fix: enable_marketplace always true.

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

.github/workflows/api-tests.yml

@@ -4,7 +4,6 @@ on:
   pull_request:
     branches:
       - main
-      - plugins/beta
     paths:
       - api/**
       - docker/**
@@ -27,6 +26,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python ${{ matrix.python-version }}
         uses: ./.github/actions/setup-poetry

.github/workflows/build-push.yml

@@ -5,8 +5,7 @@ on:
     branches:
       - "main"
       - "deploy/dev"
-      - "plugins/beta"
-      - "dev/plugin-deploy"
+      - "1.0.0-fix"
   release:
     types: [published]
 
@@ -81,10 +80,12 @@ jobs:
           cache-to: type=gha,mode=max,scope=${{ matrix.service_name }}
 
       - name: Export digest
+        env:
+          DIGEST: ${{ steps.build.outputs.digest }}
         run: |
           mkdir -p /tmp/digests
-          digest="${{ steps.build.outputs.digest }}"
-          touch "/tmp/digests/${digest#sha256:}"
+          sanitized_digest=${DIGEST#sha256:}
+          touch "/tmp/digests/${sanitized_digest}"
 
       - name: Upload digest
         uses: actions/upload-artifact@v4
@@ -134,23 +135,15 @@ jobs:
 
       - name: Create manifest list and push
         working-directory: /tmp/digests
+        env:
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
         run: |
           docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
-            $(printf '${{ env[matrix.image_name_env] }}@sha256:%s ' *)
+            $(printf "$IMAGE_NAME@sha256:%s " *)
 
       - name: Inspect image
-        run: |
-          docker buildx imagetools inspect ${{ env[matrix.image_name_env] }}:${{ steps.meta.outputs.version }}
-
-      - name: print context var
-        uses: actions/checkout@v4
-
-      - name: deploy pod in plugin env
-        if: github.ref == 'refs/heads/dev/plugin-deploy'
         env:
-          IMAGEHASH: ${{ github.sha }}
-          APICMD: "${{ secrets.PLUGIN_CD_API_CURL }}"
-          WEBCMD: "${{ secrets.PLUGIN_CD_WEB_CURL }}"
+          IMAGE_NAME: ${{ env[matrix.image_name_env] }}
+          IMAGE_VERSION: ${{ steps.meta.outputs.version }}
         run: |
-          bash -c "${APICMD/yourNewVersion/$IMAGEHASH}"
-          bash -c "${WEBCMD/yourNewVersion/$IMAGEHASH}"
+          docker buildx imagetools inspect "$IMAGE_NAME:$IMAGE_VERSION"

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

@@ -20,6 +20,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Setup Poetry and Python
         uses: ./.github/actions/setup-poetry

.github/workflows/deploy-plugin-dev.yml

@@ -1,23 +0,0 @@
-name: Deploy Plugin Dev
-
-on:
-  workflow_run:
-    workflows: ["Build and Push API & Web"]
-    branches:
-      - "dev/plugin-deploy"
-    types:
-      - completed
-
-jobs:
-  deploy:
-    runs-on: ubuntu-latest
-    if: |
-      github.event.workflow_run.conclusion == 'success'
-    steps:
-      - name: Deploy to server
-        uses: appleboy/ssh-action@v0.1.8
-        with:
-          host: ${{ secrets.SSH_HOST }}
-          username: ${{ secrets.SSH_USER }}
-          key: ${{ secrets.SSH_PRIVATE_KEY }}
-          script: "echo 123"

.github/workflows/docker-build.yml

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

.github/workflows/expose_service_ports.sh

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

.github/workflows/style.yml

@@ -4,7 +4,6 @@ on:
   pull_request:
     branches:
       - main
-      - plugins/beta
 
 concurrency:
   group: style-${{ github.head_ref || github.run_id }}
@@ -18,6 +17,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -60,6 +62,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -87,7 +92,7 @@ jobs:
 
       - name: Web style check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn run lint
+        run: pnpm run lint
 
   docker-compose-template:
     name: Docker Compose Template
@@ -96,6 +101,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -124,6 +132,9 @@ jobs:
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Check changed files
         id: changed-files
@@ -141,7 +152,7 @@ jobs:
         if: steps.changed-files.outputs.any_changed == 'true'
         env:
           BASH_SEVERITY: warning
-          DEFAULT_BRANCH: plugins/beta
+          DEFAULT_BRANCH: main
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           IGNORE_GENERATED_FILES: true
           IGNORE_GITIGNORED_FILES: true

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

@@ -26,6 +26,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: false
 
       - name: Use Node.js ${{ matrix.node-version }}
         uses: actions/setup-node@v4
@@ -35,7 +38,7 @@ jobs:
           cache-dependency-path: 'pnpm-lock.yaml'
 
       - name: Install Dependencies
-        run: pnpm install
+        run: pnpm install --frozen-lockfile
 
       - name: Test
         run: pnpm test

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

@@ -16,6 +16,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           fetch-depth: 2 # last 2 commits
+          persist-credentials: false
 
       - name: Check for file changes in i18n/en-US
         id: check_files

.github/workflows/vdb-tests.yml

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

.github/workflows/web-tests.yml

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

.gitignore

@@ -163,6 +163,7 @@ docker/volumes/db/data/*
 docker/volumes/redis/data/*
 docker/volumes/weaviate/*
 docker/volumes/qdrant/*
+docker/tidb/volumes/*
 docker/volumes/etcd/*
 docker/volumes/minio/*
 docker/volumes/milvus/*

CONTRIBUTING.md

@@ -73,7 +73,7 @@ Dify requires the following dependencies to build, make sure they're installed o
 * [Docker](https://www.docker.com/)
 * [Docker Compose](https://docs.docker.com/compose/install/)
 * [Node.js v18.x (LTS)](http://nodejs.org)
-* [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
+* [pnpm](https://pnpm.io/)
 * [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. Installations

CONTRIBUTING_CN.md

@@ -70,7 +70,7 @@ Dify 依赖以下工具和库：
 - [Docker](https://www.docker.com/)
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
-- [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. 安装

CONTRIBUTING_JA.md

@@ -73,7 +73,7 @@ Dify を構築するには次の依存関係が必要です。それらがシス
 - [Docker](https://www.docker.com/)
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
-- [npm](https://www.npmjs.com/) version 8.x.x or [Yarn](https://yarnpkg.com/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) version 3.11.x or 3.12.x
 
 ### 4. インストール

CONTRIBUTING_VI.md

@@ -72,7 +72,7 @@ Dify yêu cầu các phụ thuộc sau để build, hãy đảm bảo chúng đ
 - [Docker](https://www.docker.com/)
 - [Docker Compose](https://docs.docker.com/compose/install/)
 - [Node.js v18.x (LTS)](http://nodejs.org)
-- [npm](https://www.npmjs.com/) phiên bản 8.x.x hoặc [Yarn](https://yarnpkg.com/)
+- [pnpm](https://pnpm.io/)
 - [Python](https://www.python.org/) phiên bản 3.11.x hoặc 3.12.x
 
 ### 4. Cài đặt

LICENSE

@@ -1,12 +1,12 @@
 # Open Source License
 
-Dify is licensed under the Apache License 2.0, with the following additional conditions:
+Dify is licensed under a modified version of the Apache License 2.0, with the following additional conditions:
 
 1. Dify may be utilized commercially, including as a backend service for other applications or as an application development platform for enterprises. Should the conditions below be met, a commercial license must be obtained from the producer:
 
-a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment. 
+a. Multi-tenant service: Unless explicitly authorized by Dify in writing, you may not use the Dify source code to operate a multi-tenant environment.
     - Tenant Definition: Within the context of Dify, one tenant corresponds to one workspace. The workspace provides a separated area for each tenant's data and configurations.
-    
+
 b. LOGO and copyright information: In the process of using Dify's frontend, you may not remove or modify the LOGO or copyright information in the Dify console or applications. This restriction is inapplicable to uses of Dify that do not involve its frontend.
     - Frontend Definition: For the purposes of this license, the "frontend" of Dify includes all components located in the `web/` directory when running Dify from the raw source code, or the "web" image when running Dify with Docker.
 
@@ -21,19 +21,4 @@ Apart from the specific conditions mentioned above, all other rights and restric
 
 The interactive design of this product is protected by appearance patent.
 
-© 2024 LangGenius, Inc.
-
-
-----------
-
-Licensed under the Apache License, Version 2.0 (the "License");
-you may not use this file except in compliance with the License.
-You may obtain a copy of the License at
-
-    http://www.apache.org/licenses/LICENSE-2.0
-
-Unless required by applicable law or agreed to in writing, software
-distributed under the License is distributed on an "AS IS" BASIS,
-WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-See the License for the specific language governing permissions and
-limitations under the License.
+© 2025 LangGenius, Inc.

README.md

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

README_AR.md

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

README_CN.md

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

README_ES.md

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

README_FR.md

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

README_JA.md

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

README_KL.md

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

README_KR.md

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

README_PT.md

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

README_SI.md

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

README_TR.md

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

README_VI.md

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

api/Dockerfile

@@ -48,16 +48,20 @@ ENV TZ=UTC
 
 WORKDIR /app/api
 
-RUN apt-get update \
-    && apt-get install -y --no-install-recommends curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
-    # if you located in China, you can use aliyun mirror to speed up
-    # && echo "deb http://mirrors.aliyun.com/debian testing main" > /etc/apt/sources.list \
-    && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
-    && apt-get update \
-    # For Security
-    # && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.19+dfsg-1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
-    # install a chinese font to support the use of tools like matplotlib
-    && apt-get install -y fonts-noto-cjk \
+RUN \
+    apt-get update \
+    # Install dependencies
+    && apt-get install -y --no-install-recommends \
+        # basic environment
+        curl nodejs libgmp-dev libmpfr-dev libmpc-dev \
+        # For Security
+        expat libldap-2.5-0 perl libsqlite3-0 zlib1g \
+        # install a chinese font to support the use of tools like matplotlib
+        fonts-noto-cjk \
+        # install a package to improve the accuracy of guessing mime type and file extension
+        media-types \
+        # install libmagic to support the use of python-magic guess MIMETYPE
+        libmagic1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 
@@ -80,7 +84,6 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh
 
-
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}
 

api/README.md

@@ -37,7 +37,13 @@
 
 4. Create environment.
 
-   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. You can execute `poetry shell` to activate the environment.
+   Dify API service uses [Poetry](https://python-poetry.org/docs/) to manage dependencies. First, you need to add the poetry shell plugin, if you don't have it already, in order to run in a virtual environment. [Note: Poetry shell is no longer a native command so you need to install the poetry plugin beforehand]
+
+   ```bash
+   poetry self add poetry-plugin-shell
+   ```
+   
+   Then, You can execute `poetry shell` to activate the environment.
 
