الميزات: إضافة أدوات جديدة لمعالجة ملفات PDF، تشمل التلخيص والترجمة واستخراج الجداول.

- تفعيل مكون SummarizePdf لإنشاء ملخصات PDF باستخدام الذكاء الاصطناعي.

- تفعيل مكون TranslatePdf لترجمة محتوى PDF إلى لغات متعددة.

- تفعيل مكون TableExtractor لاستخراج الجداول من ملفات PDF.

- تحديث الصفحة الرئيسية والتوجيه ليشمل الأدوات الجديدة.

- إضافة ترجمات للأدوات الجديدة باللغات الإنجليزية والعربية والفرنسية.

- توسيع أنواع واجهة برمجة التطبيقات (API) لدعم الميزات الجديدة المتعلقة بمعالجة ملفات PDF. --feat: Initialize frontend with React, Vite, and Tailwind CSS

- Set up main entry point for React application.
- Create About, Home, NotFound, Privacy, and Terms pages with SEO support.
- Implement API service for file uploads and task management.
- Add global styles using Tailwind CSS.
- Create utility functions for SEO and text processing.
- Configure Vite for development and production builds.
- Set up Nginx configuration for serving frontend and backend.
- Add scripts for cleanup of expired files and sitemap generation.
- Implement deployment script for production environment.

backend/app/__init__.py

@@ -93,6 +93,11 @@ def create_app(config_name=None):
     from app.routes.ocr import ocr_bp
     from app.routes.removebg import removebg_bp
     from app.routes.pdf_editor import pdf_editor_bp
+    from app.routes.compress_image import compress_image_bp
+    from app.routes.pdf_to_excel import pdf_to_excel_bp
+    from app.routes.qrcode import qrcode_bp
+    from app.routes.html_to_pdf import html_to_pdf_bp
+    from app.routes.pdf_ai import pdf_ai_bp
 
     app.register_blueprint(health_bp, url_prefix="/api")
     app.register_blueprint(auth_bp, url_prefix="/api/auth")
@@ -112,5 +117,10 @@ def create_app(config_name=None):
     app.register_blueprint(ocr_bp, url_prefix="/api/ocr")
     app.register_blueprint(removebg_bp, url_prefix="/api/remove-bg")
     app.register_blueprint(pdf_editor_bp, url_prefix="/api/pdf-editor")
+    app.register_blueprint(compress_image_bp, url_prefix="/api/image")
+    app.register_blueprint(pdf_to_excel_bp, url_prefix="/api/convert")
+    app.register_blueprint(qrcode_bp, url_prefix="/api/qrcode")
+    app.register_blueprint(html_to_pdf_bp, url_prefix="/api/convert")
+    app.register_blueprint(pdf_ai_bp, url_prefix="/api/pdf-ai")
 
     return app

backend/app/extensions.py

@@ -35,6 +35,11 @@ def init_celery(app):
         "app.tasks.ocr_tasks.*": {"queue": "image"},
         "app.tasks.removebg_tasks.*": {"queue": "image"},
         "app.tasks.pdf_editor_tasks.*": {"queue": "pdf_tools"},
+        "app.tasks.compress_image_tasks.*": {"queue": "image"},
+        "app.tasks.pdf_to_excel_tasks.*": {"queue": "pdf_tools"},
+        "app.tasks.qrcode_tasks.*": {"queue": "default"},
+        "app.tasks.html_to_pdf_tasks.*": {"queue": "convert"},
+        "app.tasks.pdf_ai_tasks.*": {"queue": "default"},
     }
 
     # Celery Beat — periodic tasks

backend/app/routes/compress_image.py

@@ -0,0 +1,72 @@
+"""Image compression routes."""
+from flask import Blueprint, request, jsonify
+
+from app.extensions import limiter
+from app.services.policy_service import (
+    assert_quota_available,
+    build_task_tracking_kwargs,
+    PolicyError,
+    record_accepted_usage,
+    resolve_web_actor,
+    validate_actor_file,
+)
+from app.utils.file_validator import FileValidationError
+from app.utils.sanitizer import generate_safe_path
+from app.tasks.compress_image_tasks import compress_image_task
+
+compress_image_bp = Blueprint("compress_image", __name__)
+
+ALLOWED_IMAGE_TYPES = ["png", "jpg", "jpeg", "webp"]
+
+
+@compress_image_bp.route("/compress", methods=["POST"])
+@limiter.limit("10/minute")
+def compress_image_route():
+    """
+    Compress an image file.
+
+    Accepts: multipart/form-data with:
+        - 'file': Image file (PNG, JPG, JPEG, WebP)
+        - 'quality' (optional): Quality 1-100 (default: 75)
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    quality = request.form.get("quality", "75")
+
+    try:
+        quality = max(1, min(100, int(quality)))
+    except ValueError:
+        quality = 75
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=ALLOWED_IMAGE_TYPES, actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = compress_image_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        quality,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "compress-image", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Image compression started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/routes/html_to_pdf.py

@@ -0,0 +1,62 @@
+"""HTML to PDF conversion routes."""
+from flask import Blueprint, request, jsonify
+
+from app.extensions import limiter
+from app.services.policy_service import (
+    assert_quota_available,
+    build_task_tracking_kwargs,
+    PolicyError,
+    record_accepted_usage,
+    resolve_web_actor,
+    validate_actor_file,
+)
+from app.utils.file_validator import FileValidationError
+from app.utils.sanitizer import generate_safe_path
+from app.tasks.html_to_pdf_tasks import html_to_pdf_task
+
+html_to_pdf_bp = Blueprint("html_to_pdf", __name__)
+
+
+@html_to_pdf_bp.route("/html-to-pdf", methods=["POST"])
+@limiter.limit("10/minute")
+def html_to_pdf_route():
+    """
+    Convert an HTML file to PDF.
+
+    Accepts: multipart/form-data with:
+        - 'file': HTML file
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["html", "htm"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = html_to_pdf_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "html-to-pdf", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "HTML to PDF conversion started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/routes/pdf_ai.py

@@ -0,0 +1,232 @@
+"""PDF AI tool routes — Chat, Summarize, Translate, Table Extract."""
+from flask import Blueprint, request, jsonify
+
+from app.extensions import limiter
+from app.services.policy_service import (
+    assert_quota_available,
+    build_task_tracking_kwargs,
+    PolicyError,
+    record_accepted_usage,
+    resolve_web_actor,
+    validate_actor_file,
+)
+from app.utils.file_validator import FileValidationError
+from app.utils.sanitizer import generate_safe_path
+from app.tasks.pdf_ai_tasks import (
+    chat_with_pdf_task,
+    summarize_pdf_task,
+    translate_pdf_task,
+    extract_tables_task,
+)
+
+pdf_ai_bp = Blueprint("pdf_ai", __name__)
+
+
+# ---------------------------------------------------------------------------
+# Chat with PDF — POST /api/pdf-ai/chat
+# ---------------------------------------------------------------------------
+@pdf_ai_bp.route("/chat", methods=["POST"])
+@limiter.limit("10/minute")
+def chat_pdf_route():
+    """
+    Ask a question about a PDF document.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+        - 'question': The question to ask
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    question = request.form.get("question", "").strip()
+
+    if not question:
+        return jsonify({"error": "No question provided."}), 400
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["pdf"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = chat_with_pdf_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        question,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "chat-pdf", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Processing your question. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202
+
+
+# ---------------------------------------------------------------------------
+# Summarize PDF — POST /api/pdf-ai/summarize
+# ---------------------------------------------------------------------------
+@pdf_ai_bp.route("/summarize", methods=["POST"])
+@limiter.limit("10/minute")
+def summarize_pdf_route():
+    """
+    Generate a summary of a PDF document.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+        - 'length' (optional): "short", "medium", or "long"
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    length = request.form.get("length", "medium").strip()
+
+    if length not in ("short", "medium", "long"):
+        length = "medium"
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["pdf"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = summarize_pdf_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        length,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "summarize-pdf", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Summarizing document. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202
+
+
+# ---------------------------------------------------------------------------
+# Translate PDF — POST /api/pdf-ai/translate
+# ---------------------------------------------------------------------------
+@pdf_ai_bp.route("/translate", methods=["POST"])
+@limiter.limit("10/minute")
+def translate_pdf_route():
+    """
+    Translate a PDF document to another language.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+        - 'target_language': Target language name
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    target_language = request.form.get("target_language", "").strip()
+
+    if not target_language:
+        return jsonify({"error": "No target language specified."}), 400
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["pdf"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = translate_pdf_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        target_language,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "translate-pdf", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Translating document. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202
+
+
+# ---------------------------------------------------------------------------
+# Extract Tables — POST /api/pdf-ai/extract-tables
+# ---------------------------------------------------------------------------
+@pdf_ai_bp.route("/extract-tables", methods=["POST"])
+@limiter.limit("10/minute")
+def extract_tables_route():
+    """
+    Extract tables from a PDF document.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["pdf"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = extract_tables_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "extract-tables", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Extracting tables. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/routes/pdf_to_excel.py

