V4.9.6 feature (#4565)

* Dashboard submenu (#4545)

* add app submenu (#4452)

* add app submenu

* fix

* width & i18n

* optimize submenu code (#4515)

* optimize submenu code

* fix

* fix

* fix

* fix ts

* perf: dashboard sub menu

* doc

---------

Co-authored-by: heheer <heheer@sealos.io>

* feat: value format test

* doc

* Mcp export (#4555)

* feat: mcp server

* feat: mcp server

* feat: mcp server build

* update doc

* perf: path selector (#4556)

* perf: path selector

* fix: docker file path

* perf: add image endpoint to dataset search (#4557)

* perf: add image endpoint to dataset search

* fix: mcp_server url

* human in loop (#4558)

* Support interactive nodes for loops, and enhance the function of merging nested and loop node history messages. (#4552)

* feat: add LoopInteractive definition

* feat: Support LoopInteractive type and update related logic

* fix: Refactor loop handling logic and improve output value initialization

* feat: Add mergeSignId to dispatchLoop and dispatchRunAppNode responses

* feat: Enhance mergeChatResponseData to recursively merge plugin details and improve response handling

* refactor: Remove redundant comments in mergeChatResponseData for clarity

* perf: loop interactive

* perf: human in loop

---------

Co-authored-by: Theresa <63280168+sd0ric4@users.noreply.github.com>

* mcp server ui

* integrate mcp (#4549)

* integrate mcp

* delete unused code

* fix ts

* bug fix

* fix

* support whole mcp tools

* add try catch

* fix

* fix

* fix ts

* fix test

* fix ts

* fix: interactive in v1 completions

* doc

* fix: router path

* fix mcp integrate (#4563)

* fix mcp integrate

* fix ui

* fix: mcp ux

* feat: mcp call title

* remove repeat loading

* fix mcp tools avatar (#4564)

* fix

* fix avatar

* fix update version

* update doc

* fix: value format

* close server and remove cache

* perf: avatar

---------

Co-authored-by: heheer <heheer@sealos.io>
Co-authored-by: Theresa <63280168+sd0ric4@users.noreply.github.com>

.github/doc-sync-image.yml

@@ -1,4 +1,4 @@
 yangchuansheng/fastgpt-imgs:
   - source: docSite/assets/imgs/
     dest: imgs/
-    deleteOrphaned: true
+    deleteOrphaned: true

.github/gh-bot.yml

@@ -1,30 +0,0 @@
-version: v1
-debug: true
-action:
-  printConfig: false
-  release:
-    retry: 15s
-    actionName: Release
-    allowOps:
-      - cuisongliu
-bot:
-  prefix: /
-  spe: _
-  allowOps:
-    - sealos-ci-robot
-    - sealos-release-robot
-  email: sealos-ci-robot@sealos.io
-  username: sealos-ci-robot
-repo:
-  org: false
-
-message:
-  success: |
-    🤖 says: Hooray! The action {{.Body}} has been completed successfully. 🎉
-  format_error: |
-    🤖 says: ‼️ There is a formatting issue with the action, kindly verify the action's format.
-  permission_error: |
-    🤖 says: ‼️ The action doesn't have permission to trigger.
-  release_error: |
-    🤖 says: ‼️ Release action failed.
-    Error details: {{.Error}}

.github/workflows/docs-deploy-cf.yml

@@ -1,4 +1,4 @@
-name: Deploy doc image to vercel
+name: Deploy doc image to cf
 
 on:
   workflow_dispatch:
@@ -18,7 +18,12 @@ jobs:
       url: ${{ steps.vercel-action.outputs.preview-url }}
 
     # The type of runner that the job will run on
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
+
+    permissions:
+      contents: write
+    concurrency:
+      group: ${{ github.workflow }}-${{ github.ref }}
 
     # Job outputs
     outputs:
@@ -58,20 +63,9 @@ jobs:
       - name: Build
         run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs@6d0568e && hugo -v --minify
 
-      # Step 5 - Push our generated site to Vercel
-      - name: Deploy to Vercel
-        uses: amondnet/vercel-action@v25
-        id: vercel-action
-        with:
-          vercel-token: ${{ secrets.VERCEL_TOKEN }} # Required
-          vercel-org-id: ${{ secrets.VERCEL_ORG_ID }} #Required
-          vercel-project-id: ${{ secrets.VERCEL_PROJECT_ID }} #Required
-          github-comment: false
-          vercel-args: '--prod --local-config ../vercel.json' # Optional
-          working-directory: docSite/public
-
       - name: Deploy to GitHub Pages
-        uses: peaceiris/actions-gh-pages@v3
+        uses: peaceiris/actions-gh-pages@v4
+        if: github.ref == 'refs/heads/main'
         with:
-          github_token: ${{ secrets.GH_PAT }}
+          github_token: ${{ secrets.GITHUB_TOKEN }}
           publish_dir: docSite/public

.github/workflows/docs-deploy-kubeconfig.yml

@@ -10,6 +10,13 @@ on:
 jobs:
   build-fastgpt-docs-images:
     runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -27,7 +34,6 @@ jobs:
         with:
           # list of Docker images to use as base name for tags
           images: |
-            ${{ secrets.DOCKER_HUB_NAME }}/fastgpt-docs
             ghcr.io/${{ github.repository_owner }}/fastgpt-docs
             registry.cn-hangzhou.aliyuncs.com/${{ secrets.ALI_HUB_USERNAME }}/fastgpt-docs
           tags: |
@@ -40,18 +46,12 @@ jobs:
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3
 
-      - name: Login to DockerHub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKER_HUB_NAME }}
-          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
-
       - name: Login to ghcr.io
         uses: docker/login-action@v3
         with:
           registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Login to Aliyun
         uses: docker/login-action@v3
@@ -70,9 +70,10 @@ jobs:
           labels: ${{ steps.meta.outputs.labels }}
     outputs:
       tags: ${{ steps.datetime.outputs.datetime }}
+
   update-docs-image:
     needs: build-fastgpt-docs-images
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     if: github.repository == 'labring/FastGPT'
     steps:
       - name: Checkout code

.github/workflows/docs-preview.yml

@@ -10,13 +10,19 @@ on:
 jobs:
   # This workflow contains jobs "deploy-production"
   deploy-preview:
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+      pull-requests: write
     # The environment this job references
     environment:
       name: Preview
       url: ${{ steps.vercel-action.outputs.preview-url }}
 
     # The type of runner that the job will run on
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
 
     # Job outputs
     outputs:
@@ -32,6 +38,7 @@ jobs:
           repository: ${{ github.event.pull_request.head.repo.full_name }}
           submodules: recursive # Fetch submodules
           fetch-depth: 0 # Fetch all history for .GitInfo and .Lastmod
+          token: ${{ secrets.GITHUB_TOKEN }}
 
       # Step 2 Detect changes to Docs Content
       - name: Detect changes in doc content
@@ -43,10 +50,6 @@ jobs:
               - 'docSite/content/docs/**'
           base: main
 
-      - name: Add cdn for images
-        run: |
-          sed -i "s#\](/imgs/#\](https://cdn.jsdelivr.net/gh/yangchuansheng/fastgpt-imgs@main/imgs/#g" $(grep -rl "\](/imgs/" docSite/content/zh-cn/docs)
-
       # Step 3 - Install Hugo (specific version)
       - name: Install Hugo
         uses: peaceiris/actions-hugo@v2
@@ -58,39 +61,35 @@ jobs:
       - name: Build
         run: cd docSite && hugo mod get -u github.com/colinwilson/lotusdocs@6d0568e && hugo -v --minify
 
-      # Step 5 - Push our generated site to Vercel
-      - name: Deploy to Vercel
-        uses: amondnet/vercel-action@v25
-        id: vercel-action
+      # Step 5 - Push our generated site to Cloudflare
+      - name: Deploy to Cloudflare Pages
+        id: deploy
+        uses: cloudflare/wrangler-action@v3
         with:
-          vercel-token: ${{ secrets.VERCEL_TOKEN }} # Required
-          vercel-org-id: ${{ secrets.VERCEL_ORG_ID }} #Required
-          vercel-project-id: ${{ secrets.VERCEL_PROJECT_ID }} #Required
-          github-comment: false
-          vercel-args: '--local-config ../vercel.json' # Optional
-          working-directory: docSite/public
-          alias-domains: | #Optional
-            fastgpt-staging.vercel.app
-  docsOutput:
-    needs: [deploy-preview]
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v3
-        with:
-          ref: ${{ github.event.pull_request.head.ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-      - name: Write md
-        run: |
-          echo "# 🤖 Generated by deploy action" > report.md
-          echo "[👀 Visit Preview](${{ needs.deploy-preview.outputs.url }})" >> report.md
-          cat report.md
-      - name: Gh Rebot for Sealos
-        uses: labring/gh-rebot@v0.0.6
-        if: ${{ (github.event_name == 'pull_request_target') }}
-        with:
-          version: v0.0.6
+          apiToken: ${{ secrets.CLOUDFLARE_API_TOKEN }}
+          accountId: ${{ secrets.CLOUDFLARE_ACCOUNT_ID }}
+          command: pages deploy ./docSite/public --project-name=fastgpt-doc
+          packageManager: npm
+
+      - name: Create deployment status comment
+        if: always()
         env:
-          GH_TOKEN: '${{ secrets.GH_PAT }}'
-          SEALOS_TYPE: 'pr_comment'
-          SEALOS_FILENAME: 'report.md'
-          SEALOS_REPLACE_TAG: 'DEFAULT_REPLACE_DEPLOY'
+          JOB_STATUS: ${{ job.status }}
+          PREVIEW_URL: ${{ steps.deploy.outputs.deployment-url }}
+        uses: actions/github-script@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          script: |
+            const success = process.env.JOB_STATUS === 'success';
+            const deploymentUrl = `${process.env.PREVIEW_URL}`;
+            const status = success ? '✅ Success' : '❌ Failed';
+            console.log(process.env.JOB_STATUS);
+
+            const commentBody = `**Deployment Status: ${status}**
+            ${success ? `🔗 Preview URL: ${deploymentUrl}` : ''}`;
+
+            await github.rest.issues.createComment({
+              ...context.repo,
+              issue_number: context.payload.pull_request.number,
+              body: commentBody
+            });

.github/workflows/docs-sync_imgs.yml

@@ -1,6 +1,6 @@
 name: Sync images
 on:
-  pull_request_target:
+  pull_request:
     branches:
       - main
     paths:
@@ -15,13 +15,6 @@ jobs:
   sync:
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout
-        uses: actions/checkout@v3
-        if: ${{ (github.event_name == 'pull_request_target') }}
-        with:
-          ref: ${{ github.event.pull_request.head.ref }}
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-
       - name: Checkout
         uses: actions/checkout@v3
 