 5. Install dependencies
 

api/app_factory.py

@@ -2,6 +2,7 @@ import logging
 import time
 
 from configs import dify_config
+from contexts.wrapper import RecyclableContextVar
 from dify_app import DifyApp
 
 
@@ -16,6 +17,12 @@ def create_flask_app_with_configs() -> DifyApp:
     dify_app = DifyApp(__name__)
     dify_app.config.from_mapping(dify_config.model_dump())
 
+    # add before request hook
+    @dify_app.before_request
+    def before_request():
+        # add an unique identifier to each request
+        RecyclableContextVar.increment_thread_recycles()
+
     return dify_app
 
 

api/commands.py

@@ -707,12 +707,13 @@ def extract_unique_plugins(output_file: str, input_file: str):
 @click.option(
     "--output_file", prompt=True, help="The file to store the installed plugins.", default="installed_plugins.jsonl"
 )
-def install_plugins(input_file: str, output_file: str):
+@click.option("--workers", prompt=True, help="The number of workers to install plugins.", default=100)
+def install_plugins(input_file: str, output_file: str, workers: int):
     """
     Install plugins.
     """
     click.echo(click.style("Starting install plugins.", fg="white"))
 
-    PluginMigration.install_plugins(input_file, output_file)
+    PluginMigration.install_plugins(input_file, output_file, workers)
 
     click.echo(click.style("Install plugins completed.", fg="green"))

api/configs/feature/__init__.py

@@ -373,8 +373,8 @@ class HttpConfig(BaseSettings):
     )
 
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
-        description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
-        " to respect X-* headers to redirect clients",
+        description="Enable handling of X-Forwarded-For, X-Forwarded-Proto, and X-Forwarded-Port headers"
+        " when the app is behind a single trusted reverse proxy.",
         default=False,
     )
 
@@ -556,6 +556,11 @@ class AuthConfig(BaseSettings):
         default=86400,
     )
 
+    FORGOT_PASSWORD_LOCKOUT_DURATION: PositiveInt = Field(
+        description="Time (in seconds) a user must wait before retrying password reset after exceeding the rate limit.",
+        default=86400,
+    )
+
 
 class ModerationConfig(BaseSettings):
     """

api/configs/feature/hosted_service/__init__.py

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

api/configs/middleware/__init__.py

@@ -1,3 +1,4 @@
+import os
 from typing import Any, Literal, Optional
 from urllib.parse import quote_plus
 
@@ -166,6 +167,11 @@ class DatabaseConfig(BaseSettings):
         default=False,
     )
 
+    RETRIEVAL_SERVICE_EXECUTORS: NonNegativeInt = Field(
+        description="Number of processes for the retrieval service, default to CPU cores.",
+        default=os.cpu_count(),
+    )
+
     @computed_field
     def SQLALCHEMY_ENGINE_OPTIONS(self) -> dict[str, Any]:
         return {

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="1.0.0-beta.1",
+        default="1.0.0",
     )
 
     COMMIT_SHA: str = Field(

api/constants/__init__.py

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

api/contexts/__init__.py

@@ -2,6 +2,8 @@ from contextvars import ContextVar
 from threading import Lock
 from typing import TYPE_CHECKING
 
+from contexts.wrapper import RecyclableContextVar
+
 if TYPE_CHECKING:
     from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
     from core.tools.plugin_tool.provider import PluginToolProviderController
@@ -12,8 +14,17 @@ tenant_id: ContextVar[str] = ContextVar("tenant_id")
 
 workflow_variable_pool: ContextVar["VariablePool"] = ContextVar("workflow_variable_pool")
 
-plugin_tool_providers: ContextVar[dict[str, "PluginToolProviderController"]] = ContextVar("plugin_tool_providers")
-plugin_tool_providers_lock: ContextVar[Lock] = ContextVar("plugin_tool_providers_lock")
+"""
+To avoid race-conditions caused by gunicorn thread recycling, using RecyclableContextVar to replace with
+"""
+plugin_tool_providers: RecyclableContextVar[dict[str, "PluginToolProviderController"]] = RecyclableContextVar(
+    ContextVar("plugin_tool_providers")
+)
+plugin_tool_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(ContextVar("plugin_tool_providers_lock"))
 
-plugin_model_providers: ContextVar[list["PluginModelProviderEntity"] | None] = ContextVar("plugin_model_providers")
-plugin_model_providers_lock: ContextVar[Lock] = ContextVar("plugin_model_providers_lock")
+plugin_model_providers: RecyclableContextVar[list["PluginModelProviderEntity"] | None] = RecyclableContextVar(
+    ContextVar("plugin_model_providers")
+)
+plugin_model_providers_lock: RecyclableContextVar[Lock] = RecyclableContextVar(
+    ContextVar("plugin_model_providers_lock")
+)

api/contexts/wrapper.py

@@ -0,0 +1,65 @@
+from contextvars import ContextVar
+from typing import Generic, TypeVar
+
+T = TypeVar("T")
+
+
+class HiddenValue:
+    pass
+
+
+_default = HiddenValue()
+
+
+class RecyclableContextVar(Generic[T]):
+    """
+    RecyclableContextVar is a wrapper around ContextVar
+    It's safe to use in gunicorn with thread recycling, but features like `reset` are not available for now
+
+    NOTE: you need to call `increment_thread_recycles` before requests
+    """
+
+    _thread_recycles: ContextVar[int] = ContextVar("thread_recycles")
+
+    @classmethod
+    def increment_thread_recycles(cls):
+        try:
+            recycles = cls._thread_recycles.get()
+            cls._thread_recycles.set(recycles + 1)
+        except LookupError:
+            cls._thread_recycles.set(0)
+
+    def __init__(self, context_var: ContextVar[T]):
+        self._context_var = context_var
+        self._updates = ContextVar[int](context_var.name + "_updates", default=0)
+
+    def get(self, default: T | HiddenValue = _default) -> T:
+        thread_recycles = self._thread_recycles.get(0)
+        self_updates = self._updates.get()
+        if thread_recycles > self_updates:
+            self._updates.set(thread_recycles)
+
+        # check if thread is recycled and should be updated
+        if thread_recycles < self_updates:
+            return self._context_var.get()
+        else:
+            # thread_recycles >= self_updates, means current context is invalid
+            if isinstance(default, HiddenValue) or default is _default:
+                raise LookupError
+            else:
+                return default
+
+    def set(self, value: T):
+        # it leads to a situation that self.updates is less than cls.thread_recycles if `set` was never called before
+        # increase it manually
+        thread_recycles = self._thread_recycles.get(0)
+        self_updates = self._updates.get()
+        if thread_recycles > self_updates:
+            self._updates.set(thread_recycles)
+
+        if self._updates.get() == self._thread_recycles.get(0):
+            # after increment,
+            self._updates.set(self._updates.get() + 1)
+
+        # set the context
+        self._context_var.set(value)

api/controllers/common/helpers.py

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

api/controllers/console/auth/error.py

@@ -59,3 +59,9 @@ class EmailCodeAccountDeletionRateLimitExceededError(BaseHTTPException):
     error_code = "email_code_account_deletion_rate_limit_exceeded"
     description = "Too many account deletion emails have been sent. Please try again in 5 minutes."
     code = 429
+
+
+class EmailPasswordResetLimitError(BaseHTTPException):
+    error_code = "email_password_reset_limit"
+    description = "Too many failed password reset attempts. Please try again in 24 hours."
+    code = 429

api/controllers/console/auth/forgot_password.py

@@ -8,7 +8,13 @@ from sqlalchemy.orm import Session
 
 from constants.languages import languages
 from controllers.console import api
-from controllers.console.auth.error import EmailCodeError, InvalidEmailError, InvalidTokenError, PasswordMismatchError
+from controllers.console.auth.error import (
+    EmailCodeError,
+    EmailPasswordResetLimitError,
+    InvalidEmailError,
+    InvalidTokenError,
+    PasswordMismatchError,
+)
 from controllers.console.error import AccountInFreezeError, AccountNotFound, EmailSendIpLimitError
 from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
@@ -65,6 +71,10 @@ class ForgotPasswordCheckApi(Resource):
 
         user_email = args["email"]
 
+        is_forgot_password_error_rate_limit = AccountService.is_forgot_password_error_rate_limit(args["email"])
+        if is_forgot_password_error_rate_limit:
+            raise EmailPasswordResetLimitError()
+
         token_data = AccountService.get_reset_password_data(args["token"])
         if token_data is None:
             raise InvalidTokenError()
@@ -73,8 +83,10 @@ class ForgotPasswordCheckApi(Resource):
             raise InvalidEmailError()
 
         if args["code"] != token_data.get("code"):
+            AccountService.add_forgot_password_error_rate_limit(args["email"])
             raise EmailCodeError()
 
+        AccountService.reset_forgot_password_error_rate_limit(args["email"])
         return {"is_valid": True, "email": token_data.get("email")}
 
 

api/controllers/console/datasets/datasets.py

@@ -14,6 +14,7 @@ from controllers.console.wraps import account_initialization_required, enterpris
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType
+from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 from core.rag.datasource.vdb.vector_type import VectorType
 from core.rag.extractor.entity.extract_setting import ExtractSetting
@@ -72,7 +73,9 @@ class DatasetListApi(Resource):
 
         data = marshal(datasets, dataset_detail_fields)
         for item in data:
+            # convert embedding_model_provider to plugin standard format
             if item["indexing_technique"] == "high_quality":
+                item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                 item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                 if item_model in model_names:
                     item["embedding_available"] = True
@@ -620,7 +623,6 @@ class DatasetRetrievalSettingApi(Resource):
         match vector_type:
             case (
                 VectorType.RELYT
-                | VectorType.PGVECTOR
                 | VectorType.TIDB_VECTOR
                 | VectorType.CHROMA
                 | VectorType.TENCENT

api/controllers/console/explore/message.py

@@ -50,7 +50,7 @@ class MessageListApi(InstalledAppResource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/controllers/files/image_preview.py

@@ -1,3 +1,5 @@
+from urllib.parse import quote
+
 from flask import Response, request
 from flask_restful import Resource, reqparse  # type: ignore
 from werkzeug.exceptions import NotFound
@@ -71,7 +73,8 @@ class FilePreviewApi(Resource):
         if upload_file.size > 0:
             response.headers["Content-Length"] = str(upload_file.size)
         if args["as_attachment"]:
-            response.headers["Content-Disposition"] = f"attachment; filename={upload_file.name}"
+            encoded_filename = quote(upload_file.name)
+            response.headers["Content-Disposition"] = f"attachment; filename*=UTF-8''{encoded_filename}"
 
         return response
 

api/controllers/inner_api/workspace/workspace.py

@@ -1,3 +1,5 @@
+import json
+
 from flask_restful import Resource, reqparse  # type: ignore
 
 from controllers.console.wraps import setup_required
@@ -29,4 +31,34 @@ class EnterpriseWorkspace(Resource):
         return {"message": "enterprise workspace created."}
 
 
+class EnterpriseWorkspaceNoOwnerEmail(Resource):
+    @setup_required
+    @enterprise_inner_api_only
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("name", type=str, required=True, location="json")
+        args = parser.parse_args()
+
+        tenant = TenantService.create_tenant(args["name"], is_from_dashboard=True)
+
+        tenant_was_created.send(tenant)
+
+        resp = {
+            "id": tenant.id,
+            "name": tenant.name,
+            "encrypt_public_key": tenant.encrypt_public_key,
+            "plan": tenant.plan,
+            "status": tenant.status,
+            "custom_config": json.loads(tenant.custom_config) if tenant.custom_config else {},
+            "created_at": tenant.created_at.isoformat() + "Z" if tenant.created_at else None,
+            "updated_at": tenant.updated_at.isoformat() + "Z" if tenant.updated_at else None,
+        }
+
+        return {
+            "message": "enterprise workspace created.",
+            "tenant": resp,
+        }
+
+
 api.add_resource(EnterpriseWorkspace, "/enterprise/workspace")
+api.add_resource(EnterpriseWorkspaceNoOwnerEmail, "/enterprise/workspace/ownerless")

api/controllers/service_api/app/message.py

@@ -10,6 +10,7 @@ from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import message_file_fields
+from fields.message_fields import feedback_fields, retriever_resource_fields
 from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
 from models.model import App, AppMode, EndUser
@@ -18,26 +19,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(Resource):
-    feedback_fields = {"rating": fields.String}
-    retriever_resource_fields = {
-        "id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "dataset_id": fields.String,
-        "dataset_name": fields.String,
-        "document_id": fields.String,
-        "document_name": fields.String,
-        "data_source_type": fields.String,
-        "segment_id": fields.String,
-        "score": fields.Float,
-        "hit_count": fields.Integer,
-        "word_count": fields.Integer,
-        "segment_position": fields.Integer,
-        "index_node_hash": fields.String,
-        "content": fields.String,
-        "created_at": TimestampField,
-    }
-
     agent_thought_fields = {
         "id": fields.String,
         "chain_id": fields.String,
@@ -89,7 +70,7 @@ class MessageListApi(Resource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/controllers/service_api/dataset/document.py

@@ -18,6 +18,7 @@ from controllers.service_api.app.error import (
 from controllers.service_api.dataset.error import (
     ArchivedDocumentImmutableError,
     DocumentIndexingError,
+    InvalidMetadataError,
 )
 from controllers.service_api.wraps import DatasetApiResource, cloud_edition_billing_resource_check
 from core.errors.error import ProviderTokenNotInitError
@@ -50,6 +51,9 @@ class DocumentAddByTextApi(DatasetApiResource):
             "indexing_technique", type=str, choices=Dataset.INDEXING_TECHNIQUE_LIST, nullable=False, location="json"
         )
         parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
+
         args = parser.parse_args()
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -61,6 +65,28 @@ class DocumentAddByTextApi(DatasetApiResource):
         if not dataset.indexing_technique and not args["indexing_technique"]:
             raise ValueError("indexing_technique is required.")
 