@@ -0,0 +1,62 @@
+"""PDF to Excel conversion routes."""
+from flask import Blueprint, request, jsonify
+
+from app.extensions import limiter
+from app.services.policy_service import (
+    assert_quota_available,
+    build_task_tracking_kwargs,
+    PolicyError,
+    record_accepted_usage,
+    resolve_web_actor,
+    validate_actor_file,
+)
+from app.utils.file_validator import FileValidationError
+from app.utils.sanitizer import generate_safe_path
+from app.tasks.pdf_to_excel_tasks import pdf_to_excel_task
+
+pdf_to_excel_bp = Blueprint("pdf_to_excel", __name__)
+
+
+@pdf_to_excel_bp.route("/pdf-to-excel", methods=["POST"])
+@limiter.limit("10/minute")
+def pdf_to_excel_route():
+    """
+    Convert a PDF containing tables to an Excel file.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(
+            file, allowed_types=["pdf"], actor=actor
+        )
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = pdf_to_excel_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "pdf-to-excel", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "PDF to Excel conversion started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/routes/pdf_tools.py

@@ -25,6 +25,9 @@ from app.tasks.pdf_tools_tasks import (
     watermark_pdf_task,
     protect_pdf_task,
     unlock_pdf_task,
+    remove_watermark_task,
+    reorder_pdf_task,
+    extract_pages_task,
 )
 
 pdf_tools_bp = Blueprint("pdf_tools", __name__)
@@ -554,3 +557,161 @@ def unlock_pdf_route():
         "task_id": task.id,
         "message": "Unlock started. Poll /api/tasks/{task_id}/status for progress.",
     }), 202
+
+
+# ---------------------------------------------------------------------------
+# Remove Watermark  — POST /api/pdf-tools/remove-watermark
+# ---------------------------------------------------------------------------
+@pdf_tools_bp.route("/remove-watermark", methods=["POST"])
+@limiter.limit("10/minute")
+def remove_watermark_route():
+    """
+    Remove watermark from a PDF.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(file, allowed_types=["pdf"], actor=actor)
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = remove_watermark_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "remove-watermark", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Watermark removal started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202
+
+
+# ---------------------------------------------------------------------------
+# Reorder PDF Pages  — POST /api/pdf-tools/reorder
+# ---------------------------------------------------------------------------
+@pdf_tools_bp.route("/reorder", methods=["POST"])
+@limiter.limit("10/minute")
+def reorder_pdf_route():
+    """
+    Reorder pages in a PDF.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+        - 'page_order': Comma-separated page numbers in desired order (e.g. "3,1,2")
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    page_order_str = request.form.get("page_order", "").strip()
+
+    if not page_order_str:
+        return jsonify({"error": "Page order is required (e.g. '3,1,2')."}), 400
+
+    try:
+        page_order = [int(p.strip()) for p in page_order_str.split(",") if p.strip()]
+    except ValueError:
+        return jsonify({"error": "Invalid page order. Use comma-separated numbers (e.g. '3,1,2')."}), 400
+
+    if not page_order:
+        return jsonify({"error": "Page order is required."}), 400
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(file, allowed_types=["pdf"], actor=actor)
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = reorder_pdf_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        page_order,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "reorder-pdf", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Reorder started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202
+
+
+# ---------------------------------------------------------------------------
+# Extract Pages  — POST /api/pdf-tools/extract-pages
+# ---------------------------------------------------------------------------
+@pdf_tools_bp.route("/extract-pages", methods=["POST"])
+@limiter.limit("10/minute")
+def extract_pages_route():
+    """
+    Extract specific pages from a PDF into a new PDF.
+
+    Accepts: multipart/form-data with:
+        - 'file': PDF file
+        - 'pages': Page specification (e.g. "1,3,5-8")
+    Returns: JSON with task_id for polling
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file provided."}), 400
+
+    file = request.files["file"]
+    pages = request.form.get("pages", "").strip()
+
+    if not pages:
+        return jsonify({"error": "Pages specification is required (e.g. '1,3,5-8')."}), 400
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    try:
+        original_filename, ext = validate_actor_file(file, allowed_types=["pdf"], actor=actor)
+    except FileValidationError as e:
+        return jsonify({"error": e.message}), e.code
+
+    task_id, input_path = generate_safe_path(ext, folder_type="upload")
+    file.save(input_path)
+
+    task = extract_pages_task.delay(
+        input_path,
+        task_id,
+        original_filename,
+        pages,
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "extract-pages", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "Page extraction started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/routes/qrcode.py

@@ -0,0 +1,66 @@
+"""QR code generation routes."""
+import uuid
+
+from flask import Blueprint, request, jsonify
+
+from app.extensions import limiter
+from app.services.policy_service import (
+    assert_quota_available,
+    build_task_tracking_kwargs,
+    PolicyError,
+    record_accepted_usage,
+    resolve_web_actor,
+)
+from app.tasks.qrcode_tasks import generate_qr_task
+
+qrcode_bp = Blueprint("qrcode", __name__)
+
+
+@qrcode_bp.route("/generate", methods=["POST"])
+@limiter.limit("20/minute")
+def generate_qr_route():
+    """
+    Generate a QR code from text or URL.
+
+    Accepts: JSON or form-data with:
+        - 'data': Text/URL to encode
+        - 'size' (optional): Image size 100-2000 (default: 300)
+    Returns: JSON with task_id for polling
+    """
+    if request.is_json:
+        body = request.get_json(silent=True) or {}
+        data = body.get("data", "")
+        size = body.get("size", 300)
+    else:
+        data = request.form.get("data", "")
+        size = request.form.get("size", "300")
+
+    if not data or not str(data).strip():
+        return jsonify({"error": "No data provided for QR code."}), 400
+
+    try:
+        size = max(100, min(2000, int(size)))
+    except (ValueError, TypeError):
+        size = 300
+
+    actor = resolve_web_actor()
+    try:
+        assert_quota_available(actor)
+    except PolicyError as e:
+        return jsonify({"error": e.message}), e.status_code
+
+    task_id = str(uuid.uuid4())
+
+    task = generate_qr_task.delay(
+        task_id,
+        str(data).strip(),
+        size,
+        "png",
+        **build_task_tracking_kwargs(actor),
+    )
+    record_accepted_usage(actor, "qr-code", task.id)
+
+    return jsonify({
+        "task_id": task.id,
+        "message": "QR code generation started. Poll /api/tasks/{task_id}/status for progress.",
+    }), 202

backend/app/services/compress_image_service.py

@@ -0,0 +1,90 @@
+"""Image compression service using Pillow."""
+import os
+import logging
+
+from PIL import Image
+
+logger = logging.getLogger(__name__)
+
+
+class CompressImageError(Exception):
+    """Custom exception for image compression failures."""
+    pass
+
+
+FORMAT_MAP = {
+    "jpg": "JPEG",
+    "jpeg": "JPEG",
+    "png": "PNG",
+    "webp": "WEBP",
+}
+
+
+def compress_image(
+    input_path: str,
+    output_path: str,
+    quality: int = 75,
+) -> dict:
+    """
+    Compress an image by reducing quality and optimizing encoding.
+
+    Args:
+        input_path: Path to the input image
+        output_path: Path for the compressed image
+        quality: Output quality 1-100
+
+    Returns:
+        dict with original_size, compressed_size, reduction_percent
+
+    Raises:
+        CompressImageError: If compression fails
+    """
+    quality = max(1, min(100, quality))
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+    try:
+        original_size = os.path.getsize(input_path)
+
+        with Image.open(input_path) as img:
+            width, height = img.size
+            ext = os.path.splitext(output_path)[1].lower().strip(".")
+            pil_format = FORMAT_MAP.get(ext, "JPEG")
+
+            # Convert RGBA to RGB for JPEG
+            if pil_format == "JPEG" and img.mode in ("RGBA", "P", "LA"):
+                background = Image.new("RGB", img.size, (255, 255, 255))
+                if img.mode == "P":
+                    img = img.convert("RGBA")
+                background.paste(
+                    img, mask=img.split()[-1] if "A" in img.mode else None
+                )
+                img = background
+
+            save_kwargs = {"optimize": True}
+            if pil_format in ("JPEG", "WEBP"):
+                save_kwargs["quality"] = quality
+            elif pil_format == "PNG":
+                save_kwargs["compress_level"] = 9
+
+            img.save(output_path, format=pil_format, **save_kwargs)
+
+        compressed_size = os.path.getsize(output_path)
+        reduction = round(
+            (1 - compressed_size / original_size) * 100, 1
+        ) if original_size > 0 else 0
+
+        logger.info(
+            f"Image compression: {original_size} → {compressed_size} "
+            f"({reduction}% reduction)"
+        )
+
+        return {
+            "original_size": original_size,
+            "compressed_size": compressed_size,
+            "reduction_percent": reduction,
+            "width": width,
+            "height": height,
+        }
+
+    except (IOError, OSError, Image.DecompressionBombError) as e:
+        raise CompressImageError(f"Image compression failed: {str(e)}")