@@ -32,4 +25,4 @@ jobs:
           CONFIG_PATH: .github/sync_imgs.yml
           ORIGINAL_MESSAGE: true
           SKIP_PR: true
-          COMMIT_EACH_FILE: false
+          COMMIT_EACH_FILE: false

.github/workflows/fastgpt-build-image-personal.yml

@@ -9,7 +9,12 @@ on:
       - 'main'
 jobs:
   build-fastgpt-images:
-    runs-on: ubuntu-20.04
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    runs-on: ubuntu-24.04
     if: github.repository != 'labring/FastGPT'
     steps:
       - name: Checkout
@@ -32,7 +37,7 @@ jobs:
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
+          password: ${{ secrets.GITHUB_TOKEN }}
       - name: Set DOCKER_REPO_TAGGED based on branch or tag
         run: |
           echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt:latest" >> $GITHUB_ENV

.github/workflows/fastgpt-build-image.yml

@@ -1,258 +1,171 @@
 name: Build FastGPT images
+
 on:
   workflow_dispatch:
   push:
     paths:
-      - 'projects/app/**'
-      - 'packages/**'
+      - "projects/app/**"
+      - "packages/**"
     tags:
-      - 'v*'
+      - "v*"
+
 jobs:
   build-fastgpt-images:
-    runs-on: ubuntu-20.04
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    strategy:
+      matrix:
+        sub_routes:
+          - repo: fastgpt
+            base_url: ""
+          - repo: fastgpt-sub-route
+            base_url: "/fastai"
+          - repo: fastgpt-sub-route-gchat
+            base_url: "/gchat"
+        archs:
+          - arch: amd64
+          - arch: arm64
+            runs-on: ubuntu-24.04-arm
+    runs-on: ${{ matrix.archs.runs-on || 'ubuntu-24.04' }}
     steps:
       # install env
       - name: Checkout
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           fetch-depth: 1
-      - name: Install Dependencies
-        run: |
-          sudo apt update && sudo apt install -y nodejs npm
-      - name: Set up QEMU (optional)
-        uses: docker/setup-qemu-action@v2
+
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
         with:
           driver-opts: network=host
+
       - name: Cache Docker layers
         uses: actions/cache@v4
         with:
           path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          key: ${{ runner.os }}-${{ matrix.sub_routes.repo }}-buildx-${{ github.sha }}
           restore-keys: |
-            ${{ runner.os }}-buildx-
+            ${{ runner.os }}-${{ matrix.sub_routes.repo }}-buildx-
 
       # login docker
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
+          password: ${{ secrets.GITHUB_TOKEN }}
       - name: Login to Ali Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: registry.cn-hangzhou.aliyuncs.com
           username: ${{ secrets.ALI_HUB_USERNAME }}
           password: ${{ secrets.ALI_HUB_PASSWORD }}
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_NAME }}
           password: ${{ secrets.DOCKER_HUB_PASSWORD }}
 
-      # Set tag
-      - name: Set image name and tag
-        run: |
-          if [[ "${{ github.ref_name }}" == "main" ]]; then
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-          else
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt:latest" >> $GITHUB_ENV
-          fi
+      - name: Build for ${{ matrix.archs.arch }}
+        id: build
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: projects/app/Dockerfile
+          platforms: linux/${{ matrix.archs.arch }}
+          build-args: |
+            ${{ matrix.sub_routes.base_url && format('base_url={0}', matrix.sub_routes.base_url) || '' }}
+          labels: |
+            org.opencontainers.image.source=https://github.com/${{ github.repository }}
+            org.opencontainers.image.description=${{ matrix.sub_routes.repo }} image
+          outputs: type=image,"name=ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }},${{ secrets.ALI_IMAGE_NAME }}/${{ matrix.sub_routes.repo }},${{ secrets.DOCKER_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}",push-by-digest=true,push=true
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
 
-      - name: Build and publish image for main branch or tag push event
-        env:
-          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
+      - name: Export digest
         run: |
-          docker buildx build \
-          -f projects/app/Dockerfile \
-          --platform linux/amd64,linux/arm64 \
-          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
-          --label "org.opencontainers.image.description=fastgpt image" \
-          --push \
-          --cache-from=type=local,src=/tmp/.buildx-cache \
-          --cache-to=type=local,dest=/tmp/.buildx-cache \
-          -t ${Git_Tag} \
-          -t ${Git_Latest} \
-          -t ${Ali_Tag} \
-          -t ${Ali_Latest} \
-          -t ${Docker_Hub_Tag} \
-          -t ${Docker_Hub_Latest} \
-          .
-  build-fastgpt-images-sub-route:
-    runs-on: ubuntu-20.04
+          mkdir -p ${{ runner.temp }}/digests/${{ matrix.sub_routes.repo }}
+          digest="${{ steps.build.outputs.digest }}"
+          touch "${{ runner.temp }}/digests/${{ matrix.sub_routes.repo }}/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ matrix.sub_routes.repo }}-${{ github.sha }}-${{ matrix.archs.arch }}
+          path: ${{ runner.temp }}/digests/${{ matrix.sub_routes.repo }}/*
+          if-no-files-found: error
+          retention-days: 1
+
+  release-fastgpt-images:
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    needs: build-fastgpt-images
+    strategy:
+      matrix:
+        sub_routes:
+          - repo: fastgpt
+          - repo: fastgpt-sub-route
+          - repo: fastgpt-sub-route-gchat
+    runs-on: ubuntu-24.04
     steps:
-      # install env
-      - name: Checkout
-        uses: actions/checkout@v3
-        with:
-          fetch-depth: 1
-      - name: Install Dependencies
-        run: |
-          sudo apt update && sudo apt install -y nodejs npm
-      - name: Set up QEMU (optional)
-        uses: docker/setup-qemu-action@v2
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
-        with:
-          driver-opts: network=host
-      - name: Cache Docker layers
-        uses: actions/cache@v4
-        with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-
-
-      # login docker
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
+          password: ${{ secrets.GITHUB_TOKEN }}
       - name: Login to Ali Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: registry.cn-hangzhou.aliyuncs.com
           username: ${{ secrets.ALI_HUB_USERNAME }}
           password: ${{ secrets.ALI_HUB_PASSWORD }}
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_NAME }}
           password: ${{ secrets.DOCKER_HUB_PASSWORD }}
 
-      # Set tag
-      - name: Set image name and tag
-        run: |
-          if [[ "${{ github.ref_name }}" == "main" ]]; then
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-          else
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route:latest" >> $GITHUB_ENV
-          fi
-
-      - name: Build and publish image for main branch or tag push event
-        env:
-          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
-        run: |
-          docker buildx build \
-          -f projects/app/Dockerfile \
-          --platform linux/amd64,linux/arm64 \
-          --build-arg base_url=/fastai \
-          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
-          --label "org.opencontainers.image.description=fastgpt image" \
-          --push \
-          --cache-from=type=local,src=/tmp/.buildx-cache \
-          --cache-to=type=local,dest=/tmp/.buildx-cache \
-          -t ${Git_Tag} \
-          -t ${Git_Latest} \
-          -t ${Ali_Tag} \
-          -t ${Ali_Latest} \
-          -t ${Docker_Hub_Tag} \
-          -t ${Docker_Hub_Latest} \
-          .
-  build-fastgpt-images-sub-route-gchat:
-    runs-on: ubuntu-20.04
-    steps:
-      # install env
-      - name: Checkout
-        uses: actions/checkout@v3
+      - name: Download digests
+        uses: actions/download-artifact@v4
         with:
-          fetch-depth: 1
-      - name: Install Dependencies
-        run: |
-          sudo apt update && sudo apt install -y nodejs npm
-      - name: Set up QEMU (optional)
-        uses: docker/setup-qemu-action@v2
+          path: ${{ runner.temp }}/digests
+          pattern: digests-${{ matrix.sub_routes.repo }}-${{ github.sha }}-*
+          merge-multiple: true
+
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
-        with:
-          driver-opts: network=host
-      - name: Cache Docker layers
-        uses: actions/cache@v4
-        with:
-          path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
-          restore-keys: |
-            ${{ runner.os }}-buildx-
+        uses: docker/setup-buildx-action@v3
 
-      # login docker
-      - name: Login to GitHub Container Registry
-        uses: docker/login-action@v2
-        with:
-          registry: ghcr.io
-          username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
-      - name: Login to Ali Hub
-        uses: docker/login-action@v2
-        with:
-          registry: registry.cn-hangzhou.aliyuncs.com
-          username: ${{ secrets.ALI_HUB_USERNAME }}
-          password: ${{ secrets.ALI_HUB_PASSWORD }}
-      - name: Login to Docker Hub
-        uses: docker/login-action@v2
-        with:
-          username: ${{ secrets.DOCKER_HUB_NAME }}
-          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
-
-      # Set tag
       - name: Set image name and tag
         run: |
           if [[ "${{ github.ref_name }}" == "main" ]]; then
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
+            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
           else
-            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route-gchat:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route-gchat:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
-            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route-gchat:${{ github.ref_name }}" >> $GITHUB_ENV
-            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sub-route-gchat:latest" >> $GITHUB_ENV
+            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }}:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/${{ matrix.sub_routes.repo }}:latest" >> $GITHUB_ENV
           fi
 
-      - name: Build and publish image for main branch or tag push event
-        env:
-          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
+      - name: Create manifest list and push
+        working-directory: ${{ runner.temp }}/digests
         run: |
-          docker buildx build \
-          -f projects/app/Dockerfile \
-          --platform linux/amd64,linux/arm64 \
-          --build-arg base_url=/gchat \
-          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
-          --label "org.opencontainers.image.description=fastgpt-sub-route-gchat image" \
-          --push \
-          --cache-from=type=local,src=/tmp/.buildx-cache \
-          --cache-to=type=local,dest=/tmp/.buildx-cache \
-          -t ${Git_Tag} \
-          -t ${Git_Latest} \
-          -t ${Ali_Tag} \
-          -t ${Ali_Latest} \
-          -t ${Docker_Hub_Tag} \
-          -t ${Docker_Hub_Latest} \
-          .
+          TAGS="$(echo -e "${Git_Tag}\n${Git_Latest}\n${Ali_Tag}\n${Ali_Latest}\n${Docker_Hub_Tag}\n${Docker_Hub_Latest}")"
+          for TAG in $TAGS; do
+            docker buildx imagetools create -t $TAG \
+              $(printf 'ghcr.io/${{ github.repository_owner }}/${{ matrix.sub_routes.repo }}@sha256:%s ' *)
+            sleep 5
+          done

