Docker

.dockerignore

@@ -0,0 +1,7 @@
+.git
+__pycache__/
+*.pyc
+results/
+.venv/
+.env
+.DS_Store

CHANGELOG.md

@@ -1,11 +1,28 @@
 # Change Log
 All notable changes to this project will be documented in this file.
 
+## Beta - 2026-01-27
+
+### Added
+- [x] Added Docker support to run PageIndex in a containerized environment.
+- [x] Added `Dockerfile` for building a reproducible CLI image.
+- [x] Added `docker-compose.yml` for simplified execution with volume mounting.
+- [x] Added `.dockerignore` to optimize Docker image size and build performance.
+- [x] Enabled execution of `run_pageindex.py` as the container entrypoint.
+
+### Changed
+- [x] Standardized execution environment using Python 3.11 slim image.
+- [x] Improved dependency installation reliability for PDF processing libraries.
+
+---
+
 ## Beta - 2025-04-23
 
 ### Fixed
 - [x] Fixed a bug introduced on April 18 where `start_index` was incorrectly passed.
 
+---
+
 ## Beta - 2025-04-03
 
 ### Added

Dockerfile

@@ -0,0 +1,21 @@
+# syntax=docker/dockerfile:1
+FROM python:3.11-slim
+
+# Dependencias del sistema.
+# DeepWiki menciona que si falla pymupdf, puede requerir libmupdf-dev. :contentReference[oaicite:1]{index=1}
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libmupdf-dev \
+    gcc \
+ && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Instala deps primero para aprovechar cache
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copia el resto del proyecto
+COPY . .
+
+# Por defecto, ejecuta el CLI (puedes pasar flags en docker run)
+ENTRYPOINT ["python", "run_pageindex.py"]

docker-compose.yml

@@ -0,0 +1,9 @@
+services:
+  pageindex:
+    build: .
+    image: pageindex:local
+    env_file:
+      - .env
+    volumes:
+      - ./data:/data
+      - ./results:/app/results