fix: version check

fix: agent thought not saved (#13631 )
fix: unexpected None embedding model provdier (#13610 )
2026-01-22 21:15:24 +08:00 · 2025-02-13 14:44:24 +08:00 · 2025-02-13 10:17:39 +08:00 · 2025-02-12 18:40:15 +08:00 · 2025-02-12 17:38:56 +08:00 · 2025-02-12 16:42:03 +08:00
1166 changed files with 60867 additions and 14838 deletions
--- a/.devcontainer/post_create_command.sh
+++ b/.devcontainer/post_create_command.sh
@ -1,11 +1,12 @@
 #!/bin/bash

-cd web && npm install
+npm add -g pnpm@9.12.2
+cd web && pnpm install
 pipx install poetry

 echo 'alias start-api="cd /workspaces/dify/api && poetry run python -m flask run --host 0.0.0.0 --port=5001 --debug"' >> ~/.bashrc
 echo 'alias start-worker="cd /workspaces/dify/api && poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion"' >> ~/.bashrc
-echo 'alias start-web="cd /workspaces/dify/web && npm run dev"' >> ~/.bashrc
+echo 'alias start-web="cd /workspaces/dify/web && pnpm dev"' >> ~/.bashrc
 echo 'alias start-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify up -d"' >> ~/.bashrc
 echo 'alias stop-containers="cd /workspaces/dify/docker && docker-compose -f docker-compose.middleware.yaml -p dify down"' >> ~/.bashrc

--- a/.github/actions/setup-poetry/action.yml
+++ b/.github/actions/setup-poetry/action.yml
@ -8,7 +8,7 @@ inputs:
  poetry-version:
    description: Poetry version to set up
    required: true
-    default: '1.8.4'
+    default: '2.0.1'
  poetry-lockfile:
    description: Path to the Poetry lockfile to restore cache from
    required: true
--- a/.github/workflows/api-tests.yml
+++ b/.github/workflows/api-tests.yml
@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta
    paths:
      - api/**
      - docker/**
@ -42,25 +43,17 @@ jobs:
        run: poetry install -C api --with dev

      - name: Check dependencies in pyproject.toml
-        run: poetry run -C api bash dev/pytest/pytest_artifacts.sh
+        run: poetry run -P api bash dev/pytest/pytest_artifacts.sh

      - name: Run Unit tests
-        run: poetry run -C api bash dev/pytest/pytest_unit_tests.sh
-
-      - name: Run ModelRuntime
-        run: poetry run -C api bash dev/pytest/pytest_model_runtime.sh
+        run: poetry run -P api bash dev/pytest/pytest_unit_tests.sh

      - name: Run dify config tests
-        run: poetry run -C api python dev/pytest/pytest_config_tests.py
-
-      - name: Run Tool
-        run: poetry run -C api bash dev/pytest/pytest_tools.sh
+        run: poetry run -P api python dev/pytest/pytest_config_tests.py

      - name: Run mypy
        run: |
-          pushd api
-          poetry run python -m mypy --install-types --non-interactive .
-          popd
+          poetry run -C api python -m mypy --install-types --non-interactive .

      - name: Set up dotenvs
        run: |
@ -80,4 +73,4 @@ jobs:
            ssrf_proxy

      - name: Run Workflow
-        run: poetry run -C api bash dev/pytest/pytest_workflow.sh
+        run: poetry run -P api bash dev/pytest/pytest_workflow.sh
--- a/.github/workflows/build-push.yml
+++ b/.github/workflows/build-push.yml
@ -5,6 +5,7 @@ on:
    branches:
      - "main"
      - "deploy/dev"
+      - "plugins/beta"
  release:
    types: [published]

--- a/.github/workflows/db-migration-test.yml
+++ b/.github/workflows/db-migration-test.yml
@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta
    paths:
      - api/migrations/**
      - .github/workflows/db-migration-test.yml
--- a/.github/workflows/docker-build.yml
+++ b/.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
--- a/.github/workflows/style.yml
+++ b/.github/workflows/style.yml
@ -4,6 +4,7 @@ on:
  pull_request:
    branches:
      - main
+      - plugins/beta

 concurrency:
  group: style-${{ github.head_ref || github.run_id }}
@ -38,12 +39,12 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        run: |
          poetry run -C api ruff --version
-          poetry run -C api ruff check ./api
-          poetry run -C api ruff format --check ./api
+          poetry run -C api ruff check ./
+          poetry run -C api ruff format --check ./

      - name: Dotenv check
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
+        run: poetry run -P api dotenv-linter ./api/.env.example ./web/.env.example

      - name: Lint hints
        if: failure()
@ -66,22 +67,55 @@ jobs:
        with:
          files: web/**

+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 10
+          run_install: false
+
      - name: Setup NodeJS
        uses: actions/setup-node@v4
        if: steps.changed-files.outputs.any_changed == 'true'
        with:
          node-version: 20
-          cache: yarn
+          cache: pnpm
          cache-dependency-path: ./web/package.json

      - name: Web dependencies
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Web style check
        if: steps.changed-files.outputs.any_changed == 'true'
        run: yarn run lint

+  docker-compose-template:
+    name: Docker Compose Template
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Check changed files
+        id: changed-files
+        uses: tj-actions/changed-files@v45
+        with:
+          files: |
+            docker/generate_docker_compose
+            docker/.env.example
+            docker/docker-compose-template.yaml
+            docker/docker-compose.yaml
+
+      - name: Generate Docker Compose
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: |
+          cd docker
+          ./generate_docker_compose
+
+      - name: Check for changes
+        if: steps.changed-files.outputs.any_changed == 'true'
+        run: git diff --exit-code

  superlinter:
    name: SuperLinter
@ -107,7 +141,7 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        env:
          BASH_SEVERITY: warning
-          DEFAULT_BRANCH: main
+          DEFAULT_BRANCH: plugins/beta
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
          IGNORE_GENERATED_FILES: true
          IGNORE_GITIGNORED_FILES: true
--- a/.github/workflows/tool-test-sdks.yaml
+++ b/.github/workflows/tool-test-sdks.yaml
@ -32,10 +32,10 @@ jobs:
        with:
          node-version: ${{ matrix.node-version }}
          cache: ''
-          cache-dependency-path: 'yarn.lock'
+          cache-dependency-path: 'pnpm-lock.yaml'

      - name: Install Dependencies
-        run: yarn install
+        run: pnpm install

      - name: Test
-        run: yarn test
+        run: pnpm test
--- a/.github/workflows/translate-i18n-base-on-english.yml
+++ b/.github/workflows/translate-i18n-base-on-english.yml
@ -38,11 +38,11 @@ jobs:

      - name: Install dependencies
        if: env.FILES_CHANGED == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Run npm script
        if: env.FILES_CHANGED == 'true'
-        run: npm run auto-gen-i18n
+        run: pnpm run auto-gen-i18n

      - name: Create Pull Request
        if: env.FILES_CHANGED == 'true'
--- a/.github/workflows/vdb-tests.yml
+++ b/.github/workflows/vdb-tests.yml
@ -70,4 +70,4 @@ jobs:
            tidb

      - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh
+        run: poetry run -P api bash dev/pytest/pytest_vdb.sh
--- a/.github/workflows/web-tests.yml
+++ b/.github/workflows/web-tests.yml
@ -34,13 +34,13 @@ jobs:
        if: steps.changed-files.outputs.any_changed == 'true'
        with:
          node-version: 20
-          cache: yarn
+          cache: pnpm
          cache-dependency-path: ./web/package.json

      - name: Install dependencies
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
+        run: pnpm install --frozen-lockfile

      - name: Run tests
        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn test
+        run: pnpm test
--- a/.gitignore
+++ b/.gitignore
@ -194,3 +194,9 @@ api/.vscode

 .idea/
 .vscode
+
+# pnpm
+/.pnpm-store
+
+# plugin migrate
+plugins.jsonl
--- a/README.md
+++ b/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">
--- a/README_AR.md
+++ b/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">
--- a/README_CN.md
+++ b/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">
--- a/README_ES.md
+++ b/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">
--- a/README_FR.md
+++ b/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">
--- a/README_JA.md
+++ b/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">
--- a/README_KL.md
+++ b/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">
--- a/README_KR.md
+++ b/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">
--- a/README_PT.md
+++ b/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">
--- a/README_SI.md
+++ b/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">
--- a/README_TR.md
+++ b/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
--- a/README_VI.md
+++ b/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">
--- a/api/.env.example
+++ b/api/.env.example
@ -422,8 +422,8 @@ POSITION_PROVIDER_INCLUDES=
 POSITION_PROVIDER_EXCLUDES=

 # Plugin configuration
-PLUGIN_API_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1
-PLUGIN_API_URL=http://127.0.0.1:5002
+PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi
+PLUGIN_DAEMON_URL=http://127.0.0.1:5002
 PLUGIN_REMOTE_INSTALL_PORT=5003
 PLUGIN_REMOTE_INSTALL_HOST=localhost
 PLUGIN_MAX_PACKAGE_SIZE=15728640
@ -435,7 +435,7 @@ MARKETPLACE_ENABLED=true
 MARKETPLACE_API_URL=https://marketplace.dify.ai

 # Endpoint configuration
-ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id}
+ENDPOINT_URL_TEMPLATE=http://localhost:5002/e/{hook_id}

 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
--- a/api/.ruff.toml
+++ b/api/.ruff.toml
@ -53,10 +53,12 @@ ignore = [
    "FURB152", # math-constant
    "UP007", # non-pep604-annotation
    "UP032", # f-string
+    "UP045", # non-pep604-annotation-optional
    "B005", # strip-with-multi-characters
    "B006", # mutable-argument-default
    "B007", # unused-loop-control-variable
    "B026", # star-arg-unpacking-after-keyword-arg
+    "B903", # class-as-data-structure
    "B904", # raise-without-from-inside-except
    "B905", # zip-without-explicit-strict
    "N806", # non-lowercase-variable-in-function
--- a/api/Dockerfile
+++ b/api/Dockerfile
@ -4,7 +4,7 @@ FROM python:3.12-slim-bookworm AS base
 WORKDIR /app/api

 # Install Poetry
-ENV POETRY_VERSION=1.8.4
+ENV POETRY_VERSION=2.0.1

 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@ -48,16 +48,18 @@ 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 libmagic to support the use of python-magic guess MIMETYPE
+        libmagic1 \
    && apt-get autoremove -y \
    && rm -rf /var/lib/apt/lists/*

@ -80,7 +82,6 @@ COPY . /app/api/
 COPY docker/entrypoint.sh /entrypoint.sh
 RUN chmod +x /entrypoint.sh