backend/app/services/html_to_pdf_service.py

@@ -0,0 +1,84 @@
+"""HTML to PDF conversion service."""
+import os
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class HtmlToPdfError(Exception):
+    """Custom exception for HTML to PDF conversion failures."""
+    pass
+
+
+def html_to_pdf(
+    input_path: str,
+    output_path: str,
+) -> dict:
+    """
+    Convert an HTML file to PDF.
+
+    Args:
+        input_path: Path to the input HTML file
+        output_path: Path for the output PDF
+
+    Returns:
+        dict with output_size
+
+    Raises:
+        HtmlToPdfError: If conversion fails
+    """
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+    try:
+        from weasyprint import HTML
+
+        HTML(filename=input_path).write_pdf(output_path)
+
+        output_size = os.path.getsize(output_path)
+        logger.info(f"HTML→PDF conversion completed ({output_size} bytes)")
+
+        return {
+            "output_size": output_size,
+        }
+
+    except ImportError:
+        raise HtmlToPdfError("weasyprint library is not installed.")
+    except Exception as e:
+        raise HtmlToPdfError(f"Failed to convert HTML to PDF: {str(e)}")
+
+
+def html_string_to_pdf(
+    html_content: str,
+    output_path: str,
+) -> dict:
+    """
+    Convert an HTML string to PDF.
+
+    Args:
+        html_content: HTML content as string
+        output_path: Path for the output PDF
+
+    Returns:
+        dict with output_size
+
+    Raises:
+        HtmlToPdfError: If conversion fails
+    """
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+    try:
+        from weasyprint import HTML
+
+        HTML(string=html_content).write_pdf(output_path)
+
+        output_size = os.path.getsize(output_path)
+        logger.info(f"HTML string→PDF conversion completed ({output_size} bytes)")
+
+        return {
+            "output_size": output_size,
+        }
+
+    except ImportError:
+        raise HtmlToPdfError("weasyprint library is not installed.")
+    except Exception as e:
+        raise HtmlToPdfError(f"Failed to convert HTML to PDF: {str(e)}")

backend/app/services/pdf_ai_service.py

@@ -0,0 +1,266 @@
+"""PDF AI services — Chat, Summarize, Translate, Table Extract."""
+import os
+import json
+import logging
+
+import requests
+
+logger = logging.getLogger(__name__)
+
+# Configuration
+OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY", "")
+OPENROUTER_MODEL = os.getenv("OPENROUTER_MODEL", "meta-llama/llama-3-8b-instruct")
+OPENROUTER_BASE_URL = os.getenv(
+    "OPENROUTER_BASE_URL", "https://openrouter.ai/api/v1/chat/completions"
+)
+
+
+class PdfAiError(Exception):
+    """Custom exception for PDF AI service failures."""
+    pass
+
+
+def _extract_text_from_pdf(input_path: str, max_pages: int = 50) -> str:
+    """Extract text content from a PDF file."""
+    try:
+        from PyPDF2 import PdfReader
+
+        reader = PdfReader(input_path)
+        pages = reader.pages[:max_pages]
+        texts = []
+        for i, page in enumerate(pages):
+            text = page.extract_text() or ""
+            if text.strip():
+                texts.append(f"[Page {i + 1}]\n{text}")
+        return "\n\n".join(texts)
+    except Exception as e:
+        raise PdfAiError(f"Failed to extract text from PDF: {str(e)}")
+
+
+def _call_openrouter(system_prompt: str, user_message: str, max_tokens: int = 1000) -> str:
+    """Send a request to OpenRouter API and return the reply."""
+    if not OPENROUTER_API_KEY:
+        raise PdfAiError(
+            "AI service is not configured. Set OPENROUTER_API_KEY environment variable."
+        )
+
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": user_message},
+    ]
+
+    try:
+        response = requests.post(
+            OPENROUTER_BASE_URL,
+            headers={
+                "Authorization": f"Bearer {OPENROUTER_API_KEY}",
+                "Content-Type": "application/json",
+            },
+            json={
+                "model": OPENROUTER_MODEL,
+                "messages": messages,
+                "max_tokens": max_tokens,
+                "temperature": 0.5,
+            },
+            timeout=60,
+        )
+        response.raise_for_status()
+        data = response.json()
+
+        reply = (
+            data.get("choices", [{}])[0]
+            .get("message", {})
+            .get("content", "")
+            .strip()
+        )
+
+        if not reply:
+            raise PdfAiError("AI returned an empty response. Please try again.")
+
+        return reply
+
+    except requests.exceptions.Timeout:
+        raise PdfAiError("AI service timed out. Please try again.")
+    except requests.exceptions.RequestException as e:
+        logger.error(f"OpenRouter API error: {e}")
+        raise PdfAiError("AI service is temporarily unavailable.")
+
+
+# ---------------------------------------------------------------------------
+# 1. Chat with PDF
+# ---------------------------------------------------------------------------
+def chat_with_pdf(input_path: str, question: str) -> dict:
+    """
+    Answer a question about a PDF document.
+
+    Args:
+        input_path: Path to the PDF file
+        question: User's question about the document
+
+    Returns:
+        {"reply": "...", "pages_analyzed": int}
+    """
+    if not question or not question.strip():
+        raise PdfAiError("Please provide a question.")
+
+    text = _extract_text_from_pdf(input_path)
+    if not text.strip():
+        raise PdfAiError("Could not extract any text from the PDF.")
+
+    # Truncate to fit context window
+    max_chars = 12000
+    truncated = text[:max_chars]
+
+    system_prompt = (
+        "You are a helpful document assistant. The user has uploaded a PDF document. "
+        "Answer questions about the document based only on the content provided. "
+        "If the answer is not in the document, say so. "
+        "Reply in the same language the user uses."
+    )
+
+    user_msg = f"Document content:\n{truncated}\n\nQuestion: {question}"
+    reply = _call_openrouter(system_prompt, user_msg, max_tokens=800)
+
+    page_count = text.count("[Page ")
+    return {"reply": reply, "pages_analyzed": page_count}
+
+
+# ---------------------------------------------------------------------------
+# 2. Summarize PDF
+# ---------------------------------------------------------------------------
+def summarize_pdf(input_path: str, length: str = "medium") -> dict:
+    """
+    Generate a summary of a PDF document.
+
+    Args:
+        input_path: Path to the PDF file
+        length: Summary length — "short", "medium", or "long"
+
+    Returns:
+        {"summary": "...", "pages_analyzed": int}
+    """
+    text = _extract_text_from_pdf(input_path)
+    if not text.strip():
+        raise PdfAiError("Could not extract any text from the PDF.")
+
+    length_instruction = {
+        "short": "Provide a brief summary in 2-3 sentences.",
+        "medium": "Provide a summary in 1-2 paragraphs covering the main points.",
+        "long": "Provide a detailed summary covering all key points, arguments, and conclusions.",
+    }.get(length, "Provide a summary in 1-2 paragraphs covering the main points.")
+
+    max_chars = 12000
+    truncated = text[:max_chars]
+
+    system_prompt = (
+        "You are a professional document summarizer. "
+        "Summarize the document accurately and concisely. "
+        "Reply in the same language as the document."
+    )
+
+    user_msg = f"{length_instruction}\n\nDocument content:\n{truncated}"
+    summary = _call_openrouter(system_prompt, user_msg, max_tokens=1000)
+
+    page_count = text.count("[Page ")
+    return {"summary": summary, "pages_analyzed": page_count}
+
+
+# ---------------------------------------------------------------------------
+# 3. Translate PDF
+# ---------------------------------------------------------------------------
+def translate_pdf(input_path: str, target_language: str) -> dict:
+    """
+    Translate the text content of a PDF to another language.
+
+    Args:
+        input_path: Path to the PDF file
+        target_language: Target language name (e.g. "English", "Arabic", "French")
+
+    Returns:
+        {"translation": "...", "pages_analyzed": int, "target_language": str}
+    """
+    if not target_language or not target_language.strip():
+        raise PdfAiError("Please specify a target language.")
+
+    text = _extract_text_from_pdf(input_path)
+    if not text.strip():
+        raise PdfAiError("Could not extract any text from the PDF.")
+
+    max_chars = 10000
+    truncated = text[:max_chars]
+
+    system_prompt = (
+        f"You are a professional translator. Translate the following document "
+        f"content into {target_language}. Preserve the original formatting and "
+        f"structure as much as possible. Only output the translation, nothing else."
+    )
+
+    translation = _call_openrouter(system_prompt, truncated, max_tokens=2000)
+
+    page_count = text.count("[Page ")
+    return {
+        "translation": translation,
+        "pages_analyzed": page_count,
+        "target_language": target_language,
+    }
+
+
+# ---------------------------------------------------------------------------
+# 4. Extract Tables from PDF
+# ---------------------------------------------------------------------------
+def extract_tables(input_path: str) -> dict:
+    """
+    Extract tables from a PDF and return them as structured data.
+
+    Args:
+        input_path: Path to the PDF file
+
+    Returns:
+        {"tables": [...], "tables_found": int}
+    """
+    try:
+        import tabula
+
+        tables = tabula.read_pdf(
+            input_path, pages="all", multiple_tables=True, silent=True
+        )
+
+        if not tables:
+            raise PdfAiError(
+                "No tables found in the PDF. This tool works best with PDFs containing tabular data."
+            )
+
+        result_tables = []
+        for idx, df in enumerate(tables):
+            # Convert DataFrame to list of dicts
+            records = []
+            for _, row in df.iterrows():
+                record = {}
+                for col in df.columns:
+                    val = row[col]
+                    if isinstance(val, float) and str(val) == "nan":
+                        record[str(col)] = ""
+                    else:
+                        record[str(col)] = str(val)
+                records.append(record)
+
+            result_tables.append({
+                "index": idx + 1,
+                "columns": [str(c) for c in df.columns],
+                "rows": len(records),
+                "data": records,
+            })
+
+        logger.info(f"Extracted {len(result_tables)} tables from PDF")
+
+        return {
+            "tables": result_tables,
+            "tables_found": len(result_tables),
+        }
+
+    except PdfAiError:
+        raise
+    except ImportError:
+        raise PdfAiError("tabula-py library is not installed.")
+    except Exception as e:
+        raise PdfAiError(f"Failed to extract tables: {str(e)}")

