init

.github/workflows/code-style.yml

@@ -0,0 +1,16 @@
+name: Code style
+on: [push, pull_request]
+jobs:
+  code-style:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v4
+      - name: Check formatting
+        uses: chartboost/ruff-action@v1
+        with:
+          args: 'format --check'
+      - name: Check coding style
+        uses: chartboost/ruff-action@v1
+        with:
+          args: 'check --select F,E,W,I,PLW'

.github/workflows/docker-publish.yml

@@ -0,0 +1,81 @@
+name: Build and Publish Docker Image
+
+on:
+  push:
+    branches:
+      - master
+    tags:
+      - 'v*.*.*'  # Matches version tags like v1.0.0
+  workflow_dispatch:
+
+env:
+  DOCKER_HUB_NAMESPACE: pdfix
+  DOCKER_HUB_REPOSITORY: table-summary-openai
+
+jobs:
+  push_to_registry:
+    name: Push Docker image to Docker Hub
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+      attestations: write
+      id-token: write
+    steps:
+      - name: Check out the repo
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v2
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Set Docker tag
+        id: vars
+        run: |
+          if [[ $GITHUB_EVENT_NAME == 'workflow_dispatch' || $GITHUB_REF == refs/heads/master ]]; then
+            echo "tag=latest" >> $GITHUB_ENV
+          else
+            echo "tag=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
+          fi
+
+      - name: Update config.json version
+        run: chmod +x update_version.sh && ./update_version.sh ${{ env.tag }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: ${{ env.DOCKER_HUB_NAMESPACE }}/${{ env.DOCKER_HUB_REPOSITORY }}
+          tags: ${{ env.tag }}
+
+      - name: Build and push Docker image
+        id: push
+        uses: docker/build-push-action@v6
+        with:
+          platforms: linux/amd64 #,linux/arm64
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      # - name: Generate artifact attestation
+      #   uses: actions/attest-build-provenance@v1
+      #   with:
+      #     subject-name: index.docker.io/${{ env.DOCKER_HUB_NAMESPACE }}/${{ env.DOCKER_HUB_REPOSITORY }}:${{ env.tag }}
+      #     subject-digest: ${{ steps.push.outputs.digest }}
+      #     push-to-registry: true
+      - name: Docker Hub Description
+        uses: peter-evans/dockerhub-description@v4
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+          repository: ${{ env.DOCKER_HUB_NAMESPACE }}/${{ env.DOCKER_HUB_REPOSITORY }}

.gitignore

@@ -0,0 +1,9 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+.vscode
+
+build/
+dist/
+env/
+venv/
+.env/

Dockerfile

@@ -0,0 +1,32 @@
+# Use the official Debian slim image as a base
+FROM debian:bookworm-slim
+
+# Install necessary dependencies
+RUN apt-get update && \
+    apt-get install -y \
+    python3 \
+    python3-pip \
+    python3-venv \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /usr/tab-sum-openai/
+
+ENV VIRTUAL_ENV=venv
+
+
+# Create a virtual environment and install dependencies
+RUN python3 -m venv venv
+ENV PATH="$VIRTUAL_ENV/bin:$PATH"
+
+
+# Copy the source code and requirements.txt into the container
+COPY src/ /usr/tab-sum-openai/src/
+COPY requirements.txt /usr/tab-sum-openai/
+COPY config.json /usr/tab-sum-openai/
+
+
+RUN pip install --no-cache-dir -r requirements.txt 
+
+
+ENTRYPOINT ["/usr/tab-sum-openai/venv/bin/python3", "/usr/tab-sum-openai/src/main.py"]