-
 ARG COMMIT_SHA
 ENV COMMIT_SHA=${COMMIT_SHA}

--- a/api/README.md
+++ b/api/README.md
@ -79,5 +79,5 @@
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`

   ```bash
-   poetry run -C api bash dev/pytest/pytest_all_tests.sh
+   poetry run -P api bash dev/pytest/pytest_all_tests.sh
   ```
--- a/api/configs/feature/init.py
+++ b/api/configs/feature/init.py
@ -141,10 +141,10 @@ class PluginConfig(BaseSettings):

    PLUGIN_DAEMON_URL: HttpUrl = Field(
        description="Plugin API URL",
-        default="http://plugin:5002",
+        default="http://localhost:5002",
    )

-    PLUGIN_API_KEY: str = Field(
+    PLUGIN_DAEMON_KEY: str = Field(
        description="Plugin API key",
        default="plugin-api-key",
    )
@ -200,7 +200,7 @@ class EndpointConfig(BaseSettings):
    )

    CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
+        description="Base URL for the console web interface,used for frontend references and CORS configuration",
        default="",
    )

@ -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):
    """
--- a/api/configs/feature/hosted_service/init.py
+++ b/api/configs/feature/hosted_service/init.py
@ -1,9 +1,40 @@
 from typing import Optional

-from pydantic import Field, NonNegativeInt
+from pydantic import Field, NonNegativeInt, computed_field
 from pydantic_settings import BaseSettings


+class HostedCreditConfig(BaseSettings):
+    HOSTED_MODEL_CREDIT_CONFIG: str = Field(
+        description="Model credit configuration in format 'model:credits,model:credits', e.g., 'gpt-4:20,gpt-4o:10'",
+        default="",
+    )
+
+    def get_model_credits(self, model_name: str) -> int:
+        """
+        Get credit value for a specific model name.
+        Returns 1 if model is not found in configuration (default credit).
+
+        :param model_name: The name of the model to search for
+        :return: The credit value for the model
+        """
+        if not self.HOSTED_MODEL_CREDIT_CONFIG:
+            return 1
+
+        try:
+            credit_map = dict(
+                item.strip().split(":", 1) for item in self.HOSTED_MODEL_CREDIT_CONFIG.split(",") if ":" in item
+            )
+
+            # Search for matching model pattern
+            for pattern, credit in credit_map.items():
+                if pattern.strip() == model_name:
+                    return int(credit)
+            return 1  # Default quota if no match found
+        except (ValueError, AttributeError):
+            return 1  # Return default quota if parsing fails
+
+
 class HostedOpenAiConfig(BaseSettings):
    """
    Configuration for hosted OpenAI service
@ -181,7 +212,7 @@ class HostedFetchAppTemplateConfig(BaseSettings):
    """

    HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
+        description="Mode for fetching app templates: remote, db, or builtin default to remote,",
        default="remote",
    )

@ -202,5 +233,7 @@ class HostedServiceConfig(
    HostedZhipuAIConfig,
    # moderation
    HostedModerationConfig,
+    # credit config
+    HostedCreditConfig,
 ):
    pass
--- a/api/configs/packaging/init.py
+++ b/api/configs/packaging/init.py
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):

    CURRENT_VERSION: str = Field(
        description="Dify version",
-        default="0.15.0",
+        default="1.0.0",
    )

    COMMIT_SHA: str = Field(
--- a/api/controllers/common/helpers.py
+++ b/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
--- a/api/controllers/console/admin.py
+++ b/api/controllers/console/admin.py
@ -59,7 +59,7 @@ class InsertExploreAppListApi(Resource):
        with Session(db.engine) as session:
            app = session.execute(select(App).filter(App.id == args["app_id"])).scalar_one_or_none()
        if not app:
-            raise NotFound(f'App \'{args["app_id"]}\' is not found')
+            raise NotFound(f"App '{args['app_id']}' is not found")

        site = app.site
        if not site:
--- a/api/controllers/console/app/audio.py
+++ b/api/controllers/console/app/audio.py
@ -22,7 +22,7 @@ from controllers.console.wraps import account_initialization_required, setup_req
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required
-from models.model import AppMode
+from models import App, AppMode
 from services.audio_service import AudioService
 from services.errors.audio import (
    AudioTooLargeServiceError,
@ -79,7 +79,7 @@ class ChatMessageTextApi(Resource):
    @login_required
    @account_initialization_required
    @get_app_model
-    def post(self, app_model):
+    def post(self, app_model: App):
        from werkzeug.exceptions import InternalServerError

        try:
@ -98,9 +98,13 @@ class ChatMessageTextApi(Resource):
                and app_model.workflow.features_dict
            ):
                text_to_speech = app_model.workflow.features_dict.get("text_to_speech")
+                if text_to_speech is None:
+                    raise ValueError("TTS is not enabled")
                voice = args.get("voice") or text_to_speech.get("voice")
            else:
                try:
+                    if app_model.app_model_config is None:
+                        raise ValueError("AppModelConfig not found")
                    voice = args.get("voice") or app_model.app_model_config.text_to_speech_dict.get("voice")
                except Exception:
                    voice = None
--- a/api/controllers/console/auth/error.py
+++ b/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
--- a/api/controllers/console/auth/forgot_password.py
+++ b/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")}


--- a/api/controllers/console/datasets/data_source.py
+++ b/api/controllers/console/datasets/data_source.py
@ -135,7 +135,7 @@ class DataSourceNotionListApi(Resource):
                        data_source_info = json.loads(document.data_source_info)
                        exist_page_ids.append(data_source_info["notion_page_id"])
            # get all authorized pages
-            data_source_bindings = session.execute(
+            data_source_bindings = session.scalars(
                select(DataSourceOauthBinding).filter_by(
                    tenant_id=current_user.current_tenant_id, provider="notion", disabled=False
                )
--- a/api/controllers/console/datasets/datasets.py
+++ b/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
@ -52,12 +53,12 @@ class DatasetListApi(Resource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
-
+        include_all = request.args.get("include_all", default="false").lower() == "true"
        if ids:
            datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
        else:
            datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, current_user.current_tenant_id, current_user, search, tag_ids, include_all
            )

        # check embedding setting
@ -72,7 +73,9 @@ class DatasetListApi(Resource):

        data = marshal(datasets, dataset_detail_fields)
        for item in data:
+            # convert embedding_model_provider to plugin standard format
            if item["indexing_technique"] == "high_quality":
+                item["embedding_model_provider"] = str(ModelProviderID(item["embedding_model_provider"]))
                item_model = f"{item['embedding_model']}:{item['embedding_model_provider']}"
                if item_model in model_names:
                    item["embedding_available"] = True
@ -457,7 +460,7 @@ class DatasetIndexingEstimateApi(Resource):
            )
        except LLMBadRequestError:
            raise ProviderNotInitializeError(
-                "No Embedding Model available. Please configure a valid provider " "in the Settings -> Model Provider."
+                "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
            )
        except ProviderTokenNotInitError as ex:
            raise ProviderNotInitializeError(ex.description)
@ -619,8 +622,7 @@ class DatasetRetrievalSettingApi(Resource):
        vector_type = dify_config.VECTOR_STORE
        match vector_type:
            case (
-                VectorType.MILVUS
-                | VectorType.RELYT
+                VectorType.RELYT
                | VectorType.PGVECTOR
                | VectorType.TIDB_VECTOR
                | VectorType.CHROMA
@ -645,6 +647,7 @@ class DatasetRetrievalSettingApi(Resource):
                | VectorType.TIDB_ON_QDRANT
                | VectorType.LINDORM
                | VectorType.COUCHBASE
+                | VectorType.MILVUS
            ):
                return {
                    "retrieval_method": [
--- a/api/controllers/console/datasets/datasets_document.py
+++ b/api/controllers/console/datasets/datasets_document.py
@ -362,8 +362,7 @@ class DatasetInitApi(Resource):
                )
            except InvokeAuthorizationError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -540,8 +539,7 @@ class DocumentBatchIndexingEstimateApi(DocumentResource):
                return response.model_dump(), 200
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/console/datasets/datasets_segments.py
+++ b/api/controllers/console/datasets/datasets_segments.py
@ -168,8 +168,7 @@ class DatasetDocumentSegmentApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -217,8 +216,7 @@ class DatasetDocumentSegmentAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -267,8 +265,7 @@ class DatasetDocumentSegmentUpdateApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -368,9 +365,9 @@ class DatasetDocumentSegmentBatchImportApi(Resource):
            result = []
            for index, row in df.iterrows():
                if document.doc_form == "qa_model":
-                    data = {"content": row[0], "answer": row[1]}
+                    data = {"content": row.iloc[0], "answer": row.iloc[1]}
                else:
-                    data = {"content": row[0]}
+                    data = {"content": row.iloc[0]}
                result.append(data)
            if len(result) == 0:
                raise ValueError("The CSV file is empty.")
@ -437,8 +434,7 @@ class ChildChunkAddApi(Resource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/console/explore/conversation.py
+++ b/api/controllers/console/explore/conversation.py
@ -32,7 +32,7 @@ class ConversationListApi(InstalledAppResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"

        try:
            with Session(db.engine) as session:
--- a/api/controllers/console/explore/message.py
+++ b/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.")
--- a/api/controllers/inner_api/workspace/workspace.py
+++ b/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() if tenant.created_at else None,
+            "updated_at": tenant.updated_at.isoformat() 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")
--- a/api/controllers/inner_api/wraps.py
+++ b/api/controllers/inner_api/wraps.py
@ -65,7 +65,7 @@ def enterprise_inner_api_user_auth(view):
 def plugin_inner_api_only(view):
    @wraps(view)
    def decorated(*args, **kwargs):
-        if not dify_config.PLUGIN_API_KEY:
+        if not dify_config.PLUGIN_DAEMON_KEY:
            abort(404)

        # get header 'X-Inner-Api-Key'
--- a/api/controllers/service_api/init.py
+++ b/api/controllers/service_api/init.py
@ -7,4 +7,4 @@ api = ExternalApi(bp)

 from . import index
 from .app import app, audio, completion, conversation, file, message, workflow
-from .dataset import dataset, document, hit_testing, segment
+from .dataset import dataset, document, hit_testing, segment, upload_file
--- a/api/controllers/service_api/dataset/dataset.py
+++ b/api/controllers/service_api/dataset/dataset.py
@ -31,8 +31,11 @@ class DatasetListApi(DatasetApiResource):
        # provider = request.args.get("provider", default="vendor")
        search = request.args.get("keyword", default=None, type=str)
        tag_ids = request.args.getlist("tag_ids")
+        include_all = request.args.get("include_all", default="false").lower() == "true"