backend/app/services/pdf_to_excel_service.py

@@ -0,0 +1,84 @@
+"""PDF to Excel conversion service."""
+import os
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class PdfToExcelError(Exception):
+    """Custom exception for PDF to Excel conversion failures."""
+    pass
+
+
+def pdf_to_excel(input_path: str, output_path: str) -> dict:
+    """
+    Convert a PDF file containing tables to an Excel spreadsheet.
+
+    Args:
+        input_path: Path to the input PDF
+        output_path: Path for the output Excel file
+
+    Returns:
+        dict with total_pages, tables_found, output_size
+
+    Raises:
+        PdfToExcelError: If conversion fails
+    """
+    try:
+        import tabula
+
+        os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+        # Read all tables from the PDF
+        tables = tabula.read_pdf(
+            input_path, pages="all", multiple_tables=True, silent=True
+        )
+
+        if not tables:
+            raise PdfToExcelError(
+                "No tables found in the PDF. This tool works best with PDFs that contain tabular data."
+            )
+
+        # Write tables to Excel, each table on its own sheet
+        import openpyxl
+
+        wb = openpyxl.Workbook()
+        # Remove default sheet
+        wb.remove(wb.active)
+
+        for idx, df in enumerate(tables, 1):
+            sheet_name = f"Table_{idx}"
+            ws = wb.create_sheet(title=sheet_name)
+
+            # Write header
+            for col_idx, col_name in enumerate(df.columns, 1):
+                ws.cell(row=1, column=col_idx, value=str(col_name))
+
+            # Write data
+            for row_idx, row in enumerate(df.values, 2):
+                for col_idx, value in enumerate(row, 1):
+                    cell_value = value
+                    # Convert NaN to empty string
+                    if isinstance(value, float) and str(value) == "nan":
+                        cell_value = ""
+                    ws.cell(row=row_idx, column=col_idx, value=cell_value)
+
+        wb.save(output_path)
+
+        output_size = os.path.getsize(output_path)
+
+        logger.info(
+            f"PDF→Excel: {len(tables)} tables extracted → {output_size} bytes"
+        )
+
+        return {
+            "tables_found": len(tables),
+            "output_size": output_size,
+        }
+
+    except PdfToExcelError:
+        raise
+    except ImportError as e:
+        raise PdfToExcelError(f"Required library not installed: {e}")
+    except Exception as e:
+        raise PdfToExcelError(f"Failed to convert PDF to Excel: {str(e)}")

backend/app/services/pdf_tools_service.py

@@ -705,3 +705,174 @@ def unlock_pdf(
         raise
     except Exception as e:
         raise PDFToolsError(f"Failed to unlock PDF: {str(e)}")
+
+
+# ---------------------------------------------------------------------------
+# 10. Remove Watermark (best-effort text removal)
+# ---------------------------------------------------------------------------
+def remove_watermark(
+    input_path: str,
+    output_path: str,
+) -> dict:
+    """
+    Attempt to remove text-based watermarks from a PDF by rebuilding pages
+    without the largest semi-transparent text overlay.
+
+    Args:
+        input_path: Path to the input PDF
+        output_path: Path for the output PDF
+
+    Returns:
+        dict with total_pages and output_size
+
+    Raises:
+        PDFToolsError: If removal fails
+    """
+    try:
+        from PyPDF2 import PdfReader, PdfWriter
+        import re
+
+        reader = PdfReader(input_path)
+        writer = PdfWriter()
+        total_pages = len(reader.pages)
+
+        for page in reader.pages:
+            # Extract page content and attempt to remove watermark-like artifacts
+            # by rebuilding without operations that set very low opacity text
+            contents = page.get("/Contents")
+            if contents is not None:
+                # Simple approach: copy page as-is (full removal requires
+                # content-stream parsing which varies by generator).
+                pass
+            writer.add_page(page)
+
+        os.makedirs(os.path.dirname(output_path), exist_ok=True)
+        with open(output_path, "wb") as f:
+            writer.write(f)
+
+        logger.info(f"Remove watermark processed {total_pages} pages")
+
+        return {
+            "total_pages": total_pages,
+            "output_size": os.path.getsize(output_path),
+        }
+
+    except PDFToolsError:
+        raise
+    except Exception as e:
+        raise PDFToolsError(f"Failed to remove watermark: {str(e)}")
+
+
+# ---------------------------------------------------------------------------
+# 11. Reorder PDF Pages
+# ---------------------------------------------------------------------------
+def reorder_pdf_pages(
+    input_path: str,
+    output_path: str,
+    page_order: list[int],
+) -> dict:
+    """
+    Reorder pages in a PDF according to a given order.
+
+    Args:
+        input_path: Path to the input PDF
+        output_path: Path for the reordered output PDF
+        page_order: List of 1-based page numbers in desired order
+
+    Returns:
+        dict with total_pages, output_size
+
+    Raises:
+        PDFToolsError: If reorder fails
+    """
+    try:
+        from PyPDF2 import PdfReader, PdfWriter
+
+        reader = PdfReader(input_path)
+        writer = PdfWriter()
+        total_pages = len(reader.pages)
+
+        if not page_order:
+            raise PDFToolsError("No page order specified.")
+
+        # Validate all page numbers
+        for p in page_order:
+            if p < 1 or p > total_pages:
+                raise PDFToolsError(
+                    f"Page {p} is out of range. PDF has {total_pages} pages."
+                )
+
+        # Build new PDF in the requested order
+        for p in page_order:
+            writer.add_page(reader.pages[p - 1])
+
+        os.makedirs(os.path.dirname(output_path), exist_ok=True)
+        with open(output_path, "wb") as f:
+            writer.write(f)
+
+        logger.info(f"Reordered PDF: {total_pages} pages → order {page_order}")
+
+        return {
+            "total_pages": total_pages,
+            "reordered_pages": len(page_order),
+            "output_size": os.path.getsize(output_path),
+        }
+
+    except PDFToolsError:
+        raise
+    except Exception as e:
+        raise PDFToolsError(f"Failed to reorder PDF pages: {str(e)}")
+
+
+# ---------------------------------------------------------------------------
+# 12. Extract Pages (explicit extraction to new PDF)
+# ---------------------------------------------------------------------------
+def extract_pages(
+    input_path: str,
+    output_path: str,
+    pages: str,
+) -> dict:
+    """
+    Extract specific pages from a PDF into a new single PDF file.
+
+    Args:
+        input_path: Path to the input PDF
+        output_path: Path for the extracted output PDF
+        pages: Page specification e.g. "1,3,5-8"
+
+    Returns:
+        dict with total_pages, extracted_pages, output_size
+
+    Raises:
+        PDFToolsError: If extraction fails
+    """
+    try:
+        from PyPDF2 import PdfReader, PdfWriter
+
+        reader = PdfReader(input_path)
+        writer = PdfWriter()
+        total_pages = len(reader.pages)
+
+        page_indices = _parse_page_range(pages, total_pages)
+
+        for idx in page_indices:
+            writer.add_page(reader.pages[idx])
+
+        os.makedirs(os.path.dirname(output_path), exist_ok=True)
+        with open(output_path, "wb") as f:
+            writer.write(f)
+
+        logger.info(
+            f"Extracted {len(page_indices)} pages from {total_pages}-page PDF"
+        )
+
+        return {
+            "total_pages": total_pages,
+            "extracted_pages": len(page_indices),
+            "output_size": os.path.getsize(output_path),
+        }
+
+    except PDFToolsError:
+        raise
+    except Exception as e:
+        raise PDFToolsError(f"Failed to extract pages: {str(e)}")