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
         text = args.get("text")
         name = args.get("name")
         if text is None or name is None:
@@ -107,6 +133,8 @@ class DocumentUpdateByTextApi(DatasetApiResource):
             "doc_language", type=str, default="English", required=False, nullable=False, location="json"
         )
         parser.add_argument("retrieval_model", type=dict, required=False, nullable=False, location="json")
+        parser.add_argument("doc_type", type=str, required=False, nullable=True, location="json")
+        parser.add_argument("doc_metadata", type=dict, required=False, nullable=True, location="json")
         args = parser.parse_args()
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -115,6 +143,32 @@ class DocumentUpdateByTextApi(DatasetApiResource):
         if not dataset:
             raise ValueError("Dataset is not exist.")
 
+        # indexing_technique is already set in dataset since this is an update
+        args["indexing_technique"] = dataset.indexing_technique
+
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
         if args["text"]:
             text = args.get("text")
             name = args.get("name")
@@ -161,6 +215,30 @@ class DocumentAddByFileApi(DatasetApiResource):
             args["doc_form"] = "text_model"
         if "doc_language" not in args:
             args["doc_language"] = "English"
+
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
         # get dataset info
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -228,6 +306,29 @@ class DocumentUpdateByFileApi(DatasetApiResource):
         if "doc_language" not in args:
             args["doc_language"] = "English"
 
+        # Validate metadata if provided
+        if args.get("doc_type") or args.get("doc_metadata"):
+            if not args.get("doc_type") or not args.get("doc_metadata"):
+                raise InvalidMetadataError("Both doc_type and doc_metadata must be provided when adding metadata")
+
+            if args["doc_type"] not in DocumentService.DOCUMENT_METADATA_SCHEMA:
+                raise InvalidMetadataError(
+                    "Invalid doc_type. Must be one of: " + ", ".join(DocumentService.DOCUMENT_METADATA_SCHEMA.keys())
+                )
+
+            if not isinstance(args["doc_metadata"], dict):
+                raise InvalidMetadataError("doc_metadata must be a dictionary")
+
+            # Validate metadata schema based on doc_type
+            if args["doc_type"] != "others":
+                metadata_schema = DocumentService.DOCUMENT_METADATA_SCHEMA[args["doc_type"]]
+                for key, value in args["doc_metadata"].items():
+                    if key in metadata_schema and not isinstance(value, metadata_schema[key]):
+                        raise InvalidMetadataError(f"Invalid type for metadata field {key}")
+
+            # set to MetaDataConfig
+            args["metadata"] = {"doc_type": args["doc_type"], "doc_metadata": args["doc_metadata"]}
+
         # get dataset info
         dataset_id = str(dataset_id)
         tenant_id = str(tenant_id)
@@ -235,6 +336,10 @@ class DocumentUpdateByFileApi(DatasetApiResource):
 
         if not dataset:
             raise ValueError("Dataset is not exist.")
+
+        # indexing_technique is already set in dataset since this is an update
+        args["indexing_technique"] = dataset.indexing_technique
+
         if "file" in request.files:
             # save file info
             file = request.files["file"]

api/controllers/service_api/wraps.py

@@ -154,7 +154,7 @@ def validate_dataset_token(view=None):
             )  # TODO: only owner information is required, so only one is returned.
             if tenant_account_join:
                 tenant, ta = tenant_account_join
-                account = Account.query.filter_by(id=ta.account_id).first()
+                account = db.session.query(Account).filter(Account.id == ta.account_id).first()
                 # Login admin
                 if account:
                     account.current_tenant = tenant

api/controllers/web/message.py

@@ -21,7 +21,7 @@ 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
 from fields.conversation_fields import message_file_fields
-from fields.message_fields import agent_thought_fields
+from fields.message_fields import agent_thought_fields, feedback_fields, retriever_resource_fields
 from fields.raws import FilesContainedField
 from libs import helper
 from libs.helper import TimestampField, uuid_value
@@ -34,27 +34,6 @@ from services.message_service import MessageService
 
 
 class MessageListApi(WebApiResource):
-    feedback_fields = {"rating": fields.String}
-
-    retriever_resource_fields = {
-        "id": fields.String,
-        "message_id": fields.String,
-        "position": fields.Integer,
-        "dataset_id": fields.String,
-        "dataset_name": fields.String,
-        "document_id": fields.String,
-        "document_name": fields.String,
-        "data_source_type": fields.String,
-        "segment_id": fields.String,
-        "score": fields.Float,
-        "hit_count": fields.Integer,
-        "word_count": fields.Integer,
-        "segment_position": fields.Integer,
-        "index_node_hash": fields.String,
-        "content": fields.String,
-        "created_at": TimestampField,
-    }
-
     message_fields = {
         "id": fields.String,
         "conversation_id": fields.String,
@@ -91,7 +70,7 @@ class MessageListApi(WebApiResource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/core/agent/base_agent_runner.py

@@ -329,6 +329,7 @@ class BaseAgentRunner(AppRunner):
         )
         if not updated_agent_thought:
             raise ValueError("agent thought not found")
+        agent_thought = updated_agent_thought
 
         if thought:
             agent_thought.thought = thought

api/core/agent/entities.py

@@ -1,7 +1,7 @@
 from enum import StrEnum
 from typing import Any, Optional, Union
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolProviderType
 
@@ -14,7 +14,7 @@ class AgentToolEntity(BaseModel):
     provider_type: ToolProviderType
     provider_id: str
     tool_name: str
-    tool_parameters: dict[str, Any] = {}
+    tool_parameters: dict[str, Any] = Field(default_factory=dict)
     plugin_unique_identifier: str | None = None
 
 

api/core/app/app_config/easy_ui_based_app/model_config/manager.py

@@ -2,9 +2,9 @@ from collections.abc import Mapping
 from typing import Any
 
 from core.app.app_config.entities import ModelConfigEntity
-from core.entities import DEFAULT_PLUGIN_ID
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.plugin.entities.plugin import ModelProviderID
 from core.provider_manager import ProviderManager
 
 
@@ -61,9 +61,7 @@ class ModelConfigManager:
             raise ValueError(f"model.provider is required and must be in {str(model_provider_names)}")
 
         if "/" not in config["model"]["provider"]:
-            config["model"]["provider"] = (
-                f"{DEFAULT_PLUGIN_ID}/{config['model']['provider']}/{config['model']['provider']}"
-            )
+            config["model"]["provider"] = str(ModelProviderID(config["model"]["provider"]))
 
         if config["model"]["provider"] not in model_provider_names:
             raise ValueError(f"model.provider is required and must be in {str(model_provider_names)}")

api/core/app/app_config/entities.py

@@ -17,8 +17,8 @@ class ModelConfigEntity(BaseModel):
     provider: str
     model: str
     mode: Optional[str] = None
-    parameters: dict[str, Any] = {}
-    stop: list[str] = []
+    parameters: dict[str, Any] = Field(default_factory=dict)
+    stop: list[str] = Field(default_factory=list)
 
 
 class AdvancedChatMessageEntity(BaseModel):
@@ -132,7 +132,7 @@ class ExternalDataVariableEntity(BaseModel):
 
     variable: str
     type: str
-    config: dict[str, Any] = {}
+    config: dict[str, Any] = Field(default_factory=dict)
 
 
 class DatasetRetrieveConfigEntity(BaseModel):
@@ -188,7 +188,7 @@ class SensitiveWordAvoidanceEntity(BaseModel):
     """
 
     type: str
-    config: dict[str, Any] = {}
+    config: dict[str, Any] = Field(default_factory=dict)
 
 
 class TextToSpeechEntity(BaseModel):

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

@@ -140,9 +140,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             app_config=app_config,
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

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

@@ -384,6 +384,7 @@ class AdvancedChatAppGenerateTaskPipeline:
                         task_id=self._application_generate_entity.task_id,
                         workflow_node_execution=workflow_node_execution,
                     )
+                    session.commit()
 
                 if node_finish_resp:
                     yield node_finish_resp

api/core/app/apps/agent_chat/app_generator.py

@@ -149,9 +149,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

api/core/app/apps/agent_chat/app_runner.py

@@ -8,16 +8,16 @@ from core.agent.fc_agent_runner import FunctionCallAgentRunner
 from core.app.apps.agent_chat.app_config_manager import AgentChatAppConfig
 from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
 from core.app.apps.base_app_runner import AppRunner
-from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity, ModelConfigWithCredentialsEntity
+from core.app.entities.app_invoke_entities import AgentChatAppGenerateEntity
 from core.app.entities.queue_entities import QueueAnnotationReplyEvent
 from core.memory.token_buffer_memory import TokenBufferMemory
 from core.model_manager import ModelInstance
-from core.model_runtime.entities.llm_entities import LLMMode, LLMUsage
+from core.model_runtime.entities.llm_entities import LLMMode
 from core.model_runtime.entities.model_entities import ModelFeature, ModelPropertyKey
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.moderation.base import ModerationError
 from extensions.ext_database import db
-from models.model import App, Conversation, Message, MessageAgentThought
+from models.model import App, Conversation, Message
 
 logger = logging.getLogger(__name__)
 
@@ -191,7 +191,8 @@ class AgentChatAppRunner(AppRunner):
         # change function call strategy based on LLM model
         llm_model = cast(LargeLanguageModel, model_instance.model_type_instance)
         model_schema = llm_model.get_model_schema(model_instance.model, model_instance.credentials)
-        assert model_schema is not None
+        if not model_schema:
+            raise ValueError("Model schema not found")
 
         if {ModelFeature.MULTI_TOOL_CALL, ModelFeature.TOOL_CALL}.intersection(model_schema.features or []):
             agent_entity.strategy = AgentEntity.Strategy.FUNCTION_CALLING
@@ -247,29 +248,3 @@ class AgentChatAppRunner(AppRunner):
             stream=application_generate_entity.stream,
             agent=True,
         )
-
-    def _get_usage_of_all_agent_thoughts(
-        self, model_config: ModelConfigWithCredentialsEntity, message: Message
-    ) -> LLMUsage:
-        """
-        Get usage of all agent thoughts
-        :param model_config: model config
-        :param message: message
-        :return:
-        """
-        agent_thoughts = (
-            db.session.query(MessageAgentThought).filter(MessageAgentThought.message_id == message.id).all()
-        )
-
-        all_message_tokens = 0
-        all_answer_tokens = 0
-        for agent_thought in agent_thoughts:
-            all_message_tokens += agent_thought.message_tokens
-            all_answer_tokens += agent_thought.answer_tokens
-
-        model_type_instance = model_config.provider_model_bundle.model_type_instance
-        model_type_instance = cast(LargeLanguageModel, model_type_instance)
-
-        return model_type_instance._calc_response_usage(
-            model_config.model, model_config.credentials, all_message_tokens, all_answer_tokens
-        )

api/core/app/apps/chat/app_generator.py

@@ -141,9 +141,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             model_conf=ModelConfigConverter.convert(app_config),
             file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
-            inputs=conversation.inputs
-            if conversation
-            else self._prepare_user_inputs(
+            inputs=self._prepare_user_inputs(
                 user_inputs=inputs, variables=app_config.variables, tenant_id=app_model.tenant_id
             ),
             query=query,

api/core/app/apps/message_based_app_generator.py

@@ -42,7 +42,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             ChatAppGenerateEntity,
             CompletionAppGenerateEntity,
             AgentChatAppGenerateEntity,
-            AgentChatAppGenerateEntity,
         ],
         queue_manager: AppQueueManager,
         conversation: Conversation,

api/core/app/apps/workflow_app_runner.py

@@ -387,7 +387,6 @@ class WorkflowBasedAppRunner(AppRunner):
                     status=event.status,
                     data=event.data,
                     metadata=event.metadata,
-                    node_id=event.node_id,
                 )
             )
         elif isinstance(event, ParallelBranchRunStartedEvent):

api/core/app/entities/app_invoke_entities.py

@@ -63,9 +63,9 @@ class ModelConfigWithCredentialsEntity(BaseModel):
     model_schema: AIModelEntity
     mode: str
     provider_model_bundle: ProviderModelBundle
-    credentials: dict[str, Any] = {}
-    parameters: dict[str, Any] = {}
-    stop: list[str] = []
+    credentials: dict[str, Any] = Field(default_factory=dict)
+    parameters: dict[str, Any] = Field(default_factory=dict)
+    stop: list[str] = Field(default_factory=list)
 