-        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(
+            page, limit, tenant_id, current_user, search, tag_ids, include_all
+        )
        # check embedding setting
        provider_manager = ProviderManager()
        configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
--- a/api/controllers/service_api/dataset/document.py
+++ b/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)
--- a/api/controllers/service_api/dataset/segment.py
+++ b/api/controllers/service_api/dataset/segment.py
@ -53,8 +53,7 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -95,8 +94,7 @@ class SegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
@ -175,8 +173,7 @@ class DatasetSegmentApi(DatasetApiResource):
                )
            except LLMBadRequestError:
                raise ProviderNotInitializeError(
-                    "No Embedding Model available. Please configure a valid provider "
-                    "in the Settings -> Model Provider."
+                    "No Embedding Model available. Please configure a valid provider in the Settings -> Model Provider."
                )
            except ProviderTokenNotInitError as ex:
                raise ProviderNotInitializeError(ex.description)
--- a/api/controllers/service_api/dataset/upload_file.py
+++ b/api/controllers/service_api/dataset/upload_file.py
@ -0,0 +1,54 @@
+from werkzeug.exceptions import NotFound
+
+from controllers.service_api import api
+from controllers.service_api.wraps import (
+    DatasetApiResource,
+)
+from core.file import helpers as file_helpers
+from extensions.ext_database import db
+from models.dataset import Dataset
+from models.model import UploadFile
+from services.dataset_service import DocumentService
+
+
+class UploadFileApi(DatasetApiResource):
+    def get(self, tenant_id, dataset_id, document_id):
+        """Get upload file."""
+        # check dataset
+        dataset_id = str(dataset_id)
+        tenant_id = str(tenant_id)
+        dataset = db.session.query(Dataset).filter(Dataset.tenant_id == tenant_id, Dataset.id == dataset_id).first()
+        if not dataset:
+            raise NotFound("Dataset not found.")
+        # check document
+        document_id = str(document_id)
+        document = DocumentService.get_document(dataset.id, document_id)
+        if not document:
+            raise NotFound("Document not found.")
+        # check upload file
+        if document.data_source_type != "upload_file":
+            raise ValueError(f"Document data source type ({document.data_source_type}) is not upload_file.")
+        data_source_info = document.data_source_info_dict
+        if data_source_info and "upload_file_id" in data_source_info:
+            file_id = data_source_info["upload_file_id"]
+            upload_file = db.session.query(UploadFile).filter(UploadFile.id == file_id).first()
+            if not upload_file:
+                raise NotFound("UploadFile not found.")
+        else:
+            raise ValueError("Upload file id not found in document data source info.")
+
+        url = file_helpers.get_signed_file_url(upload_file_id=upload_file.id)
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": url,
+            "download_url": f"{url}&as_attachment=true",
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at.timestamp(),
+        }, 200
+
+
+api.add_resource(UploadFileApi, "/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/upload-file")
--- a/api/controllers/service_api/wraps.py
+++ b/api/controllers/service_api/wraps.py
@ -195,7 +195,11 @@ def validate_and_get_api_token(scope: str | None = None):
    with Session(db.engine, expire_on_commit=False) as session:
        update_stmt = (
            update(ApiToken)
-            .where(ApiToken.token == auth_token, ApiToken.last_used_at < cutoff_time, ApiToken.type == scope)
+            .where(
+                ApiToken.token == auth_token,
+                (ApiToken.last_used_at.is_(None) | (ApiToken.last_used_at < cutoff_time)),
+                ApiToken.type == scope,
+            )
            .values(last_used_at=current_time)
            .returning(ApiToken)
        )
@ -236,7 +240,7 @@ def create_or_update_end_user_for_user_id(app_model: App, user_id: Optional[str]
            tenant_id=app_model.tenant_id,
            app_id=app_model.id,
            type="service_api",
-            is_anonymous=True if user_id == "DEFAULT-USER" else False,
+            is_anonymous=user_id == "DEFAULT-USER",
            session_id=user_id,
        )
        db.session.add(end_user)
--- a/api/controllers/web/conversation.py
+++ b/api/controllers/web/conversation.py
@ -39,7 +39,7 @@ class ConversationListApi(WebApiResource):

        pinned = None
        if "pinned" in args and args["pinned"] is not None:
-            pinned = True if args["pinned"] == "true" else False
+            pinned = args["pinned"] == "true"

        try:
            with Session(db.engine) as session:
--- a/api/controllers/web/message.py
+++ b/api/controllers/web/message.py
@ -91,7 +91,7 @@ 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.")
--- a/api/core/agent/base_agent_runner.py
+++ b/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
--- a/api/core/agent/cot_agent_runner.py
+++ b/api/core/agent/cot_agent_runner.py
@ -168,7 +168,7 @@ class CotAgentRunner(BaseAgentRunner, ABC):

            self.save_agent_thought(
                agent_thought=agent_thought,
-                tool_name=scratchpad.action.action_name if scratchpad.action else "",
+                tool_name=(scratchpad.action.action_name if scratchpad.action and not scratchpad.is_final() else ""),
                tool_input={scratchpad.action.action_name: scratchpad.action.action_input} if scratchpad.action else {},
                tool_invoke_meta={},
                thought=scratchpad.thought or "",
--- a/api/core/app/apps/agent_chat/app_runner.py
+++ b/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
-        )
--- a/api/core/app/apps/base_app_queue_manager.py
+++ b/api/core/app/apps/base_app_queue_manager.py
@ -167,8 +167,7 @@ class AppQueueManager:
        else:
            if isinstance(data, DeclarativeMeta) or hasattr(data, "_sa_instance_state"):
                raise TypeError(
-                    "Critical Error: Passing SQLAlchemy Model instances "
-                    "that cause thread safety issues is not allowed."
+                    "Critical Error: Passing SQLAlchemy Model instances that cause thread safety issues is not allowed."
                )


--- a/api/core/app/apps/message_based_app_generator.py
+++ b/api/core/app/apps/message_based_app_generator.py
@ -89,6 +89,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
            Conversation.id == conversation_id,
            Conversation.app_id == app_model.id,
            Conversation.status == "normal",
+            Conversation.is_deleted.is_(False),
        ]

        if isinstance(user, Account):
--- a/api/core/app/apps/workflow_app_runner.py
+++ b/api/core/app/apps/workflow_app_runner.py
@ -241,6 +241,7 @@ class WorkflowBasedAppRunner(AppRunner):
                    predecessor_node_id=event.predecessor_node_id,
                    in_iteration_id=event.in_iteration_id,
                    parallel_mode_run_id=event.parallel_mode_run_id,
+                    agent_strategy=event.agent_strategy,
                )
            )
        elif isinstance(event, NodeRunSucceededEvent):
@ -386,7 +387,6 @@ class WorkflowBasedAppRunner(AppRunner):
                    status=event.status,
                    data=event.data,
                    metadata=event.metadata,
-                    node_id=event.node_id,
                )
            )
        elif isinstance(event, ParallelBranchRunStartedEvent):
--- a/api/core/app/entities/queue_entities.py
+++ b/api/core/app/entities/queue_entities.py
@ -6,7 +6,7 @@ from typing import Any, Optional
 from pydantic import BaseModel

 from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk
-from core.workflow.entities.node_entities import NodeRunMetadataKey
+from core.workflow.entities.node_entities import AgentNodeStrategyInit, NodeRunMetadataKey
 from core.workflow.graph_engine.entities.graph_runtime_state import GraphRuntimeState
 from core.workflow.nodes import NodeType
 from core.workflow.nodes.base import BaseNodeData
@ -281,6 +281,7 @@ class QueueNodeStartedEvent(AppQueueEvent):
    start_at: datetime
    parallel_mode_run_id: Optional[str] = None
    """iteratoin run in parallel mode run id"""
+    agent_strategy: Optional[AgentNodeStrategyInit] = None


 class QueueNodeSucceededEvent(AppQueueEvent):
@ -330,7 +331,6 @@ class QueueAgentLogEvent(AppQueueEvent):
    status: str
    data: Mapping[str, Any]
    metadata: Optional[Mapping[str, Any]] = None
-    node_id: str


 class QueueNodeRetryEvent(QueueNodeStartedEvent):
--- a/api/core/app/entities/task_entities.py
+++ b/api/core/app/entities/task_entities.py
@ -6,6 +6,7 @@ from pydantic import BaseModel, ConfigDict

 from core.model_runtime.entities.llm_entities import LLMResult
 from core.model_runtime.utils.encoders import jsonable_encoder
+from core.workflow.entities.node_entities import AgentNodeStrategyInit
 from models.workflow import WorkflowNodeExecutionStatus


@ -248,6 +249,7 @@ class NodeStartStreamResponse(StreamResponse):
        parent_parallel_start_node_id: Optional[str] = None
        iteration_id: Optional[str] = None
        parallel_run_id: Optional[str] = None
+        agent_strategy: Optional[AgentNodeStrategyInit] = None

    event: StreamEvent = StreamEvent.NODE_STARTED
    workflow_run_id: str
@ -717,7 +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
--- a/api/core/app/task_pipeline/message_cycle_manage.py
+++ b/api/core/app/task_pipeline/message_cycle_manage.py
@ -145,7 +145,7 @@ class MessageCycleManage:

            # get extension
            if "." in message_file.url:
-                extension = f'.{message_file.url.split(".")[-1]}'
+                extension = f".{message_file.url.split('.')[-1]}"
                if len(extension) > 10:
                    extension = ".bin"
            else:
--- a/api/core/app/task_pipeline/workflow_cycle_manage.py
+++ b/api/core/app/task_pipeline/workflow_cycle_manage.py
@ -541,6 +541,7 @@ class WorkflowCycleManage:
                parent_parallel_start_node_id=event.parent_parallel_start_node_id,
                iteration_id=event.in_iteration_id,
                parallel_run_id=event.parallel_mode_run_id,
+                agent_strategy=event.agent_strategy,
            ),
        )

@ -863,6 +864,5 @@ class WorkflowCycleManage:
                status=event.status,
                data=event.data,
                metadata=event.metadata,
-                node_id=event.node_id,
            ),
        )
--- a/api/core/external_data_tool/api/api.py
+++ b/api/core/external_data_tool/api/api.py
@ -62,8 +62,9 @@ class ApiExternalDataTool(ExternalDataTool):

        if not api_based_extension:
            raise ValueError(
-                "[External data tool] API query failed, variable: {}, "
-                "error: api_based_extension_id is invalid".format(self.variable)
+                "[External data tool] API query failed, variable: {}, error: api_based_extension_id is invalid".format(
+                    self.variable
+                )
            )

