feat: InferPage dockerization, model catalog expansion, and Ollama im…

.github/workflows/docker-publish-inferpage.yml

@@ -0,0 +1,66 @@
+name: Build and Publish InferPage Docker Images
+
+on:
+  push:
+    branches: [main]
+
+jobs:
+  docker:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up QEMU (for linux/arm64 cross-build)
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push CPU image (linux/amd64 + linux/arm64)
+        uses: docker/build-push-action@v6
+        with:
+          context: ./src
+          file: ./src/Dockerfile.inferpage
+          target: runtime-cpu
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ghcr.io/${{ github.repository_owner }}/main-inferpage:cpu
+            ghcr.io/${{ github.repository_owner }}/main-inferpage:latest
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Build and push CUDA image (linux/amd64)
+        uses: docker/build-push-action@v6
+        with:
+          context: ./src
+          file: ./src/Dockerfile.inferpage
+          target: runtime-cuda
+          platforms: linux/amd64
+          push: true
+          tags: ghcr.io/${{ github.repository_owner }}/main-inferpage:cuda
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Build and push Ollama-bundled image (linux/amd64 + linux/arm64)
+        uses: docker/build-push-action@v6
+        with:
+          context: ./src
+          file: ./src/Dockerfile.inferpage
+          target: runtime-ollama-bundled
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ghcr.io/${{ github.repository_owner }}/main-inferpage:ollama
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

scripts/docker-compose.inferpage-ollama.yml

@@ -0,0 +1,33 @@
+services:
+
+  ollama:
+    image: ollama/ollama:latest
+    container_name: ollama
+    restart: unless-stopped
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama-models:/root/.ollama
+    # Uncomment to enable NVIDIA GPU pass-through:
+    # deploy:
+    #   resources:
+    #     reservations:
+    #       devices:
+    #         - driver: nvidia
+    #           count: all
+    #           capabilities: [gpu]
+
+  inferpage:
+    image: ghcr.io/${GITHUB_OWNER}/main-inferpage:ollama
+    container_name: inferpage
+    restart: unless-stopped
+    ports:
+      - "5555:5555"
+    environment:
+      MaIN__OllamaBaseUrl: http://ollama:11434
+      MaIN__BackendType: 7
+    depends_on:
+      - ollama
+
+volumes:
+  ollama-models:

src/.dockerignore

@@ -0,0 +1,10 @@
+**/bin/
+**/obj/
+**/.vs/
+**/.idea/
+**/*.user
+**/*.suo
+MaIN.Core.UnitTests/
+MaIN.Core.IntegrationTests/
+MaIN.Core.E2ETests/
+**/appsettings.*.local.json

