Add document extraction providers for PdfPig, Azure, Mistral and VisionLanguageModel

.github/workflows/document-extraction.yml

@@ -0,0 +1,112 @@
+name: Document extraction
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - 'DocumentExtraction/**'
+      - 'Directory.Build.props'
+      - 'Directory.Build.targets'
+      - 'Directory.Packages.props'
+      - 'CommunityToolkit.AI.slnx'
+      - 'global.json'
+      - 'eng/Bootstrap-DocumentExtractionCore.ps1'
+      - 'eng/New-DocumentExtractionNuGetConfig.ps1'
+      - 'eng/Test-DocumentExtractionPackages.ps1'
+      - 'eng/DocumentExtraction.PackageSmoke/**'
+      - 'eng/LegacySupport.props'
+      - 'Shared/**'
+      - 'nuget.config'
+      - '.github/workflows/document-extraction.yml'
+  pull_request:
+    branches: [main, 'copilot/*']
+    paths:
+      - 'DocumentExtraction/**'
+      - 'Directory.Build.props'
+      - 'Directory.Build.targets'
+      - 'Directory.Packages.props'
+      - 'CommunityToolkit.AI.slnx'
+      - 'global.json'
+      - 'eng/Bootstrap-DocumentExtractionCore.ps1'
+      - 'eng/New-DocumentExtractionNuGetConfig.ps1'
+      - 'eng/Test-DocumentExtractionPackages.ps1'
+      - 'eng/DocumentExtraction.PackageSmoke/**'
+      - 'eng/LegacySupport.props'
+      - 'Shared/**'
+      - 'nuget.config'
+      - '.github/workflows/document-extraction.yml'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  DOTNET_NOLOGO: true
+  DOTNET_CLI_TELEMETRY_OPTOUT: true
+
+jobs:
+  bootstrap-core:
+    name: Pack pinned public upstream core
+    runs-on: windows-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-dotnet@v5
+        env:
+          DOTNET_INSTALL_DIR: ${{ runner.temp }}/document-extraction-sdk
+        with:
+          dotnet-version: 11.0.100-rc.3.26522.148
+      - name: Pack original owning upstream projects
+        shell: pwsh
+        env:
+          # Match the verified ordinary owning-project recipe rather than
+          # enabling upstream CI-only build defaults.
+          CI: 'false'
+        run: ./eng/Bootstrap-DocumentExtractionCore.ps1 -OutputDirectory "${{ runner.temp }}/document-extraction-core" -DotnetPath "${{ runner.temp }}/document-extraction-sdk/dotnet.exe"
+      - uses: actions/upload-artifact@v6
+        with:
+          name: document-extraction-core-source-packages
+          path: |
+            ${{ runner.temp }}/document-extraction-core/*.11.0.0-review.20261106.1.nupkg
+            ${{ runner.temp }}/document-extraction-core/core-bootstrap.json
+          if-no-files-found: error
+
+  build-test-pack:
+    name: Offline acceptance (${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    needs: bootstrap-core
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+    steps:
+      - uses: actions/checkout@v6
+      - uses: actions/setup-dotnet@v5
+        with:
+          global-json-file: global.json
+      - uses: actions/download-artifact@v7
+        with:
+          name: document-extraction-core-source-packages
+          path: ${{ runner.temp }}/document-extraction-core
+      - name: Configure isolated source-built core feed
+        shell: pwsh
+        run: ./eng/New-DocumentExtractionNuGetConfig.ps1 -CorePackageDirectory "${{ runner.temp }}/document-extraction-core" -OutputPath "${{ runner.temp }}/document-extraction-nuget.config"
+      - name: Restore exact dependencies
+        run: dotnet restore DocumentExtraction/DocumentExtraction.slnf --configfile "${{ runner.temp }}/document-extraction-nuget.config"
+      - name: Build
+        run: dotnet build DocumentExtraction/DocumentExtraction.slnf --no-restore -c Release
+      - name: Offline tests
+        run: dotnet test DocumentExtraction/DocumentExtraction.slnf --no-build --no-restore -c Release
+      - name: Restore portable test dependency closure
+        run: dotnet restore DocumentExtraction/DocumentExtraction.slnf -p:DocumentExtractionTestAsset=netstandard2.0 --configfile "${{ runner.temp }}/document-extraction-nuget.config"
+      - name: Offline tests using actual netstandard assets
+        run: dotnet test DocumentExtraction/DocumentExtraction.slnf --no-restore -c Release -p:DocumentExtractionTestAsset=netstandard2.0
+      - name: Pack preview artifacts
+        run: dotnet pack DocumentExtraction/DocumentExtraction.slnf --no-build --no-restore -c Release --output artifacts/document-extraction
+      - name: Verify packaged assets and experimental opt-in
+        shell: pwsh
+        run: ./eng/Test-DocumentExtractionPackages.ps1 -PackageDirectory artifacts/document-extraction -CorePackageDirectory "${{ runner.temp }}/document-extraction-core" -NuGetConfig "${{ runner.temp }}/document-extraction-nuget.config" -OutputDirectory "${{ runner.temp }}/document-extraction-package-checks"
+      - uses: actions/upload-artifact@v6
+        with:
+          name: document-extraction-preview-packages-${{ matrix.os }}
+          path: artifacts/document-extraction/*.nupkg
+          if-no-files-found: error