     # pydantic configs
     model_config = ConfigDict(protected_namespaces=())
@@ -94,7 +94,7 @@ class AppGenerateEntity(BaseModel):
     call_depth: int = 0
 
     # extra parameters, like: auto_generate_conversation_name
-    extras: dict[str, Any] = {}
+    extras: dict[str, Any] = Field(default_factory=dict)
 
     # tracing instance
     trace_manager: Optional[TraceQueueManager] = None

api/core/app/entities/queue_entities.py

@@ -331,7 +331,6 @@ class QueueAgentLogEvent(AppQueueEvent):
     status: str
     data: Mapping[str, Any]
     metadata: Optional[Mapping[str, Any]] = None
-    node_id: str
 
 
 class QueueNodeRetryEvent(QueueNodeStartedEvent):

api/core/app/entities/task_entities.py

@@ -719,7 +719,6 @@ class AgentLogStreamResponse(StreamResponse):
         status: str
         data: Mapping[str, Any]
         metadata: Optional[Mapping[str, Any]] = None
-        node_id: str
 
     event: StreamEvent = StreamEvent.AGENT_LOG
     data: Data

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -844,7 +844,7 @@ class WorkflowCycleManage:
         if node_execution_id not in self._workflow_node_executions:
             raise ValueError(f"Workflow node execution not found: {node_execution_id}")
         cached_workflow_node_execution = self._workflow_node_executions[node_execution_id]
-        return cached_workflow_node_execution
+        return session.merge(cached_workflow_node_execution)
 
     def _handle_agent_log(self, task_id: str, event: QueueAgentLogEvent) -> AgentLogStreamResponse:
         """
@@ -864,6 +864,5 @@ class WorkflowCycleManage:
                 status=event.status,
                 data=event.data,
                 metadata=event.metadata,
-                node_id=event.node_id,
             ),
         )

api/core/entities/provider_configuration.py

@@ -6,10 +6,10 @@ from collections.abc import Iterator, Sequence
 from json import JSONDecodeError
 from typing import Optional
 
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
+from sqlalchemy import or_
 
 from constants import HIDDEN_VALUE
-from core.entities import DEFAULT_PLUGIN_ID
 from core.entities.model_entities import ModelStatus, ModelWithProviderEntity, SimpleModelProviderEntity
 from core.entities.provider_entities import (
     CustomConfiguration,
@@ -28,6 +28,7 @@ from core.model_runtime.entities.provider_entities import (
 )
 from core.model_runtime.model_providers.__base.ai_model import AIModel
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.plugin.entities.plugin import ModelProviderID
 from extensions.ext_database import db
 from models.provider import (
     LoadBalancingModelConfig,
@@ -190,8 +191,11 @@ class ProviderConfiguration(BaseModel):
             db.session.query(Provider)
             .filter(
                 Provider.tenant_id == self.tenant_id,
-                Provider.provider_name == self.provider.provider,
                 Provider.provider_type == ProviderType.CUSTOM.value,
+                or_(
+                    Provider.provider_name == ModelProviderID(self.provider.provider).plugin_name,
+                    Provider.provider_name == self.provider.provider,
+                ),
             )
             .first()
         )
@@ -279,7 +283,10 @@ class ProviderConfiguration(BaseModel):
             db.session.query(Provider)
             .filter(
                 Provider.tenant_id == self.tenant_id,
-                Provider.provider_name == self.provider.provider,
+                or_(
+                    Provider.provider_name == ModelProviderID(self.provider.provider).plugin_name,
+                    Provider.provider_name == self.provider.provider,
+                ),
                 Provider.provider_type == ProviderType.CUSTOM.value,
             )
             .first()
@@ -996,7 +1003,7 @@ class ProviderConfigurations(BaseModel):
     """
 
     tenant_id: str
-    configurations: dict[str, ProviderConfiguration] = {}
+    configurations: dict[str, ProviderConfiguration] = Field(default_factory=dict)
 
     def __init__(self, tenant_id: str):
         super().__init__(tenant_id=tenant_id)
@@ -1052,7 +1059,7 @@ class ProviderConfigurations(BaseModel):
 
     def __getitem__(self, key):
         if "/" not in key:
-            key = f"{DEFAULT_PLUGIN_ID}/{key}/{key}"
+            key = str(ModelProviderID(key))
 
         return self.configurations[key]
 
@@ -1067,7 +1074,7 @@ class ProviderConfigurations(BaseModel):
 
     def get(self, key, default=None) -> ProviderConfiguration | None:
         if "/" not in key:
-            key = f"{DEFAULT_PLUGIN_ID}/{key}/{key}"
+            key = str(ModelProviderID(key))
 
         return self.configurations.get(key, default)  # type: ignore
 

api/core/helper/ssrf_proxy.py

@@ -11,15 +11,6 @@ from configs import dify_config
 
 SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES
 
-proxy_mounts = (
-    {
-        "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
-        "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
-    }
-    if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL
-    else None
-)
-
 BACKOFF_FACTOR = 0.5
 STATUS_FORCELIST = [429, 500, 502, 503, 504]
 
@@ -50,7 +41,11 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
             if dify_config.SSRF_PROXY_ALL_URL:
                 with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
                     response = client.request(method=method, url=url, **kwargs)
-            elif proxy_mounts:
+            elif dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL:
+                proxy_mounts = {
+                    "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
+                    "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
+                }
                 with httpx.Client(mounts=proxy_mounts) as client:
                     response = client.request(method=method, url=url, **kwargs)
             else:
@@ -70,8 +65,7 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
         retries += 1
         if retries <= max_retries:
             time.sleep(BACKOFF_FACTOR * (2 ** (retries - 1)))
-    raise MaxRetriesExceededError(
-        f"Reached maximum retries ({max_retries}) for URL {url}")
+    raise MaxRetriesExceededError(f"Reached maximum retries ({max_retries}) for URL {url}")
 
 
 def get(url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):

api/core/hosting_configuration.py

@@ -41,9 +41,13 @@ class HostedModerationConfig(BaseModel):
 
 
 class HostingConfiguration:
-    provider_map: dict[str, HostingProvider] = {}
+    provider_map: dict[str, HostingProvider]
     moderation_config: Optional[HostedModerationConfig] = None
 
+    def __init__(self) -> None:
+        self.provider_map = {}
+        self.moderation_config = None
+
     def init_app(self, app: Flask) -> None:
         if dify_config.EDITION != "CLOUD":
             return

api/core/model_runtime/entities/__init__.py

@@ -1,4 +1,4 @@
-from .llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
+from .llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
 from .message_entities import (
     AssistantPromptMessage,
     AudioPromptMessageContent,
@@ -23,6 +23,7 @@ __all__ = [
     "AudioPromptMessageContent",
     "DocumentPromptMessageContent",
     "ImagePromptMessageContent",
+    "LLMMode",
     "LLMResult",
     "LLMResultChunk",
     "LLMResultChunkDelta",

api/core/model_runtime/entities/llm_entities.py

@@ -1,5 +1,5 @@
 from decimal import Decimal
-from enum import Enum
+from enum import StrEnum
 from typing import Optional
 
 from pydantic import BaseModel
@@ -8,7 +8,7 @@ from core.model_runtime.entities.message_entities import AssistantPromptMessage,
 from core.model_runtime.entities.model_entities import ModelUsage, PriceInfo
 
 
-class LLMMode(Enum):
+class LLMMode(StrEnum):
     """
     Enum class for large language model mode.
     """

api/core/model_runtime/model_providers/__base/ai_model.py

@@ -3,8 +3,11 @@ from typing import Optional
 
 from pydantic import BaseModel, ConfigDict, Field
 
+from core.model_runtime.entities.common_entities import I18nObject
+from core.model_runtime.entities.defaults import PARAMETER_RULE_TEMPLATE
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,
+    DefaultParameterName,
     ModelType,
     PriceConfig,
     PriceInfo,
@@ -18,6 +21,7 @@ from core.model_runtime.errors.invoke import (
     InvokeRateLimitError,
     InvokeServerUnavailableError,
 )
+from core.model_runtime.model_providers.__base.tokenizers.gpt2_tokenzier import GPT2Tokenizer
 from core.plugin.entities.plugin_daemon import PluginDaemonInnerError, PluginModelProviderEntity
 from core.plugin.manager.model import PluginModelManager
 
@@ -144,3 +148,102 @@ class AIModel(BaseModel):
             model=model,
             credentials=credentials or {},
         )
+
+    def get_customizable_model_schema_from_credentials(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+        """
+        Get customizable model schema from credentials
+
+        :param model: model name
+        :param credentials: model credentials
+        :return: model schema
+        """
+        return self._get_customizable_model_schema(model, credentials)
+
+    def _get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+        """
+        Get customizable model schema and fill in the template
+        """
+        schema = self.get_customizable_model_schema(model, credentials)
+
+        if not schema:
+            return None
+
+        # fill in the template
+        new_parameter_rules = []
+        for parameter_rule in schema.parameter_rules:
+            if parameter_rule.use_template:
+                try:
+                    default_parameter_name = DefaultParameterName.value_of(parameter_rule.use_template)
+                    default_parameter_rule = self._get_default_parameter_rule_variable_map(default_parameter_name)
+                    if not parameter_rule.max and "max" in default_parameter_rule:
+                        parameter_rule.max = default_parameter_rule["max"]
+                    if not parameter_rule.min and "min" in default_parameter_rule:
+                        parameter_rule.min = default_parameter_rule["min"]
+                    if not parameter_rule.default and "default" in default_parameter_rule:
+                        parameter_rule.default = default_parameter_rule["default"]
+                    if not parameter_rule.precision and "precision" in default_parameter_rule:
+                        parameter_rule.precision = default_parameter_rule["precision"]
+                    if not parameter_rule.required and "required" in default_parameter_rule:
+                        parameter_rule.required = default_parameter_rule["required"]
+                    if not parameter_rule.help and "help" in default_parameter_rule:
+                        parameter_rule.help = I18nObject(
+                            en_US=default_parameter_rule["help"]["en_US"],
+                        )
+                    if (
+                        parameter_rule.help
+                        and not parameter_rule.help.en_US
+                        and ("help" in default_parameter_rule and "en_US" in default_parameter_rule["help"])
+                    ):
+                        parameter_rule.help.en_US = default_parameter_rule["help"]["en_US"]
+                    if (
+                        parameter_rule.help
+                        and not parameter_rule.help.zh_Hans
+                        and ("help" in default_parameter_rule and "zh_Hans" in default_parameter_rule["help"])
+                    ):
+                        parameter_rule.help.zh_Hans = default_parameter_rule["help"].get(
+                            "zh_Hans", default_parameter_rule["help"]["en_US"]
+                        )
+                except ValueError:
+                    pass
+
+            new_parameter_rules.append(parameter_rule)
+
+        schema.parameter_rules = new_parameter_rules
+
+        return schema
+
+    def get_customizable_model_schema(self, model: str, credentials: dict) -> Optional[AIModelEntity]:
+        """
+        Get customizable model schema
+
+        :param model: model name
+        :param credentials: model credentials
+        :return: model schema
+        """
+        return None
+
+    def _get_default_parameter_rule_variable_map(self, name: DefaultParameterName) -> dict:
+        """
+        Get default parameter rule for given name
+
+        :param name: parameter name
+        :return: parameter rule
+        """
+        default_parameter_rule = PARAMETER_RULE_TEMPLATE.get(name)
+
+        if not default_parameter_rule:
+            raise Exception(f"Invalid model parameter rule name {name}")
+
+        return default_parameter_rule
+
+    def _get_num_tokens_by_gpt2(self, text: str) -> int:
+        """
+        Get number of tokens for given prompt messages by gpt2
+        Some provider models do not provide an interface for obtaining the number of tokens.
+        Here, the gpt2 tokenizer is used to calculate the number of tokens.
+        This method can be executed offline, and the gpt2 tokenizer has been cached in the project.
+
+        :param text: plain text of prompt. You need to convert the original message to plain text
+        :return: number of tokens
+        """
+        return GPT2Tokenizer.get_num_tokens(text)