src/Dockerfile.inferpage

@@ -0,0 +1,111 @@
+FROM mcr.microsoft.com/dotnet/sdk:10.0 AS restore
+WORKDIR /src
+
+COPY MaIN.Domain/MaIN.Domain.csproj                 MaIN.Domain/
+COPY MaIN.Infrastructure/MaIN.Infrastructure.csproj MaIN.Infrastructure/
+COPY MaIN.Services/MaIN.Services.csproj              MaIN.Services/
+COPY MaIN.Core/MaIN.Core.csproj                      MaIN.Core/
+COPY MaIN.InferPage/MaIN.InferPage.csproj            MaIN.InferPage/
+
+RUN dotnet restore MaIN.InferPage/MaIN.InferPage.csproj
+
+FROM restore AS publish
+
+COPY MaIN.Domain/         MaIN.Domain/
+COPY MaIN.Infrastructure/ MaIN.Infrastructure/
+COPY MaIN.Services/       MaIN.Services/
+COPY MaIN.Core/           MaIN.Core/
+COPY MaIN.InferPage/      MaIN.InferPage/
+
+RUN dotnet publish MaIN.InferPage/MaIN.InferPage.csproj \
+    --framework net10.0 \
+    --configuration Release \
+    --no-restore \
+    --output /app/out
+
+FROM nvidia/cuda:12.9.1-runtime-ubuntu24.04 AS runtime-cuda
+
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends \
+        ca-certificates \
+        libicu74 \
+        libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY --from=mcr.microsoft.com/dotnet/aspnet:10.0 /usr/share/dotnet /usr/share/dotnet
+RUN ln -sf /usr/share/dotnet/dotnet /usr/local/bin/dotnet
+
+WORKDIR /app
+
+ENV DOTNET_ROOT=/usr/share/dotnet
+ENV ASPNETCORE_URLS=http://+:5555
+ENV ASPNETCORE_ENVIRONMENT=Production
+ENV MaIN__ModelsPath=/app/Models
+ENV NVIDIA_VISIBLE_DEVICES=all
+ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
+ENV LD_LIBRARY_PATH=/usr/lib/wsl/lib
+
+VOLUME /app/Models
+EXPOSE 5555
+
+COPY --from=publish /app/out .
+
+RUN find /app/runtimes/linux-x64/native -maxdepth 2 -mindepth 1 -type d \
+    | tee /etc/ld.so.conf.d/llamasharp.conf \
+    && ldconfig
+
+ENTRYPOINT ["dotnet", "MaIN.InferPage.dll"]
+
+FROM mcr.microsoft.com/dotnet/aspnet:10.0 AS runtime-cpu
+
+RUN apt-get update && apt-get install -y --no-install-recommends libgomp1 \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+ENV ASPNETCORE_URLS=http://+:5555
+ENV ASPNETCORE_ENVIRONMENT=Production
+ENV MaIN__ModelsPath=/app/Models
+
+VOLUME /app/Models
+EXPOSE 5555
+
+COPY --from=publish /app/out .
+
+ENTRYPOINT ["dotnet", "MaIN.InferPage.dll"]
+
+FROM mcr.microsoft.com/dotnet/aspnet:10.0 AS runtime-ollama
+
+WORKDIR /app
+
+ENV ASPNETCORE_URLS=http://+:5555
+ENV ASPNETCORE_ENVIRONMENT=Production
+ENV MaIN__OllamaBaseUrl=http://host.docker.internal:11434
+ENV MaIN__BackendType=7
+
+EXPOSE 5555
+
+COPY --from=publish /app/out .
+
+ENTRYPOINT ["dotnet", "MaIN.InferPage.dll"]
+
+FROM mcr.microsoft.com/dotnet/aspnet:10.0 AS runtime-ollama-bundled
+
+COPY --from=ollama/ollama:latest /usr/bin/ollama /usr/bin/ollama
+
+WORKDIR /app
+
+ENV ASPNETCORE_URLS=http://+:5555
+ENV ASPNETCORE_ENVIRONMENT=Production
+ENV MaIN__OllamaBaseUrl=http://localhost:11434
+ENV MaIN__BackendType=7
+
+VOLUME /root/.ollama
+EXPOSE 5555
+EXPOSE 11434
+
+COPY --from=publish /app/out .
+COPY entrypoint-ollama.sh /entrypoint.sh
+RUN chmod +x /entrypoint.sh
+
+ENTRYPOINT ["/entrypoint.sh"]

src/MaIN.Core/.nuspec

@@ -2,7 +2,7 @@
 <package>
   <metadata>
     <id>MaIN.NET</id>
-    <version>0.10.5</version>
+    <version>0.10.9</version>
     <authors>Wisedev</authors>
     <owners>Wisedev</owners>
     <icon>favicon.png</icon>

src/MaIN.Core/Hub/Contexts/Interfaces/ModelContext/IModelContext.cs

@@ -1,4 +1,6 @@
-using MaIN.Domain.Models.Abstract;
+using MaIN.Core.Hub.Contexts;
+using MaIN.Domain.Models.Abstract;
+using MaIN.Infrastructure.Models;
 
 namespace MaIN.Core.Hub.Contexts.Interfaces.ModelContext;
 
@@ -51,6 +53,8 @@ public interface IModelContext
     /// returning the context instance implementing <see cref="IModelContext"/> for method chaining.</returns>
     Task<IModelContext> DownloadAsync(string modelId, CancellationToken cancellationToken = default);
 
+    Task<IModelContext> DownloadAsync(string modelId, IProgress<DownloadProgress>? progress, CancellationToken cancellationToken = default);
+
     /// <summary>
     /// Ensures a known local model is downloaded before use. If the model is already present on disk the call
     /// returns immediately; if not, the model is downloaded. Cloud models are silently skipped.
@@ -62,6 +66,8 @@ public interface IModelContext
     /// <see cref="IModelContext"/> for method chaining.</returns>
     Task<IModelContext> EnsureDownloadedAsync(string modelId, CancellationToken cancellationToken = default);
 
+    Task<IModelContext> EnsureDownloadedAsync(string modelId, IProgress<DownloadProgress>? progress, CancellationToken cancellationToken = default);
+
     /// <summary>
     /// Ensures a known local model is downloaded before use using a strongly-typed model reference.
     /// If the model is already present on disk the call returns immediately; if not, the model is downloaded.