.gitignore

@@ -24,3 +24,7 @@ examples/perl/**/local/*
 **cpanfile.snapshot
 **/.modules/
 **/*.AppHost.TypeScript/nuget.config
+
+# Private review inputs and local test-generation reports.
+/.review-inputs/
+/.testagent/

CommunityToolkit.AI.slnx

@@ -21,6 +21,22 @@
     <Project Path="MEVD/src/SqlServer/SqlServer.csproj" />
     <Project Path="MEVD/src/Weaviate/Weaviate.csproj" />
   </Folder>
+  <Folder Name="/DocumentExtraction/src/">
+    <File Path="DocumentExtraction/src/Directory.Build.props" />
+    <Project Path="DocumentExtraction/src/PdfPig/PdfPig.csproj" />
+    <Project Path="DocumentExtraction/src/AzureContentUnderstanding/AzureContentUnderstanding.csproj" />
+    <Project Path="DocumentExtraction/src/AzureDocumentIntelligence/AzureDocumentIntelligence.csproj" />
+    <Project Path="DocumentExtraction/src/Mistral/Mistral.csproj" />
+    <Project Path="DocumentExtraction/src/VisionLanguageModel/VisionLanguageModel.csproj" />
+  </Folder>
+  <Folder Name="/DocumentExtraction/test/">
+    <File Path="DocumentExtraction/test/Directory.Build.props" />
+    <Project Path="DocumentExtraction/test/PdfPig.UnitTests/PdfPig.UnitTests.csproj" />
+    <Project Path="DocumentExtraction/test/AzureContentUnderstanding.UnitTests/AzureContentUnderstanding.UnitTests.csproj" />
+    <Project Path="DocumentExtraction/test/AzureDocumentIntelligence.UnitTests/AzureDocumentIntelligence.UnitTests.csproj" />
+    <Project Path="DocumentExtraction/test/Mistral.UnitTests/Mistral.UnitTests.csproj" />
+    <Project Path="DocumentExtraction/test/VisionLanguageModel.UnitTests/VisionLanguageModel.UnitTests.csproj" />
+  </Folder>
   <Folder Name="/MEVD/test/">
     <File Path="MEVD/test/Directory.Build.props" />
     <Project Path="MEVD/test/AzureAISearch.UnitTests/AzureAISearch.UnitTests.csproj" />

Directory.Packages.props

@@ -27,6 +27,17 @@
     <PackageVersion Include="sqlite-vec" Version="0.1.7-alpha.2.1" />
   </ItemGroup>
 
+  <ItemGroup Label="DocumentExtraction">
+    <PackageVersion Update="Microsoft.Extensions.AI.Abstractions" Version="11.0.0-review.20261106.1" Condition="'$(DocumentExtractionBuild)' == 'true'" />
+    <PackageVersion Update="System.Text.Json" Version="11.0.0-rc.3.26522.148" Condition="'$(DocumentExtractionBuild)' == 'true'" />
+    <PackageVersion Include="Microsoft.Extensions.Documents.Abstractions" Version="11.0.0-review.20261106.1" />
+    <PackageVersion Include="Microsoft.Extensions.DocumentExtraction.Abstractions" Version="11.0.0-review.20261106.1" />
+    <PackageVersion Include="Azure.AI.ContentUnderstanding" Version="1.1.0" />
+    <PackageVersion Include="Azure.AI.DocumentIntelligence" Version="1.0.0" />
+    <PackageVersion Include="Azure.Core" Version="1.53.0" />
+    <PackageVersion Include="PdfPig" Version="0.1.15" />
+  </ItemGroup>
+
   <ItemGroup Label="Build">
     <PackageVersion Include="Microsoft.SourceLink.GitHub" Version="10.0.401" />
   </ItemGroup>

DocumentExtraction/DocumentExtraction.slnf

@@ -0,0 +1,17 @@
+{
+  "solution": {
+    "path": "../CommunityToolkit.AI.slnx",
+    "projects": [
+      "DocumentExtraction/src/PdfPig/PdfPig.csproj",
+      "DocumentExtraction/src/AzureContentUnderstanding/AzureContentUnderstanding.csproj",
+      "DocumentExtraction/src/AzureDocumentIntelligence/AzureDocumentIntelligence.csproj",
+      "DocumentExtraction/src/Mistral/Mistral.csproj",
+      "DocumentExtraction/src/VisionLanguageModel/VisionLanguageModel.csproj",
+      "DocumentExtraction/test/PdfPig.UnitTests/PdfPig.UnitTests.csproj",
+      "DocumentExtraction/test/AzureContentUnderstanding.UnitTests/AzureContentUnderstanding.UnitTests.csproj",
+      "DocumentExtraction/test/AzureDocumentIntelligence.UnitTests/AzureDocumentIntelligence.UnitTests.csproj",
+      "DocumentExtraction/test/Mistral.UnitTests/Mistral.UnitTests.csproj",
+      "DocumentExtraction/test/VisionLanguageModel.UnitTests/VisionLanguageModel.UnitTests.csproj"
+    ]
+  }
+}