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -228,7 +228,7 @@ class LargeLanguageModel(AIModel):
         :return: result generator
         """
         callbacks = callbacks or []
-        prompt_message = AssistantPromptMessage(content="")
+        assistant_message = AssistantPromptMessage(content="")
         usage = None
         system_fingerprint = None
         real_model = model
@@ -250,7 +250,7 @@ class LargeLanguageModel(AIModel):
                     callbacks=callbacks,
                 )
 
-                prompt_message.content += chunk.delta.message.content
+                assistant_message.content += chunk.delta.message.content
                 real_model = chunk.model
                 if chunk.delta.usage:
                     usage = chunk.delta.usage
@@ -265,7 +265,7 @@ class LargeLanguageModel(AIModel):
             result=LLMResult(
                 model=real_model,
                 prompt_messages=prompt_messages,
-                message=prompt_message,
+                message=assistant_message,
                 usage=usage or LLMUsage.empty_usage(),
                 system_fingerprint=system_fingerprint,
             ),

api/core/model_runtime/model_providers/_position.yaml

@@ -1,4 +1,5 @@
 - openai
+- deepseek
 - anthropic
 - azure_openai
 - google
@@ -32,7 +33,6 @@
 - localai
 - volcengine_maas
 - openai_api_compatible
-- deepseek
 - hunyuan
 - siliconflow
 - perfxcloud

api/core/model_runtime/model_providers/model_provider_factory.py

@@ -7,7 +7,6 @@ from typing import Optional
 from pydantic import BaseModel
 
 import contexts
-from core.entities import DEFAULT_PLUGIN_ID
 from core.helper.position_helper import get_provider_position_map, sort_to_dict_by_position_map
 from core.model_runtime.entities.model_entities import AIModelEntity, ModelType
 from core.model_runtime.entities.provider_entities import ProviderConfig, ProviderEntity, SimpleProviderEntity
@@ -20,6 +19,7 @@ from core.model_runtime.model_providers.__base.text_embedding_model import TextE
 from core.model_runtime.model_providers.__base.tts_model import TTSModel
 from core.model_runtime.schema_validators.model_credential_schema_validator import ModelCredentialSchemaValidator
 from core.model_runtime.schema_validators.provider_credential_schema_validator import ProviderCredentialSchemaValidator
+from core.plugin.entities.plugin import ModelProviderID
 from core.plugin.entities.plugin_daemon import PluginModelProviderEntity
 from core.plugin.manager.asset import PluginAssetManager
 from core.plugin.manager.model import PluginModelManager
@@ -33,9 +33,11 @@ class ModelProviderExtension(BaseModel):
 
 
 class ModelProviderFactory:
-    provider_position_map: dict[str, int] = {}
+    provider_position_map: dict[str, int]
 
     def __init__(self, tenant_id: str) -> None:
+        self.provider_position_map = {}
+
         self.tenant_id = tenant_id
         self.plugin_model_manager = PluginModelManager()
 
@@ -112,6 +114,9 @@ class ModelProviderFactory:
         :param provider: provider name
         :return: provider schema
         """
+        if "/" not in provider:
+            provider = str(ModelProviderID(provider))
+
         # fetch plugin model providers
         plugin_model_provider_entities = self.get_plugin_model_providers()
 
@@ -356,11 +361,5 @@ class ModelProviderFactory:
         :param provider: provider name
         :return: plugin id and provider name
         """
-        plugin_id = DEFAULT_PLUGIN_ID
-        provider_name = provider
-        if "/" in provider:
-            # get the plugin_id before provider
-            plugin_id = "/".join(provider.split("/")[:-1])
-            provider_name = provider.split("/")[-1]
-
-        return plugin_id, provider_name
+        provider_id = ModelProviderID(provider)
+        return provider_id.plugin_id, provider_id.provider_name

api/core/model_runtime/model_providers/vertex_ai/llm/_position.yaml

@@ -0,0 +1,22 @@
+- claude-3-haiku@20240307
+- claude-3-opus@20240229
+- claude-3-sonnet@20240229
+- claude-3-5-sonnet-v2@20241022
+- claude-3-5-sonnet@20240620
+- gemini-1.0-pro-vision-001
+- gemini-1.0-pro-002
+- gemini-1.5-flash-001
+- gemini-1.5-flash-002
+- gemini-1.5-pro-001
+- gemini-1.5-pro-002
+- gemini-2.0-flash-001
+- gemini-2.0-flash-exp
+- gemini-2.0-flash-lite-preview-02-05
+- gemini-2.0-flash-thinking-exp-01-21
+- gemini-2.0-flash-thinking-exp-1219
+- gemini-2.0-pro-exp-02-05
+- gemini-exp-1114
+- gemini-exp-1121
+- gemini-exp-1206
+- gemini-flash-experimental
+- gemini-pro-experimental

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-001.yaml

@@ -0,0 +1,41 @@
+model: gemini-2.0-flash-001
+label:
+  en_US: Gemini 2.0 Flash 001
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-lite-preview-02-05.yaml

@@ -0,0 +1,41 @@
+model: gemini-2.0-flash-lite-preview-02-05
+label:
+  en_US: Gemini 2.0 Flash Lite Preview 0205
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 1048576
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-01-21.yaml

@@ -0,0 +1,39 @@
+model: gemini-2.0-flash-thinking-exp-01-21
+label:
+  en_US: Gemini 2.0 Flash Thinking Exp 0121
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-1219.yaml

@@ -0,0 +1,39 @@
+model: gemini-2.0-flash-thinking-exp-1219
+label:
+  en_US: Gemini 2.0 Flash Thinking Exp 1219
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-pro-exp-02-05.yaml

@@ -0,0 +1,37 @@
+model: gemini-2.0-pro-exp-02-05
+label:
+  en_US: Gemini 2.0 Pro Exp 0205
+model_type: llm
+features:
+  - agent-thought
+  - document
+model_properties:
+  mode: chat
+  context_size: 2000000
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      en_US: Top k
+    type: int
+    help:
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: presence_penalty
+    use_template: presence_penalty
+  - name: frequency_penalty
+    use_template: frequency_penalty
+  - name: max_output_tokens
+    use_template: max_tokens
+    required: true
+    default: 8192
+    min: 1
+    max: 8192
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1114.yaml

@@ -0,0 +1,41 @@
+model: gemini-exp-1114
+label:
+  en_US: Gemini exp 1114
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml

@@ -0,0 +1,41 @@
+model: gemini-exp-1121
+label:
+  en_US: Gemini exp 1121
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 32767
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1206.yaml

@@ -0,0 +1,41 @@
+model: gemini-exp-1206
+label:
+  en_US: Gemini exp 1206
+model_type: llm
+features:
+  - agent-thought
+  - vision
+  - tool-call
+  - stream-tool-call
+  - document
+  - video
+  - audio
+model_properties:
+  mode: chat
+  context_size: 2097152
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+  - name: top_p
+    use_template: top_p
+  - name: top_k
+    label:
+      zh_Hans: 取样数量
+      en_US: Top k
+    type: int
+    help:
+      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
+      en_US: Only sample from the top K options for each subsequent token.
+    required: false
+  - name: max_output_tokens
+    use_template: max_tokens
+    default: 8192
+    min: 1
+    max: 8192
+  - name: json_schema
+    use_template: json_schema
+pricing:
+  input: '0.00'
+  output: '0.00'
+  unit: '0.000001'
+  currency: USD

api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml

@@ -0,0 +1,66 @@
+model: glm-4-air-0111
+label:
+  en_US: glm-4-air-0111
+model_type: llm
+features:
+  - multi-tool-call
+  - agent-thought
+  - stream-tool-call
+model_properties:
+  mode: chat
+  context_size: 131072
+parameter_rules:
+  - name: temperature
+    use_template: temperature
+    default: 0.95
+    min: 0.0
+    max: 1.0
+    help:
+      zh_Hans: 采样温度，控制输出的随机性，必须为正数取值范围是：(0.0,1.0]，不能等于 0,默认值为 0.95 值越大，会使输出更随机，更具创造性；值越小，输出会更加稳定或确定建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Sampling temperature, controls the randomness of the output, must be a positive number. The value range is (0.0,1.0], which cannot be equal to 0. The default value is 0.95. The larger the value, the more random and creative the output will be; the smaller the value, The output will be more stable or certain. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: top_p
+    use_template: top_p
+    default: 0.7
+    help:
+      zh_Hans: 用温度取样的另一种方法，称为核取样取值范围是：(0.0, 1.0) 开区间，不能等于 0 或 1，默认值为 0.7 模型考虑具有 top_p 概率质量tokens的结果例如：0.1 意味着模型解码器只考虑从前 10% 的概率的候选集中取 tokens 建议您根据应用场景调整 top_p 或 temperature 参数，但不要同时调整两个参数。
+      en_US: Another method of temperature sampling is called kernel sampling. The value range is (0.0, 1.0) open interval, which cannot be equal to 0 or 1. The default value is 0.7. The model considers the results with top_p probability mass tokens. For example 0.1 means The model decoder only considers tokens from the candidate set with the top 10% probability. It is recommended that you adjust the top_p or temperature parameters according to the application scenario, but do not adjust both parameters at the same time.
+  - name: do_sample
+    label:
+      zh_Hans: 采样策略
+      en_US: Sampling strategy
+    type: boolean
+    help:
+      zh_Hans: do_sample 为 true 时启用采样策略，do_sample 为 false 时采样策略 temperature、top_p 将不生效。默认值为 true。
+      en_US: When `do_sample` is set to true, the sampling strategy is enabled. When `do_sample` is set to false, the sampling strategies such as `temperature` and `top_p` will not take effect. The default value is true.
+    default: true
+  - name: max_tokens
+    use_template: max_tokens
+    default: 1024
+    min: 1
+    max: 4095
+  - name: web_search
+    type: boolean
+    label:
+      zh_Hans: 联网搜索
+      en_US: Web Search
+    default: false
+    help:
+      zh_Hans: 模型内置了互联网搜索服务，该参数控制模型在生成文本时是否参考使用互联网搜索结果。启用互联网搜索，模型会将搜索结果作为文本生成过程中的参考信息，但模型会基于其内部逻辑“自行判断”是否使用互联网搜索结果。
+      en_US: The model has a built-in Internet search service. This parameter controls whether the model refers to Internet search results when generating text. When Internet search is enabled, the model will use the search results as reference information in the text generation process, but the model will "judge" whether to use Internet search results based on its internal logic.
+  - name: response_format
+    label:
+      zh_Hans: 回复格式
+      en_US: Response Format
+    type: string
+    help:
+      zh_Hans: 指定模型必须输出的格式
+      en_US: specifying the format that the model must output
+    required: false
+    options:
+      - text
+      - json_object
+pricing:
+  input: '0.0005'
+  output: '0.0005'
+  unit: '0.001'
+  currency: RMB

api/core/plugin/entities/plugin.py

@@ -159,7 +159,7 @@ class GenericProviderID:
             if re.match(r"^[a-z0-9_-]+$", value):
                 value = f"langgenius/{value}/{value}"
             else:
-                raise ValueError("Invalid plugin id")
+                raise ValueError(f"Invalid plugin id {value}")
 
         self.organization, self.plugin_name, self.provider_name = value.split("/")
         self.is_hardcoded = is_hardcoded
@@ -169,6 +169,21 @@ class GenericProviderID:
         return f"{self.organization}/{self.plugin_name}"
 