.github/workflows/fastgpt-preview-image.yml

@@ -5,63 +5,85 @@ on:
 
 jobs:
   preview-fastgpt-images:
-    runs-on: ubuntu-20.04
+    permissions:
+      contents: read
+      packages: write
+      attestations: write
+      id-token: write
+      pull-requests: write
+
+    runs-on: ubuntu-24.04
+    strategy:
+      matrix:
+        image: [fastgpt, sandbox, mcp_server]
+      fail-fast: false # 即使一个镜像构建失败，也继续构建其他镜像
+
     steps:
       - name: Checkout
         uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
-          submodules: recursive # Fetch submodules
-          fetch-depth: 0 # Fetch all history for .GitInfo and .Lastmod
+          fetch-depth: 0
+          token: ${{ secrets.GITHUB_TOKEN }}
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v2
         with:
           driver-opts: network=host
+
       - name: Cache Docker layers
         uses: actions/cache@v3
         with:
           path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          key: ${{ runner.os }}-buildx-${{ github.sha }}-${{ matrix.image }}
           restore-keys: |
+            ${{ runner.os }}-buildx-${{ github.sha }}-
             ${{ runner.os }}-buildx-
+
       - name: Login to GitHub Container Registry
         uses: docker/login-action@v2
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
-      - name: Set DOCKER_REPO_TAGGED based on branch or tag
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Set image config
+        id: config
         run: |
-          echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:${{ github.event.pull_request.head.sha }}" >> $GITHUB_ENV
-      - name: Build image for PR
-        env:
-          DOCKER_REPO_TAGGED: ${{ env.DOCKER_REPO_TAGGED }}
+          if [[ "${{ matrix.image }}" == "fastgpt" ]]; then
+            echo "DOCKERFILE=projects/app/Dockerfile" >> $GITHUB_OUTPUT
+            echo "DESCRIPTION=fastgpt-pr image" >> $GITHUB_OUTPUT
+            echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:fatsgpt_${{ github.event.pull_request.head.sha }}" >> $GITHUB_OUTPUT
+          elif [[ "${{ matrix.image }}" == "sandbox" ]]; then
+            echo "DOCKERFILE=projects/sandbox/Dockerfile" >> $GITHUB_OUTPUT
+            echo "DESCRIPTION=fastgpt-sandbox-pr image" >> $GITHUB_OUTPUT
+            echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:fatsgpt_sandbox_${{ github.event.pull_request.head.sha }}" >> $GITHUB_OUTPUT
+          elif [[ "${{ matrix.image }}" == "mcp_server" ]]; then
+            echo "DOCKERFILE=projects/mcp_server/Dockerfile" >> $GITHUB_OUTPUT
+            echo "DESCRIPTION=fastgpt-mcp_server-pr image" >> $GITHUB_OUTPUT
+            echo "DOCKER_REPO_TAGGED=ghcr.io/${{ github.repository_owner }}/fastgpt-pr:fatsgpt_mcp_server_${{ github.event.pull_request.head.sha }}" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Build ${{ matrix.image }} image for PR
         run: |
           docker buildx build \
-          -f projects/app/Dockerfile \
+          -f ${{ steps.config.outputs.DOCKERFILE }} \
           --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/FastGPT" \
-          --label "org.opencontainers.image.description=fastgpt-pr image" \
-          --label "org.opencontainers.image.licenses=Apache" \
+          --label "org.opencontainers.image.description=${{ steps.config.outputs.DESCRIPTION }}" \
           --push \
           --cache-from=type=local,src=/tmp/.buildx-cache \
           --cache-to=type=local,dest=/tmp/.buildx-cache \
-          -t ${DOCKER_REPO_TAGGED} \
+          -t ${{ steps.config.outputs.DOCKER_REPO_TAGGED }} \
           .
-      # Add write md step after build
-      - name: Write md
-        run: |
-          echo "# 🤖 Generated by deploy action" > report.md
-          echo "📦 Preview Image: \`${DOCKER_REPO_TAGGED}\`" >> report.md
-          cat report.md
 
-      - name: Gh Rebot for Sealos
-        uses: labring/gh-rebot@v0.0.6
-        if: ${{ (github.event_name == 'pull_request_target') }}
+      - uses: actions/github-script@v7
         with:
-          version: v0.0.6
-        env:
-          GH_TOKEN: '${{ secrets.GH_PAT }}'
-          SEALOS_TYPE: 'pr_comment'
-          SEALOS_FILENAME: 'report.md'
-          SEALOS_REPLACE_TAG: 'DEFAULT_REPLACE_DEPLOY'
+          github-token: ${{secrets.GITHUB_TOKEN}}
+          script: |
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              body: 'Preview ${{ matrix.image }} Image: `${{ steps.config.outputs.DOCKER_REPO_TAGGED }}`'
+            })

.github/workflows/fastgpt-test.yaml

@@ -15,6 +15,9 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
       - uses: pnpm/action-setup@v4
         with:
           version: 10

.github/workflows/helm-release.yaml

@@ -8,7 +8,12 @@ on:
 
 jobs:
   helm:
-    runs-on: ubuntu-20.04
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    runs-on: ubuntu-24.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -20,7 +25,7 @@ jobs:
         run: echo "tag=$(git describe --tags)" >> $GITHUB_OUTPUT
       - name: Release Helm
         run: |
-          echo ${{ secrets.GH_PAT }} | helm registry login ghcr.io -u ${{ github.repository_owner }} --password-stdin
+          echo ${{ secrets.GITHUB_TOKEN }} | helm registry login ghcr.io -u ${{ github.repository_owner }} --password-stdin
           export APP_VERSION=${{ steps.vars.outputs.tag }}
           export HELM_VERSION=${{ steps.vars.outputs.tag }}
           export HELM_REPO=ghcr.io/${{ github.repository_owner }}

.github/workflows/mcp_server-build-image.yml

@@ -0,0 +1,151 @@
+name: Build fastgpt-mcp-server images
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - 'projects/sandbox/**'
+    tags:
+      - 'v*'
+jobs:
+  build-fastgpt-mcp_server-images:
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    strategy:
+      matrix:
+        include:
+          - arch: amd64
+          - arch: arm64
+            runs-on: ubuntu-24.04-arm
+    runs-on: ${{ matrix.runs-on || 'ubuntu-24.04' }}
+    steps:
+      # install env
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          driver-opts: network=host
+      - name: Cache Docker layers
+        uses: actions/cache@v4
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-mcp-server-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-mcp_server-buildx-
+
+      # login docker
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Login to Ali Hub
+        uses: docker/login-action@v3
+        with:
+          registry: registry.cn-hangzhou.aliyuncs.com
+          username: ${{ secrets.ALI_HUB_USERNAME }}
+          password: ${{ secrets.ALI_HUB_PASSWORD }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_HUB_NAME }}
+          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
+
+      - name: Build for ${{ matrix.arch }}
+        id: build
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: projects/mcp_server/Dockerfile
+          platforms: linux/${{ matrix.arch }}
+          labels: |
+            org.opencontainers.image.source=https://github.com/${{ github.repository }}
+            org.opencontainers.image.description=fastgpt-mcp_server image
+          outputs: type=image,"name=ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server,${{ secrets.ALI_IMAGE_NAME }}/fastgpt-mcp_server,${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-mcp_server",push-by-digest=true,push=true
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
+
+      - name: Export digest
+        run: |
+          mkdir -p ${{ runner.temp }}/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "${{ runner.temp }}/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-fastgpt-mcp_server-${{ github.sha }}-${{ matrix.arch }}
+          path: ${{ runner.temp }}/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  release-fastgpt-mcp_server-images:
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    needs: build-fastgpt-mcp_server-images
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Login to Ali Hub
+        uses: docker/login-action@v3
+        with:
+          registry: registry.cn-hangzhou.aliyuncs.com
+          username: ${{ secrets.ALI_HUB_USERNAME }}
+          password: ${{ secrets.ALI_HUB_PASSWORD }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_HUB_NAME }}
+          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
+
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: ${{ runner.temp }}/digests
+          pattern: digests-fastgpt-mcp_server-${{ github.sha }}-*
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set image name and tag
+        run: |
+          if [[ "${{ github.ref_name }}" == "main" ]]; then
+            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+          else
+            echo "Git_Tag=ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Git_Latest=ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Ali_Tag=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-mcp_server:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Ali_Latest=${{ secrets.ALI_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+            echo "Docker_Hub_Tag=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-mcp_server:${{ github.ref_name }}" >> $GITHUB_ENV
+            echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-mcp_server:latest" >> $GITHUB_ENV
+          fi
+
+      - name: Create manifest list and push
+        working-directory: ${{ runner.temp }}/digests
+        run: |
+          TAGS="$(echo -e "${Git_Tag}\n${Git_Latest}\n${Ali_Tag}\n${Ali_Latest}\n${Docker_Hub_Tag}\n${Docker_Hub_Latest}")"
+          for TAG in $TAGS; do
+            docker buildx imagetools create -t $TAG \
+              $(printf 'ghcr.io/${{ github.repository_owner }}/fastgpt-mcp_server@sha256:%s ' *)
+            sleep 5
+          done

.github/workflows/sandbox-build-image.yml

@@ -8,50 +8,120 @@ on:
       - 'v*'
 jobs:
   build-fastgpt-sandbox-images:
-    runs-on: ubuntu-20.04
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    strategy:
+      matrix:
+        include:
+          - arch: amd64
+          - arch: arm64
+            runs-on: ubuntu-24.04-arm
+    runs-on: ${{ matrix.runs-on || 'ubuntu-24.04' }}
     steps:
       # install env
       - name: Checkout
         uses: actions/checkout@v3
         with:
           fetch-depth: 0
-      - name: Install Dependencies
-        run: |
-          sudo apt update && sudo apt install -y nodejs npm
-      - name: Set up QEMU (optional)
-        uses: docker/setup-qemu-action@v2
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v2
+        uses: docker/setup-buildx-action@v3
         with:
           driver-opts: network=host
       - name: Cache Docker layers
         uses: actions/cache@v4
         with:
           path: /tmp/.buildx-cache
-          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          key: ${{ runner.os }}-sandbox-buildx-${{ github.sha }}
           restore-keys: |
-            ${{ runner.os }}-buildx-
+            ${{ runner.os }}-sandbox-buildx-
 
