feat: docker compose

.dockerignore

@@ -0,0 +1,20 @@
+.git
+.gitignore
+.env
+.venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+*.py[cod]
+*$py.class
+.pytest_cache
+.coverage
+htmlcov
+.mypy_cache
+.ruff_cache
+.DS_Store
+notebooks/
+tests/
+docs/

.github/workflows/ci.yml

@@ -9,13 +9,18 @@ on:
 jobs:
   test:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.10", "3.11", "3.12"]
+      fail-fast: false
+
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python 3.12
+      - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v5
         with:
-          python-version: "3.12"
+          python-version: ${{ matrix.python-version }}
           cache: "pip"
 
       - name: Install Poetry
@@ -27,9 +32,14 @@ jobs:
           poetry config virtualenvs.create true
           poetry config virtualenvs.in-project true
 
+      - name: Cache Poetry virtualenv
+        uses: actions/cache@v3
+        with:
+          path: ./.venv
+          key: venv-${{ runner.os }}-${{ matrix.python-version }}-${{ hashFiles('**/poetry.lock') }}
+
       - name: Install dependencies
         run: |
-          poetry lock --no-update
           poetry install
 
       - name: Run pre-commit hooks
@@ -39,5 +49,24 @@ jobs:
         env:
           PRE_COMMIT_CACHE_KEY: ${{ hashFiles('.pre-commit-config.yaml', 'pyproject.toml') }}
 
-      - name: Run tests
-        run: poetry run pytest
+      - name: Run tests with coverage
+        run: |
+          poetry run pytest --cov=llmdataparser --cov-report=xml
+
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./coverage.xml
+          fail_ci_if_error: true
+
+      - name: Build documentation
+        run: |
+          poetry run mkdocs build
+        if: matrix.python-version == '3.12'
+
+      - name: Upload documentation artifact
+        uses: actions/upload-artifact@v3
+        with:
+          name: documentation
+          path: site/
+        if: matrix.python-version == '3.12'

CHANGELOG.md

@@ -0,0 +1,16 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## \[1.0.0\] - 2024-12-30
+
+### Added
+
+- Initial release
+- Support for multiple benchmark datasets (MMLU, GSM8k, etc.)
+- Gradio interface for dataset exploration
+- Comprehensive test suite
+- Documentation and examples

Makefile

@@ -1,8 +1,13 @@
+# -----------------------------
 # Variables
+# -----------------------------
 IMAGE_NAME = llmdataparser
 CONTAINER_NAME = llmdataparser
 VERSION = latest
 
+# -----------------------------
+# Docker Basic Commands
+# -----------------------------
 # Build the Docker image
 build:
 	docker build -t $(IMAGE_NAME):$(VERSION) .
@@ -23,28 +28,80 @@ rm:
 rmi:
 	docker rmi $(IMAGE_NAME):$(VERSION)
 
-# Clean everything
-clean: stop rm rmi
+# -----------------------------
+# Docker Compose Commands
+# -----------------------------
+# Start with docker-compose (development)
+compose-up:
+	docker compose up -d
+
+# Stop and remove containers
+compose-down:
+	docker compose down
+
+# View logs
+compose-logs:
+	docker compose logs -f
+
+# Rebuild containers
+compose-build:
+	docker compose build
 
-# Build and run
+# Restart containers
+compose-restart:
+	docker compose restart
+
+# -----------------------------
+# Convenience Commands
+# -----------------------------
+# Build and run with docker
 up: build run
 
 # Stop and remove container
 down: stop rm
 
+# Clean everything
+clean: stop rm rmi
+
+# -----------------------------
+# Monitoring Commands
+# -----------------------------
 # Show container logs
 logs:
 	docker logs $(CONTAINER_NAME)
 
+# Follow container logs
+logs-follow:
+	docker logs -f $(CONTAINER_NAME)
+
+# Show container status
+status:
+	docker ps -a | grep $(CONTAINER_NAME)
+
 # Enter container shell
 shell:
 	docker exec -it $(CONTAINER_NAME) /bin/bash
 