        # decrypt api_key
--- a/api/core/file/helpers.py
+++ b/api/core/file/helpers.py
@ -33,7 +33,7 @@ def get_signed_file_url_for_plugin(filename: str, mimetype: str, tenant_id: str,
    sign = hmac.new(key, msg.encode(), hashlib.sha256).digest()
    encoded_sign = base64.urlsafe_b64encode(sign).decode()

-    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}"
+    return f"{url}?timestamp={timestamp}&nonce={nonce}&sign={encoded_sign}&user_id={user_id}&tenant_id={tenant_id}"


 def verify_plugin_file_signature(
--- a/api/core/file/models.py
+++ b/api/core/file/models.py
@ -90,7 +90,7 @@ class File(BaseModel):
    def markdown(self) -> str:
        url = self.generate_url()
        if self.type == FileType.IMAGE:
-            text = f'![{self.filename or ""}]({url})'
+            text = f"![{self.filename or ''}]({url})"
        else:
            text = f"[{self.filename or url}]({url})"

--- a/api/core/helper/ssrf_proxy.py
+++ b/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:
--- a/api/core/indexing_runner.py
+++ b/api/core/indexing_runner.py
@ -530,7 +530,6 @@ class IndexingRunner:
        # chunk nodes by chunk size
        indexing_start_at = time.perf_counter()
        tokens = 0
-        chunk_size = 10
        if dataset_document.doc_form != IndexType.PARENT_CHILD_INDEX:
            # create keyword index
            create_keyword_thread = threading.Thread(
@ -539,11 +538,22 @@ class IndexingRunner:
            )
            create_keyword_thread.start()

+        max_workers = 10
        if dataset.indexing_technique == "high_quality":
-            with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
                futures = []
-                for i in range(0, len(documents), chunk_size):
-                    chunk_documents = documents[i : i + chunk_size]
+
+                # Distribute documents into multiple groups based on the hash values of page_content
+                # This is done to prevent multiple threads from processing the same document,
+                # Thereby avoiding potential database insertion deadlocks
+                document_groups: list[list[Document]] = [[] for _ in range(max_workers)]
+                for document in documents:
+                    hash = helper.generate_text_hash(document.page_content)
+                    group_index = int(hash, 16) % max_workers
+                    document_groups[group_index].append(document)
+                for chunk_documents in document_groups:
+                    if len(chunk_documents) == 0:
+                        continue
                    futures.append(
                        executor.submit(
                            self._process_chunk,
--- a/api/core/llm_generator/prompts.py
+++ b/api/core/llm_generator/prompts.py
@ -131,7 +131,7 @@ JAVASCRIPT_CODE_GENERATOR_PROMPT_TEMPLATE = (
 SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
    "Please help me predict the three most likely questions that human would ask, "
    "and keeping each question under 20 characters.\n"
-    "MAKE SURE your output is the SAME language as the Assistant's latest response"
+    "MAKE SURE your output is the SAME language as the Assistant's latest response. "
    "The output must be an array in JSON format following the specified schema:\n"
    '["question1","question2","question3"]\n'
 )
--- a/api/core/model_runtime/entities/init.py
+++ b/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",
--- a/api/core/model_runtime/entities/llm_entities.py
+++ b/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.
    """
--- a/api/core/model_runtime/model_providers/__base/ai_model.py
+++ b/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)
--- a/api/core/model_runtime/model_providers/__base/large_language_model.py
+++ b/api/core/model_runtime/model_providers/__base/large_language_model.py
@ -107,11 +107,46 @@ class LargeLanguageModel(AIModel):
                content_list = []
                usage = LLMUsage.empty_usage()
                system_fingerprint = None
+                tools_calls: list[AssistantPromptMessage.ToolCall] = []
+
+                def increase_tool_call(new_tool_calls: list[AssistantPromptMessage.ToolCall]):
+                    def get_tool_call(tool_name: str):
+                        if not tool_name:
+                            return tools_calls[-1]
+
+                        tool_call = next(
+                            (tool_call for tool_call in tools_calls if tool_call.function.name == tool_name), None
+                        )
+                        if tool_call is None:
+                            tool_call = AssistantPromptMessage.ToolCall(
+                                id="",
+                                type="",
+                                function=AssistantPromptMessage.ToolCall.ToolCallFunction(name=tool_name, arguments=""),
+                            )
+                            tools_calls.append(tool_call)
+
+                        return tool_call
+
+                    for new_tool_call in new_tool_calls:
+                        # get tool call
+                        tool_call = get_tool_call(new_tool_call.function.name)
+                        # update tool call
+                        if new_tool_call.id:
+                            tool_call.id = new_tool_call.id
+                        if new_tool_call.type:
+                            tool_call.type = new_tool_call.type
+                        if new_tool_call.function.name:
+                            tool_call.function.name = new_tool_call.function.name
+                        if new_tool_call.function.arguments:
+                            tool_call.function.arguments += new_tool_call.function.arguments
+
                for chunk in result:
                    if isinstance(chunk.delta.message.content, str):
                        content += chunk.delta.message.content
                    elif isinstance(chunk.delta.message.content, list):
                        content_list.extend(chunk.delta.message.content)
+                    if chunk.delta.message.tool_calls:
+                        increase_tool_call(chunk.delta.message.tool_calls)

                    usage = chunk.delta.usage or LLMUsage.empty_usage()
                    system_fingerprint = chunk.system_fingerprint
@ -120,7 +155,10 @@ class LargeLanguageModel(AIModel):
                result = LLMResult(
                    model=model,
                    prompt_messages=prompt_messages,
-                    message=AssistantPromptMessage(content=content or content_list),
+                    message=AssistantPromptMessage(
+                        content=content or content_list,
+                        tool_calls=tools_calls,
+                    ),
                    usage=usage,
                    system_fingerprint=system_fingerprint,
                )
--- a/api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
+++ b/api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py
@ -1,6 +1,9 @@
+import logging
 from threading import Lock
 from typing import Any

+logger = logging.getLogger(__name__)
+
 _tokenizer: Any = None
 _lock = Lock()

@ -43,5 +46,6 @@ class GPT2Tokenizer:
                    base_path = abspath(__file__)
                    gpt2_tokenizer_path = join(dirname(base_path), "gpt2")
                    _tokenizer = TransformerGPT2Tokenizer.from_pretrained(gpt2_tokenizer_path)
+                    logger.info("Fallback to Transformers' GPT-2 tokenizer from tiktoken")

            return _tokenizer
--- a/api/core/model_runtime/model_providers/_position.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/model_provider_factory.py
+++ b/api/core/model_runtime/model_providers/model_provider_factory.py
@ -20,6 +20,7 @@ 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
@ -112,6 +113,9 @@ 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()

@ -363,4 +367,4 @@ class ModelProviderFactory:
            plugin_id = "/".join(provider.split("/")[:-1])
            provider_name = provider.split("/")[-1]

-        return plugin_id, provider_name
+        return str(plugin_id), provider_name
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-001.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-lite-preview-02-05.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-01-21.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-flash-thinking-exp-1219.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-2.0-pro-exp-02-05.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1114.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1121.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/vertex_ai/llm/gemini-exp-1206.yaml
+++ b/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
--- a/api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-pro-128k.yaml
+++ b/api/core/model_runtime/model_providers/wenxin/llm/ernie-lite-pro-128k.yaml
@ -1,42 +0,0 @@
-model: ernie-lite-pro-128k
-label:
-  en_US: Ernie-Lite-Pro-128K
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 128000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-    min: 0.1
-    max: 1.0
-    default: 0.8
-  - name: top_p
-    use_template: top_p
-  - name: min_output_tokens
-    label:
-      en_US: "Min Output Tokens"
-      zh_Hans: "最小输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    help:
-      zh_Hans: 指定模型最小输出token数
-      en_US: Specifies the lower limit on the length of generated results.
-  - name: max_output_tokens
-    label:
-      en_US: "Max Output Tokens"
-      zh_Hans: "最大输出Token数"
-    use_template: max_tokens
-    min: 2
-    max: 2048
-    default: 2048
-    help:
-      zh_Hans: 指定模型最大输出token数
-      en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
-  - name: presence_penalty
-    use_template: presence_penalty
-  - name: frequency_penalty
-    use_template: frequency_penalty
--- a/api/core/model_runtime/model_providers/zhipuai/llm/glm-4-air-0111.yaml
+++ b/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
--- a/api/core/model_runtime/schema_validators/common_validator.py
+++ b/api/core/model_runtime/schema_validators/common_validator.py
@ -87,6 +87,6 @@ class CommonValidator:
            if value.lower() not in {"true", "false"}:
                raise ValueError(f"Variable {credential_form_schema.variable} should be true or false")

-            value = True if value.lower() == "true" else False
+            value = value.lower() == "true"

        return value
--- a/api/core/ops/entities/config_entity.py
+++ b/api/core/ops/entities/config_entity.py
@ -6,6 +6,7 @@ from pydantic import BaseModel, ValidationInfo, field_validator
 class TracingProviderEnum(Enum):
    LANGFUSE = "langfuse"
    LANGSMITH = "langsmith"
+    OPIK = "opik"


 class BaseTracingConfig(BaseModel):
@ -56,5 +57,36 @@ class LangSmithConfig(BaseTracingConfig):
        return v


