mirror of
https://github.com/DS4SD/docling.git
synced 2025-07-30 22:14:37 +00:00
7a5dc3c438
This commit completely revamps the Actor implementation with two major improvements:
1) CRITICAL CHANGE: Switch to official docling-serve image
* Now using quay.io/ds4sd/docling-serve-cpu:latest as base image
* Eliminates need for custom docling installation
* Ensures compatibility with latest docling-serve features
* Provides more reliable and consistent document processing
2) Fix Apify Actor KVS storage issues:
* Standardize key names to follow Apify conventions:
- Change "OUTPUT_RESULT" to "OUTPUT"
- Change "DOCLING_LOG" to "LOG"
* Add proper multi-stage Docker build:
- First stage builds dependencies including apify-cli
- Second stage uses official image and adds only necessary tools
* Fix permission issues in Docker container:
- Set up proper user and directory permissions
- Create writable directories for temporary files and models
- Configure environment variables for proper execution
3) Solve EACCES permission errors during CLI version checks:
* Create temporary HOME directory with proper write permissions
* Set APIFY_DISABLE_VERSION_CHECK=1 environment variable
* Add NODE_OPTIONS="--no-warnings" to suppress update checks
* Support --no-update-notifier CLI flag when available
4) Improve code organization and reliability:
* Create reusable upload_to_kvs() function for all KVS operations
* Ensure log files are uploaded before tools directory is removed
* Set proper MIME types based on output format
* Add detailed error reporting and proper cleanup
* Display final output URLs for easy verification
This major refactoring significantly improves reliability and maintainability by leveraging the official docling-serve image while solving persistent permission and storage issues. The Actor now properly follows Apify standards while providing a more robust document processing pipeline.
Signed-off-by: Václav Vančura <commit@vancura.dev>
84 lines
2.9 KiB
Docker
84 lines
2.9 KiB
Docker
# Build stage for installing dependencies
|
|
FROM node:20-slim AS builder
|
|
|
|
# Install necessary tools and prepare dependencies environment in one layer
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ca-certificates \
|
|
&& rm -rf /var/lib/apt/lists/* \
|
|
&& mkdir -p /build/bin /build/lib/node_modules \
|
|
&& cp /usr/local/bin/node /build/bin/
|
|
|
|
# Set working directory
|
|
WORKDIR /build
|
|
|
|
# Create package.json and install Apify CLI in one layer
|
|
RUN echo '{"name":"docling-actor-dependencies","version":"1.0.0","description":"Dependencies for Docling Actor","private":true,"type":"module","engines":{"node":">=18"}}' > package.json \
|
|
&& npm install apify-cli@latest \
|
|
&& cp -r node_modules/* lib/node_modules/ \
|
|
&& echo '#!/bin/sh\n/tmp/docling-tools/bin/node /tmp/docling-tools/lib/node_modules/apify-cli/bin/run "$@"' > bin/actor \
|
|
&& chmod +x bin/actor \
|
|
# Clean up npm cache to reduce image size
|
|
&& npm cache clean --force
|
|
|
|
# Final stage with docling-serve-cpu
|
|
FROM quay.io/ds4sd/docling-serve-cpu:latest
|
|
|
|
LABEL maintainer="Vaclav Vancura <@vancura>" \
|
|
description="Apify Actor for document processing using Docling" \
|
|
version="1.1.0"
|
|
|
|
# Set only essential environment variables
|
|
ENV PYTHONUNBUFFERED=1 \
|
|
PYTHONDONTWRITEBYTECODE=1 \
|
|
DOCLING_SERVE_HOST=0.0.0.0 \
|
|
DOCLING_SERVE_PORT=5001
|
|
|
|
# Switch to root temporarily to set up directories and permissions
|
|
USER root
|
|
WORKDIR /app
|
|
|
|
# Create all required directories and fix permissions in a single layer
|
|
RUN mkdir -p /build-files \
|
|
/tmp \
|
|
/tmp/actor-input \
|
|
/tmp/actor-output \
|
|
/tmp/actor-storage \
|
|
/tmp/apify_input \
|
|
/apify_input \
|
|
/opt/app-root/src/.EasyOCR/user_network \
|
|
/tmp/easyocr-models \
|
|
&& chown 1000:1000 /build-files \
|
|
&& chown -R 1000:1000 /opt/app-root/src/.EasyOCR \
|
|
&& chmod 1777 /tmp \
|
|
&& chmod 1777 /tmp/easyocr-models \
|
|
&& chmod 777 /tmp/actor-input /tmp/actor-output /tmp/actor-storage /tmp/apify_input /apify_input \
|
|
# Fix for uv_os_get_passwd error in Node.js
|
|
&& echo "docling:x:1000:1000:Docling User:/app:/bin/sh" >> /etc/passwd
|
|
|
|
# Set environment variable to tell EasyOCR to use a writable location for models
|
|
ENV EASYOCR_MODULE_PATH=/tmp/easyocr-models
|
|
|
|
# Copy only required files
|
|
COPY --chown=1000:1000 .actor/actor.sh .actor/actor.sh
|
|
COPY --chown=1000:1000 .actor/actor.json .actor/actor.json
|
|
COPY --chown=1000:1000 .actor/input_schema.json .actor/input_schema.json
|
|
RUN chmod +x .actor/actor.sh
|
|
|
|
# Copy the build files from builder
|
|
COPY --from=builder --chown=1000:1000 /build /build-files
|
|
|
|
# Switch to non-root user
|
|
USER 1000
|
|
|
|
# Set up TMPFS for temporary files
|
|
VOLUME ["/tmp"]
|
|
|
|
# Create additional volumes for OCR models persistence
|
|
VOLUME ["/tmp/easyocr-models"]
|
|
|
|
# Expose the docling-serve API port
|
|
EXPOSE 5001
|
|
|
|
# Run the actor script
|
|
ENTRYPOINT [".actor/actor.sh"]
|