chore: update Dockerfile dependencies and copy files (#3277)

# Description

Please include a summary of the changes and the related issue. Please
also include relevant motivation and context.

## Checklist before requesting a review

Please delete options that are not relevant.

- [ ] My code follows the style guidelines of this project
- [ ] I have performed a self-review of my code
- [ ] I have commented hard-to-understand areas
- [ ] I have ideally added tests that prove my fix is effective or that
my feature works
- [ ] New and existing unit tests pass locally with my changes
- [ ] Any dependent changes have been merged

## Screenshots (if appropriate):

backend/Dockerfile

@@ -3,22 +3,28 @@ FROM python:3.11.6-slim-bullseye
 WORKDIR /app
 
 # Install runtime dependencies
-RUN apt-get update && apt-get install -y \
+RUN apt-get clean && apt-get update && apt-get install -y \
     libgeos-dev \
     libcurl4-openssl-dev \
     libssl-dev \
     binutils \
-    pandoc \
     curl \
     git \
+    autoconf \
+    automake \
+    build-essential \
+    libtool \
+    python-dev \
+    build-essential \
+    # Additional dependencies for document handling
+    libmagic-dev \
     poppler-utils \
     tesseract-ocr \
-    libmagic-dev \
     libreoffice \
     libpq-dev \
     gcc \
-    wget \
+    pandoc && \
-    && rm -rf /var/lib/apt/lists/*
+    rm -rf /var/lib/apt/lists/* && apt-get clean
 
 # Install Supabase CLI
 RUN ARCHITECTURE=$(uname -m) && \
@@ -32,7 +38,15 @@ RUN ARCHITECTURE=$(uname -m) && \
     rm supabase_1.163.6_linux_arm64.deb; \
     fi
 
-COPY . .
+COPY requirements.lock  pyproject.toml README.md ./
+COPY api/pyproject.toml api/README.md ./api/
+COPY api/quivr_api/__init__.py ./api/quivr_api/__init__.py
+COPY core/pyproject.toml core/README.md ./core/
+COPY core/quivr_core/__init__.py ./core/quivr_core/__init__.py
+COPY worker/pyproject.toml worker/README.md ./worker/
+COPY worker/quivr_worker/__init__.py ./worker/quivr_worker/__init__.py
+COPY core/MegaParse/pyproject.toml core/MegaParse/README.md ./core/MegaParse/
+COPY core/MegaParse/megaparse/__init__.py ./core/MegaParse/megaparse/__init__.py
 
 RUN PYTHONDONTWRITEBYTECODE=1 pip install --no-cache-dir -r requirements.lock
 
@@ -43,4 +57,5 @@ RUN playwright install --with-deps && \
 
 ENV PYTHONPATH=/app
 
+COPY . .
 EXPOSE 5050

backend/api/quivr_api/modules/sync/utils/sync.py

@@ -6,6 +6,7 @@ from abc import ABC, abstractmethod
 from datetime import datetime
 from io import BytesIO
 from typing import Any, Dict, List, Optional, Union
+from urllib.parse import urlparse
 
 import dropbox
 import markdownify
@@ -25,7 +26,18 @@ from quivr_api.modules.sync.service.sync_notion import SyncNotionService
 from quivr_api.modules.sync.utils.normalize import remove_special_characters
 
 logger = get_logger(__name__)
-redis_client = redis.Redis(host="redis", port=int(os.getenv("REDIS_PORT", 6379)), db=0)
+
+# Parse the CELERY_BROKER_URL
+broker_url = os.getenv("CELERY_BROKER_URL", "redis://redis:6379/0")
+parsed_url = urlparse(broker_url)
+
+# Create the Redis client using the parsed URL
+redis_client = redis.Redis(
+    host=parsed_url.hostname,
+    port=parsed_url.port,
+    password=parsed_url.password,
+    db=int(parsed_url.path.lstrip('/'))
+)
 
 
 class BaseSync(ABC):