+class OpikConfig(BaseTracingConfig):
+    """
+    Model class for Opik tracing config.
+    """
+
+    api_key: str | None = None
+    project: str | None = None
+    workspace: str | None = None
+    url: str = "https://www.comet.com/opik/api/"
+
+    @field_validator("project")
+    @classmethod
+    def project_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "Default Project"
+
+        return v
+
+    @field_validator("url")
+    @classmethod
+    def url_validator(cls, v, info: ValidationInfo):
+        if v is None or v == "":
+            v = "https://www.comet.com/opik/api/"
+        if not v.startswith(("https://", "http://")):
+            raise ValueError("url must start with https:// or http://")
+        if not v.endswith("/api/"):
+            raise ValueError("url should ends with /api/")
+
+        return v
+
+
 OPS_FILE_PATH = "ops_trace/"
 OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"
--- a/docker-legacy/volumes/sandbox/dependencies/python-requirements.txt
+++ b/docker-legacy/volumes/sandbox/dependencies/python-requirements.txt
--- a/api/core/ops/opik_trace/opik_trace.py
+++ b/api/core/ops/opik_trace/opik_trace.py
@ -0,0 +1,469 @@
+import json
+import logging
+import os
+import uuid
+from datetime import datetime, timedelta
+from typing import Optional, cast
+
+from opik import Opik, Trace
+from opik.id_helpers import uuid4_to_uuid7
+
+from core.ops.base_trace_instance import BaseTraceInstance
+from core.ops.entities.config_entity import OpikConfig
+from core.ops.entities.trace_entity import (
+    BaseTraceInfo,
+    DatasetRetrievalTraceInfo,
+    GenerateNameTraceInfo,
+    MessageTraceInfo,
+    ModerationTraceInfo,
+    SuggestedQuestionTraceInfo,
+    ToolTraceInfo,
+    TraceTaskName,
+    WorkflowTraceInfo,
+)
+from extensions.ext_database import db
+from models.model import EndUser, MessageFile
+from models.workflow import WorkflowNodeExecution
+
+logger = logging.getLogger(__name__)
+
+
+def wrap_dict(key_name, data):
+    """Make sure that the input data is a dict"""
+    if not isinstance(data, dict):
+        return {key_name: data}
+
+    return data
+
+
+def wrap_metadata(metadata, **kwargs):
+    """Add common metatada to all Traces and Spans"""
+    metadata["created_from"] = "dify"
+
+    metadata.update(kwargs)
+
+    return metadata
+
+
+def prepare_opik_uuid(user_datetime: Optional[datetime], user_uuid: Optional[str]):
+    """Opik needs UUIDv7 while Dify uses UUIDv4 for identifier of most
+    messages and objects. The type-hints of BaseTraceInfo indicates that
+    objects start_time and message_id could be null which means we cannot map
+    it to a UUIDv7. Given that we have no way to identify that object
+    uniquely, generate a new random one UUIDv7 in that case.
+    """
+
+    if user_datetime is None:
+        user_datetime = datetime.now()
+
+    if user_uuid is None:
+        user_uuid = str(uuid.uuid4())
+
+    return uuid4_to_uuid7(user_datetime, user_uuid)
+
+
+class OpikDataTrace(BaseTraceInstance):
+    def __init__(
+        self,
+        opik_config: OpikConfig,
+    ):
+        super().__init__(opik_config)
+        self.opik_client = Opik(
+            project_name=opik_config.project,
+            workspace=opik_config.workspace,
+            host=opik_config.url,
+            api_key=opik_config.api_key,
+        )
+        self.project = opik_config.project
+        self.file_base_url = os.getenv("FILES_URL", "http://127.0.0.1:5001")
+
+    def trace(self, trace_info: BaseTraceInfo):
+        if isinstance(trace_info, WorkflowTraceInfo):
+            self.workflow_trace(trace_info)
+        if isinstance(trace_info, MessageTraceInfo):
+            self.message_trace(trace_info)
+        if isinstance(trace_info, ModerationTraceInfo):
+            self.moderation_trace(trace_info)
+        if isinstance(trace_info, SuggestedQuestionTraceInfo):
+            self.suggested_question_trace(trace_info)
+        if isinstance(trace_info, DatasetRetrievalTraceInfo):
+            self.dataset_retrieval_trace(trace_info)
+        if isinstance(trace_info, ToolTraceInfo):
+            self.tool_trace(trace_info)
+        if isinstance(trace_info, GenerateNameTraceInfo):
+            self.generate_name_trace(trace_info)
+
+    def workflow_trace(self, trace_info: WorkflowTraceInfo):
+        dify_trace_id = trace_info.workflow_run_id
+        opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+        workflow_metadata = wrap_metadata(
+            trace_info.metadata, message_id=trace_info.message_id, workflow_app_log_id=trace_info.workflow_app_log_id
+        )
+        root_span_id = None
+
+        if trace_info.message_id:
+            dify_trace_id = trace_info.message_id
+            opik_trace_id = prepare_opik_uuid(trace_info.start_time, dify_trace_id)
+
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["message", "workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+            root_span_id = prepare_opik_uuid(trace_info.start_time, trace_info.workflow_run_id)
+            span_data = {
+                "id": root_span_id,
+                "parent_span_id": None,
+                "trace_id": opik_trace_id,
+                "name": TraceTaskName.WORKFLOW_TRACE.value,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_span(span_data)
+        else:
+            trace_data = {
+                "id": opik_trace_id,
+                "name": TraceTaskName.MESSAGE_TRACE.value,
+                "start_time": trace_info.start_time,
+                "end_time": trace_info.end_time,
+                "metadata": workflow_metadata,
+                "input": wrap_dict("input", trace_info.workflow_run_inputs),
+                "output": wrap_dict("output", trace_info.workflow_run_outputs),
+                "tags": ["workflow"],
+                "project_name": self.project,
+            }
+            self.add_trace(trace_data)
+
+        # through workflow_run_id get all_nodes_execution
+        workflow_nodes_execution_id_records = (
+            db.session.query(WorkflowNodeExecution.id)
+            .filter(WorkflowNodeExecution.workflow_run_id == trace_info.workflow_run_id)
+            .all()
+        )
+
+        for node_execution_id_record in workflow_nodes_execution_id_records:
+            node_execution = (
+                db.session.query(
+                    WorkflowNodeExecution.id,
+                    WorkflowNodeExecution.tenant_id,
+                    WorkflowNodeExecution.app_id,
+                    WorkflowNodeExecution.title,
+                    WorkflowNodeExecution.node_type,
+                    WorkflowNodeExecution.status,
+                    WorkflowNodeExecution.inputs,
+                    WorkflowNodeExecution.outputs,
+                    WorkflowNodeExecution.created_at,
+                    WorkflowNodeExecution.elapsed_time,
+                    WorkflowNodeExecution.process_data,
+                    WorkflowNodeExecution.execution_metadata,
+                )
+                .filter(WorkflowNodeExecution.id == node_execution_id_record.id)
+                .first()
+            )
+
+            if not node_execution:
+                continue
+
+            node_execution_id = node_execution.id
+            tenant_id = node_execution.tenant_id
+            app_id = node_execution.app_id
+            node_name = node_execution.title
+            node_type = node_execution.node_type
+            status = node_execution.status
+            if node_type == "llm":
+                inputs = (
+                    json.loads(node_execution.process_data).get("prompts", {}) if node_execution.process_data else {}
+                )
+            else:
+                inputs = json.loads(node_execution.inputs) if node_execution.inputs else {}
+            outputs = json.loads(node_execution.outputs) if node_execution.outputs else {}
+            created_at = node_execution.created_at or datetime.now()
+            elapsed_time = node_execution.elapsed_time
+            finished_at = created_at + timedelta(seconds=elapsed_time)
+
+            execution_metadata = (
+                json.loads(node_execution.execution_metadata) if node_execution.execution_metadata else {}
+            )
+            metadata = execution_metadata.copy()
+            metadata.update(
+                {
+                    "workflow_run_id": trace_info.workflow_run_id,
+                    "node_execution_id": node_execution_id,
+                    "tenant_id": tenant_id,
+                    "app_id": app_id,
+                    "app_name": node_name,
+                    "node_type": node_type,
+                    "status": status,
+                }
+            )
+
+            process_data = json.loads(node_execution.process_data) if node_execution.process_data else {}
+
+            provider = None
+            model = None
+            total_tokens = 0
+            completion_tokens = 0
+            prompt_tokens = 0
+
+            if process_data and process_data.get("model_mode") == "chat":
+                run_type = "llm"
+                provider = process_data.get("model_provider", None)
+                model = process_data.get("model_name", "")
+                metadata.update(
+                    {
+                        "ls_provider": provider,
+                        "ls_model_name": model,
+                    }
+                )
+
+                try:
+                    if outputs.get("usage"):
+                        total_tokens = outputs["usage"].get("total_tokens", 0)
+                        prompt_tokens = outputs["usage"].get("prompt_tokens", 0)
+                        completion_tokens = outputs["usage"].get("completion_tokens", 0)
+                except Exception:
+                    logger.error("Failed to extract usage", exc_info=True)
+
+            else:
+                run_type = "tool"
+
+            parent_span_id = trace_info.workflow_app_log_id or trace_info.workflow_run_id
+
+            if not total_tokens:
+                total_tokens = execution_metadata.get("total_tokens", 0)
+
+            span_data = {
+                "trace_id": opik_trace_id,
+                "id": prepare_opik_uuid(created_at, node_execution_id),
+                "parent_span_id": prepare_opik_uuid(trace_info.start_time, parent_span_id),
+                "name": node_type,
+                "type": run_type,
+                "start_time": created_at,
+                "end_time": finished_at,
+                "metadata": wrap_metadata(metadata),
+                "input": wrap_dict("input", inputs),
+                "output": wrap_dict("output", outputs),
+                "tags": ["node_execution"],
+                "project_name": self.project,
+                "usage": {
+                    "total_tokens": total_tokens,
+                    "completion_tokens": completion_tokens,
+                    "prompt_tokens": prompt_tokens,
+                },
+                "model": model,
+                "provider": provider,
+            }
+
+            self.add_span(span_data)
+
+    def message_trace(self, trace_info: MessageTraceInfo):
+        # get message file data
+        file_list = cast(list[str], trace_info.file_list) or []
+        message_file_data: Optional[MessageFile] = trace_info.message_file_data
+
+        if message_file_data is not None:
+            file_url = f"{self.file_base_url}/{message_file_data.url}" if message_file_data else ""
+            file_list.append(file_url)
+
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        metadata = trace_info.metadata
+        message_id = trace_info.message_id
+
+        user_id = message_data.from_account_id
+        metadata["user_id"] = user_id
+        metadata["file_list"] = file_list
+
+        if message_data.from_end_user_id:
+            end_user_data: Optional[EndUser] = (
+                db.session.query(EndUser).filter(EndUser.id == message_data.from_end_user_id).first()
+            )
+            if end_user_data is not None:
+                end_user_id = end_user_data.session_id
+                metadata["end_user_id"] = end_user_id
+
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, message_id),
+            "name": TraceTaskName.MESSAGE_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": trace_info.inputs,
+            "output": message_data.answer,
+            "tags": ["message", str(trace_info.conversation_mode)],
+            "project_name": self.project,
+        }
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": "llm",
+            "type": "llm",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(metadata),
+            "input": {"input": trace_info.inputs},
+            "output": {"output": message_data.answer},
+            "tags": ["llm", str(trace_info.conversation_mode)],
+            "usage": {
+                "completion_tokens": trace_info.answer_tokens,
+                "prompt_tokens": trace_info.message_tokens,
+                "total_tokens": trace_info.total_tokens,
+            },
+            "project_name": self.project,
+        }
+        self.add_span(span_data)
+
+    def moderation_trace(self, trace_info: ModerationTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.MODERATION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {
+                "action": trace_info.action,
+                "flagged": trace_info.flagged,
+                "preset_response": trace_info.preset_response,
+                "inputs": trace_info.inputs,
+            },
+            "tags": ["moderation"],
+        }
+
+        self.add_span(span_data)
+
+    def suggested_question_trace(self, trace_info: SuggestedQuestionTraceInfo):
+        message_data = trace_info.message_data
+        if message_data is None:
+            return
+
+        start_time = trace_info.start_time or message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.SUGGESTED_QUESTION_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.suggested_question),
+            "tags": ["suggested_question"],
+        }
+
+        self.add_span(span_data)
+
+    def dataset_retrieval_trace(self, trace_info: DatasetRetrievalTraceInfo):
+        if trace_info.message_data is None:
+            return
+
+        start_time = trace_info.start_time or trace_info.message_data.created_at
+
+        span_data = {
+            "trace_id": prepare_opik_uuid(start_time, trace_info.message_id),
+            "name": TraceTaskName.DATASET_RETRIEVAL_TRACE.value,
+            "type": "tool",
+            "start_time": start_time,
+            "end_time": trace_info.end_time or trace_info.message_data.updated_at,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": {"documents": trace_info.documents},
+            "tags": ["dataset_retrieval"],
+        }
+
+        self.add_span(span_data)
+
+    def tool_trace(self, trace_info: ToolTraceInfo):
+        span_data = {
+            "trace_id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": trace_info.tool_name,
+            "type": "tool",
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.tool_inputs),
+            "output": wrap_dict("output", trace_info.tool_outputs),
+            "tags": ["tool", trace_info.tool_name],
+        }
+
+        self.add_span(span_data)
+
+    def generate_name_trace(self, trace_info: GenerateNameTraceInfo):
+        trace_data = {
+            "id": prepare_opik_uuid(trace_info.start_time, trace_info.message_id),
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": trace_info.inputs,
+            "output": trace_info.outputs,
+            "tags": ["generate_name"],
+            "project_name": self.project,
+        }
+
+        trace = self.add_trace(trace_data)
+
+        span_data = {
+            "trace_id": trace.id,
+            "name": TraceTaskName.GENERATE_NAME_TRACE.value,
+            "start_time": trace_info.start_time,
+            "end_time": trace_info.end_time,
+            "metadata": wrap_metadata(trace_info.metadata),
+            "input": wrap_dict("input", trace_info.inputs),
+            "output": wrap_dict("output", trace_info.outputs),
+            "tags": ["generate_name"],
+        }
+
+        self.add_span(span_data)
+
+    def add_trace(self, opik_trace_data: dict) -> Trace:
+        try:
+            trace = self.opik_client.trace(**opik_trace_data)
+            logger.debug("Opik Trace created successfully")
+            return trace
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create trace: {str(e)}")
+
+    def add_span(self, opik_span_data: dict):
+        try:
+            self.opik_client.span(**opik_span_data)
+            logger.debug("Opik Span created successfully")
+        except Exception as e:
+            raise ValueError(f"Opik Failed to create span: {str(e)}")
+
+    def api_check(self):
+        try:
+            self.opik_client.auth_check()
+            return True
+        except Exception as e:
+            logger.info(f"Opik API check failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik API check failed: {str(e)}")
+
+    def get_project_url(self):
+        try:
+            return self.opik_client.get_project_url(project_name=self.project)
+        except Exception as e:
+            logger.info(f"Opik get run url failed: {str(e)}", exc_info=True)
+            raise ValueError(f"Opik get run url failed: {str(e)}")
--- a/api/core/ops/ops_trace_manager.py
+++ b/api/core/ops/ops_trace_manager.py
@ -17,6 +17,7 @@ from core.ops.entities.config_entity import (
    OPS_FILE_PATH,
    LangfuseConfig,
    LangSmithConfig,
+    OpikConfig,
    TracingProviderEnum,
 )
 from core.ops.entities.trace_entity import (
@ -32,6 +33,7 @@ from core.ops.entities.trace_entity import (
 )
 from core.ops.langfuse_trace.langfuse_trace import LangFuseDataTrace
 from core.ops.langsmith_trace.langsmith_trace import LangSmithDataTrace
+from core.ops.opik_trace.opik_trace import OpikDataTrace
 from core.ops.utils import get_message_data
 from extensions.ext_database import db
 from extensions.ext_storage import storage
@ -52,6 +54,12 @@ provider_config_map: dict[str, dict[str, Any]] = {
        "other_keys": ["project", "endpoint"],
        "trace_instance": LangSmithDataTrace,
    },
+    TracingProviderEnum.OPIK.value: {
+        "config_class": OpikConfig,
+        "secret_keys": ["api_key"],
+        "other_keys": ["project", "url", "workspace"],
+        "trace_instance": OpikDataTrace,
+    },
 }