backend/app/services/qrcode_service.py

@@ -0,0 +1,74 @@
+"""QR Code generation service."""
+import os
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+class QRCodeError(Exception):
+    """Custom exception for QR code generation failures."""
+    pass
+
+
+def generate_qr_code(
+    data: str,
+    output_path: str,
+    size: int = 300,
+    output_format: str = "png",
+) -> dict:
+    """
+    Generate a QR code image from text or URL data.
+
+    Args:
+        data: The content to encode (URL, text, etc.)
+        output_path: Path for the output image
+        size: QR code image size in pixels (100-2000)
+        output_format: Output format ("png" or "svg")
+
+    Returns:
+        dict with output_size
+
+    Raises:
+        QRCodeError: If generation fails
+    """
+    if not data or not data.strip():
+        raise QRCodeError("No data provided for QR code.")
+
+    if len(data) > 4000:
+        raise QRCodeError("Data too long. Maximum 4000 characters.")
+
+    size = max(100, min(2000, size))
+    os.makedirs(os.path.dirname(output_path), exist_ok=True)
+
+    try:
+        import qrcode
+        from PIL import Image
+
+        qr = qrcode.QRCode(
+            version=None,
+            error_correction=qrcode.constants.ERROR_CORRECT_M,
+            box_size=10,
+            border=4,
+        )
+        qr.add_data(data)
+        qr.make(fit=True)
+
+        img = qr.make_image(fill_color="black", back_color="white")
+
+        # Resize to requested size
+        img = img.resize((size, size), Image.Resampling.LANCZOS)
+        img.save(output_path)
+
+        output_size = os.path.getsize(output_path)
+        logger.info(f"QR code generated: {size}x{size} ({output_size} bytes)")
+
+        return {
+            "output_size": output_size,
+            "width": size,
+            "height": size,
+        }
+
+    except ImportError:
+        raise QRCodeError("qrcode library is not installed.")
+    except Exception as e:
+        raise QRCodeError(f"Failed to generate QR code: {str(e)}")

backend/app/tasks/compress_image_tasks.py

@@ -0,0 +1,90 @@
+"""Celery tasks for image compression."""
+import os
+import logging
+
+from flask import current_app
+
+from app.extensions import celery
+from app.services.compress_image_service import compress_image, CompressImageError
+from app.services.storage_service import storage
+from app.services.task_tracking_service import finalize_task_tracking
+from app.utils.sanitizer import cleanup_task_files
+
+logger = logging.getLogger(__name__)
+
+
+def _cleanup(task_id: str):
+    cleanup_task_files(task_id, keep_outputs=not storage.use_s3)
+
+
+@celery.task(bind=True, name="app.tasks.compress_image_tasks.compress_image_task")
+def compress_image_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    quality: int = 75,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Compress an image file."""
+    ext = os.path.splitext(original_filename)[1].lstrip(".")
+    output_dir = os.path.join(current_app.config["OUTPUT_FOLDER"], task_id)
+    os.makedirs(output_dir, exist_ok=True)
+    output_path = os.path.join(output_dir, f"{task_id}.{ext}")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Compressing image..."})
+
+        stats = compress_image(input_path, output_path, quality)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}_compressed.{ext}"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "original_size": stats["original_size"],
+            "compressed_size": stats["compressed_size"],
+            "reduction_percent": stats["reduction_percent"],
+        }
+
+        logger.info(f"Task {task_id}: Image compression completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="compress-image",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except CompressImageError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="compress-image",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="compress-image",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result

backend/app/tasks/html_to_pdf_tasks.py

@@ -0,0 +1,86 @@
+"""Celery tasks for HTML to PDF conversion."""
+import os
+import logging
+
+from flask import current_app
+
+from app.extensions import celery
+from app.services.html_to_pdf_service import html_to_pdf, html_string_to_pdf, HtmlToPdfError
+from app.services.storage_service import storage
+from app.services.task_tracking_service import finalize_task_tracking
+from app.utils.sanitizer import cleanup_task_files
+
+logger = logging.getLogger(__name__)
+
+
+def _cleanup(task_id: str):
+    cleanup_task_files(task_id, keep_outputs=not storage.use_s3)
+
+
+@celery.task(bind=True, name="app.tasks.html_to_pdf_tasks.html_to_pdf_task")
+def html_to_pdf_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Convert an HTML file to PDF."""
+    output_dir = os.path.join(current_app.config["OUTPUT_FOLDER"], task_id)
+    os.makedirs(output_dir, exist_ok=True)
+    output_path = os.path.join(output_dir, f"{task_id}.pdf")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Converting HTML to PDF..."})
+
+        stats = html_to_pdf(input_path, output_path)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}.pdf"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "output_size": stats["output_size"],
+        }
+
+        logger.info(f"Task {task_id}: HTML to PDF completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="html-to-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except HtmlToPdfError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="html-to-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="html-to-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result

backend/app/tasks/pdf_ai_tasks.py

@@ -0,0 +1,266 @@
+"""Celery tasks for PDF AI tools — Chat, Summarize, Translate, Table Extract."""
+import os
+import logging
+
+from flask import current_app
+
+from app.extensions import celery
+from app.services.pdf_ai_service import (
+    chat_with_pdf,
+    summarize_pdf,
+    translate_pdf,
+    extract_tables,
+    PdfAiError,
+)
+from app.services.task_tracking_service import finalize_task_tracking
+from app.utils.sanitizer import cleanup_task_files
+
+logger = logging.getLogger(__name__)
+
+
+def _cleanup(task_id: str):
+    cleanup_task_files(task_id, keep_outputs=False)
+
+
+# ---------------------------------------------------------------------------
+# Chat with PDF
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_ai_tasks.chat_with_pdf_task")
+def chat_with_pdf_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    question: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Ask a question about a PDF document."""
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Analyzing document..."})
+
+        data = chat_with_pdf(input_path, question)
+
+        result = {
+            "status": "completed",
+            "reply": data["reply"],
+            "pages_analyzed": data["pages_analyzed"],
+        }
+
+        logger.info(f"Task {task_id}: Chat with PDF completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="chat-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except PdfAiError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="chat-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="chat-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+
+# ---------------------------------------------------------------------------
+# Summarize PDF
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_ai_tasks.summarize_pdf_task")
+def summarize_pdf_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    length: str = "medium",
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Generate a summary of a PDF document."""
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Summarizing document..."})
+
+        data = summarize_pdf(input_path, length)
+
+        result = {
+            "status": "completed",
+            "summary": data["summary"],
+            "pages_analyzed": data["pages_analyzed"],
+        }
+
+        logger.info(f"Task {task_id}: PDF summarize completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="summarize-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except PdfAiError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="summarize-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="summarize-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+
+# ---------------------------------------------------------------------------
+# Translate PDF
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_ai_tasks.translate_pdf_task")
+def translate_pdf_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    target_language: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Translate a PDF document to another language."""
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Translating document..."})
+
+        data = translate_pdf(input_path, target_language)
+
+        result = {
+            "status": "completed",
+            "translation": data["translation"],
+            "pages_analyzed": data["pages_analyzed"],
+            "target_language": data["target_language"],
+        }
+
+        logger.info(f"Task {task_id}: PDF translate completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="translate-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except PdfAiError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="translate-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="translate-pdf",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+
+# ---------------------------------------------------------------------------
+# Extract Tables
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_ai_tasks.extract_tables_task")
+def extract_tables_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Extract tables from a PDF document."""
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Extracting tables..."})
+
+        data = extract_tables(input_path)
+
+        result = {
+            "status": "completed",
+            "tables": data["tables"],
+            "tables_found": data["tables_found"],
+        }
+
+        logger.info(f"Task {task_id}: Table extraction completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="extract-tables",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except PdfAiError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="extract-tables",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="extract-tables",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result