README.md

@@ -0,0 +1,63 @@
+# Alt Text Generator OpenAI
+
+A Docker image that automatically generates and applies alternative image descriptions to PDF files using PDFix SDK and OpenAI.
+
+## Table of Contents
+
+- [Alt Text Generator OpenAI](#alt-text-generator-openai)
+  - [Table of Contents](#table-of-contents)
+  - [Getting Started](#getting-started)
+  - [Run using Command Line Interface](#run-using-command-line-interface)
+  - [Run Description Generation using REST API](#run-description-generation-using-rest-api)
+    - [Exporting Configuration for Integration](#exporting-configuration-for-integration)
+  - [License \& libraries used](#license--libraries-used)
+  - [Help \& Support](#help--support)
+
+
+## Getting Started
+
+To use this Docker application, you'll need to have Docker installed on your system. If Docker is not installed, please follow the instructions on the [official Docker website](https://docs.docker.com/get-docker/) to install it.
+
+
+## Run using Command Line Interface
+
+To run the docker container as CLI, you should share the folder containing the PDF for processing using the `-i` parameter. In this example, the current folder is used.
+
+```bash 
+docker run -v $(pwd):/data/ -w /data pdfix/alt-text-openai:latest detect -i document.pdf -o out.pdf --tags "Figure|Formula" --openai <api_key> --lang English --overwrite true
+```
+
+With an account-based PDFix License add these arguments.
+```bash
+--name ${LICENSE_NAME} --key ${LICENSE_KEY}
+```
+Contact support for more infomation.
+
+First run will pull the docker image, which may take some time. Make your own image for more advanced use.
+
+For more detailed information about the available command-line arguments, you can run the following command:
+
+```bash
+docker run --rm pdfix/alt-text-openai:latest --help
+```
+
+## Run Description Generation using REST API
+Comming soon. Please contact us.
+
+### Exporting Configuration for Integration
+To export the configuration JSON file, use the following command:
+```bash
+docker run -v $(pwd):/data -w /data --rm pdfix/alt-text-openai:latest config -o config.json
+```
+
+## License & libraries used
+- PDFix SDK - https://pdfix.net/terms
+- OpenAI API - https://openai.com/policies/
+
+Trial version of the PDFix SDK may apply a watermark on the page and redact random parts of the PDF including the scanned image in background. Contact us to get an evaluation or production license.
+
+## Help & Support
+To obtain a PDFix SDK license or report an issue please contact us at support@pdfix.net.
+For more information visit https://pdfix.net
+
+

config.json

@@ -0,0 +1,135 @@
+{
+  "actions": [
+    {
+      "name": "Table Summary Generator OpenAI",
+      "desc": "A Docker image that automatically generates and applies table summary to PDF files using PDFix SDK and OpenAI",
+      "version": {
+        "major": 1,
+        "minor": 0
+      },
+      "icon": "add_table_summary",
+      "category": "Tags",
+      "configurations": [
+        {
+          "program": "docker run --platform linux/amd64 -v \"${working_directory}:/data\" -w /data --rm pdfix/table-summary-openai:latest --name \"${license_name}\" --key \"${license_key}\" detect -i \"${input_pdf}\" -o \"${output_pdf}\" --tags \"${tag_name}\" --openai \"${openai_key}\" --lang \"${lang}\" --overwrite \"${overwrite}\"",
+          "name": "Generate Table Summary for all specified Tags",
+          "desc": "Generate Table Summary for all specified Tags"
+        }
+      ],
+      "args": [
+        {
+          "name": "input_pdf",
+          "desc": "Input PDF file",
+          "flags": 2,
+          "type": "file_path",
+          "ext": "pdf",
+          "value": ""
+        },
+        {
+          "name": "output_pdf",
+          "desc": "Output PDF file",
+          "flags": 4,
+          "type": "file_path",
+          "ext": "pdf",
+          "value": ""
+        },
+        {
+          "title": "OpenAI API Key",
+          "name": "openai_key",
+          "desc": "OpenAI API Key",
+          "type": "string",
+          "value": ""
+        },
+        {
+          "title": "Tag Name",
+          "name": "tag_name",
+          "desc": "Tag name defined by a regular expression",
+          "type": "string",
+          "value": "Table"
+        },
+        {
+          "title": "Language",
+          "name": "lang",
+          "desc": "Alternate description language",
+          "type": "string",
+          "value": "English",
+          "set": [
+            {
+              "value": "English"
+            },
+            {
+              "value": "Deutsch"
+            },
+            {
+              "value": "Español"
+            },
+            {
+              "value": "Français"
+            },
+            {
+              "value": "Italiano"
+            },
+            {
+              "value": "Português"
+            },
+            {
+              "value": "Nederlands"
+            },
+            {
+              "value": "Polski"
+            },
+            {
+              "value": "Русский"
+            },
+            {
+              "value": "中文"
+            },
+            {
+              "value": "日本語"
+            },
+            {
+              "value": "한국어"
+            },
+            {
+              "value": "Türkçe"
+            },
+            {
+              "value": "Svenska"
+            },
+            {
+              "value": "Norsk"
+            },
+            {
+              "value": "Suomi"
+            },
+            {
+              "value": "Čeština"
+            },
+            {
+              "value": "Magyar"
+            },
+            {
+              "value": "Slovenčina"
+            },
+            {
+              "value": "Українська"
+            },
+            {
+              "value": "Ελληνικά"
+            },
+            {
+              "value": "Română"
+            }
+          ]
+        },
+        {
+          "title": "Overwrite",
+          "desc": "Replace the alternate text if it exists",
+          "name": "overwrite",
+          "type": "bool",
+          "value": false
+        }
+      ]
+    }
+  ]
+}