       # login docker
       - name: Login to GitHub Container Registry
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: ghcr.io
           username: ${{ github.repository_owner }}
-          password: ${{ secrets.GH_PAT }}
+          password: ${{ secrets.GITHUB_TOKEN }}
       - name: Login to Ali Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           registry: registry.cn-hangzhou.aliyuncs.com
           username: ${{ secrets.ALI_HUB_USERNAME }}
           password: ${{ secrets.ALI_HUB_PASSWORD }}
       - name: Login to Docker Hub
-        uses: docker/login-action@v2
+        uses: docker/login-action@v3
         with:
           username: ${{ secrets.DOCKER_HUB_NAME }}
           password: ${{ secrets.DOCKER_HUB_PASSWORD }}
 
-      # Set tag
+      - name: Build for ${{ matrix.arch }}
+        id: build
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: projects/sandbox/Dockerfile
+          platforms: linux/${{ matrix.arch }}
+          labels: |
+            org.opencontainers.image.source=https://github.com/${{ github.repository }}
+            org.opencontainers.image.description=fastgpt-sandbox image
+          outputs: type=image,"name=ghcr.io/${{ github.repository_owner }}/fastgpt-sandbox,${{ secrets.ALI_IMAGE_NAME }}/fastgpt-sandbox,${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sandbox",push-by-digest=true,push=true
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache
+
+      - name: Export digest
+        run: |
+          mkdir -p ${{ runner.temp }}/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "${{ runner.temp }}/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-fastgpt-sandbox-${{ github.sha }}-${{ matrix.arch }}
+          path: ${{ runner.temp }}/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  release-fastgpt-sandbox-images:
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    needs: build-fastgpt-sandbox-images
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Login to Ali Hub
+        uses: docker/login-action@v3
+        with:
+          registry: registry.cn-hangzhou.aliyuncs.com
+          username: ${{ secrets.ALI_HUB_USERNAME }}
+          password: ${{ secrets.ALI_HUB_PASSWORD }}
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_HUB_NAME }}
+          password: ${{ secrets.DOCKER_HUB_PASSWORD }}
+
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: ${{ runner.temp }}/digests
+          pattern: digests-fastgpt-sandbox-${{ github.sha }}-*
+          merge-multiple: true
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
       - name: Set image name and tag
         run: |
           if [[ "${{ github.ref_name }}" == "main" ]]; then
@@ -70,27 +140,12 @@ jobs:
             echo "Docker_Hub_Latest=${{ secrets.DOCKER_IMAGE_NAME }}/fastgpt-sandbox:latest" >> $GITHUB_ENV
           fi
 
-      - name: Build and publish image for main branch or tag push event
-        env:
-          Git_Tag: ${{ env.Git_Tag }}
-          Git_Latest: ${{ env.Git_Latest }}
-          Ali_Tag: ${{ env.Ali_Tag }}
-          Ali_Latest: ${{ env.Ali_Latest }}
-          Docker_Hub_Tag: ${{ env.Docker_Hub_Tag }}
-          Docker_Hub_Latest: ${{ env.Docker_Hub_Latest }}
+      - name: Create manifest list and push
+        working-directory: ${{ runner.temp }}/digests
         run: |
-          docker buildx build \
-          -f projects/sandbox/Dockerfile \
-          --platform linux/amd64,linux/arm64 \
-          --label "org.opencontainers.image.source=https://github.com/${{ github.repository_owner }}/fastgpt-sandbox" \
-          --label "org.opencontainers.image.description=fastgpt-sandbox image" \
-          --push \
-          --cache-from=type=local,src=/tmp/.buildx-cache \
-          --cache-to=type=local,dest=/tmp/.buildx-cache \
-          -t ${Git_Tag} \
-          -t ${Git_Latest} \
-          -t ${Ali_Tag} \
-          -t ${Ali_Latest} \
-          -t ${Docker_Hub_Tag} \
-          -t ${Docker_Hub_Latest} \
-          .
+          TAGS="$(echo -e "${Git_Tag}\n${Git_Latest}\n${Ali_Tag}\n${Ali_Latest}\n${Docker_Hub_Tag}\n${Docker_Hub_Latest}")"
+          for TAG in $TAGS; do
+            docker buildx imagetools create -t $TAG \
+              $(printf 'ghcr.io/${{ github.repository_owner }}/fastgpt-sandbox@sha256:%s ' *)
+            sleep 5
+          done

.vscode/launch.json

@@ -0,0 +1,39 @@
+{
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "name": "Next.js: debug server-side",
+      "type": "node-terminal",
+      "request": "launch",
+      "command": "pnpm run dev",
+      "cwd": "${workspaceFolder}/projects/app"
+    },
+    {
+      "name": "Next.js: debug client-side",
+      "type": "chrome",
+      "request": "launch",
+      "url": "http://localhost:3000"
+    },
+    {
+      "name": "Next.js: debug client-side (Edge)",
+      "type": "msedge",
+      "request": "launch",
+      "url": "http://localhost:3000"
+    },
+    {
+      "name": "Next.js: debug full stack",
+      "type": "node-terminal",
+      "request": "launch",
+      "command": "pnpm run dev",
+      "cwd": "${workspaceFolder}/projects/app",
+      "skipFiles": ["<node_internals>/**"],
+      "serverReadyAction": {
+        "action": "debugWithEdge",
+        "killOnServerStop": true,
+        "pattern": "- Local:.+(https?://.+)",
+        "uriFormat": "%s",
+        "webRoot": "${workspaceFolder}/projects/app"
+      }
+    }
+  ]
+}

.vscode/nextapi.code-snippets

@@ -52,71 +52,17 @@
 		"description": "FastGPT usecontext template"
 	},
 
-	"Jest test template": {
-		"scope": "typescriptreact",
-		"prefix": "jesttest",
+	"Vitest test case template": {
+		"scope": "typescript",
+		"prefix": "template_test",
 		"body": [
-			"import '@/pages/api/__mocks__/base';",
-			"import { root } from '@/pages/api/__mocks__/db/init';",
-			"import { getTestRequest } from '@fastgpt/service/test/utils'; ;",
-			"import { AppErrEnum } from '@fastgpt/global/common/error/code/app';",
-			"import handler from './demo';",
+			"import { describe, it, expect } from 'vitest';",
 			"",
-			"// Import the schema",
-			"import { MongoOutLink } from '@fastgpt/service/support/outLink/schema';",
-			"",
-			"beforeAll(async () => {",
-			"  // await MongoOutLink.create({",
-			"  //   shareId: 'aaa',",
-			"  //   appId: root.appId,",
-			"  //   tmbId: root.tmbId,",
-			"  //   teamId: root.teamId,",
-			"  //   type: 'share',",
-			"  //   name: 'aaa'",
-			"  // })",
-			"});",
-			"",
-			"test('Should return a list of outLink', async () => {",
-			"  // Mock request",
-			"  const res = (await handler(",
-			"    ...getTestRequest({",
-			"      query: {",
-			"        appId: root.appId,",
-			"        type: 'share'",
-			"      },",
-			"      user: root",
-			"    })",
-			"  )) as any;",
-			"",
-			"  expect(res.code).toBe(200);",
-			"  expect(res.data.length).toBe(2);",
-			"});",
-			"",
-			"test('appId is required', async () => {",
-			"  const res = (await handler(",
-			"    ...getTestRequest({",
-			"      query: {",
-			"        type: 'share'",
-			"      },",
-			"      user: root",
-			"    })",
-			"  )) as any;",
-			"  expect(res.code).toBe(500);",
-			"  expect(res.error).toBe(AppErrEnum.unExist);",
-			"});",
-			"",
-			"test('if type is not provided, return nothing', async () => {",
-			"  const res = (await handler(",
-			"    ...getTestRequest({",
-			"      query: {",
-			"        appId: root.appId",
-			"      },",
-			"      user: root",
-			"    })",
-			"  )) as any;",
-			"  expect(res.code).toBe(200);",
-			"  expect(res.data.length).toBe(0);",
+			"describe('authType2UsageSource', () => {",
+			"  it('Test description', () => {",
+			"    expect().toBe();",
+			"  });",
 			"});"
-			]
+		]
 	}
 }

Makefile

@@ -17,7 +17,7 @@ dev:
 
 build:
 ifeq ($(proxy), taobao)
-	docker build -f $(filePath) -t $(image) . --build-arg proxy=taobao 
+	docker build -f $(filePath) -t $(image) . --build-arg proxy=taobao
 else ifeq ($(proxy), clash)
 	docker build -f $(filePath) -t $(image) . --network host --build-arg HTTP_PROXY=http://127.0.0.1:7890 --build-arg HTTPS_PROXY=http://127.0.0.1:7890
 else

README.md

@@ -10,7 +10,7 @@
   <a href="./README_ja.md">日语</a>
 </p>
 
-FastGPT 是一个基于 LLM 大语言模型的知识库问答系统，提供开箱即用的数据处理、模型调用等能力。同时可以通过 Flow 可视化进行工作流编排，从而实现复杂的问答场景！
+FastGPT 是一个 AI Agent 构建平台，提供开箱即用的数据处理、模型调用等能力，同时可以通过 Flow 可视化进行工作流编排，从而实现复杂的应用场景！
 
 </div>
 

deploy/docker/docker-compose-milvus.yml

@@ -110,19 +110,31 @@ services:
 