--- a/api/core/plugin/entities/plugin.py
+++ b/api/core/plugin/entities/plugin.py
@ -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"]:
+                self.plugin_name = f"{self.provider_name}_tool"
+
+
 class PluginDependency(BaseModel):
    class Type(enum.StrEnum):
        Github = PluginInstallationSource.Github.value
--- a/api/core/plugin/manager/base.py
+++ b/api/core/plugin/manager/base.py
@ -30,7 +30,7 @@ from core.plugin.manager.exc import (
 )

 plugin_daemon_inner_api_baseurl = dify_config.PLUGIN_DAEMON_URL
-plugin_daemon_inner_api_key = dify_config.PLUGIN_API_KEY
+plugin_daemon_inner_api_key = dify_config.PLUGIN_DAEMON_KEY

 T = TypeVar("T", bound=(BaseModel | dict | list | bool | str))

--- a/api/core/plugin/manager/tool.py
+++ b/api/core/plugin/manager/tool.py
@ -48,8 +48,10 @@ class PluginToolManager(BasePluginManager):
        tool_provider_id = GenericProviderID(provider)

        def transformer(json_response: dict[str, Any]) -> dict:
-            for tool in json_response.get("data", {}).get("declaration", {}).get("tools", []):
-                tool["identity"]["provider"] = tool_provider_id.provider_name
+            data = json_response.get("data")
+            if data:
+                for tool in data.get("declaration", {}).get("tools", []):
+                    tool["identity"]["provider"] = tool_provider_id.provider_name

            return json_response

--- a/api/core/provider_manager.py
+++ b/api/core/provider_manager.py
@ -23,8 +23,14 @@ from core.helper import encrypter
 from core.helper.model_provider_cache import ProviderCredentialsCache, ProviderCredentialsCacheType
 from core.helper.position_helper import is_filtered
 from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.entities.provider_entities import CredentialFormSchema, FormType, ProviderEntity
+from core.model_runtime.entities.provider_entities import (
+    ConfigurateMethod,
+    CredentialFormSchema,
+    FormType,
+    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
@ -186,7 +192,7 @@ 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
@ -839,11 +845,18 @@ class ProviderManager:
        :return:
        """
        # Get provider model credential secret variables
-        model_credential_secret_variables = self._extract_secret_variables(
-            provider_entity.model_credential_schema.credential_form_schemas
-            if provider_entity.model_credential_schema
-            else []
-        )
+        if ConfigurateMethod.PREDEFINED_MODEL in provider_entity.configurate_methods:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.provider_credential_schema.credential_form_schemas
+                if provider_entity.provider_credential_schema
+                else []
+            )
+        else:
+            model_credential_secret_variables = self._extract_secret_variables(
+                provider_entity.model_credential_schema.credential_form_schemas
+                if provider_entity.model_credential_schema
+                else []
+            )

        model_settings: list[ModelSettings] = []
        if not provider_model_settings:
--- a/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py
+++ b/api/core/rag/datasource/vdb/lindorm/lindorm_vector.py
@ -174,7 +174,7 @@ class LindormVectorStore(BaseVector):
            if self._using_ugc:
                params["routing"] = self._routing
            response = self._client.search(index=self._collection_name, body=query, params=params)
-        except Exception as e:
+        except Exception:
            logger.exception(f"Error executing vector search, query: {query}")
            raise

@ -258,7 +258,7 @@ class LindormVectorStore(BaseVector):
            hnsw_ef_construction = kwargs.pop("hnsw_ef_construction", 500)
            ivfpq_m = kwargs.pop("ivfpq_m", dimension)
            nlist = kwargs.pop("nlist", 1000)
-            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", True if nlist >= 5000 else False)
+            centroids_use_hnsw = kwargs.pop("centroids_use_hnsw", nlist >= 5000)
            centroids_hnsw_m = kwargs.pop("centroids_hnsw_m", 24)
            centroids_hnsw_ef_construct = kwargs.pop("centroids_hnsw_ef_construct", 500)
            centroids_hnsw_ef_search = kwargs.pop("centroids_hnsw_ef_search", 100)
@ -305,7 +305,7 @@ def default_text_mapping(dimension: int, method_name: str, **kwargs: Any) -> dic
    if method_name == "ivfpq":
        ivfpq_m = kwargs["ivfpq_m"]
        nlist = kwargs["nlist"]
-        centroids_use_hnsw = True if nlist > 10000 else False
+        centroids_use_hnsw = nlist > 10000
        centroids_hnsw_m = 24
        centroids_hnsw_ef_construct = 500
        centroids_hnsw_ef_search = 100
@ -347,7 +347,8 @@ def default_text_mapping(dimension: int, method_name: str, **kwargs: Any) -> dic
    }

    if excludes_from_source:
-        mapping["mappings"]["_source"] = {"excludes": excludes_from_source}  # e.g. {"excludes": ["vector_field"]}
+        # e.g. {"excludes": ["vector_field"]}
+        mapping["mappings"]["_source"] = {"excludes": excludes_from_source}

    if using_ugc and method_name == "ivfpq":
        mapping["settings"]["index"]["knn_routing"] = True
--- a/api/core/rag/datasource/vdb/pgvector/pgvector.py
+++ b/api/core/rag/datasource/vdb/pgvector/pgvector.py
@ -57,6 +57,11 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 ) using heap;
 """