 
+class ModelProviderID(GenericProviderID):
+    def __init__(self, value: str, is_hardcoded: bool = False) -> None:
+        super().__init__(value, is_hardcoded)
+        if self.organization == "langgenius" and self.provider_name == "google":
+            self.plugin_name = "gemini"
+
+
+class ToolProviderID(GenericProviderID):
+    def __init__(self, value: str, is_hardcoded: bool = False) -> None:
+        super().__init__(value, is_hardcoded)
+        if self.organization == "langgenius":
+            if self.provider_name in ["jina", "siliconflow", "stepfun", "gitee_ai"]:
+                self.plugin_name = f"{self.provider_name}_tool"
+
+
 class PluginDependency(BaseModel):
     class Type(enum.StrEnum):
         Github = PluginInstallationSource.Github.value
@@ -197,3 +212,9 @@ class PluginDependency(BaseModel):
 
     type: Type
     value: Github | Marketplace | Package
+    current_identifier: Optional[str] = None
+
+
+class MissingPluginDependency(BaseModel):
+    plugin_unique_identifier: str
+    current_identifier: Optional[str] = None

api/core/plugin/manager/plugin.py

@@ -3,6 +3,7 @@ from collections.abc import Sequence
 from core.plugin.entities.bundle import PluginBundleDependency
 from core.plugin.entities.plugin import (
     GenericProviderID,
+    MissingPluginDependency,
     PluginDeclaration,
     PluginEntity,
     PluginInstallation,
@@ -175,14 +176,16 @@ class PluginInstallationManager(BasePluginManager):
             headers={"Content-Type": "application/json"},
         )
 
-    def fetch_missing_dependencies(self, tenant_id: str, plugin_unique_identifiers: list[str]) -> list[str]:
+    def fetch_missing_dependencies(
+        self, tenant_id: str, plugin_unique_identifiers: list[str]
+    ) -> list[MissingPluginDependency]:
         """
         Fetch missing dependencies
         """
         return self._request_with_plugin_daemon_response(
             "POST",
             f"plugin/{tenant_id}/management/installation/missing",
-            list[str],
+            list[MissingPluginDependency],
             data={"plugin_unique_identifiers": plugin_unique_identifiers},
             headers={"Content-Type": "application/json"},
         )

api/core/plugin/manager/tool.py

@@ -3,7 +3,7 @@ from typing import Any, Optional
 
 from pydantic import BaseModel
 
-from core.plugin.entities.plugin import GenericProviderID
+from core.plugin.entities.plugin import GenericProviderID, ToolProviderID
 from core.plugin.entities.plugin_daemon import PluginBasicBooleanResponse, PluginToolProviderEntity
 from core.plugin.manager.base import BasePluginManager
 from core.tools.entities.tool_entities import ToolInvokeMessage, ToolParameter
@@ -45,7 +45,7 @@ class PluginToolManager(BasePluginManager):
         """
         Fetch tool provider for the given tenant and plugin.
         """
-        tool_provider_id = GenericProviderID(provider)
+        tool_provider_id = ToolProviderID(provider)
 
         def transformer(json_response: dict[str, Any]) -> dict:
             data = json_response.get("data")

api/core/provider_manager.py

@@ -30,6 +30,7 @@ from core.model_runtime.entities.provider_entities import (
     ProviderEntity,
 )
 from core.model_runtime.model_providers.model_provider_factory import ModelProviderFactory
+from core.plugin.entities.plugin import ModelProviderID
 from extensions import ext_hosting_provider
 from extensions.ext_database import db
 from extensions.ext_redis import redis_client
@@ -99,8 +100,23 @@ class ProviderManager:
             tenant_id, provider_name_to_provider_records_dict
         )
 
+        # append providers with langgenius/openai/openai
+        provider_name_list = list(provider_name_to_provider_records_dict.keys())
+        for provider_name in provider_name_list:
+            provider_id = ModelProviderID(provider_name)
+            if str(provider_id) not in provider_name_list:
+                provider_name_to_provider_records_dict[str(provider_id)] = provider_name_to_provider_records_dict[
+                    provider_name
+                ]
+
         # Get all provider model records of the workspace
         provider_name_to_provider_model_records_dict = self._get_all_provider_models(tenant_id)
+        for provider_name in list(provider_name_to_provider_model_records_dict.keys()):
+            provider_id = ModelProviderID(provider_name)
+            if str(provider_id) not in provider_name_to_provider_model_records_dict:
+                provider_name_to_provider_model_records_dict[str(provider_id)] = (
+                    provider_name_to_provider_model_records_dict[provider_name]
+                )
 
         # Get all provider entities
         model_provider_factory = ModelProviderFactory(tenant_id)
@@ -191,7 +207,7 @@ class ProviderManager:
                 model_settings=model_settings,
             )
 
-            provider_configurations[provider_name] = provider_configuration
+            provider_configurations[str(ModelProviderID(provider_name))] = provider_configuration
 
         # Return the encapsulated object
         return provider_configurations
@@ -359,7 +375,8 @@ class ProviderManager:
 
         provider_name_to_provider_records_dict = defaultdict(list)
         for provider in providers:
-            provider_name_to_provider_records_dict[provider.provider_name].append(provider)
+            # TODO: Use provider name with prefix after the data migration
+            provider_name_to_provider_records_dict[str(ModelProviderID(provider.provider_name))].append(provider)
 
         return provider_name_to_provider_records_dict
 
@@ -453,11 +470,9 @@ class ProviderManager:
 
         provider_name_to_provider_load_balancing_model_configs_dict = defaultdict(list)
         for provider_load_balancing_config in provider_load_balancing_configs:
-            (
-                provider_name_to_provider_load_balancing_model_configs_dict[
-                    provider_load_balancing_config.provider_name
-                ].append(provider_load_balancing_config)
-            )
+            provider_name_to_provider_load_balancing_model_configs_dict[
+                provider_load_balancing_config.provider_name
+            ].append(provider_load_balancing_config)
 
         return provider_name_to_provider_load_balancing_model_configs_dict
 
@@ -500,7 +515,8 @@ class ProviderManager:
                             # FIXME ignore the type errork, onyl TrialHostingQuota has limit need to change the logic
                             provider_record = Provider(
                                 tenant_id=tenant_id,
-                                provider_name=provider_name,
+                                # TODO: Use provider name with prefix after the data migration.
+                                provider_name=ModelProviderID(provider_name).provider_name,
                                 provider_type=ProviderType.SYSTEM.value,
                                 quota_type=ProviderQuotaType.TRIAL.value,
                                 quota_limit=quota.quota_limit,  # type: ignore
@@ -515,13 +531,12 @@ class ProviderManager:
                                 db.session.query(Provider)
                                 .filter(
                                     Provider.tenant_id == tenant_id,
-                                    Provider.provider_name == provider_name,
+                                    Provider.provider_name == ModelProviderID(provider_name).provider_name,
                                     Provider.provider_type == ProviderType.SYSTEM.value,
                                     Provider.quota_type == ProviderQuotaType.TRIAL.value,
                                 )
                                 .first()
                             )
-
                             if provider_record and not provider_record.is_valid:
                                 provider_record.is_valid = True
                                 db.session.commit()

api/core/rag/datasource/retrieval_service.py

@@ -1,8 +1,12 @@
-import threading
+import concurrent.futures
+import json
+from concurrent.futures import ThreadPoolExecutor
 from typing import Optional
 
 from flask import Flask, current_app
+from sqlalchemy.orm import load_only
 
+from configs import dify_config
 from core.rag.data_post_processor.data_post_processor import DataPostProcessor
 from core.rag.datasource.keyword.keyword_factory import Keyword
 from core.rag.datasource.vdb.vector_factory import Vector
@@ -26,6 +30,7 @@ default_retrieval_model = {
 
 
 class RetrievalService:
+    # Cache precompiled regular expressions to avoid repeated compilation
     @classmethod
     def retrieve(
         cls,
@@ -40,74 +45,62 @@ class RetrievalService:
     ):
         if not query:
             return []
-        dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
-        if not dataset:
-            return []
-
+        dataset = cls._get_dataset(dataset_id)
         if not dataset or dataset.available_document_count == 0 or dataset.available_segment_count == 0:
             return []
+
         all_documents: list[Document] = []
-        threads: list[threading.Thread] = []
         exceptions: list[str] = []
-        # retrieval_model source with keyword
-        if retrieval_method == "keyword_search":
-            keyword_thread = threading.Thread(
-                target=RetrievalService.keyword_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "top_k": top_k,
-                    "all_documents": all_documents,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(keyword_thread)
-            keyword_thread.start()
-        # retrieval_model source with semantic
-        if RetrievalMethod.is_support_semantic_search(retrieval_method):
-            embedding_thread = threading.Thread(
-                target=RetrievalService.embedding_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "top_k": top_k,
-                    "score_threshold": score_threshold,
-                    "reranking_model": reranking_model,
-                    "all_documents": all_documents,
-                    "retrieval_method": retrieval_method,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(embedding_thread)
-            embedding_thread.start()
 
-        # retrieval source with full text
-        if RetrievalMethod.is_support_fulltext_search(retrieval_method):
-            full_text_index_thread = threading.Thread(
-                target=RetrievalService.full_text_index_search,
-                kwargs={
-                    "flask_app": current_app._get_current_object(),  # type: ignore
-                    "dataset_id": dataset_id,
-                    "query": query,
-                    "retrieval_method": retrieval_method,
-                    "score_threshold": score_threshold,
-                    "top_k": top_k,
-                    "reranking_model": reranking_model,
-                    "all_documents": all_documents,
-                    "exceptions": exceptions,
-                },
-            )
-            threads.append(full_text_index_thread)
-            full_text_index_thread.start()
-
-        for thread in threads:
-            thread.join()
+        # Optimize multithreading with thread pools
+        with ThreadPoolExecutor(max_workers=dify_config.RETRIEVAL_SERVICE_EXECUTORS) as executor:  # type: ignore
+            futures = []
+            if retrieval_method == "keyword_search":
+                futures.append(
+                    executor.submit(
+                        cls.keyword_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        all_documents=all_documents,
+                        exceptions=exceptions,
+                    )
+                )
+            if RetrievalMethod.is_support_semantic_search(retrieval_method):
+                futures.append(
+                    executor.submit(
+                        cls.embedding_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        score_threshold=score_threshold,
+                        reranking_model=reranking_model,
+                        all_documents=all_documents,
+                        retrieval_method=retrieval_method,
+                        exceptions=exceptions,
+                    )
+                )
+            if RetrievalMethod.is_support_fulltext_search(retrieval_method):
+                futures.append(
+                    executor.submit(
+                        cls.full_text_index_search,
+                        flask_app=current_app._get_current_object(),  # type: ignore
+                        dataset_id=dataset_id,
+                        query=query,
+                        top_k=top_k,
+                        score_threshold=score_threshold,
+                        reranking_model=reranking_model,
+                        all_documents=all_documents,
+                        retrieval_method=retrieval_method,
+                        exceptions=exceptions,
+                    )
+                )
+            concurrent.futures.wait(futures, timeout=30, return_when=concurrent.futures.ALL_COMPLETED)
 
         if exceptions:
-            exception_message = ";\n".join(exceptions)
-            raise ValueError(exception_message)
+            raise ValueError(";\n".join(exceptions))
 
         if retrieval_method == RetrievalMethod.HYBRID_SEARCH.value:
             data_post_processor = DataPostProcessor(
@@ -132,18 +125,21 @@ class RetrievalService:
         )
         return all_documents
 