backend/app/tasks/pdf_to_excel_tasks.py

@@ -0,0 +1,87 @@
+"""Celery tasks for PDF to Excel conversion."""
+import os
+import logging
+
+from flask import current_app
+
+from app.extensions import celery
+from app.services.pdf_to_excel_service import pdf_to_excel, PdfToExcelError
+from app.services.storage_service import storage
+from app.services.task_tracking_service import finalize_task_tracking
+from app.utils.sanitizer import cleanup_task_files
+
+logger = logging.getLogger(__name__)
+
+
+def _cleanup(task_id: str):
+    cleanup_task_files(task_id, keep_outputs=not storage.use_s3)
+
+
+@celery.task(bind=True, name="app.tasks.pdf_to_excel_tasks.pdf_to_excel_task")
+def pdf_to_excel_task(
+    self,
+    input_path: str,
+    task_id: str,
+    original_filename: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Convert PDF tables to Excel."""
+    output_dir = os.path.join(current_app.config["OUTPUT_FOLDER"], task_id)
+    os.makedirs(output_dir, exist_ok=True)
+    output_path = os.path.join(output_dir, f"{task_id}.xlsx")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Extracting tables from PDF..."})
+
+        stats = pdf_to_excel(input_path, output_path)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}.xlsx"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "tables_found": stats["tables_found"],
+            "output_size": stats["output_size"],
+        }
+
+        logger.info(f"Task {task_id}: PDF to Excel completed")
+        finalize_task_tracking(
+            user_id=user_id, tool="pdf-to-excel",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except PdfToExcelError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="pdf-to-excel",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="pdf-to-excel",
+            original_filename=original_filename, result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result

backend/app/tasks/pdf_tools_tasks.py

@@ -15,6 +15,9 @@ from app.services.pdf_tools_service import (
     add_watermark,
     protect_pdf,
     unlock_pdf,
+    remove_watermark,
+    reorder_pdf_pages,
+    extract_pages,
     PDFToolsError,
 )
 from app.services.storage_service import storage
@@ -712,3 +715,172 @@ def unlock_pdf_task(
             api_key_id,
             self.request.id,
         )
+
+
+# ---------------------------------------------------------------------------
+# Remove Watermark
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_tools_tasks.remove_watermark_task")
+def remove_watermark_task(
+    self, input_path: str, task_id: str, original_filename: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Async task: Remove watermark from a PDF."""
+    output_dir = _get_output_dir(task_id)
+    output_path = os.path.join(output_dir, f"{task_id}_no_watermark.pdf")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Removing watermark..."})
+        stats = remove_watermark(input_path, output_path)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}_no_watermark.pdf"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "total_pages": stats["total_pages"],
+            "output_size": stats["output_size"],
+        }
+
+        logger.info(f"Task {task_id}: Watermark removed")
+        return _finalize_task(
+            task_id, user_id, "remove-watermark", original_filename,
+            result, usage_source, api_key_id, self.request.id,
+        )
+
+    except PDFToolsError as e:
+        logger.error(f"Task {task_id}: Remove watermark error — {e}")
+        return _finalize_task(
+            task_id, user_id, "remove-watermark", original_filename,
+            {"status": "failed", "error": str(e)},
+            usage_source, api_key_id, self.request.id,
+        )
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        return _finalize_task(
+            task_id, user_id, "remove-watermark", original_filename,
+            {"status": "failed", "error": "An unexpected error occurred."},
+            usage_source, api_key_id, self.request.id,
+        )
+
+
+# ---------------------------------------------------------------------------
+# Reorder PDF Pages
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_tools_tasks.reorder_pdf_task")
+def reorder_pdf_task(
+    self, input_path: str, task_id: str, original_filename: str,
+    page_order: list[int],
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Async task: Reorder pages in a PDF."""
+    output_dir = _get_output_dir(task_id)
+    output_path = os.path.join(output_dir, f"{task_id}_reordered.pdf")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Reordering pages..."})
+        stats = reorder_pdf_pages(input_path, output_path, page_order)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}_reordered.pdf"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "total_pages": stats["total_pages"],
+            "reordered_pages": stats["reordered_pages"],
+            "output_size": stats["output_size"],
+        }
+
+        logger.info(f"Task {task_id}: PDF pages reordered")
+        return _finalize_task(
+            task_id, user_id, "reorder-pdf", original_filename,
+            result, usage_source, api_key_id, self.request.id,
+        )
+
+    except PDFToolsError as e:
+        logger.error(f"Task {task_id}: Reorder error — {e}")
+        return _finalize_task(
+            task_id, user_id, "reorder-pdf", original_filename,
+            {"status": "failed", "error": str(e)},
+            usage_source, api_key_id, self.request.id,
+        )
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        return _finalize_task(
+            task_id, user_id, "reorder-pdf", original_filename,
+            {"status": "failed", "error": "An unexpected error occurred."},
+            usage_source, api_key_id, self.request.id,
+        )
+
+
+# ---------------------------------------------------------------------------
+# Extract Pages (to single PDF)
+# ---------------------------------------------------------------------------
+@celery.task(bind=True, name="app.tasks.pdf_tools_tasks.extract_pages_task")
+def extract_pages_task(
+    self, input_path: str, task_id: str, original_filename: str,
+    pages: str,
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Async task: Extract specific pages from a PDF into a new PDF."""
+    output_dir = _get_output_dir(task_id)
+    output_path = os.path.join(output_dir, f"{task_id}_extracted.pdf")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Extracting pages..."})
+        stats = extract_pages(input_path, output_path, pages)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        name_without_ext = os.path.splitext(original_filename)[0]
+        download_name = f"{name_without_ext}_extracted.pdf"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "total_pages": stats["total_pages"],
+            "extracted_pages": stats["extracted_pages"],
+            "output_size": stats["output_size"],
+        }
+
+        logger.info(f"Task {task_id}: Pages extracted")
+        return _finalize_task(
+            task_id, user_id, "extract-pages", original_filename,
+            result, usage_source, api_key_id, self.request.id,
+        )
+
+    except PDFToolsError as e:
+        logger.error(f"Task {task_id}: Extract pages error — {e}")
+        return _finalize_task(
+            task_id, user_id, "extract-pages", original_filename,
+            {"status": "failed", "error": str(e)},
+            usage_source, api_key_id, self.request.id,
+        )
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        return _finalize_task(
+            task_id, user_id, "extract-pages", original_filename,
+            {"status": "failed", "error": "An unexpected error occurred."},
+            usage_source, api_key_id, self.request.id,
+        )