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
 
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.5 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.5 # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -157,6 +169,8 @@ services:
       # zilliz 连接参数
       - MILVUS_ADDRESS=http://milvusStandalone:19530
       - MILVUS_TOKEN=none
+      # Redis 地址
+      - REDIS_URL=redis://default:mypassword@redis:6379
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
       # 日志等级: debug, info, warn, error
@@ -170,6 +184,8 @@ services:
       - ALLOWED_ORIGINS=
       # 是否开启IP限制，默认不开启
       - USE_IP_LIMIT=false
+      # 对话文件过期天数
+      - CHAT_FILE_EXPIRE_TIME=7
     volumes:
       - ./config.json:/app/data/config.json
 

deploy/docker/docker-compose-oceanbase/docker-compose.yml

@@ -0,0 +1,202 @@
+# 数据库的默认账号和密码仅首次运行时设置有效
+# 如果修改了账号密码，记得改数据库和项目连接参数，别只改一处~
+# 该配置文件只是给快速启动，测试使用。正式使用，记得务必修改账号密码，以及调整合适的知识库参数，共享内存等。
+# 如何无法访问 dockerhub 和 git，可以用阿里云（阿里云没有arm包）
+
+version: '3.3'
+services:
+  # vector db
+  ob:
+    image: oceanbase/oceanbase-ce # docker hub
+    # image: quay.io/oceanbase/oceanbase-ce:4.3.5.1-101000042025031818 # 镜像
+    container_name: ob
+    restart: always
+    # ports: # 生产环境建议不要暴露
+    #   - 2881:2881
+    networks:
+      - fastgpt
+    environment:
+      # 这里的配置只有首次运行生效。修改后，重启镜像是不会生效的。需要把持久化数据删除再重启，才有效果
+      - OB_SYS_PASSWORD=obsyspassword
+      # 不同于传统数据库，OceanBase 数据库的账号包含更多字段，包括用户名、租户名和集群名。经典格式为“用户名@租户名#集群名”
+      # 比如用mysql客户端连接时，根据本文件的默认配置，应该指定 “-uroot@tenantname”
+      - OB_TENANT_NAME=tenantname
+      - OB_TENANT_PASSWORD=tenantpassword
+      # MODE分为MINI和NORMAL， 后者会最大程度使用主机资源
+      - MODE=NORMAL
+      - OB_SERVER_IP=127.0.0.1
+      # 更多环境变量配置见oceanbase官方文档： https://www.oceanbase.com/docs/common-oceanbase-database-cn-1000000002013494
+    volumes:
+      - ./ob/data:/root/ob
+      - ./ob/config:/root/.obd/cluster
+      - ./init.sql:/root/boot/init.d/init.sql
+    healthcheck:
+    # obclient -h127.0.0.1 -P2881 -uroot@tenantname -ptenantpassword -e "SELECT 1;"
+      test: ["CMD-SHELL", "obclient -h$OB_SERVER_IP -P2881 -uroot@$OB_TENANT_NAME -p$OB_TENANT_PASSWORD -e \"SELECT 1;\""]
+      interval: 30s
+      timeout: 10s
+      retries: 1000
+      start_period: 10s
+  mongo:
+    image: mongo:5.0.18 # dockerhub
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/mongo:5.0.18 # 阿里云
+    # image: mongo:4.4.29 # cpu不支持AVX时候使用
+    container_name: mongo
+    restart: always
+    # ports:
+    #   - 27017:27017
+    networks:
+      - fastgpt
+    command: mongod --keyFile /data/mongodb.key --replSet rs0
+    environment:
+      - MONGO_INITDB_ROOT_USERNAME=myusername
+      - MONGO_INITDB_ROOT_PASSWORD=mypassword
+    volumes:
+      - ./mongo/data:/data/db
+    entrypoint:
+      - bash
+      - -c
+      - |
+        openssl rand -base64 128 > /data/mongodb.key
+        chmod 400 /data/mongodb.key
+        chown 999:999 /data/mongodb.key
+        echo 'const isInited = rs.status().ok === 1
+        if(!isInited){
+          rs.initiate({
+              _id: "rs0",
+              members: [
+                  { _id: 0, host: "mongo:27017" }
+              ]
+          })
+        }' > /data/initReplicaSet.js
+        # 启动MongoDB服务
+        exec docker-entrypoint.sh "$$@" &
+
+        # 等待MongoDB服务启动
+        until mongo -u myusername -p mypassword --authenticationDatabase admin --eval "print('waited for connection')"; do
+          echo "Waiting for MongoDB to start..."
+          sleep 2
+        done
+
+        # 执行初始化副本集的脚本
+        mongo -u myusername -p mypassword --authenticationDatabase admin /data/initReplicaSet.js
+
+        # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
+        wait $$!
+
+  # fastgpt
+  sandbox:
+    container_name: sandbox
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.3 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.3 # 阿里云
+    networks:
+      - fastgpt
+    restart: always
+  fastgpt:
+    container_name: fastgpt
+    image: ghcr.io/labring/fastgpt:v4.9.3 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.3 # 阿里云
+    ports:
+      - 3000:3000
+    networks:
+      - fastgpt
+    depends_on:
+      mongo:
+        condition: service_started
+      ob:
+        condition: service_healthy
+      sandbox:
+        condition: service_started
+    restart: always
+    environment:
+      # 前端外部可访问的地址，用于自动补全文件资源路径。例如 https:fastgpt.cn，不能填 localhost。这个值可以不填，不填则发给模型的图片会是一个相对路径，而不是全路径，模型可能伪造Host。
+      - FE_DOMAIN=
+      # root 密码，用户名为: root。如果需要修改 root 密码，直接修改这个环境变量，并重启即可。
+      - DEFAULT_ROOT_PSW=1234
+      # # AI Proxy 的地址，如果配了该地址，优先使用
+      # - AIPROXY_API_ENDPOINT=http://aiproxy:3000
+      # # AI Proxy 的 Admin Token，与 AI Proxy 中的环境变量 ADMIN_KEY
+      # - AIPROXY_API_TOKEN=aiproxy
+      # 模型中转地址（如果用了 AI Proxy，下面 2 个就不需要了，旧版 OneAPI 用户，使用下面的变量）
+      - # openai 基本地址，可用作中转。
+      - OPENAI_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1
+      - # OpenAI API Key
+      - CHAT_API_KEY=sk-8990fa15a34b464a805237cfe9561f11
+      # 数据库最大连接数
+      - DB_MAX_LINK=30
+      # 登录凭证密钥
+      - TOKEN_KEY=any
+      # root的密钥，常用于升级时候的初始化请求
+      - ROOT_KEY=root_key
+      # 文件阅读加密
+      - FILE_TOKEN_KEY=filetoken
+      # MongoDB 连接参数. 用户名myusername,密码mypassword。
+      - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
+      # OceanBase 向量库连接参数
+      - OCEANBASE_URL=mysql://root%40tenantname:tenantpassword@ob:2881/test
+      # sandbox 地址
+      - SANDBOX_URL=http://sandbox:3000
+      # 日志等级: debug, info, warn, error
+      - LOG_LEVEL=info
+      - STORE_LOG_LEVEL=warn
+      # 工作流最大运行次数
+      - WORKFLOW_MAX_RUN_TIMES=1000
+      # 批量执行节点，最大输入长度
+      - WORKFLOW_MAX_LOOP_TIMES=100
+      # 自定义跨域，不配置时，默认都允许跨域（多个域名通过逗号分割）
+      - ALLOWED_ORIGINS=
+      # 是否开启IP限制，默认不开启
+      - USE_IP_LIMIT=false
+    volumes:
+      - ./config.json:/app/data/config.json
+
+  # AI Proxy
+  aiproxy:
+    image: ghcr.io/labring/aiproxy:v0.1.5
+    # image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3 # 阿里云
+    container_name: aiproxy
+    restart: unless-stopped
+    depends_on:
+      aiproxy_pg:
+        condition: service_healthy
+    networks:
+      - fastgpt
+    environment:
+      # 对应 fastgpt 里的AIPROXY_API_TOKEN
+      - ADMIN_KEY=aiproxy
+      # 错误日志详情保存时间（小时）
+      - LOG_DETAIL_STORAGE_HOURS=1
+      # 数据库连接地址
+      - SQL_DSN=postgres://postgres:aiproxy@aiproxy_pg:5432/aiproxy
+      # 最大重试次数
+      - RETRY_TIMES=3
+      # 不需要计费
+      - BILLING_ENABLED=false
+      # 不需要严格检测模型
+      - DISABLE_MODEL_CONFIG=true
+    healthcheck:
+      test: ['CMD', 'curl', '-f', 'http://localhost:3000/api/status']
+      interval: 5s
+      timeout: 5s
+      retries: 10
+  aiproxy_pg:
+    image: pgvector/pgvector:0.8.0-pg15 # docker hub
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/pgvector:v0.8.0-pg15 # 阿里云
+    restart: unless-stopped
+    container_name: aiproxy_pg
+    volumes:
+      - ./aiproxy_pg:/var/lib/postgresql/data
+    networks:
+      - fastgpt
+    environment:
+      TZ: Asia/Shanghai
+      POSTGRES_USER: postgres
+      POSTGRES_DB: aiproxy
+      POSTGRES_PASSWORD: aiproxy
+    healthcheck:
+      test: ['CMD', 'pg_isready', '-U', 'postgres', '-d', 'aiproxy']
+      interval: 5s
+      timeout: 5s
+      retries: 10
+networks:
+  fastgpt:

deploy/docker/docker-compose-oceanbase/init.sql

@@ -0,0 +1,2 @@
+ALTER SYSTEM SET ob_vector_memory_limit_percentage = 30;
+

deploy/docker/docker-compose-pgvector.yml

@@ -69,18 +69,31 @@ services:
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
 
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
+
   # fastgpt
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.5 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.5 # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -114,6 +127,8 @@ services:
       - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
       # pg 连接参数
       - PG_URL=postgresql://username:password@pg:5432/postgres
+      # Redis 连接参数
+      - REDIS_URL=redis://default:mypassword@redis:6379
       # sandbox 地址
       - SANDBOX_URL=http://sandbox:3000
       # 日志等级: debug, info, warn, error
@@ -127,12 +142,14 @@ services:
       - ALLOWED_ORIGINS=
       # 是否开启IP限制，默认不开启
       - USE_IP_LIMIT=false
+      # 对话文件过期天数
+      - CHAT_FILE_EXPIRE_TIME=7
     volumes:
       - ./config.json:/app/data/config.json
 
   # AI Proxy
   aiproxy:
-    image: ghcr.io/labring/aiproxy:v0.1.3
+    image: ghcr.io/labring/aiproxy:v0.1.5
     # image: registry.cn-hangzhou.aliyuncs.com/labring/aiproxy:v0.1.3 # 阿里云
     container_name: aiproxy
     restart: unless-stopped

deploy/docker/docker-compose-zilliz.yml

@@ -51,17 +51,30 @@ services:
 
