From c846f2ae3150fa9c130608f04a295b7dccdabc99 Mon Sep 17 00:00:00 2001
From: Yury Kossakovsky <kossakovsky93@gmail.com>
Date: Wed, 27 Aug 2025 13:46:02 -0600
Subject: [PATCH] Add PaddleOCR service configuration

- Added PaddleOCR hostname to .env.example for environment variable setup.
- Updated Caddyfile to include reverse proxy configuration for PaddleOCR.
- Modified docker-compose.yml to define PaddleOCR service with necessary commands and health checks.
- Enhanced service selection wizard to include PaddleOCR in the options.
- Updated final report script to display PaddleOCR service details if active.
---
 .env.example               |  1 +
 Caddyfile                  |  5 +++++
 docker-compose.yml         | 20 ++++++++++++++++++++
 scripts/04_wizard.sh       |  3 ++-
 scripts/06_final_report.sh |  9 +++++++++
 5 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/.env.example b/.env.example
index 068c510..970bd8f 100644
--- a/.env.example
+++ b/.env.example
@@ -147,6 +147,7 @@ PORTAINER_HOSTNAME=portainer.yourdomain.com
 POSTIZ_HOSTNAME=postiz.yourdomain.com
 LETTA_HOSTNAME=letta.yourdomain.com
 QDRANT_HOSTNAME=qdrant.yourdomain.com
+PADDLEOCR_HOSTNAME=paddleocr.yourdomain.com
 COMFYUI_HOSTNAME=comfyui.yourdomain.com
 RAGAPP_HOSTNAME=ragapp.yourdomain.com
 LETSENCRYPT_EMAIL=
diff --git a/Caddyfile b/Caddyfile
index 68b11e4..da48f67 100644
--- a/Caddyfile
+++ b/Caddyfile
@@ -104,6 +104,11 @@ https://{$NEO4J_HOSTNAME}:7687 {
     reverse_proxy neo4j:7687
 }
 
+# PaddleOCR (PaddleX Basic Serving)
+{$PADDLEOCR_HOSTNAME} {
+    reverse_proxy paddleocr:8080
+}
+
 import /etc/caddy/addons/*.conf
 
 # # SearXNG
diff --git a/docker-compose.yml b/docker-compose.yml
index 705dbdc..4ff7d0e 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -217,6 +217,7 @@ services:
       - PROMETHEUS_PASSWORD_HASH=${PROMETHEUS_PASSWORD_HASH}
       - PROMETHEUS_USERNAME=${PROMETHEUS_USERNAME}
       - QDRANT_HOSTNAME=${QDRANT_HOSTNAME}
+      - PADDLEOCR_HOSTNAME=${PADDLEOCR_HOSTNAME}
       - RAGAPP_HOSTNAME=${RAGAPP_HOSTNAME}
       - RAGAPP_PASSWORD_HASH=${RAGAPP_PASSWORD_HASH}
       - RAGAPP_USERNAME=${RAGAPP_USERNAME}
@@ -697,3 +698,22 @@ services:
     command: /bin/sh -c 'if [ -f /app/requirements.txt ]; then python -m pip install --no-cache-dir -r /app/requirements.txt; fi; python /app/main.py'
     volumes:
       - ./python-runner:/app
+
+  paddleocr:
+    image: paddlepaddle/paddle:latest
+    container_name: paddleocr
+    profiles: ["paddleocr"]
+    restart: unless-stopped
+    command: /bin/sh -c "set -e; \
+      apt-get update && apt-get install -y --no-install-recommends git wget && rm -rf /var/lib/apt/lists/*; \
+      python -m pip install --upgrade pip; \
+      pip install paddlex; \
+      paddlex --install serving; \
+      exec paddlex --serve --pipeline OCR --device cpu --port 8080"
+    healthcheck:
+      test: ["CMD-SHELL", "wget -qO- http://localhost:8080 > /dev/null || exit 1"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+    expose:
+      - "8080"
diff --git a/scripts/04_wizard.sh b/scripts/04_wizard.sh
index a802141..cced2f8 100755
--- a/scripts/04_wizard.sh
+++ b/scripts/04_wizard.sh
@@ -64,6 +64,7 @@ base_services_data=(
     "neo4j" "Neo4j (Graph Database)"
     "letta" "Letta (Agent Server & SDK)"
     "gotenberg" "Gotenberg (Document Conversion API)"
+    "paddleocr" "PaddleOCR (OCR API Server)"
     "crawl4ai" "Crawl4ai (Web Crawler for AI)"
     "ragapp" "RAGApp (Open-source RAG UI + API)"
     "open-webui" "Open WebUI (ChatGPT-like Interface)"
@@ -105,7 +106,7 @@ done
 
 # Use whiptail to display the checklist
 CHOICES=$(whiptail --title "Service Selection Wizard" --checklist \
-  "Choose the services you want to deploy.\nUse ARROW KEYS to navigate, SPACEBAR to select/deselect, ENTER to confirm." 32 90 21 \
+  "Choose the services you want to deploy.\nUse ARROW KEYS to navigate, SPACEBAR to select/deselect, ENTER to confirm." 32 90 22 \
   "${services[@]}" \
   3>&1 1>&2 2>&3)
 
diff --git a/scripts/06_final_report.sh b/scripts/06_final_report.sh
index bc05644..4df5943 100755
--- a/scripts/06_final_report.sh
+++ b/scripts/06_final_report.sh
@@ -195,6 +195,15 @@ if is_profile_active "gotenberg"; then
   echo "  Office to PDF: POST /forms/libreoffice/convert"
 fi
 
+if is_profile_active "paddleocr"; then
+  echo
+  echo "================================= PaddleOCR ==========================="
+  echo
+  echo "Host: ${PADDLEOCR_HOSTNAME:-<hostname_not_set>}"
+  echo "Internal Access (HTTP): http://paddleocr:8080"
+  echo "Notes: PaddleX Basic Serving (CPU), pipeline=OCR"
+fi
+
 if is_profile_active "python-runner"; then
   echo
   echo "================================= Python Runner ========================"