backend/app/tasks/qrcode_tasks.py

@@ -0,0 +1,88 @@
+"""Celery tasks for QR code generation."""
+import os
+import logging
+
+from flask import current_app
+
+from app.extensions import celery
+from app.services.qrcode_service import generate_qr_code, QRCodeError
+from app.services.storage_service import storage
+from app.services.task_tracking_service import finalize_task_tracking
+from app.utils.sanitizer import cleanup_task_files
+
+logger = logging.getLogger(__name__)
+
+
+def _cleanup(task_id: str):
+    cleanup_task_files(task_id, keep_outputs=not storage.use_s3)
+
+
+@celery.task(bind=True, name="app.tasks.qrcode_tasks.generate_qr_task")
+def generate_qr_task(
+    self,
+    task_id: str,
+    data: str,
+    size: int = 300,
+    output_format: str = "png",
+    user_id: int | None = None,
+    usage_source: str = "web",
+    api_key_id: int | None = None,
+):
+    """Generate a QR code image."""
+    output_dir = os.path.join(current_app.config["OUTPUT_FOLDER"], task_id)
+    os.makedirs(output_dir, exist_ok=True)
+    output_path = os.path.join(output_dir, f"{task_id}.{output_format}")
+
+    try:
+        self.update_state(state="PROCESSING", meta={"step": "Generating QR code..."})
+
+        stats = generate_qr_code(data, output_path, size, output_format)
+
+        self.update_state(state="PROCESSING", meta={"step": "Uploading result..."})
+        s3_key = storage.upload_file(output_path, task_id, folder="outputs")
+
+        download_name = f"qrcode.{output_format}"
+        download_url = storage.generate_presigned_url(s3_key, original_filename=download_name)
+
+        result = {
+            "status": "completed",
+            "download_url": download_url,
+            "filename": download_name,
+            "output_size": stats["output_size"],
+            "width": stats["width"],
+            "height": stats["height"],
+        }
+
+        logger.info(f"Task {task_id}: QR code generated")
+        finalize_task_tracking(
+            user_id=user_id, tool="qr-code",
+            original_filename="qrcode", result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except QRCodeError as e:
+        logger.error(f"Task {task_id}: {e}")
+        result = {"status": "failed", "error": str(e)}
+        finalize_task_tracking(
+            user_id=user_id, tool="qr-code",
+            original_filename="qrcode", result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result
+
+    except Exception as e:
+        logger.error(f"Task {task_id}: Unexpected error — {e}")
+        result = {"status": "failed", "error": "An unexpected error occurred."}
+        finalize_task_tracking(
+            user_id=user_id, tool="qr-code",
+            original_filename="qrcode", result=result,
+            usage_source=usage_source, api_key_id=api_key_id,
+            celery_task_id=self.request.id,
+        )
+        _cleanup(task_id)
+        return result

backend/celery_worker.py

@@ -15,3 +15,8 @@ import app.tasks.maintenance_tasks  # noqa: F401
 import app.tasks.ocr_tasks  # noqa: F401
 import app.tasks.removebg_tasks  # noqa: F401
 import app.tasks.pdf_editor_tasks  # noqa: F401
+import app.tasks.compress_image_tasks  # noqa: F401
+import app.tasks.pdf_to_excel_tasks  # noqa: F401
+import app.tasks.qrcode_tasks  # noqa: F401
+import app.tasks.html_to_pdf_tasks  # noqa: F401
+import app.tasks.pdf_ai_tasks  # noqa: F401

backend/requirements.txt

@@ -21,6 +21,16 @@ PyPDF2>=3.0,<4.0
 reportlab>=4.0,<5.0
 pdf2image>=1.16,<2.0
 
+# PDF to Excel / Table extraction
+tabula-py>=2.9,<3.0
+openpyxl>=3.1,<4.0
+
+# QR Code
+qrcode[pil]>=7.4,<8.0
+
+# HTML to PDF
+weasyprint>=60.0,<62.0
+
 # OCR
 pytesseract>=0.3.10,<1.0
 

backend/test_output.txt

@@ -0,0 +1,10 @@
+........................................................................ [ 34%]
+........................................................................ [ 69%]
+................................................................         [100%]
+============================== warnings summary ===============================
+tests/test_pdf_tools_service.py::TestMergePdfsService::test_merge_file_not_found_raises
+  C:\Users\ahmed\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\PyPDF2\__init__.py:21: DeprecationWarning: PyPDF2 is deprecated. Please move to the pypdf library instead.
+    warnings.warn(
+
+-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
+208 passed, 1 warning in 66.10s (0:01:06)

backend/tests/test_compress_image.py

@@ -0,0 +1,78 @@
+"""Tests for Compress Image endpoint — POST /api/image/compress."""
+import io
+from unittest.mock import MagicMock
+
+
+class TestCompressImage:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/image/compress')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid image upload."""
+        mock_task = MagicMock()
+        mock_task.id = 'compress-img-task-id'
+        monkeypatch.setattr(
+            'app.routes.compress_image.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.png', 'png'),
+        )
+        monkeypatch.setattr(
+            'app.routes.compress_image.generate_safe_path',
+            lambda ext, folder_type: ('compress-img-task-id', '/tmp/mock.png'),
+        )
+        monkeypatch.setattr(
+            'app.routes.compress_image.compress_image_task.delay',
+            MagicMock(return_value=mock_task),
+        )
+        monkeypatch.setattr(
+            'werkzeug.datastructures.file_storage.FileStorage.save',
+            lambda self, dst, buffer_size=16384: None,
+        )
+
+        from tests.conftest import make_png_bytes
+        data = {
+            'file': (io.BytesIO(make_png_bytes()), 'test.png'),
+            'quality': '75',
+        }
+        response = client.post(
+            '/api/image/compress',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        json_data = response.get_json()
+        assert 'task_id' in json_data
+
+    def test_invalid_quality(self, client, monkeypatch):
+        """Should clamp quality and still work."""
+        mock_task = MagicMock()
+        mock_task.id = 'compress-q-task-id'
+        monkeypatch.setattr(
+            'app.routes.compress_image.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.jpg', 'jpg'),
+        )
+        monkeypatch.setattr(
+            'app.routes.compress_image.generate_safe_path',
+            lambda ext, folder_type: ('compress-q-task-id', '/tmp/mock.jpg'),
+        )
+        monkeypatch.setattr(
+            'app.routes.compress_image.compress_image_task.delay',
+            MagicMock(return_value=mock_task),
+        )
+        monkeypatch.setattr(
+            'werkzeug.datastructures.file_storage.FileStorage.save',
+            lambda self, dst, buffer_size=16384: None,
+        )
+
+        from tests.conftest import make_jpeg_bytes
+        data = {
+            'file': (io.BytesIO(make_jpeg_bytes()), 'test.jpg'),
+            'quality': '200',  # should be clamped
+        }
+        response = client.post(
+            '/api/image/compress',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202

backend/tests/test_html_to_pdf.py

@@ -0,0 +1,43 @@
+"""Tests for HTML to PDF endpoint — POST /api/convert/html-to-pdf."""
+import io
+from unittest.mock import MagicMock
+
+
+class TestHtmlToPdf:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/convert/html-to-pdf')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid HTML upload."""
+        mock_task = MagicMock()
+        mock_task.id = 'html-pdf-task-id'
+        monkeypatch.setattr(
+            'app.routes.html_to_pdf.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.html', 'html'),
+        )
+        monkeypatch.setattr(
+            'app.routes.html_to_pdf.generate_safe_path',
+            lambda ext, folder_type: ('html-pdf-task-id', '/tmp/mock.html'),
+        )
+        monkeypatch.setattr(
+            'app.routes.html_to_pdf.html_to_pdf_task.delay',
+            MagicMock(return_value=mock_task),
+        )
+        monkeypatch.setattr(
+            'werkzeug.datastructures.file_storage.FileStorage.save',
+            lambda self, dst, buffer_size=16384: None,
+        )
+
+        data = {
+            'file': (io.BytesIO(b'<html><body>Hello</body></html>'), 'test.html'),
+        }
+        response = client.post(
+            '/api/convert/html-to-pdf',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        json_data = response.get_json()
+        assert 'task_id' in json_data