         # 等待docker-entrypoint.sh脚本执行的MongoDB服务进程
         wait $$!
+  redis:
+    image: redis:7.2-alpine
+    container_name: redis
+    # ports:
+    # - 6379:6379
+    networks:
+      - fastgpt
+    restart: always
+    command: |
+      redis-server --requirepass mypassword --loglevel warning --maxclients 10000 --appendonly yes --save 60 10 --maxmemory 4gb --maxmemory-policy noeviction
+    volumes:
+      - ./redis/data:/data
+
   sandbox:
     container_name: sandbox
-    image: ghcr.io/labring/fastgpt-sandbox:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt-sandbox:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-sandbox:v4.9.5 # 阿里云
     networks:
       - fastgpt
     restart: always
   fastgpt:
     container_name: fastgpt
-    image: ghcr.io/labring/fastgpt:v4.9.1-fix2 # git
-    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.1-fix2 # 阿里云
+    image: ghcr.io/labring/fastgpt:v4.9.5 # git
+    # image: registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt:v4.9.5 # 阿里云
     ports:
       - 3000:3000
     networks:
@@ -92,6 +105,8 @@ services:
       - FILE_TOKEN_KEY=filetoken
       # MongoDB 连接参数. 用户名myusername,密码mypassword。
       - MONGODB_URI=mongodb://myusername:mypassword@mongo:27017/fastgpt?authSource=admin
+      # Redis 连接参数
+      - REDIS_URI=redis://default:mypassword@redis:6379
       # zilliz 连接参数
       - MILVUS_ADDRESS=zilliz_cloud_address
       - MILVUS_TOKEN=zilliz_cloud_token
@@ -108,6 +123,8 @@ services:
       - ALLOWED_ORIGINS=
       # 是否开启IP限制，默认不开启
       - USE_IP_LIMIT=false
+      # 对话文件过期天数
+      - CHAT_FILE_EXPIRE_TIME=7
     volumes:
       - ./config.json:/app/data/config.json
 

deploy/helm/fastgpt/templates/configmap-config.yaml

@@ -7,7 +7,7 @@ data:
         "vectorMaxProcess": 15,
         "qaMaxProcess": 15,
         "vlmMaxProcess": 15,
-        "pgHNSWEfSearch": 100
+        "hnswEfSearch": 100
       },
       "llmModels": [
         {

docSite/content/zh-cn/docs/development/configuration.md

@@ -25,7 +25,7 @@ weight: 707
     "qaMaxProcess": 15, // 问答拆分线程数量
     "vlmMaxProcess": 15, // 图片理解模型最大处理进程
     "tokenWorkers": 50, // Token 计算线程保持数，会持续占用内存，不能设置太大。
-    "pgHNSWEfSearch": 100, // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
+    "hnswEfSearch": 100, // 向量搜索参数，仅对 PG 和 OB 生效。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
     "customPdfParse": { // 4.9.0 新增配置
       "url": "", // 自定义 PDF 解析服务地址
       "key": "", // 自定义 PDF 解析服务密钥

docSite/content/zh-cn/docs/development/custom-models/bge-rerank.md

@@ -31,9 +31,9 @@ weight: 920
 
 3 个模型代码分别为：
 
-1. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-base)
-2. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-large)
-3. [https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/plugins/rerank-bge/bge-reranker-v2-m3)
+1. [https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-base](https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-base)
+2. [https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-large](https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-large)
+3. [https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-v2-m3](https://github.com/labring/FastGPT/tree/main/plugins/model/rerank-bge/bge-reranker-v2-m3)
 
 ### 3. 安装依赖
 

docSite/content/zh-cn/docs/development/custom-models/chatglm2.md

@@ -46,7 +46,7 @@ ChatGLM2-6B 是开源中英双语对话模型 ChatGLM-6B 的第二代版本，
 ### 源码部署
 
 1. 根据上面的环境配置配置好环境，具体教程自行 GPT；
-2. 下载 [python 文件](https://github.com/labring/FastGPT/blob/main/files/models/ChatGLM2/openai_api.py)
+2. 下载 [python 文件](https://github.com/labring/FastGPT/blob/main/plugins/model/llm-ChatGLM2/openai_api.py)
 3. 在命令行输入命令 `pip install -r requirements.txt`；
 4. 打开你需要启动的 py 文件，在代码的 `verify_token` 方法中配置 token，这里的 token 只是加一层验证，防止接口被人盗用；
 5. 执行命令 `python openai_api.py --model_name 16`。这里的数字根据上面的配置进行选择。

docSite/content/zh-cn/docs/development/custom-models/ollama.md

@@ -0,0 +1,184 @@
+---
+title: '使用 Ollama 接入本地模型 '
+description: ' 采用 Ollama 部署自己的模型'
+icon: 'api'
+draft: false
+toc: true
+weight: 950
+---
+
+[Ollama](https://ollama.com/) 是一个开源的AI大模型部署工具，专注于简化大语言模型的部署和使用，支持一键下载和运行各种大模型。
+
+## 安装 Ollama
+
+Ollama 本身支持多种安装方式，但是推荐使用 Docker 拉取镜像部署。如果是个人设备上安装了 Ollama 后续需要解决如何让 Docker 中 FastGPT 容器访问宿主机 Ollama的问题，较为麻烦。 
+
+### Docker 安装（推荐）
+
+你可以使用 Ollama 官方的 Docker 镜像来一键安装和启动 Ollama 服务（确保你的机器上已经安装了 Docker），命令如下：
+
+```bash
+docker pull ollama/ollama 
+docker run --rm -d --name ollama -p 11434:11434 ollama/ollama
+```
+
+如果你的 FastGPT 是在 Docker 中进行部署的，建议在拉取 Ollama 镜像时保证和 FastGPT 镜像处于同一网络，否则可能出现 FastGPT 无法访问的问题，命令如下：
+
+```bash
+docker run --rm -d --name ollama --network （你的 Fastgpt 容器所在网络） -p 11434:11434 ollama/ollama
+```
+
+### 主机安装
+
+如果你不想使用 Docker ，也可以采用主机安装，以下是主机安装的一些方式。
+
+#### MacOS
+
+如果你使用的是 macOS，且系统中已经安装了 Homebrew 包管理器，可通过以下命令来安装 Ollama：
+
+```bash
+brew install ollama
+ollama serve #安装完成后，使用该命令启动服务
+```
+
+#### Linux
+
+在 Linux 系统上，你可以借助包管理器来安装 Ollama。以 Ubuntu 为例，在终端执行以下命令：
+
+```bash
+curl https://ollama.com/install.sh | sh #此命令会从官方网站下载并执行安装脚本。
+ollama serve #安装完成后，同样启动服务
+```
+
+#### Windows
+
+在 Windows 系统中，你可以从 Ollama 官方网站 下载 Windows 版本的安装程序。下载完成后，运行安装程序，按照安装向导的提示完成安装。安装完成后，在命令提示符或 PowerShell 中启动服务：
+
+```bash
+ollama serve #安装完成并启动服务后，你可以在浏览器中访问 http://localhost:11434 来验证 Ollama 是否安装成功。
+```
+
+#### 补充说明
+
+如果你是采用的主机应用 Ollama 而不是镜像，需要确保你的 Ollama 可以监听0.0.0.0。
+
+##### 1. Linxu 系统
+
+如果 Ollama 作为 systemd 服务运行，打开终端，编辑 Ollama 的 systemd 服务文件，使用命令sudo systemctl edit ollama.service，在[Service]部分添加Environment="OLLAMA_HOST=0.0.0.0"。保存并退出编辑器，然后执行sudo systemctl daemon - reload和sudo systemctl restart ollama使配置生效。
+
+##### 2. MacOS 系统
+
+打开终端，使用launchctl setenv ollama_host "0.0.0.0"命令设置环境变量，然后重启 Ollama 应用程序以使更改生效。
+
+##### 3. Windows 系统
+
+通过 “开始” 菜单或搜索栏打开 “编辑系统环境变量”，在 “系统属性” 窗口中点击 “环境变量”，在 “系统变量” 部分点击 “新建”，创建一个名为OLLAMA_HOST的变量，变量值设置为0.0.0.0，点击 “确定” 保存更改，最后从 “开始” 菜单重启 Ollama 应用程序。
+
+### Ollama 拉取模型镜像
+
+在安装后 Ollama 后，本地是没有模型镜像的，需要自己去拉取 Ollama 中的模型镜像。命令如下：
+
+```bash
+# Docker 部署需要先进容器，命令为： docker exec -it < Ollama 容器名 > /bin/sh
+ollama pull <模型名>
+```
+
+![](/imgs/Ollama-pull.png)
+
+
+### 测试通信
+
+在安装完成后，需要进行检测测试，首先进入 FastGPT 所在的容器，尝试访问自己的 Ollama ，命令如下：
+
+```bash
+docker exec -it < FastGPT 所在的容器名 > /bin/sh
+curl http://XXX.XXX.XXX.XXX:11434  #容器部署地址为“http://<容器名>:<端口>”,主机安装地址为"http://<主机IP>:<端口>"，主机IP不可为localhost
+```
+
+看到访问显示自己的 Ollama 服务以及启动，说明可以正常通信。
+
+## 将 Ollama 接入 FastGPT
+
+### 1. 查看 Ollama 所拥有的模型
+
+首先采用下述命令查看 Ollama 中所拥有的模型，
+
+```bash
+# Docker 部署 Ollama，需要此命令 docker exec -it < Ollama 容器名 > /bin/sh
+ollama ls
+```
+
+![](/imgs/Ollama-models1.png)
+
+### 2. AI Proxy 接入
+
+如果你采用的是 FastGPT 中的默认配置文件部署[这里](/docs/development/docker.md)，即默认采用 AI Proxy 进行启动。
+
+![](/imgs/Ollama-aiproxy1.png)
+
+以及在确保你的 FastGPT 可以直接访问 Ollama 容器的情况下，无法访问，参考上文[点此跳转](#安装-ollama)的安装过程，检测是不是主机不能监测0.0.0.0，或者容器不在同一个网络。
+
+![](/imgs/Ollama-aiproxy2.png)
+
+在 FastGPT 中点击账号->模型提供商->模型配置->新增模型，添加自己的模型即可，添加模型时需要保证模型ID和 OneAPI 中的模型名称一致。详细参考[这里](/docs/development/modelConfig/intro.md)
+
+![](/imgs/Ollama-models2.png)
+
+![](/imgs/Ollama-models3.png)
+
+运行 FastGPT ，在页面中选择账号->模型提供商->模型渠道->新增渠道。之后，在渠道选择中选择 Ollama ，然后加入自己拉取的模型，填入代理地址，如果是容器中安装 Ollama ，代理地址为http://地址:端口，补充：容器部署地址为“http://<容器名>:<端口>”,主机安装地址为"http://<主机IP>:<端口>"，主机IP不可为localhost
+
+![](/imgs/Ollama-aiproxy3.png)
+
+在工作台中创建一个应用，选择自己之前添加的模型，此处模型名称为自己当时设置的别名。注：同一个模型无法多次添加，系统会采取最新添加时设置的别名。
+
+![](/imgs/Ollama-models4.png)
+
+### 3. OneAPI 接入
+
+如果你想使用 OneAPI ，首先需要拉取 OneAPI 镜像，然后将其在 FastGPT 容器的网络中运行。具体命令如下：
+
+```bash
+# 拉取 oneAPI 镜像
+docker pull intel/oneapi-hpckit
+
+# 运行容器并指定自定义网络和容器名
+docker run -it --network < FastGPT 网络 > --name 容器名 intel/oneapi-hpckit /bin/bash
+```
+
+进入 OneAPI 页面，添加新的渠道，类型选择 Ollama ，在模型中填入自己 Ollama 中的模型，需要保证添加的模型名称和 Ollama 中一致，再在下方填入自己的 Ollama 代理地址，默认http://地址:端口，不需要填写/v1。添加成功后在 OneAPI 进行渠道测试，测试成功则说明添加成功。此处演示采用的是 Docker 部署 Ollama 的效果，主机 Ollama需要修改代理地址为http://<主机IP>:<端口>
+
+![](/imgs/Ollama-oneapi1.png)
+
+渠道添加成功后，点击令牌，点击添加令牌，填写名称，修改配置。
+
+![](/imgs/Ollama-oneapi2.png)
+
+修改部署 FastGPT 的 docker-compose.yml 文件，在其中将 AI Proxy 的使用注释，在 OPENAI_BASE_URL 中加入自己的 OneAPI 开放地址，默认是http://地址:端口/v1，v1必须填写。KEY 中填写自己在 OneAPI 的令牌。
+
+![](/imgs/Ollama-oneapi3.png)
+
+[直接跳转5](#5-模型添加和使用)添加模型，并使用。
+
+### 4. 直接接入
+
+如果你既不想使用 AI Proxy，也不想使用 OneAPI，也可以选择直接接入，修改部署 FastGPT 的 docker-compose.yml 文件，在其中将 AI Proxy 的使用注释，采用和 OneAPI 的类似配置。注释掉 AIProxy 相关代码，在OPENAI_BASE_URL中加入自己的 Ollama 开放地址，默认是http://地址:端口/v1，强调:v1必须填写。在KEY中随便填入，因为 Ollama 默认没有鉴权，如果开启鉴权，请自行填写。其他操作和在 OneAPI 中加入 Ollama 一致，只需在 FastGPT 中加入自己的模型即可使用。此处演示采用的是 Docker 部署 Ollama 的效果，主机 Ollama需要修改代理地址为http://<主机IP>:<端口>
+
+![](/imgs/Ollama-direct1.png)
+
+完成后[点击这里](#5-模型添加和使用)进行模型添加并使用。
+
+### 5. 模型添加和使用
+
+在 FastGPT 中点击账号->模型提供商->模型配置->新增模型，添加自己的模型即可，添加模型时需要保证模型ID和 OneAPI 中的模型名称一致。
+
+![](/imgs/Ollama-models2.png)
+
+![](/imgs/Ollama-models3.png)
+
+在工作台中创建一个应用，选择自己之前添加的模型，此处模型名称为自己当时设置的别名。注：同一个模型无法多次添加，系统会采取最新添加时设置的别名。
+
+![](/imgs/Ollama-models4.png)
+
+### 6. 补充
+上述接入 Ollama 的代理地址中，主机安装 Ollama 的地址为“http://<主机IP>:<端口>”，容器部署 Ollama 地址为“http://<容器名>:<端口>”