+    @classmethod
+    def _get_dataset(cls, dataset_id: str) -> Optional[Dataset]:
+        return db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+
     @classmethod
     def keyword_search(
         cls, flask_app: Flask, dataset_id: str, query: str, top_k: int, all_documents: list, exceptions: list
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
                 keyword = Keyword(dataset=dataset)
-
                 documents = keyword.search(cls.escape_query_for_search(query), top_k=top_k)
                 all_documents.extend(documents)
             except Exception as e:
@@ -164,14 +160,13 @@ class RetrievalService:
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
                 vector = Vector(dataset=dataset)
-
                 documents = vector.search_by_vector(
-                    cls.escape_query_for_search(query),
+                    query,
                     search_type="similarity_score_threshold",
                     top_k=top_k,
                     score_threshold=score_threshold,
@@ -186,7 +181,7 @@ class RetrievalService:
                         and retrieval_method == RetrievalMethod.SEMANTIC_SEARCH.value
                     ):
                         data_post_processor = DataPostProcessor(
-                            str(dataset.tenant_id), RerankMode.RERANKING_MODEL.value, reranking_model, None, False
+                            str(dataset.tenant_id), str(RerankMode.RERANKING_MODEL.value), reranking_model, None, False
                         )
                         all_documents.extend(
                             data_post_processor.invoke(
@@ -216,13 +211,11 @@ class RetrievalService:
     ):
         with flask_app.app_context():
             try:
-                dataset = db.session.query(Dataset).filter(Dataset.id == dataset_id).first()
+                dataset = cls._get_dataset(dataset_id)
                 if not dataset:
                     raise ValueError("dataset not found")
 
-                vector_processor = Vector(
-                    dataset=dataset,
-                )
+                vector_processor = Vector(dataset=dataset)
 
                 documents = vector_processor.search_by_full_text(cls.escape_query_for_search(query), top_k=top_k)
                 if documents:
@@ -233,7 +226,7 @@ class RetrievalService:
                         and retrieval_method == RetrievalMethod.FULL_TEXT_SEARCH.value
                     ):
                         data_post_processor = DataPostProcessor(
-                            str(dataset.tenant_id), RerankMode.RERANKING_MODEL.value, reranking_model, None, False
+                            str(dataset.tenant_id), str(RerankMode.RERANKING_MODEL.value), reranking_model, None, False
                         )
                         all_documents.extend(
                             data_post_processor.invoke(
@@ -250,66 +243,106 @@ class RetrievalService:
 
     @staticmethod
     def escape_query_for_search(query: str) -> str:
-        return query.replace('"', '\\"')
+        return json.dumps(query).strip('"')
+
+    @classmethod
+    def format_retrieval_documents(cls, documents: list[Document]) -> list[RetrievalSegments]:
+        """Format retrieval documents with optimized batch processing"""
+        if not documents:
+            return []
+
+        try:
+            # Collect document IDs
+            document_ids = {doc.metadata.get("document_id") for doc in documents if "document_id" in doc.metadata}
+            if not document_ids:
+                return []
+
+            # Batch query dataset documents
+            dataset_documents = {
+                doc.id: doc
+                for doc in db.session.query(DatasetDocument)
+                .filter(DatasetDocument.id.in_(document_ids))
+                .options(load_only(DatasetDocument.id, DatasetDocument.doc_form, DatasetDocument.dataset_id))
+                .all()
+            }
+
+            records = []
+            include_segment_ids = set()
+            segment_child_map = {}
+
+            # Process documents
+            for document in documents:
+                document_id = document.metadata.get("document_id")
+                if document_id not in dataset_documents:
+                    continue
+
+                dataset_document = dataset_documents[document_id]
 
-    @staticmethod
-    def format_retrieval_documents(documents: list[Document]) -> list[RetrievalSegments]:
-        records = []
-        include_segment_ids = []
-        segment_child_map = {}
-        for document in documents:
-            document_id = document.metadata.get("document_id")
-            dataset_document = db.session.query(DatasetDocument).filter(DatasetDocument.id == document_id).first()
-            if dataset_document:
                 if dataset_document.doc_form == IndexType.PARENT_CHILD_INDEX:
+                    # Handle parent-child documents
                     child_index_node_id = document.metadata.get("doc_id")
-                    result = (
-                        db.session.query(ChildChunk, DocumentSegment)
-                        .join(DocumentSegment, ChildChunk.segment_id == DocumentSegment.id)
+
+                    child_chunk = (
+                        db.session.query(ChildChunk).filter(ChildChunk.index_node_id == child_index_node_id).first()
+                    )
+
+                    if not child_chunk:
+                        continue
+
+                    segment = (
+                        db.session.query(DocumentSegment)
                         .filter(
-                            ChildChunk.index_node_id == child_index_node_id,
                             DocumentSegment.dataset_id == dataset_document.dataset_id,
                             DocumentSegment.enabled == True,
                             DocumentSegment.status == "completed",
+                            DocumentSegment.id == child_chunk.segment_id,
+                        )
+                        .options(
+                            load_only(
+                                DocumentSegment.id,
+                                DocumentSegment.content,
+                                DocumentSegment.answer,
+                            )
                         )
                         .first()
                     )
-                    if result:
-                        child_chunk, segment = result
-                        if not segment:
-                            continue
-                        if segment.id not in include_segment_ids:
-                            include_segment_ids.append(segment.id)
-                            child_chunk_detail = {
-                                "id": child_chunk.id,
-                                "content": child_chunk.content,
-                                "position": child_chunk.position,
-                                "score": document.metadata.get("score", 0.0),
-                            }
-                            map_detail = {
-                                "max_score": document.metadata.get("score", 0.0),
-                                "child_chunks": [child_chunk_detail],
-                            }
-                            segment_child_map[segment.id] = map_detail
-                            record = {
-                                "segment": segment,
-                            }
-                            records.append(record)
-                        else:
-                            child_chunk_detail = {
-                                "id": child_chunk.id,
-                                "content": child_chunk.content,
-                                "position": child_chunk.position,
-                                "score": document.metadata.get("score", 0.0),
-                            }
-                            segment_child_map[segment.id]["child_chunks"].append(child_chunk_detail)
-                            segment_child_map[segment.id]["max_score"] = max(
-                                segment_child_map[segment.id]["max_score"], document.metadata.get("score", 0.0)
-                            )
-                    else:
+
+                    if not segment:
                         continue
+
+                    if segment.id not in include_segment_ids:
+                        include_segment_ids.add(segment.id)
+                        child_chunk_detail = {
+                            "id": child_chunk.id,
+                            "content": child_chunk.content,
+                            "position": child_chunk.position,
+                            "score": document.metadata.get("score", 0.0),
+                        }
+                        map_detail = {
+                            "max_score": document.metadata.get("score", 0.0),
+                            "child_chunks": [child_chunk_detail],
+                        }
+                        segment_child_map[segment.id] = map_detail
+                        record = {
+                            "segment": segment,
+                        }
+                        records.append(record)
+                    else:
+                        child_chunk_detail = {
+                            "id": child_chunk.id,
+                            "content": child_chunk.content,
+                            "position": child_chunk.position,
+                            "score": document.metadata.get("score", 0.0),
+                        }
+                        segment_child_map[segment.id]["child_chunks"].append(child_chunk_detail)
+                        segment_child_map[segment.id]["max_score"] = max(
+                            segment_child_map[segment.id]["max_score"], document.metadata.get("score", 0.0)
+                        )
                 else:
-                    index_node_id = document.metadata["doc_id"]
+                    # Handle normal documents
+                    index_node_id = document.metadata.get("doc_id")
+                    if not index_node_id:
+                        continue
 
                     segment = (
                         db.session.query(DocumentSegment)
@@ -324,16 +357,21 @@ class RetrievalService:
 
                     if not segment:
                         continue
-                    include_segment_ids.append(segment.id)
+
+                    include_segment_ids.add(segment.id)
                     record = {
                         "segment": segment,
-                        "score": document.metadata.get("score", None),
+                        "score": document.metadata.get("score"),  # type: ignore
                     }
-
                     records.append(record)
+
+            # Add child chunks information to records
             for record in records:
                 if record["segment"].id in segment_child_map:
-                    record["child_chunks"] = segment_child_map[record["segment"].id].get("child_chunks", None)
+                    record["child_chunks"] = segment_child_map[record["segment"].id].get("child_chunks")  # type: ignore
                     record["score"] = segment_child_map[record["segment"].id]["max_score"]
 
-        return [RetrievalSegments(**record) for record in records]
+            return [RetrievalSegments(**record) for record in records]
+        except Exception as e:
+            db.session.rollback()
+            raise e

api/core/rag/datasource/vdb/chroma/chroma_vector.py

@@ -111,8 +111,9 @@ class ChromaVector(BaseVector):
         for index in range(len(ids)):
             distance = distances[index]
             metadata = dict(metadatas[index])
-            if distance >= score_threshold:
-                metadata["score"] = distance
+            score = 1 - distance
+            if score > score_threshold:
+                metadata["score"] = score
                 doc = Document(
                     page_content=documents[index],
                     metadata=metadata,

api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py

@@ -9,6 +9,7 @@ from sqlalchemy import text as sql_text
 from sqlalchemy.orm import Session, declarative_base
 
 from configs import dify_config
+from core.rag.datasource.vdb.field import Field
 from core.rag.datasource.vdb.vector_base import BaseVector
 from core.rag.datasource.vdb.vector_factory import AbstractVectorFactory
 from core.rag.datasource.vdb.vector_type import VectorType
@@ -54,14 +55,13 @@ class TiDBVector(BaseVector):
         return Table(
             self._collection_name,
             self._orm_base.metadata,
-            Column("id", String(36), primary_key=True, nullable=False),
+            Column(Field.PRIMARY_KEY.value, String(36), primary_key=True, nullable=False),
             Column(
-                "vector",
+                Field.VECTOR.value,
                 VectorType(dim),
                 nullable=False,
-                comment="" if self._distance_func is None else f"hnsw(distance={self._distance_func})",
             ),
-            Column("text", TEXT, nullable=False),
+            Column(Field.TEXT_KEY.value, TEXT, nullable=False),
             Column("meta", JSON, nullable=False),
             Column("create_time", DateTime, server_default=sqlalchemy.text("CURRENT_TIMESTAMP")),
             Column(
@@ -96,6 +96,7 @@ class TiDBVector(BaseVector):
             collection_exist_cache_key = "vector_indexing_{}".format(self._collection_name)
             if redis_client.get(collection_exist_cache_key):
                 return
+            tidb_dist_func = self._get_distance_func()
             with Session(self._engine) as session:
                 session.begin()
                 create_statement = sql_text(f"""
@@ -104,14 +105,14 @@ class TiDBVector(BaseVector):
                         text TEXT NOT NULL,
                         meta JSON NOT NULL,
                         doc_id VARCHAR(64) AS (JSON_UNQUOTE(JSON_EXTRACT(meta, '$.doc_id'))) STORED,
-                        KEY (doc_id),
-                        vector VECTOR<FLOAT>({dimension}) NOT NULL COMMENT "hnsw(distance={self._distance_func})",
+                        vector VECTOR<FLOAT>({dimension}) NOT NULL,
                         create_time DATETIME DEFAULT CURRENT_TIMESTAMP,
-                        update_time DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP
+                        update_time DATETIME DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
+                        KEY (doc_id),
+                        VECTOR INDEX idx_vector (({tidb_dist_func}(vector))) USING HNSW
                     );
                 """)
                 session.execute(create_statement)
-                # tidb vector not support 'CREATE/ADD INDEX' now
                 session.commit()
             redis_client.set(collection_exist_cache_key, 1, ex=3600)
 
@@ -194,23 +195,30 @@ class TiDBVector(BaseVector):
         )
 
         docs = []
-        if self._distance_func == "l2":
-            tidb_func = "Vec_l2_distance"
-        elif self._distance_func == "cosine":
-            tidb_func = "Vec_Cosine_distance"
-        else:
-            tidb_func = "Vec_Cosine_distance"
+        tidb_dist_func = self._get_distance_func()
 
         with Session(self._engine) as session:
-            select_statement = sql_text(
-                f"""SELECT meta, text, distance FROM (
-                        SELECT meta, text, {tidb_func}(vector, "{query_vector_str}")  as distance
-                        FROM {self._collection_name}
-                        ORDER BY distance
-                        LIMIT {top_k}
-                    ) t WHERE distance < {distance};"""
+            select_statement = sql_text(f"""
+                SELECT meta, text, distance 
+                FROM (
+                  SELECT 
+                    meta,
+                    text,
+                    {tidb_dist_func}(vector, :query_vector_str) AS distance
+                  FROM {self._collection_name}
+                  ORDER BY distance ASC
+                  LIMIT :top_k
+                ) t
+                WHERE distance <= :distance
+                """)
+            res = session.execute(
+                select_statement,
+                params={
+                    "query_vector_str": query_vector_str,
+                    "distance": distance,
+                    "top_k": top_k,
+                },
             )
-            res = session.execute(select_statement)
             results = [(row[0], row[1], row[2]) for row in res]
             for meta, text, distance in results:
                 metadata = json.loads(meta)
@@ -227,6 +235,16 @@ class TiDBVector(BaseVector):
             session.execute(sql_text(f"""DROP TABLE IF EXISTS {self._collection_name};"""))
             session.commit()
 
