutionStatus.SUCCEEDED
+                if event.error is None
+                else WorkflowNodeExecutionStatus.FAILED,
                 error=None,
                 elapsed_time=(datetime.now(timezone.utc).replace(tzinfo=None) - event.start_at).total_seconds(),
                 total_tokens=event.metadata.get("total_tokens", 0) if event.metadata else 0,

api/core/file/file_manager.py

@@ -76,8 +76,16 @@ def to_prompt_message_content(f: File, /):
 
 
 def download(f: File, /):
-    upload_file = file_repository.get_upload_file(session=db.session(), file=f)
-    return _download_file_content(upload_file.key)
+    if f.transfer_method == FileTransferMethod.TOOL_FILE:
+        tool_file = file_repository.get_tool_file(session=db.session(), file=f)
+        return _download_file_content(tool_file.file_key)
+    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
+        upload_file = file_repository.get_upload_file(session=db.session(), file=f)
+        return _download_file_content(upload_file.key)
+    # remote file
+    response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
+    response.raise_for_status()
+    return response.content
 
 
 def _download_file_content(path: str, /):

api/core/helper/ssrf_proxy.py

@@ -12,6 +12,10 @@ SSRF_PROXY_ALL_URL = os.getenv("SSRF_PROXY_ALL_URL", "")
 SSRF_PROXY_HTTP_URL = os.getenv("SSRF_PROXY_HTTP_URL", "")
 SSRF_PROXY_HTTPS_URL = os.getenv("SSRF_PROXY_HTTPS_URL", "")
 SSRF_DEFAULT_MAX_RETRIES = int(os.getenv("SSRF_DEFAULT_MAX_RETRIES", "3"))
+SSRF_DEFAULT_TIME_OUT = float(os.getenv("SSRF_DEFAULT_TIME_OUT", "5"))
+SSRF_DEFAULT_CONNECT_TIME_OUT = float(os.getenv("SSRF_DEFAULT_CONNECT_TIME_OUT", "5"))
+SSRF_DEFAULT_READ_TIME_OUT = float(os.getenv("SSRF_DEFAULT_READ_TIME_OUT", "5"))
+SSRF_DEFAULT_WRITE_TIME_OUT = float(os.getenv("SSRF_DEFAULT_WRITE_TIME_OUT", "5"))
 
 proxy_mounts = (
     {
@@ -32,6 +36,14 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
         if "follow_redirects" not in kwargs:
             kwargs["follow_redirects"] = allow_redirects
 
+    if "timeout" not in kwargs:
+        kwargs["timeout"] = httpx.Timeout(
+            SSRF_DEFAULT_TIME_OUT,
+            connect=SSRF_DEFAULT_CONNECT_TIME_OUT,
+            read=SSRF_DEFAULT_READ_TIME_OUT,
+            write=SSRF_DEFAULT_WRITE_TIME_OUT,
+        )
+
     retries = 0
     while retries <= max_retries:
         try:

api/core/indexing_runner.py

@@ -17,6 +17,7 @@ from core.errors.error import ProviderTokenNotInitError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_manager import ModelInstance, ModelManager
 from core.model_runtime.entities.model_entities import ModelType
+from core.rag.cleaner.clean_processor import CleanProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.docstore.dataset_docstore import DatasetDocumentStore
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -597,26 +598,9 @@ class IndexingRunner:
             rules = DatasetProcessRule.AUTOMATIC_RULES
         else:
             rules = json.loads(processing_rule.rules) if processing_rule.rules else {}
+        document_text = CleanProcessor.clean(text, {"rules": rules})
 
-        if "pre_processing_rules" in rules:
-            pre_processing_rules = rules["pre_processing_rules"]
-            for pre_processing_rule in pre_processing_rules:
-                if pre_processing_rule["id"] == "remove_extra_spaces" and pre_processing_rule["enabled"] is True:
-                    # Remove extra spaces
-                    pattern = r"\n{3,}"
-                    text = re.sub(pattern, "\n\n", text)
-                    pattern = r"[\t\f\r\x20\u00a0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]{2,}"
-                    text = re.sub(pattern, " ", text)
-                elif pre_processing_rule["id"] == "remove_urls_emails" and pre_processing_rule["enabled"] is True:
-                    # Remove email
-                    pattern = r"([a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+)"
-                    text = re.sub(pattern, "", text)
-
-                    # Remove URL
-                    pattern = r"https?://[^\s]+"
-                    text = re.sub(pattern, "", text)
-
-        return text
+        return document_text
 
     @staticmethod
     def format_split_text(text):

api/core/model_runtime/entities/llm_entities.py

@@ -105,6 +105,7 @@ class LLMResult(BaseModel):
     Model class for llm result.
     """
 
+    id: Optional[str] = None
     model: str
     prompt_messages: list[PromptMessage]
     message: AssistantPromptMessage