+SQL_CREATE_INDEX = """
+CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} 
+USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
+"""
+

 class PGVector(BaseVector):
    def __init__(self, collection_name: str, config: PGVectorConfig):
@ -205,7 +210,10 @@ class PGVector(BaseVector):
            with self._get_cursor() as cur:
                cur.execute("CREATE EXTENSION IF NOT EXISTS vector")
                cur.execute(SQL_CREATE_TABLE.format(table_name=self.table_name, dimension=dimension))
-                # TODO: create index https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                # PG hnsw index only support 2000 dimension or less
+                # ref: https://github.com/pgvector/pgvector?tab=readme-ov-file#indexing
+                if dimension <= 2000:
+                    cur.execute(SQL_CREATE_INDEX.format(table_name=self.table_name))
            redis_client.set(collection_exist_cache_key, 1, ex=3600)


--- a/api/core/rag/embedding/cached_embedding.py
+++ b/api/core/rag/embedding/cached_embedding.py
@ -74,7 +74,7 @@ class CacheEmbedding(Embeddings):
                            embedding_queue_embeddings.append(normalized_embedding)
                        except IntegrityError:
                            db.session.rollback()
-                        except Exception as e:
+                        except Exception:
                            logging.exception("Failed transform embedding")
                cache_embeddings = []
                try:
--- a/api/core/rag/extractor/firecrawl/firecrawl_app.py
+++ b/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}")
--- a/api/core/rag/extractor/firecrawl/firecrawl_web_extractor.py
+++ b/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
--- a/api/core/rag/extractor/notion_extractor.py
+++ b/api/core/rag/extractor/notion_extractor.py
@ -358,8 +358,7 @@ class NotionExtractor(BaseExtractor):

        if not data_source_binding:
            raise Exception(
-                f"No notion data source binding found for tenant {tenant_id} "
-                f"and notion workspace {notion_workspace_id}"
+                f"No notion data source binding found for tenant {tenant_id} and notion workspace {notion_workspace_id}"
            )