+    def _get_distance_func(self) -> str:
+        match self._distance_func:
+            case "l2":
+                tidb_dist_func = "VEC_L2_DISTANCE"
+            case "cosine":
+                tidb_dist_func = "VEC_COSINE_DISTANCE"
+            case _:
+                tidb_dist_func = "VEC_COSINE_DISTANCE"
+        return tidb_dist_func
+
 
 class TiDBVectorFactory(AbstractVectorFactory):
     def init_vector(self, dataset: Dataset, attributes: list, embeddings: Embeddings) -> TiDBVector:

api/core/rag/extractor/firecrawl/firecrawl_app.py

@@ -1,6 +1,6 @@
 import json
 import time
-from typing import cast
+from typing import Any, cast
 
 import requests
 
@@ -14,48 +14,47 @@ class FirecrawlApp:
         if self.api_key is None and self.base_url == "https://api.firecrawl.dev":
             raise ValueError("No API key provided")
 
-    def scrape_url(self, url, params=None) -> dict:
-        headers = {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"}
-        json_data = {"url": url}
+    def scrape_url(self, url, params=None) -> dict[str, Any]:
+        # Documentation: https://docs.firecrawl.dev/api-reference/endpoint/scrape
+        headers = self._prepare_headers()
+        json_data = {
+            "url": url,
+            "formats": ["markdown"],
+            "onlyMainContent": True,
+            "timeout": 30000,
+        }
         if params:
             json_data.update(params)
-        response = requests.post(f"{self.base_url}/v0/scrape", headers=headers, json=json_data)
+        response = self._post_request(f"{self.base_url}/v1/scrape", json_data, headers)
         if response.status_code == 200:
             response_data = response.json()
-            if response_data["success"] == True:
-                data = response_data["data"]
-                return {
-                    "title": data.get("metadata").get("title"),
-                    "description": data.get("metadata").get("description"),
-                    "source_url": data.get("metadata").get("sourceURL"),
-                    "markdown": data.get("markdown"),
-                }
-            else:
-                raise Exception(f"Failed to scrape URL. Error: {response_data['error']}")
-
-        elif response.status_code in {402, 409, 500}:
-            error_message = response.json().get("error", "Unknown error occurred")
-            raise Exception(f"Failed to scrape URL. Status code: {response.status_code}. Error: {error_message}")
+            data = response_data["data"]
+            return self._extract_common_fields(data)
+        elif response.status_code in {402, 409, 500, 429, 408}:
+            self._handle_error(response, "scrape URL")
+            return {}  # Avoid additional exception after handling error
         else:
             raise Exception(f"Failed to scrape URL. Status code: {response.status_code}")
 
     def crawl_url(self, url, params=None) -> str:
+        # Documentation: https://docs.firecrawl.dev/api-reference/endpoint/crawl-post
         headers = self._prepare_headers()
         json_data = {"url": url}
         if params:
             json_data.update(params)
-        response = self._post_request(f"{self.base_url}/v0/crawl", json_data, headers)
+        response = self._post_request(f"{self.base_url}/v1/crawl", json_data, headers)
         if response.status_code == 200:
-            job_id = response.json().get("jobId")
+            # There's also another two fields in the response: "success" (bool) and "url" (str)
+            job_id = response.json().get("id")
             return cast(str, job_id)
         else:
             self._handle_error(response, "start crawl job")
             # FIXME: unreachable code for mypy
             return ""  # unreachable
 
-    def check_crawl_status(self, job_id) -> dict:
+    def check_crawl_status(self, job_id) -> dict[str, Any]:
         headers = self._prepare_headers()
-        response = self._get_request(f"{self.base_url}/v0/crawl/status/{job_id}", headers)
+        response = self._get_request(f"{self.base_url}/v1/crawl/{job_id}", headers)
         if response.status_code == 200:
             crawl_status_response = response.json()
             if crawl_status_response.get("status") == "completed":
@@ -66,42 +65,48 @@ class FirecrawlApp:
                 url_data_list = []
                 for item in data:
                     if isinstance(item, dict) and "metadata" in item and "markdown" in item:
-                        url_data = {
-                            "title": item.get("metadata", {}).get("title"),
-                            "description": item.get("metadata", {}).get("description"),
-                            "source_url": item.get("metadata", {}).get("sourceURL"),
-                            "markdown": item.get("markdown"),
-                        }
+                        url_data = self._extract_common_fields(item)
                         url_data_list.append(url_data)
                 if url_data_list:
                     file_key = "website_files/" + job_id + ".txt"
-                    if storage.exists(file_key):
-                        storage.delete(file_key)
-                    storage.save(file_key, json.dumps(url_data_list).encode("utf-8"))
-                return {
-                    "status": "completed",
-                    "total": crawl_status_response.get("total"),
-                    "current": crawl_status_response.get("current"),
-                    "data": url_data_list,
-                }
-
+                    try:
+                        if storage.exists(file_key):
+                            storage.delete(file_key)
+                        storage.save(file_key, json.dumps(url_data_list).encode("utf-8"))
+                    except Exception as e:
+                        raise Exception(f"Error saving crawl data: {e}")
+                return self._format_crawl_status_response("completed", crawl_status_response, url_data_list)
             else:
-                return {
-                    "status": crawl_status_response.get("status"),
-                    "total": crawl_status_response.get("total"),
-                    "current": crawl_status_response.get("current"),
-                    "data": [],
-                }
-
+                return self._format_crawl_status_response(
+                    crawl_status_response.get("status"), crawl_status_response, []
+                )
         else:
             self._handle_error(response, "check crawl status")
             # FIXME: unreachable code for mypy
             return {}  # unreachable
 
-    def _prepare_headers(self):
+    def _format_crawl_status_response(
+        self, status: str, crawl_status_response: dict[str, Any], url_data_list: list[dict[str, Any]]
+    ) -> dict[str, Any]:
+        return {
+            "status": status,
+            "total": crawl_status_response.get("total"),
+            "current": crawl_status_response.get("completed"),
+            "data": url_data_list,
+        }
+
+    def _extract_common_fields(self, item: dict[str, Any]) -> dict[str, Any]:
+        return {
+            "title": item.get("metadata", {}).get("title"),
+            "description": item.get("metadata", {}).get("description"),
+            "source_url": item.get("metadata", {}).get("sourceURL"),
+            "markdown": item.get("markdown"),
+        }
+
+    def _prepare_headers(self) -> dict[str, Any]:
         return {"Content-Type": "application/json", "Authorization": f"Bearer {self.api_key}"}
 
-    def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5):
+    def _post_request(self, url, data, headers, retries=3, backoff_factor=0.5) -> requests.Response:
         for attempt in range(retries):
             response = requests.post(url, headers=headers, json=data)
             if response.status_code == 502:
@@ -110,7 +115,7 @@ class FirecrawlApp:
                 return response
         return response
 
-    def _get_request(self, url, headers, retries=3, backoff_factor=0.5):
+    def _get_request(self, url, headers, retries=3, backoff_factor=0.5) -> requests.Response:
         for attempt in range(retries):
             response = requests.get(url, headers=headers)
             if response.status_code == 502:
@@ -119,6 +124,6 @@ class FirecrawlApp:
                 return response
         return response
 
-    def _handle_error(self, response, action):
+    def _handle_error(self, response, action) -> None:
         error_message = response.json().get("error", "Unknown error occurred")
         raise Exception(f"Failed to {action}. Status code: {response.status_code}. Error: {error_message}")

api/core/rag/extractor/firecrawl/firecrawl_web_extractor.py

@@ -13,9 +13,10 @@ class FirecrawlWebExtractor(BaseExtractor):
         api_key: The API key for Firecrawl.
         base_url: The base URL for the Firecrawl API. Defaults to 'https://api.firecrawl.dev'.
         mode: The mode of operation. Defaults to 'scrape'. Options are 'crawl', 'scrape' and 'crawl_return_urls'.
+        only_main_content: Only return the main content of the page excluding headers, navs, footers, etc.
     """
 
-    def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = False):
+    def __init__(self, url: str, job_id: str, tenant_id: str, mode: str = "crawl", only_main_content: bool = True):
         """Initialize with url, api_key, base_url and mode."""
         self._url = url
         self.job_id = job_id

api/core/rag/index_processor/constant/index_type.py

@@ -1,7 +1,7 @@
-from enum import Enum
+from enum import StrEnum
 
 
-class IndexType(str, Enum):
+class IndexType(StrEnum):
     PARAGRAPH_INDEX = "text_model"
     QA_INDEX = "qa_model"
     PARENT_CHILD_INDEX = "hierarchical_model"

api/core/rag/index_processor/processor/parent_child_index_processor.py

@@ -47,6 +47,8 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
                 embedding_model_instance=kwargs.get("embedding_model_instance"),
             )
             for document in documents:
+                if kwargs.get("preview") and len(all_documents) >= 10:
+                    return all_documents
                 # document clean
                 document_text = CleanProcessor.clean(document.page_content, process_rule)
                 document.page_content = document_text

api/core/rag/retrieval/dataset_retrieval.py

@@ -203,6 +203,7 @@ class DatasetRetrieval:
                                 "segment_id": segment.id,
                                 "retriever_from": invoke_from.to_source(),
                                 "score": record.score or 0.0,
+                                "doc_metadata": document.doc_metadata,
                             }
 
                             if invoke_from.to_source() == "dev":

api/core/tools/custom_tool/tool.py

@@ -105,10 +105,10 @@ class ApiTool(Tool):
         needed_parameters = [parameter for parameter in (self.api_bundle.parameters or []) if parameter.required]
         for parameter in needed_parameters:
             if parameter.required and parameter.name not in parameters:
-                raise ToolParameterValidationError(f"Missing required parameter {parameter.name}")
-
-            if parameter.default is not None and parameter.name not in parameters:
-                parameters[parameter.name] = parameter.default
+                if parameter.default is not None:
+                    parameters[parameter.name] = parameter.default
+                else:
+                    raise ToolParameterValidationError(f"Missing required parameter {parameter.name}")
 
         return headers
 

api/core/tools/entities/tool_entities.py

@@ -125,7 +125,7 @@ class ToolInvokeMessage(BaseModel):
 
     class VariableMessage(BaseModel):
         variable_name: str = Field(..., description="The name of the variable")
-        variable_value: str = Field(..., description="The value of the variable")
+        variable_value: Any = Field(..., description="The value of the variable")
         stream: bool = Field(default=False, description="Whether the variable is streamed")
 
         @model_validator(mode="before")
@@ -185,7 +185,7 @@ class ToolInvokeMessage(BaseModel):
     """
         plain text, image url or link url
     """
-    message: JsonMessage | TextMessage | BlobMessage | VariableMessage | FileMessage | LogMessage | None
+    message: JsonMessage | TextMessage | BlobMessage | LogMessage | FileMessage | None | VariableMessage
     meta: dict[str, Any] | None = None
 
     @field_validator("message", mode="before")

api/core/tools/tool_engine.py

@@ -246,10 +246,11 @@ class ToolEngine:
                     + "you do not need to create it, just tell the user to check it now."
                 )
             elif response.type == ToolInvokeMessage.MessageType.JSON:
-                text = json.dumps(cast(ToolInvokeMessage.JsonMessage, response.message).json_object, ensure_ascii=False)
-                result += f"tool response: {text}."
+                result = json.dumps(
+                    cast(ToolInvokeMessage.JsonMessage, response.message).json_object, ensure_ascii=False
+                )
             else:
-                result += f"tool response: {response.message!r}."
+                result += str(response.message)
 
         return result