37a90b734d
Switch PDF layout parsing to use the PP-DocLayoutV3 ONNX model, replacing the previous Docling-based approach. Update all environment variables, model fetching, and manifest handling for the new model and its artifacts. Refactor block kind taxonomy throughout the codebase, tests, and UI to align with PP-DocLayoutV3 labels, including expanded and renamed block types. Revise document settings, block filtering, and stitching logic to support the new set of block kinds. Update documentation and environment variable references to reflect the model transition. BREAKING CHANGE: PDF parsing now requires PP-DocLayoutV3 ONNX model and updated environment variables; block kind names and settings have changed throughout the system.
95 lines
3.5 KiB
Docker
95 lines
3.5 KiB
Docker
# Stage 1: build whisper.cpp (no model download – the app handles that)
|
||
FROM alpine:3.23 AS whisper-builder
|
||
|
||
RUN apk add --no-cache git cmake build-base
|
||
|
||
WORKDIR /opt
|
||
|
||
ARG TARGETARCH
|
||
|
||
RUN git clone --depth 1 https://github.com/ggml-org/whisper.cpp.git && \
|
||
cd whisper.cpp && \
|
||
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF $( [ "$TARGETARCH" = "arm64" ] && echo "-DGGML_CPU_ARM_ARCH=armv8-a" || true ) && \
|
||
cmake --build build -j
|
||
RUN wget -qO /tmp/whisper.cpp-LICENSE.txt "https://raw.githubusercontent.com/ggml-org/whisper.cpp/master/LICENSE"
|
||
|
||
# Stage 1b: extract seaweedfs weed binary (for optional embedded weed mini)
|
||
# Pin to 4.18 because CI observed upload regressions on 4.19.
|
||
FROM chrislusf/seaweedfs:4.18 AS seaweedfs-builder
|
||
RUN cp "$(command -v weed)" /tmp/weed && \
|
||
(wget -qO /tmp/SeaweedFS-LICENSE.txt "https://raw.githubusercontent.com/seaweedfs/seaweedfs/master/LICENSE" || \
|
||
wget -qO /tmp/SeaweedFS-LICENSE.txt "https://raw.githubusercontent.com/seaweedfs/seaweedfs/main/LICENSE")
|
||
|
||
|
||
# Stage 2: build the Next.js app
|
||
FROM node:lts-alpine AS app-builder
|
||
|
||
# Install pnpm globally
|
||
RUN npm install -g pnpm@11.1.2
|
||
|
||
# Create app directory
|
||
WORKDIR /app
|
||
|
||
# Copy package files
|
||
COPY package.json pnpm-lock.yaml pnpm-workspace.yaml ./
|
||
|
||
# Install dependencies
|
||
RUN pnpm install --frozen-lockfile
|
||
|
||
# Copy project files
|
||
COPY . .
|
||
|
||
# Build the Next.js application
|
||
RUN pnpm exec next telemetry disable
|
||
RUN pnpm build
|
||
# Generate third-party dependency license report plus copied license files.
|
||
RUN mkdir -p /app/THIRD_PARTY_LICENSES && \
|
||
pnpm dlx license-checker-rseidelsohn@4.3.0 \
|
||
--production \
|
||
--json \
|
||
--relativeLicensePath \
|
||
--out /app/THIRD_PARTY_LICENSES/licenses.json \
|
||
--files /app/THIRD_PARTY_LICENSES/files
|
||
|
||
|
||
# Stage 3: minimal runtime image
|
||
FROM node:lts-alpine AS runner
|
||
|
||
# Add runtime OS dependencies:
|
||
# - libreoffice-writer: required for DOCX → PDF conversion
|
||
# ffmpeg is provided by ffmpeg-static from node_modules.
|
||
RUN apk add --no-cache ca-certificates libreoffice-writer
|
||
|
||
# Install pnpm globally for running the app
|
||
RUN npm install -g pnpm@11.1.2
|
||
|
||
# App runtime directory
|
||
WORKDIR /app
|
||
|
||
# Copy built app and dependencies from the builder stage
|
||
COPY --from=app-builder /app ./
|
||
# Include third-party license report and copied license texts at a stable path in the image.
|
||
COPY --from=app-builder /app/THIRD_PARTY_LICENSES /licenses
|
||
# Include SeaweedFS license text for the copied weed binary.
|
||
COPY --from=seaweedfs-builder /tmp/SeaweedFS-LICENSE.txt /licenses/SeaweedFS-LICENSE.txt
|
||
# Include static model notices for runtime-downloaded assets.
|
||
COPY src/lib/server/pdf-layout/model/LICENSE.txt /licenses/pp-doclayoutv3-LICENSE.txt
|
||
|
||
# Copy the compiled whisper.cpp build output into the runtime image
|
||
# (includes whisper-cli and its shared libraries, e.g. libwhisper.so, libggml.so)
|
||
COPY --from=whisper-builder /opt/whisper.cpp/build /opt/whisper.cpp/build
|
||
COPY --from=whisper-builder /tmp/whisper.cpp-LICENSE.txt /licenses/whisper.cpp-LICENSE.txt
|
||
# Copy seaweedfs weed binary for optional embedded local S3.
|
||
COPY --from=seaweedfs-builder /tmp/weed /usr/local/bin/weed
|
||
RUN chmod +x /usr/local/bin/weed
|
||
|
||
# Point the app at the compiled whisper-cli binary and ensure its libs are discoverable
|
||
ENV WHISPER_CPP_BIN=/opt/whisper.cpp/build/bin/whisper-cli
|
||
ENV LD_LIBRARY_PATH=/opt/whisper.cpp/build
|
||
|
||
# Expose the port the app runs on
|
||
EXPOSE 3003
|
||
|
||
# Start the application
|
||
ENTRYPOINT ["node", "scripts/openreader-entrypoint.mjs", "--"]
|
||
CMD ["pnpm", "start:raw"]
|