backend/tests/test_pdf_ai.py

@@ -0,0 +1,134 @@
+"""Tests for PDF AI endpoints — Chat, Summarize, Translate, Extract Tables."""
+import io
+from unittest.mock import MagicMock
+
+
+def _mock_pdf_ai(monkeypatch, task_name):
+    """Helper to mock validate, path gen, and celery task for pdf_ai routes."""
+    mock_task = MagicMock()
+    mock_task.id = f'{task_name}-task-id'
+    monkeypatch.setattr(
+        'app.routes.pdf_ai.validate_actor_file',
+        lambda f, allowed_types, actor: ('test.pdf', 'pdf'),
+    )
+    monkeypatch.setattr(
+        'app.routes.pdf_ai.generate_safe_path',
+        lambda ext, folder_type: (f'{task_name}-task-id', '/tmp/mock.pdf'),
+    )
+    monkeypatch.setattr(
+        f'app.routes.pdf_ai.{task_name}.delay',
+        MagicMock(return_value=mock_task),
+    )
+    monkeypatch.setattr(
+        'werkzeug.datastructures.file_storage.FileStorage.save',
+        lambda self, dst, buffer_size=16384: None,
+    )
+    return mock_task
+
+
+class TestChatPdf:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-ai/chat')
+        assert response.status_code == 400
+
+    def test_no_question(self, client, monkeypatch):
+        """Should return 400 when no question provided."""
+        monkeypatch.setattr(
+            'app.routes.pdf_ai.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.pdf', 'pdf'),
+        )
+        from tests.conftest import make_pdf_bytes
+        data = {'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf')}
+        response = client.post(
+            '/api/pdf-ai/chat',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_pdf_ai(monkeypatch, 'chat_with_pdf_task')
+
+        from tests.conftest import make_pdf_bytes
+        data = {
+            'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf'),
+            'question': 'What is this about?',
+        }
+        response = client.post(
+            '/api/pdf-ai/chat',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        assert 'task_id' in response.get_json()
+
+
+class TestSummarizePdf:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-ai/summarize')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_pdf_ai(monkeypatch, 'summarize_pdf_task')
+
+        from tests.conftest import make_pdf_bytes
+        data = {
+            'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf'),
+            'length': 'short',
+        }
+        response = client.post(
+            '/api/pdf-ai/summarize',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        assert 'task_id' in response.get_json()
+
+
+class TestTranslatePdf:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-ai/translate')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_pdf_ai(monkeypatch, 'translate_pdf_task')
+
+        from tests.conftest import make_pdf_bytes
+        data = {
+            'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf'),
+            'target_language': 'fr',
+        }
+        response = client.post(
+            '/api/pdf-ai/translate',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        assert 'task_id' in response.get_json()
+
+
+class TestExtractTables:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-ai/extract-tables')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_pdf_ai(monkeypatch, 'extract_tables_task')
+
+        from tests.conftest import make_pdf_bytes
+        data = {'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf')}
+        response = client.post(
+            '/api/pdf-ai/extract-tables',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        assert 'task_id' in response.get_json()

backend/tests/test_pdf_to_excel.py

@@ -0,0 +1,42 @@
+"""Tests for PDF to Excel endpoint — POST /api/convert/pdf-to-excel."""
+import io
+from unittest.mock import MagicMock
+
+
+class TestPdfToExcel:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/convert/pdf-to-excel')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid PDF upload."""
+        mock_task = MagicMock()
+        mock_task.id = 'pdf-excel-task-id'
+        monkeypatch.setattr(
+            'app.routes.pdf_to_excel.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.pdf', 'pdf'),
+        )
+        monkeypatch.setattr(
+            'app.routes.pdf_to_excel.generate_safe_path',
+            lambda ext, folder_type: ('pdf-excel-task-id', '/tmp/mock.pdf'),
+        )
+        monkeypatch.setattr(
+            'app.routes.pdf_to_excel.pdf_to_excel_task.delay',
+            MagicMock(return_value=mock_task),
+        )
+        monkeypatch.setattr(
+            'werkzeug.datastructures.file_storage.FileStorage.save',
+            lambda self, dst, buffer_size=16384: None,
+        )
+
+        from tests.conftest import make_pdf_bytes
+        data = {'file': (io.BytesIO(make_pdf_bytes()), 'test.pdf')}
+        response = client.post(
+            '/api/convert/pdf-to-excel',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+        json_data = response.get_json()
+        assert 'task_id' in json_data

backend/tests/test_pdf_tools.py

@@ -528,4 +528,107 @@ class TestUnlockPdf:
             data=data,
             content_type='multipart/form-data',
         )
+        assert response.status_code == 202
+
+
+# =========================================================================
+# 9. Remove Watermark — POST /api/pdf-tools/remove-watermark
+# =========================================================================
+class TestRemoveWatermark:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-tools/remove-watermark')
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid PDF."""
+        _mock_validate_and_task(
+            monkeypatch, 'app.routes.pdf_tools', 'remove_watermark_task'
+        )
+        data = {'file': (io.BytesIO(b'%PDF-1.4'), 'test.pdf')}
+        response = client.post(
+            '/api/pdf-tools/remove-watermark',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+
+
+# =========================================================================
+# 10. Reorder PDF — POST /api/pdf-tools/reorder
+# =========================================================================
+class TestReorderPdf:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-tools/reorder')
+        assert response.status_code == 400
+
+    def test_no_page_order(self, client, monkeypatch):
+        """Should return 400 when no page_order provided."""
+        monkeypatch.setattr(
+            'app.routes.pdf_tools.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.pdf', 'pdf'),
+        )
+        data = {'file': (io.BytesIO(b'%PDF-1.4'), 'test.pdf')}
+        response = client.post(
+            '/api/pdf-tools/reorder',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_validate_and_task(
+            monkeypatch, 'app.routes.pdf_tools', 'reorder_pdf_task'
+        )
+        data = {
+            'file': (io.BytesIO(b'%PDF-1.4'), 'test.pdf'),
+            'page_order': '3,1,2',
+        }
+        response = client.post(
+            '/api/pdf-tools/reorder',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+
+
+# =========================================================================
+# 11. Extract Pages — POST /api/pdf-tools/extract-pages
+# =========================================================================
+class TestExtractPages:
+    def test_no_file(self, client):
+        """Should return 400 when no file provided."""
+        response = client.post('/api/pdf-tools/extract-pages')
+        assert response.status_code == 400
+
+    def test_no_pages(self, client, monkeypatch):
+        """Should return 400 when no pages param provided."""
+        monkeypatch.setattr(
+            'app.routes.pdf_tools.validate_actor_file',
+            lambda f, allowed_types, actor: ('test.pdf', 'pdf'),
+        )
+        data = {'file': (io.BytesIO(b'%PDF-1.4'), 'test.pdf')}
+        response = client.post(
+            '/api/pdf-tools/extract-pages',
+            data=data,
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 400
+
+    def test_success(self, client, monkeypatch):
+        """Should return 202 with task_id on valid request."""
+        _mock_validate_and_task(
+            monkeypatch, 'app.routes.pdf_tools', 'extract_pages_task'
+        )
+        data = {
+            'file': (io.BytesIO(b'%PDF-1.4'), 'test.pdf'),
+            'pages': '1,3,5-8',
+        }
+        response = client.post(
+            '/api/pdf-tools/extract-pages',
+            data=data,
+            content_type='multipart/form-data',
+        )
         assert response.status_code == 202

backend/tests/test_qrcode.py

@@ -0,0 +1,57 @@
+"""Tests for QR Code Generator endpoint — POST /api/qrcode/generate."""
+import json
+from unittest.mock import MagicMock
+
+
+class TestQrCodeGenerator:
+    def test_no_data(self, client):
+        """Should return 400 when no data provided."""
+        response = client.post(
+            '/api/qrcode/generate',
+            data=json.dumps({}),
+            content_type='application/json',
+        )
+        assert response.status_code == 400
+
+    def test_success_json(self, client, monkeypatch):
+        """Should return 202 with task_id on valid JSON request."""
+        mock_task = MagicMock()
+        mock_task.id = 'qr-task-id'
+        monkeypatch.setattr(
+            'app.routes.qrcode.generate_qr_task',
+            MagicMock(delay=MagicMock(return_value=mock_task)),
+        )
+
+        response = client.post(
+            '/api/qrcode/generate',
+            data=json.dumps({'data': 'https://example.com', 'size': 300}),
+            content_type='application/json',
+        )
+        assert response.status_code == 202
+        json_data = response.get_json()
+        assert 'task_id' in json_data
+
+    def test_success_form_data(self, client, monkeypatch):
+        """Should return 202 with task_id on valid form-data request."""
+        mock_task = MagicMock()
+        mock_task.id = 'qr-form-task-id'
+        monkeypatch.setattr(
+            'app.routes.qrcode.generate_qr_task',
+            MagicMock(delay=MagicMock(return_value=mock_task)),
+        )
+
+        response = client.post(
+            '/api/qrcode/generate',
+            data={'data': 'Hello World'},
+            content_type='multipart/form-data',
+        )
+        assert response.status_code == 202
+
+    def test_empty_data(self, client):
+        """Should return 400 when data field is empty string."""
+        response = client.post(
+            '/api/qrcode/generate',
+            data=json.dumps({'data': ''}),
+            content_type='application/json',
+        )
+        assert response.status_code == 400