docSite/content/zh-cn/docs/development/docker.md

@@ -135,6 +135,9 @@ curl -O https://raw.githubusercontent.com/labring/FastGPT/main/projects/app/data
 
 # pgvector 版本(测试推荐，简单快捷)
 curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-pgvector.yml
+# oceanbase 版本（需要将init.sql和docker-compose.yml放在同一个文件夹，方便挂载）
+# curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-oceanbase/docker-compose.yml
+# curl -o init.sql https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-oceanbase/init.sql
 # milvus 版本
 # curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/main/deploy/docker/docker-compose-milvus.yml
 # zilliz 版本
@@ -151,6 +154,13 @@ curl -o docker-compose.yml https://raw.githubusercontent.com/labring/FastGPT/mai
 
 无需操作
 
+{{< /markdownify >}}
+{{< /tab >}}
+{{< tab tabName="Oceanbase版本" >}}
+{{< markdownify >}}
+
+无需操作
+
 {{< /markdownify >}}
 {{< /tab >}}
 {{< tab tabName="Milvus版本" >}}

docSite/content/zh-cn/docs/development/intro.md

@@ -71,7 +71,7 @@ Mongo 数据库需要注意，需要注意在连接地址中增加 `directConnec
 - `vectorMaxProcess`: 向量生成最大进程，根据数据库和 key 的并发数来决定，通常单个 120 号，2c4g 服务器设置 10~15。
 - `qaMaxProcess`: QA 生成最大进程
 - `vlmMaxProcess`: 图片理解模型最大进程
-- `pgHNSWEfSearch`: PostgreSQL vector 索引参数，越大搜索精度越高但是速度越慢，具体可看 pgvector 官方说明。
+- `hnswEfSearch`: 向量搜索参数，仅对 PG 和 OB 生效，越大搜索精度越高但是速度越慢。
 
 ### 5. 运行
 

docSite/content/zh-cn/docs/development/modelConfig/intro.md

@@ -302,7 +302,7 @@ OneAPI 的语言识别接口，无法正确的识别其他模型（会始终识
     "vectorMaxProcess": 15, // 向量处理线程数量
     "qaMaxProcess": 15, // 问答拆分线程数量
     "tokenWorkers": 50, // Token 计算线程保持数，会持续占用内存，不能设置太大。
-    "pgHNSWEfSearch": 100 // 向量搜索参数。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
+    "hnswEfSearch": 100 // 向量搜索参数，仅对 PG 和 OB 生效。越大，搜索越精确，但是速度越慢。设置为100，有99%+精度。
   },
   "llmModels": [
     {

docSite/content/zh-cn/docs/development/openapi/chat.md

@@ -18,12 +18,14 @@ weight: 852
 {{% alert icon="🤖 " context="success" %}}
 * 该接口的 API Key 需使用`应用特定的 key`，否则会报错。  
 
+<!-- * 对话现在有`v1`和`v2`两个接口，可以按需使用，v2 自 4.9.4 版本新增，v1 接口同时不再维护 -->
+
 * 有些包调用时，`BaseUrl`需要添加`v1`路径，有些不需要，如果出现404情况，可补充`v1`重试。
 {{% /alert %}}
 
 ## 请求简易应用和工作流
 
-对话接口兼容`GPT`的接口！如果你的项目使用的是标准的`GPT`官方接口，可以直接通过修改`BaseUrl`和 `Authorization`来访问 FastGpt 应用，不过需要注意下面几个规则：
+`v1`对话接口兼容`GPT`的接口！如果你的项目使用的是标准的`GPT`官方接口，可以直接通过修改`BaseUrl`和 `Authorization`来访问 FastGpt 应用，不过需要注意下面几个规则：
 
 {{% alert icon="🤖 " context="success" %}}
 * 传入的`model`，`temperature`等参数字段均无效，这些字段由编排决定，不会根据 API 参数改变。
@@ -65,7 +67,7 @@ curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
 {{< markdownify >}}
 