        return cast(str, data_source_binding.access_token)
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
zxhlyh	3d9c8d76b9	fix: version check	2025-02-13 14:44:24 +08:00
非法操作	9ac6662635	fix: agent thought not saved (#13631 )	2025-02-13 10:17:39 +08:00
Yeuoly	316c418a01	fix: unexpected None embedding model provdier (#13610 )	2025-02-12 18:40:15 +08:00
Yeuoly	4886e5ae96	feat: add Dify-Hook-Url to endpoint headers (#13602 )	2025-02-12 17:38:56 +08:00
Yeuoly	7f4a8b955d	fix: convert provider_id to plugin_provider_id in get_configurations (#13596 )	2025-02-12 16:42:03 +08:00
zxhlyh	83d0142641	fix: refresh after install plugin (#13593 )	2025-02-12 15:51:55 +08:00
Yeuoly	56c7f49625	fix: add langgenius to list tool api (#13578 )	2025-02-12 15:37:10 +08:00
Yeuoly	7c1d842cfe	(1.0) fix: invalid default model provider (#13572 )	2025-02-12 14:21:58 +08:00
KVOJJJin	2ea3b64a45	Feat: tool setting support variable (#13465 ) Co-authored-by: zxhlyh <jasonapring2015@outlook.com>	2025-02-12 12:54:10 +08:00
Joel	824f8d8994	chore: add debug doc link (#13537 )	2025-02-11 18:32:01 +08:00
Joel	31c17e6378	fix: installed plugin not show upgrade (#13523 )	2025-02-11 14:08:43 +08:00
Yeuoly	50cfb7c9ec	fix: allow variable message to be any (#13494 )	2025-02-10 21:13:28 +08:00
Joel	8281c688ca	fix: iteration open parallel not show iteration detail (#13476 )	2025-02-10 16:05:05 +08:00
Yi Xiao	ad9d6eb5f4	fix app detail panel merge issues (#13460 )	2025-02-10 14:24:48 +08:00
zxhlyh	aa3dc9002c	fix: workflow chat preview (#13455 )	2025-02-10 11:15:56 +08:00
Yeuoly	4a43e165fb	Plugin/merge main 20250208 (#13414 ) Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: -LAN- <laipz8200@outlook.com> Signed-off-by: xhe <xw897002528@gmail.com> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com> Co-authored-by: NFish <douxc512@gmail.com> Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com> Co-authored-by: eux <euxuuu@gmail.com> Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com> Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com> Co-authored-by: lotsik <lotsik@mail.ru> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Co-authored-by: nite-knite <nkCoding@gmail.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com> Co-authored-by: CN-P5 <heibai2006@gmail.com> Co-authored-by: CN-P5 <heibai2006@qq.com> Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: Boris Feld <lothiraldan@gmail.com> Co-authored-by: mbo <himabo@gmail.com> Co-authored-by: mabo <mabo@aeyes.ai> Co-authored-by: Warren Chen <warren.chen830@gmail.com> Co-authored-by: KVOJJJin <jzongcode@gmail.com> Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com> Co-authored-by: jiandanfeng <chenjh3@wangsu.com> Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com> Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com> Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com> Co-authored-by: Xu Song <xusong.vip@gmail.com> Co-authored-by: rayshaw001 <396301947@163.com> Co-authored-by: Ding Jiatong <dingjiatong@gmail.com> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: JasonVV <jasonwangiii@outlook.com> Co-authored-by: le0zh <newlight@qq.com> Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com> Co-authored-by: k-zaku <zaku99@outlook.jp> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: luckylhb90 <luckylhb90@gmail.com> Co-authored-by: hobo.l <hobo.l@binance.com> Co-authored-by: jiangbo721 <365065261@qq.com> Co-authored-by: 刘江波 <jiangbo721@163.com> Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com> Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: sino <sino2322@gmail.com> Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com> Co-authored-by: lowell <lowell.hu@zkteco.in> Co-authored-by: Ademílson Tonato <ademilsonft@outlook.com> Co-authored-by: Ademílson Tonato <ademilson.tonato@refurbed.com> Co-authored-by: IWAI, Masaharu <iwaim.sub@gmail.com> Co-authored-by: Yueh-Po Peng (Yabi) <94939112+y10ab1@users.noreply.github.com> Co-authored-by: 非法操作 <hjlarry@163.com> Co-authored-by: Jason <ggbbddjm@gmail.com> Co-authored-by: Xin Zhang <sjhpzx@gmail.com> Co-authored-by: yjc980121 <3898524+yjc980121@users.noreply.github.com> Co-authored-by: heyszt <36215648+hieheihei@users.noreply.github.com> Co-authored-by: Abdullah AlOsaimi <osaimiacc@gmail.com> Co-authored-by: Abdullah AlOsaimi <189027247+osaimi@users.noreply.github.com> Co-authored-by: Yingchun Lai <laiyingchun@apache.org> Co-authored-by: Hash Brown <hi@xzd.me> Co-authored-by: zuodongxu <192560071+zuodongxu@users.noreply.github.com> Co-authored-by: Masashi Tomooka <tmokmss@users.noreply.github.com> Co-authored-by: aplio <ryo.091219@gmail.com> Co-authored-by: Obada Khalili <54270856+obadakhalili@users.noreply.github.com> Co-authored-by: Nam Vu <zuzoovn@gmail.com> Co-authored-by: Kei YAMAZAKI <1715090+kei-yamazaki@users.noreply.github.com> Co-authored-by: TechnoHouse <13776377+deephbz@users.noreply.github.com> Co-authored-by: Riddhimaan-Senapati <114703025+Riddhimaan-Senapati@users.noreply.github.com> Co-authored-by: MaFee921 <31881301+2284730142@users.noreply.github.com> Co-authored-by: te-chan <t-nakanome@sakura-is.co.jp> Co-authored-by: HQidea <HQidea@users.noreply.github.com> Co-authored-by: Joshbly <36315710+Joshbly@users.noreply.github.com> Co-authored-by: xhe <xw897002528@gmail.com> Co-authored-by: weiwenyan-dev <154779315+weiwenyan-dev@users.noreply.github.com> Co-authored-by: ex_wenyan.wei <ex_wenyan.wei@tcl.com> Co-authored-by: engchina <12236799+engchina@users.noreply.github.com> Co-authored-by: engchina <atjapan2015@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: 呆萌闷油瓶 <253605712@qq.com> Co-authored-by: Kemal <kemalmeler@outlook.com> Co-authored-by: Lazy_Frog <4590648+lazyFrogLOL@users.noreply.github.com> Co-authored-by: Novice Lee <novicelee@NoviPro.local> Co-authored-by: Yi Xiao <54782454+YIXIAO0@users.noreply.github.com> Co-authored-by: Steven sun <98230804+Tuyohai@users.noreply.github.com> Co-authored-by: steven <sunzwj@digitalchina.com> Co-authored-by: Kalo Chin <91766386+fdb02983rhy@users.noreply.github.com> Co-authored-by: Katy Tao <34019945+KatyTao@users.noreply.github.com> Co-authored-by: depy <42985524+h4ckdepy@users.noreply.github.com> Co-authored-by: 胡春东 <gycm520@gmail.com> Co-authored-by: Junjie.M <118170653@qq.com>	2025-02-08 19:12:36 +08:00
zxhlyh	4d25b598f9	fix: template app check dependency (#13389 )	2025-02-08 14:11:20 +08:00
Joel	3e9c3d0bb7	fix: install installed plugin problem (#13384 )	2025-02-08 11:31:55 +08:00
zxhlyh	fec3bb4469	fix: models sort in model page (#13334 )	2025-02-07 17:30:04 +08:00
Jyong	d4a09805a3	improve preview document tokenizer (#13328 )	2025-02-07 16:08:25 +08:00
zxhlyh	7e1d9894fb	fix: plugins task permission (#13330 )	2025-02-07 16:02:12 +08:00
zxhlyh	a8a8a5513c	fix: app check dependency (#13320 )	2025-02-07 14:04:49 +08:00
Nite Knite	470e72c820	chore: bump katex version and tweak UI copy (#13280 )	2025-02-07 14:02:57 +08:00
Boris Polonsky	beebba0340	Unify plugin endpoint configuration for api and worker: An alternative solution to PR #13214 (#13239 )	2025-02-06 11:29:37 +08:00
Yeuoly	4e27d82d68	improve: remove docker-legacy (#13236 )	2025-02-05 20:28:02 +08:00
Boris Polonsky	cdeaf3f70b	Fix ruff linting error caused by `api/models/dataset.py` (#13221 )	2025-02-05 17:45:23 +08:00
Yeuoly	24839bb3e1	fix: mismatches dependencies in dockerfile (#13220 )	2025-02-05 17:00:26 +08:00
KVOJJJin	1650dbfbb1	Fix: merge error of tracing and web app setting modal (#13219 )	2025-02-05 16:16:28 +08:00
Joel	fd11817044	fix: select input not show save value (#13218 )	2025-02-05 16:13:40 +08:00
Wu Tianwei	6642fc6012	fix: fix fallback route logic (#13199 )	2025-02-05 14:38:36 +08:00
KVOJJJin	2710242982	Feat: feature and log dark mode (#13208 )	2025-02-05 13:58:19 +08:00
kurokobo	1de84fdda0	fix: correct env vars for docker deployment (#13055 )	2025-01-27 11:19:29 +08:00
Wu Tianwei	3befbc1d68	feat: docx image preview (#13057 )	2025-01-26 15:12:05 +08:00
Jyong	62c413aca5	add sign-content (#13050 )	2025-01-26 10:58:47 +08:00
Joel	6887b501b8	fix: can choose selected tools and show tool name instead of label (#13025 )	2025-01-24 22:34:09 +08:00
非法操作	f93bf131ab	fix(1.0): explore market page empty (#13017 )	2025-01-24 18:43:56 +08:00
非法操作	ef1f429437	fix(1.0): update github plugin 404 (#13014 )	2025-01-24 18:42:14 +08:00
KVOJJJin	c966bf1474	Feat: dark mode of app configure (#13010 )	2025-01-24 14:16:35 +08:00
Yeuoly	899df30bf6	Plugin/merge main to plugin/beta 20250122 (#12962 ) Signed-off-by: yihong0618 <zouzou0208@gmail.com> Signed-off-by: -LAN- <laipz8200@outlook.com> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com> Co-authored-by: NFish <douxc512@gmail.com> Co-authored-by: Gen Sato <52241300+halogen22@users.noreply.github.com> Co-authored-by: eux <euxuuu@gmail.com> Co-authored-by: huangzhuo1949 <167434202+huangzhuo1949@users.noreply.github.com> Co-authored-by: huangzhuo <huangzhuo1@xiaomi.com> Co-authored-by: lotsik <lotsik@mail.ru> Co-authored-by: crazywoola <100913391+crazywoola@users.noreply.github.com> Co-authored-by: Wu Tianwei <30284043+WTW0313@users.noreply.github.com> Co-authored-by: nite-knite <nkCoding@gmail.com> Co-authored-by: Jyong <76649700+JohnJyong@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: gakkiyomi <gakkiyomi@aliyun.com> Co-authored-by: CN-P5 <heibai2006@gmail.com> Co-authored-by: CN-P5 <heibai2006@qq.com> Co-authored-by: Chuehnone <1897025+chuehnone@users.noreply.github.com> Co-authored-by: yihong <zouzou0208@gmail.com> Co-authored-by: Kevin9703 <51311316+Kevin9703@users.noreply.github.com> Co-authored-by: -LAN- <laipz8200@outlook.com> Co-authored-by: Boris Feld <lothiraldan@gmail.com> Co-authored-by: mbo <himabo@gmail.com> Co-authored-by: mabo <mabo@aeyes.ai> Co-authored-by: Warren Chen <warren.chen830@gmail.com> Co-authored-by: KVOJJJin <jzongcode@gmail.com> Co-authored-by: JzoNgKVO <27049666+JzoNgKVO@users.noreply.github.com> Co-authored-by: jiandanfeng <chenjh3@wangsu.com> Co-authored-by: zhu-an <70234959+xhdd123321@users.noreply.github.com> Co-authored-by: zhaoqingyu.1075 <zhaoqingyu.1075@bytedance.com> Co-authored-by: 海狸大師 <86974027+yenslife@users.noreply.github.com> Co-authored-by: Xu Song <xusong.vip@gmail.com> Co-authored-by: rayshaw001 <396301947@163.com> Co-authored-by: Ding Jiatong <dingjiatong@gmail.com> Co-authored-by: Bowen Liang <liangbowen@gf.com.cn> Co-authored-by: JasonVV <jasonwangiii@outlook.com> Co-authored-by: le0zh <newlight@qq.com> Co-authored-by: zhuxinliang <zhuxinliang@didiglobal.com> Co-authored-by: k-zaku <zaku99@outlook.jp> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: luckylhb90 <luckylhb90@gmail.com> Co-authored-by: hobo.l <hobo.l@binance.com> Co-authored-by: jiangbo721 <365065261@qq.com> Co-authored-by: 刘江波 <jiangbo721@163.com> Co-authored-by: Shun Miyazawa <34241526+miya@users.noreply.github.com> Co-authored-by: EricPan <30651140+Egfly@users.noreply.github.com> Co-authored-by: crazywoola <427733928@qq.com> Co-authored-by: zxhlyh <jasonapring2015@outlook.com> Co-authored-by: sino <sino2322@gmail.com> Co-authored-by: Jhvcc <37662342+Jhvcc@users.noreply.github.com> Co-authored-by: lowell <lowell.hu@zkteco.in>	2025-01-23 14:48:16 +08:00
zxhlyh	8d8d3e3f2f	fix: plugin search api url (#12977 )	2025-01-23 14:25:24 +08:00
非法操作	5f0fa38ec6	fix(1.0): invoke llm raise error (#12753 )	2025-01-22 16:46:35 +08:00
Yeuoly	cc1fe70d34	fix: add adapter for datasets update checking (#12939 )	2025-01-22 15:40:06 +08:00
Hiroki Nagai	15ee1e11be	fix: 500 error in Notion integration API (#12934 )	2025-01-22 14:38:01 +08:00
Joel	c8b4a76530	fix: agent node output vars error (#12931 )	2025-01-22 13:33:27 +08:00
Yeuoly	6ee4eba86b	fix: change default PLUGIN_DAEMON_URL to http://localhost:5002 (#12915 )	2025-01-21 22:30:24 +08:00
非法操作	357d2e8be8	fix(1.0): add cross-env to pnpm run dev (#12600 )	2025-01-21 19:51:32 +08:00
kurokobo	b5accda3fe	fix: correct validation for agent node which is invoked before publishing the app (#12805 )	2025-01-21 10:07:25 +08:00
非法操作	de4752a16b	fix(1.0): unexpected error raise (#12812 )	2025-01-21 10:04:56 +08:00
非法操作	60427f1adf	chore(1.0): improve some environment variables (#12814 )	2025-01-21 10:04:46 +08:00
非法操作	1a313c868d	fix(1.0): sometimes add tool raise error (#12821 )	2025-01-21 10:04:05 +08:00
Yeuoly	0b32b1988f	fix: missing tenant_id in get_signed_file_url_for_plugin (#12734 )	2025-01-14 19:39:21 +08:00
KVOJJJin	e56c051d97	Fix: tool card info (#12726 )	2025-01-14 16:10:00 +08:00
Joel	0a6b4d01d7	fix: save tool not add type (#12712 )	2025-01-14 10:28:41 +08:00
Novice	98b139c680	feat: add agent strategy on node start (#12667 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-01-13 13:04:05 +08:00
zxhlyh	f0a3c14adb	fix: plugins task (#12662 )	2025-01-13 10:59:34 +08:00
Yeuoly	51947575c2	feat: add skip signature verification (#12627 )	2025-01-10 20:37:33 +08:00
Yeuoly	cb8debee3e	Plugins/fix backend ci errors (#12615 )	2025-01-10 19:46:59 +08:00
zxhlyh	d56079a549	fix: marketplace card i18n (#12623 )	2025-01-10 18:15:58 +08:00
zxhlyh	c08b451874	fix: marketplace page list style (#12613 )	2025-01-10 17:31:09 +08:00
非法操作	ac336ff359	fix(1.0): add missing environment variable (#12599 )	2025-01-10 17:17:13 +08:00
Joel	4cbd511cd7	fix: ci use pnpm error (#12597 )	2025-01-10 16:55:16 +08:00
Yeuoly	c03adcb154	Fix: style checks and unittests (#12603 )	2025-01-10 16:40:39 +08:00
Hiroshi Fujita	04dade2f9b	fix: update fetchReleases to use owner and repo from meta (#12590 )	2025-01-10 15:46:10 +08:00
kurokobo	f69220ca96	fix: add location directive for /explore (#12572 )	2025-01-10 15:42:32 +08:00
Wu Tianwei	a5e24ff6d3	fix: update language change handling in I18n component (#12596 ) ok	2025-01-10 14:47:24 +08:00
zxhlyh	71976f9192	fix: marketplace serach bundle (#12581 )	2025-01-10 14:03:00 +08:00
Joel	39ec6c8025	Fix/setting model page crash (#12594 ) Co-authored-by: JzoNg <jzongcode@gmail.com>	2025-01-10 13:10:58 +08:00
NFish	e370045ac4	Fix:screenshots image missed (#12589 )	2025-01-10 11:47:20 +08:00
Yeuoly	28edbbac0b	Plugins/bump to 1.0.0 beta.1 (#12568 )	2025-01-09 22:46:24 +08:00
Yeuoly	782abcecd8	bump version to 1.0.0-beta.1 (#12567 )	2025-01-09 22:38:20 +08:00
Yeuoly	4deb02fc2c	fix: rename plugin db name to dify_plugin (#12565 )	2025-01-09 21:56:24 +08:00
Joel	f967180dc2	fix: not show stragry type (#12561 )	2025-01-09 20:55:17 +08:00
Yeuoly	cead13cbc3	plugins: remove middleware.1.yaml (#12559 )	2025-01-09 20:34:49 +08:00
Yeuoly	078c151065	fix: add-default-console-url (#12558 )	2025-01-09 20:34:13 +08:00
Yeuoly	17babca362	Introducing: Plugin Mechanism (#12553 )	2025-01-09 19:54:17 +08:00
AkaraChen	8efed8858c	feat: reset parameters when switch agent strategy (#12549 )	2025-01-09 19:31:02 +08:00
Yeuoly	0d411a0b5a	feat: refactor docker-compose (#12550 )	2025-01-09 19:08:11 +08:00
Yeuoly	13f0c01f93	feat: add ci checks to plugins/beta branch (#12542 ) Co-authored-by: Novice Lee <novicelee@NoviPro.local>	2025-01-09 18:57:09 +08:00
zxhlyh	3c014f3ae5	Feat/plugins (#12547 ) Co-authored-by: AkaraChen <akarachen@outlook.com> Co-authored-by: Yi <yxiaoisme@gmail.com> Co-authored-by: Joel <iamjoel007@gmail.com> Co-authored-by: JzoNg <jzongcode@gmail.com> Co-authored-by: twwu <twwu@dify.ai> Co-authored-by: kurokobo <kuro664@gmail.com> Co-authored-by: Hiroshi Fujita <fujita-h@users.noreply.github.com>	2025-01-09 18:47:41 +08:00
Yeuoly	e4c4490175	refactor	2025-01-09 17:27:05 +08:00