feat: 🎸 docker reduced size by 2 (#1653)

reduced size by 2

# 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):

.gitignore

@@ -70,3 +70,4 @@ backend/bin/*
 backend/lib/*
 backend/pyvenv.cfg
 backend/share/*
+backend/slim.report.json

Makefile

@@ -2,6 +2,7 @@ test:
 	pytest -s backend/tests
 
 dev:
+	docker compose -f docker-compose.dev.yml build backend-core
 	docker compose -f docker-compose.dev.yml up --build
 
 prod:

backend/.dockerignore

@@ -0,0 +1,10 @@
+**/__pycache__
+*/.pytest_cache
+**/__pycache__
+**/.benchmarks/
+**/.cache/
+**/.pytest_cache/
+**/.next/
+**/build/
+**/.docusaurus/
+**/node_modules/

backend/Dockerfile

@@ -1,20 +1,19 @@
 # Using a slim version for a smaller base image
-FROM python:3.11-slim-bullseye
+FROM python:3.11.6-slim-bullseye
 
 ARG DEV_MODE
 ENV DEV_MODE=$DEV_MODE
 
 # Install GEOS library, Rust, and other dependencies, then clean up
-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 \
-    pandoc \
     binutils \
+    pandoc \
     curl \
     git \
     build-essential && \
-    curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && \
     rm -rf /var/lib/apt/lists/* && apt-get clean
 
 # Add Rust binaries to the PATH
@@ -36,4 +35,6 @@ RUN if [ "$DEV_MODE" = "true" ]; then pip install --no-cache debugpy --timeout 2
 # Copy the rest of the application
 COPY . .
 
-CMD ["uvicorn", "main:app", "--reload", "--host", "0.0.0.0", "--port", "5050", "--workers", "6"]
+EXPOSE 5050
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "5050", "--workers", "6"]

backend/Dockerfile.dev

@@ -0,0 +1,40 @@
+# Using a slim version for a smaller base image
+FROM python:3.11.6-slim-bullseye
+
+ARG DEV_MODE
+ENV DEV_MODE=$DEV_MODE
+
+# Install GEOS library, Rust, and other dependencies, then clean up
+RUN apt-get clean && apt-get update && apt-get install -y \
+    libgeos-dev \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    binutils \
+    pandoc \
+    curl \
+    git \
+    build-essential && \
+    rm -rf /var/lib/apt/lists/* && apt-get clean
+
+# Add Rust binaries to the PATH
+ENV PATH="/root/.cargo/bin:${PATH}"
+
+WORKDIR /code
+
+# Copy just the requirements first
+COPY ./requirements.txt .
+
+# Upgrade pip
+RUN pip install --upgrade pip
+
+# Increase timeout to wait for the new installation
+RUN pip install --no-cache-dir -r requirements.txt --timeout 200
+
+RUN if [ "$DEV_MODE" = "true" ]; then pip install --no-cache debugpy --timeout 200; fi
+
+# Copy the rest of the application
+COPY . .
+
+EXPOSE 5050
+
+CMD ["uvicorn", "main:app","--reload", "--host", "0.0.0.0", "--port", "5050", "--workers", "6"]

backend/main.py

@@ -8,7 +8,6 @@
     from dotenv import load_dotenv  # type: ignore
 
     load_dotenv()
-import pypandoc
 import sentry_sdk
 from fastapi import FastAPI, HTTPException
 from fastapi.responses import JSONResponse
@@ -50,10 +49,10 @@
 add_cors_middleware(app)
 
 
-@app.on_event("startup")
-async def startup_event():
-    if not os.path.exists(pypandoc.get_pandoc_path()):
-        pypandoc.download_pandoc()
+# @app.on_event("startup")
+# async def startup_event():
+#     if not os.path.exists(pypandoc.get_pandoc_path()):
+#         pypandoc.download_pandoc()
 
 
 app.include_router(brain_router)

backend/requirements.txt

@@ -1,31 +1,27 @@
-pymupdf==1.22.3
+# pymupdf==1.22.3
 langchain==0.0.332
 litellm==0.13.2
-Markdown==3.4.4
+# Markdown==3.4.4
 openai==0.27.8
 GitPython==3.1.36
 pdf2image==1.16.3
 pypdf==3.9.0
-StrEnum==0.4.15
 supabase==1.1.0
 tiktoken==0.4.0
 unstructured==0.6.7
 fastapi==0.95.2
 python-multipart==0.0.6
 uvicorn==0.22.0
 pypandoc==1.11
+
 docx2txt==0.8
 python-jose==3.3.0
-transformers==4.30.1
 asyncpg==0.27.0
 flake8==6.0.0
 flake8-black==0.3.6
-sentence_transformers>=2.0.0
 sentry-sdk==1.26.0
 pyright==1.1.316
 resend==0.5.1
-psycopg2-binary==2.9.6
-sqlalchemy==2.0.19
 html5lib==1.1
 beautifulsoup4
 newspaper3k