 * 仅`messages`有部分区别，其他参数一致。
-* 目前不支持上次文件，需上传到自己的对象存储中，获取对应的文件链接。
+* 目前不支持上传文件，需上传到自己的对象存储中，获取对应的文件链接。
 
 ```bash
 curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
@@ -116,14 +118,284 @@ curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
 - variables: 模块变量，一个对象，会替换模块中，输入框内容里的`{{key}}`
 {{% /alert %}}
 
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}}
 
+<!-- #### v2
+
+v1,v2 接口请求参数一致，仅请求地址不一样。
+
+{{< tabs tabTotal="3" >}}
+{{< tab tabName="基础请求示例" >}}
+{{< markdownify >}}
+
+```bash
+curl --location --request POST 'http://localhost:3000/api/v2/chat/completions' \
+--header 'Authorization: fastgpt-xxxxxx' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "chatId": "my_chatId",
+    "stream": false,
+    "detail": false,
+    "responseChatItemId": "my_responseChatItemId",
+    "variables": {
+        "uid": "asdfadsfasfd2323",
+        "name": "张三"
+    },
+    "messages": [
+        {
+            "role": "user",
+            "content": "你是谁"
+        }
+    ]
+}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="图片/文件请求示例" >}}
+{{< markdownify >}}
+
+* 仅`messages`有部分区别，其他参数一致。
+* 目前不支持上传文件，需上传到自己的对象存储中，获取对应的文件链接。
+
+```bash
+curl --location --request POST 'http://localhost:3000/api/v2/chat/completions' \
+--header 'Authorization: Bearer fastgpt-xxxxxx' \
+--header 'Content-Type: application/json' \
+--data-raw '{
+    "chatId": "abcd",
+    "stream": false,
+    "messages": [
+        {
+            "role": "user",
+            "content": [
+                {
+                    "type": "text",
+                    "text": "导演是谁"
+                },
+                {
+                    "type": "image_url",
+                    "image_url": {
+                        "url": "图片链接"
+                    }
+                },
+                {
+                    "type": "file_url",
+                    "name": "文件名",
+                    "url": "文档链接，支持 txt md html word pdf ppt csv excel"
+                }
+            ]
+        }
+    ]
+}'
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="参数说明" >}}
+{{< markdownify >}}
+
+{{% alert context="info" %}}
+- headers.Authorization: Bearer {{apikey}}
+- chatId: string | undefined 。
+  - 为 `undefined` 时（不传入），不使用 FastGpt 提供的上下文功能，完全通过传入的 messages 构建上下文。
+  - 为`非空字符串`时，意味着使用 chatId 进行对话，自动从 FastGpt 数据库取历史记录，并使用 messages 数组最后一个内容作为用户问题，其余 message 会被忽略。请自行确保 chatId 唯一，长度小于250，通常可以是自己系统的对话框ID。
+- messages: 结构与 [GPT接口](https://platform.openai.com/docs/api-reference/chat/object) chat模式一致。
+- responseChatItemId: string | undefined 。如果传入，则会将该值作为本次对话的响应消息的 ID，FastGPT 会自动将该 ID 存入数据库。请确保，在当前`chatId`下，`responseChatItemId`是唯一的。
+- detail: 是否返回中间值（模块状态，响应的完整结果等），`stream模式`下会通过`event`进行区分，`非stream模式`结果保存在`responseData`中。
+- variables: 模块变量，一个对象，会替换模块中，输入框内容里的`{{key}}`
+{{% /alert %}}
 
 {{< /markdownify >}}
 {{< /tab >}}
 {{< /tabs >}}
 
+#### v1
+
+
+
 ### 响应
 
+#### v2
+
+v2 接口比起 v1，主要变变化在于：会在每个节点运行结束后及时返回 response，而不是等工作流结束后再统一返回。
+
+{{< tabs tabTotal="5" >}}
+{{< tab tabName="detail=false,stream=false 响应" >}}
+{{< markdownify >}}
+
+```json
+{
+    "id": "",
+    "model": "",
+    "usage": {
+        "prompt_tokens": 1,
+        "completion_tokens": 1,
+        "total_tokens": 1
+    },
+    "choices": [
+        {
+            "message": {
+                "role": "assistant",
+                "content": "我是一个人工智能助手，旨在回答问题和提供信息。如果你有任何问题或者需要帮助，随时问我！"
+            },
+            "finish_reason": "stop",
+            "index": 0
+        }
+    ]
+}
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="detail=false,stream=true 响应" >}}
+{{< markdownify >}}
+
+
+```bash
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"你好"},"index":0,"finish_reason":null}]}
+
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"！"},"index":0,"finish_reason":null}]}
+
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"今天"},"index":0,"finish_reason":null}]}
+
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"过得怎么样？"},"index":0,"finish_reason":null}]}
+
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":null},"index":0,"finish_reason":"stop"}]}
+
+data: [DONE]
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="detail=true,stream=false 响应" >}}
+{{< markdownify >}}
+
+```json
+{
+    "responseData": [
+        {
+            "id": "iSol79OFrBH1I9kC",
+            "nodeId": "448745",
+            "moduleName": "common:core.module.template.work_start",
+            "moduleType": "workflowStart",
+            "runningTime": 0
+        },
+        {
+            "id": "t1T94WCy6Su3BK4V",
+            "nodeId": "fjLpE3XPegmoGtbU",
+            "moduleName": "AI 对话",
+            "moduleType": "chatNode",
+            "runningTime": 1.46,
+            "totalPoints": 0,
+            "model": "GPT-4o-mini",
+            "tokens": 64,
+            "inputTokens": 10,
+            "outputTokens": 54,
+            "query": "你是谁",
+            "reasoningText": "",
+            "historyPreview": [
+                {
+                    "obj": "Human",
+                    "value": "你是谁"
+                },
+                {
+                    "obj": "AI",
+                    "value": "我是一个人工智能助手，旨在帮助回答问题和提供信息。如果你有任何问题或需要帮助，请告诉我！"
+                }
+            ],
+            "contextTotalLen": 2
+        }
+    ],
+    "newVariables": {
+
+    },
+    "id": "",
+    "model": "",
+    "usage": {
+        "prompt_tokens": 1,
+        "completion_tokens": 1,
+        "total_tokens": 1
+    },
+    "choices": [
+        {
+            "message": {
+                "role": "assistant",
+                "content": "我是一个人工智能助手，旨在帮助回答问题和提供信息。如果你有任何问题或需要帮助，请告诉我！"
+            },
+            "finish_reason": "stop",
+            "index": 0
+        }
+    ]
+}
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+
+{{< tab tabName="detail=true,stream=true 响应" >}}
+{{< markdownify >}}
+
+```bash
+event: flowNodeResponse
+data: {"id":"iYv2uA9rCWAtulWo","nodeId":"workflowStartNodeId","moduleName":"流程开始","moduleType":"workflowStart","runningTime":0}
+
+event: flowNodeStatus
+data: {"status":"running","name":"AI 对话"}
+
+event: answer
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"你好"},"index":0,"finish_reason":null}]}
+
+event: answer
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"！"},"index":0,"finish_reason":null}]}
+
+event: answer
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"今天"},"index":0,"finish_reason":null}]}
+
+event: answer
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":"过得怎么样？"},"index":0,"finish_reason":null}]}
+
+event: flowNodeResponse
+data: {"id":"pVzLBF7M3Ol4n7s6","nodeId":"ixe20AHN3jy74pKf","moduleName":"AI 对话","moduleType":"chatNode","runningTime":1.48,"totalPoints":0.0042,"model":"Qwen-plus","tokens":28,"inputTokens":8,"outputTokens":20,"query":"你好","reasoningText":"","historyPreview":[{"obj":"Human","value":"你好"},{"obj":"AI","value":"你好！今天过得怎么样？"}],"contextTotalLen":2}
+
+event: answer
+data: {"id":"","object":"","created":0,"model":"","choices":[{"delta":{"role":"assistant","content":null},"index":0,"finish_reason":"stop"}]}
+
+event: answer
+data: [DONE]
+```
+
+{{< /markdownify >}}
+{{< /tab >}}
+
+{{< tab tabName="event值" >}}
+{{< markdownify >}}
+
+event取值：
+
+- answer: 返回给客户端的文本（最终会算作回答）
+- fastAnswer: 指定回复返回给客户端的文本（最终会算作回答）
+- toolCall: 执行工具
+- toolParams: 工具参数
+- toolResponse: 工具返回
+- flowNodeStatus: 运行到的节点状态
+- flowNodeResponse: 单个节点详细响应
+- updateVariables: 更新变量
+- error: 报错
+
+{{< /markdownify >}}
+{{< /tab >}}
+{{< /tabs >}} 
+
+#### v1 -->
+
 {{< tabs tabTotal="5" >}}
 {{< tab tabName="detail=false,stream=false 响应" >}}
 {{< markdownify >}}
@@ -648,8 +920,6 @@ event取值：
 {{< /tab >}}
 {{< /tabs >}}
 
-
-
 # 对话 CRUD
 
 {{% alert icon="🤖 " context="success" %}}

docSite/content/zh-cn/docs/development/openapi/dataset.md

@@ -11,8 +11,6 @@ weight: 853
 | --------------------- | --------------------- |
 | ![](/imgs/getDatasetId.jpg) | ![](/imgs/getfile_id.webp) |
 
-
-
 ## 创建训练订单
 
 {{< tabs tabTotal="2" >}}
@@ -289,7 +287,7 @@ curl --location --request DELETE 'http://localhost:3000/api/core/dataset/delete?
 
 ## 集合
 
-### 通用创建参数说明
+### 通用创建参数说明（必看）
 
 **入参**
 
@@ -300,8 +298,11 @@ curl --location --request DELETE 'http://localhost:3000/api/core/dataset/delete?
 | trainingType | 数据处理方式。chunk: 按文本长度进行分割;qa: 问答对提取 | ✅ |
 | autoIndexes | 是否自动生成索引(仅商业版支持) |  |
 | imageIndex | 是否自动生成图片索引(仅商业版支持) |  |
-| chunkSize | 预估块大小 |  |
-| chunkSplitter | 自定义最高优先分割符号 |  |
+| chunkSettingMode | 分块参数模式。auto: 系统默认参数; custom: 手动指定参数 |  |
+| chunkSplitMode | 分块拆分模式。size: 按长度拆分; char: 按字符拆分。chunkSettingMode=auto时不生效。 |  |
+| chunkSize | 分块大小，默认 1500。chunkSettingMode=auto时不生效。 |  |
+| indexSize | 索引大小，默认 512，必须小于索引模型最大token。chunkSettingMode=auto时不生效。 |  |
+| chunkSplitter | 自定义最高优先分割符号，除非超出文件处理最大上下文，否则不会进行进一步拆分。chunkSettingMode=auto时不生效。 |  |
 | qaPrompt | qa拆分提示词 |  |
 | tags |  集合标签（字符串数组） |  |
 | createTime | 文件创建时间（Date / String） |  |
@@ -389,9 +390,8 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
     "name":"测试训练",
 
     "trainingType": "qa",
-    "chunkSize":8000,
-    "chunkSplitter":"",
-    "qaPrompt":"11",
+    "chunkSettingMode": "auto",
+    "qaPrompt":"",
 
     "metadata":{}
 }'
@@ -409,10 +409,6 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 - parentId： 父级ID，不填则默认为根目录
 - name: 集合名称（必填）
 - metadata： 元数据（暂时没啥用）
-- trainingType: 训练模式（必填）
-- chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
-- chunkSplitter: 自定义最高优先分割符号（可选）
-- qaPrompt: qa拆分自定义提示词（可选）
 {{% /alert %}}
 
 {{< /markdownify >}}
@@ -462,8 +458,7 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
     "parentId": null,
 
     "trainingType": "chunk",
-    "chunkSize":512,
-    "chunkSplitter":"",
+    "chunkSettingMode": "auto",
     "qaPrompt":"",
 
     "metadata":{
@@ -483,10 +478,6 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 - datasetId: 知识库的ID(必填)
 - parentId： 父级ID，不填则默认为根目录
 - metadata.webPageSelector: 网页选择器，用于指定网页中的哪个元素作为文本(可选)
-- trainingType:训练模式（必填）
-- chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
-- chunkSplitter: 自定义最高优先分割符号（可选）
-- qaPrompt: qa拆分自定义提示词（可选）
 {{% /alert %}}
 
 {{< /markdownify >}}
@@ -545,13 +536,7 @@ curl --location --request POST 'http://localhost:3000/api/core/dataset/collectio
 
 {{% alert icon=" " context="success" %}}
 - file: 文件
-- data: 知识库相关信息（json序列化后传入）
-  - datasetId: 知识库的ID(必填)
-  - parentId： 父级ID，不填则默认为根目录
-  - trainingType:训练模式（必填）
-  - chunkSize: 每个 chunk 的长度（可选）. chunk模式:100~3000; qa模式: 4000~模型最大token（16k模型通常建议不超过10000）
-  - chunkSplitter: 自定义最高优先分割符号（可选）
-  - qaPrompt: qa拆分自定义提示词（可选）
+- data: 知识库相关信息（json序列化后传入）,参数说明见上方“通用创建参数说明”
 {{% /alert %}}
 
 {{< /markdownify >}}

docSite/content/zh-cn/docs/development/sealos.md

@@ -138,7 +138,7 @@ FastGPT 商业版共包含了2个应用（fastgpt, fastgpt-plus）和2个数据
 SYSTEM_NAME=FastGPT
 SYSTEM_DESCRIPTION=
 SYSTEM_FAVICON=/favicon.ico
-HOME_URL=/app/list
+HOME_URL=/dashboard/apps
 ```
 
 SYSTEM_FAVICON 可以是一个网络地址

docSite/content/zh-cn/docs/development/upgrading/491.md

@@ -39,7 +39,7 @@ curl --location --request POST 'https://{{host}}/api/admin/initv491' \
 3. API 知识库支持 PDF 增强解析。
 4. 邀请团队成员，改为邀请链接模式。
 5. 支持混合检索权重设置。
-6. 支持重排模型选择和权重设置，同时调整了知识库搜索权重计算方式，改成 搜索权重 + 重排权重，而不是向量检索权重+全文检索权重+重排权重。
+6. 支持重排模型选择和权重设置，同时调整了知识库搜索权重计算方式，改成 搜索权重 + 重排权重，而不是向量检索权重+全文检索权重+重排权重。会对检索结果有一定影响，可以通过调整相关权重来进行数据适配。
 
 ## ⚙️ 优化