-# Optional: command to check container status
-status:
-	docker ps -a | grep $(CONTAINER_NAME)
+# -----------------------------
+# Production Commands
+# -----------------------------
+# Test nginx configuration (for production use)
+nginx-test:
+	docker compose run --rm nginx nginx -t
 
-logs-follow:
-	docker logs -f $(CONTAINER_NAME)
+# Start with nginx test (for production use)
+compose-up-prod: nginx-test compose-up
+
+# -----------------------------
+# Security Commands
+# -----------------------------
+security-check:
+	@echo "Checking nginx configuration..."
+	docker compose run --rm nginx nginx -t
+	@echo "Checking exposed ports..."
+	docker compose config | grep -E "ports:|127.0.0.1"
 
-.PHONY: build run stop rm rmi clean up down logs shell
+# Ensure all targets are treated as commands, not files
+.PHONY: build run stop rm rmi clean up down logs shell \
+        compose-up compose-down compose-logs compose-build compose-restart \
+        nginx-test status logs-follow compose-up-prod

app.py

@@ -390,13 +390,7 @@ if __name__ == "__main__":
     demo = create_interface()
     try:
         demo.launch(
-            server_port=7860,
-            auth=None,
-            ssl_keyfile=None,
-            ssl_certfile=None,
             show_error=True,  # Changed to True for debugging
-            share=False,
-            max_threads=40,
         )
     except Exception as e:
         print(f"Error launching Gradio: {e}")  # Add error logging

docker-compose.yml

@@ -0,0 +1,34 @@
+version: "3.8"
+
+services:
+  llmdataparser:
+    build: .
+    environment:
+      - GRADIO_SERVER_PORT=7860
+    volumes:
+      - .:/app
+      - huggingface_cache:/app/.cache/huggingface
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://127.0.0.1:7860"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+    networks:
+      - internal
+
+  nginx:
+    image: nginx:alpine
+    ports:
+      - "80:80"
+    volumes:
+      - ./nginx.conf:/etc/nginx/nginx.conf:ro
+    depends_on:
+      - llmdataparser
+    networks:
+      - internal
+
+networks:
+  internal:
+
+volumes:
+  huggingface_cache:

nginx.conf

@@ -0,0 +1,58 @@
+events {
+    worker_connections 1024;
+}
+
+http {
+    # Basic security settings
+    server_tokens off;  # Don't show nginx version
+    client_max_body_size 10M;  # Limit request size
+    client_body_timeout 12;
+    client_header_timeout 12;
+
+    upstream gradio_app {
+        server llmdataparser:7860;
+        keepalive 32;
+    }
+
+    server {
+        listen 80;
+        server_name localhost;
+
+        # Enhanced security headers
+        add_header X-Frame-Options "SAMEORIGIN" always;
+        add_header X-Content-Type-Options "nosniff" always;
+        add_header X-XSS-Protection "1; mode=block" always;
+        add_header Referrer-Policy "strict-origin-always" always;
+        add_header Content-Security-Policy "default-src 'self'; script-src 'self' 'unsafe-inline' 'unsafe-eval'; style-src 'self' 'unsafe-inline';" always;
+        add_header Strict-Transport-Security "max-age=31536000; includeSubDomains" always;
+
+        location / {
+            proxy_pass http://gradio_app;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+            proxy_set_header X-Forwarded-Proto $scheme;
+
+            # WebSocket support
+            proxy_http_version 1.1;
+            proxy_set_header Upgrade $http_upgrade;
+            proxy_set_header Connection "upgrade";
+
+            # Timeouts
+            proxy_connect_timeout 60s;
+            proxy_send_timeout 60s;
+            proxy_read_timeout 60s;
+
+            # Security
+            proxy_buffering on;
+            proxy_buffer_size 8k;
+            proxy_buffers 8 8k;
+        }
+
+        # Deny access to hidden files
+        location ~ /\. {
+            deny all;
+            return 404;
+        }
+    }
+}