docker-compose.dev.yml

@@ -22,7 +22,7 @@ services:
       - ./backend/.env
     build:
       context: backend
-      dockerfile: Dockerfile
+      dockerfile: Dockerfile.dev
       args:
         - DEV_MODE=true
     container_name: backend-core
@@ -49,7 +49,7 @@ services:
       - ./backend/.env
     build:
       context: backend
-      dockerfile: Dockerfile
+      dockerfile: Dockerfile.dev
     container_name: worker
     command: celery -A celery_worker worker -l info
     restart: unless-stopped
@@ -64,7 +64,7 @@ services:
       - ./backend/.env
     build:
       context: backend
-      dockerfile: Dockerfile
+      dockerfile: Dockerfile.dev
     container_name: flower
     command: celery -A celery_worker flower -l info --port=5555
     restart: unless-stopped

docker-compose.yml

@@ -21,8 +21,6 @@ services:
       dockerfile: Dockerfile
     container_name: backend-core
     restart: always
-    volumes:
-      - ./backend/:/code/
     depends_on:
       - redis
       - worker
@@ -49,8 +47,6 @@ services:
     restart: always
     depends_on:
       - redis
-    volumes:
-      - ./backend/:/code/
 
   beat:
     image: backend-base
@@ -64,8 +60,6 @@ services:
     restart: always
     depends_on:
       - redis
-    volumes:
-      - ./backend/:/code/
 
   flower:
     image: backend-base
@@ -77,8 +71,6 @@ services:
     container_name: flower
     command: celery -A celery_worker flower -l info --port=5555
     restart: always
-    volumes:
-      - ./backend/:/code/
     depends_on:
       - redis
       - worker

frontend/.dockerignore

@@ -1,2 +1,13 @@
-.next/
-node_modules/
+**/.next/
+**/node_modules/
+**/.vercel/
+**/__pycache__
+*/.pytest_cache
+**/__pycache__
+**/.benchmarks/
+**/.cache/
+**/.pytest_cache/
+**/.next/
+**/build/
+**/.docusaurus/
+**/node_modules/

frontend/Dockerfile

@@ -1,49 +1,31 @@
-# First stage: Build environment
-FROM node:18.13.0-alpine as builder
-
+FROM node:18.13.0-alpine
 # Install Python and essential build tools
 RUN apk add --update --no-cache python3 make g++ && ln -sf python3 /usr/bin/python
 RUN python3 -m ensurepip
 RUN pip3 install --no-cache --upgrade pip setuptools
 
-# Create a Python virtual environment
-RUN python3 -m venv /venv
-ENV PATH="/venv/bin:$PATH"
-
-# Create the directory where our app will live
+# Create the directory on the node image 
+# where our Next.js app will live
 RUN mkdir -p /app
+
+# Set /app as the working directory
 WORKDIR /app
 
-# Copy package.json and yarn.lock to the working directory
+# Copy package.json and yarn.lock
+# to the /app working directory
 COPY package*.json yarn.lock ./
 
-# Install Node.js dependencies
+# Install dependencies in /app
 RUN yarn install --network-timeout 1000000
 
-# Copy the rest of the Next.js folder into /app
+# Copy the rest of our Next.js folder into /app
 COPY . .
 
 # Build the Next.js application
 RUN yarn build
 
-# Second stage: Runtime environment
-FROM node:18.13.0-alpine
-
-# Copy the virtual environment from the builder stage
-COPY --from=builder /venv /venv
-ENV PATH="/venv/bin:$PATH"
-
-# Set the working directory
-WORKDIR /app
-
-# Copy built assets from the builder stage
-COPY --from=builder /app/.next ./.next
-COPY --from=builder /app/node_modules ./node_modules
-COPY --from=builder /app/package.json ./package.json
-COPY --from=builder /app/public ./public
-
 # Ensure port 3000 is accessible to our system
 EXPOSE 3000
 
-# Run yarn start, as we would via the command line
+# Run yarn start, as we would via the command line 
 CMD ["yarn", "start"]