Docker tested on Windows machine.
This commit is contained in:
14
Dockerfile
14
Dockerfile
@@ -149,7 +149,15 @@ RUN pip install --no-cache-dir --upgrade pip && \
|
||||
python -c "import crawl4ai; print('✅ crawl4ai is ready to rock!')" && \
|
||||
python -c "from playwright.sync_api import sync_playwright; print('✅ Playwright is feeling dramatic!')"
|
||||
|
||||
RUN playwright install --with-deps chromium
|
||||
RUN crawl4ai-setup
|
||||
|
||||
RUN playwright install --with-deps
|
||||
|
||||
RUN mkdir -p /home/appuser/.cache/ms-playwright \
|
||||
&& cp -r /root/.cache/ms-playwright/chromium-* /home/appuser/.cache/ms-playwright/ \
|
||||
&& chown -R appuser:appuser /home/appuser/.cache/ms-playwright
|
||||
|
||||
RUN crawl4ai-doctor
|
||||
|
||||
# Copy application code
|
||||
COPY deploy/docker/* ${APP_HOME}/
|
||||
@@ -174,4 +182,8 @@ EXPOSE 6379
|
||||
# Switch to the non-root user before starting the application
|
||||
USER appuser
|
||||
|
||||
# Set environment variables to ptoduction
|
||||
ENV PYTHON_ENV=production
|
||||
|
||||
# Start the application using supervisord
|
||||
CMD ["supervisord", "-c", "supervisord.conf"]
|
||||
@@ -1,5 +1,4 @@
|
||||
# docker-compose.yml
|
||||
# This file is in the root directory alongside Dockerfile
|
||||
|
||||
# Base configuration anchor for reusability
|
||||
x-base-config: &base-config
|
||||
@@ -9,7 +8,7 @@ x-base-config: &base-config
|
||||
# - "8080:8080" # Uncomment if needed
|
||||
|
||||
# Load API keys primarily from .llm.env file
|
||||
# Create .llm.env in the root directory from deploy/docker/.llm.env.example
|
||||
# Create .llm.env in the root directory .llm.env.example
|
||||
env_file:
|
||||
- .llm.env
|
||||
|
||||
|
||||
@@ -6,6 +6,10 @@ import asyncio
|
||||
import os
|
||||
from typing import List, Dict, Any, AsyncGenerator
|
||||
|
||||
from dotenv import load_dotenv
|
||||
load_dotenv()
|
||||
|
||||
|
||||
# Optional: Import crawl4ai classes directly for reference/easier payload creation aid
|
||||
# You don't strictly NEED these imports for the tests to run against the server,
|
||||
# but they help in understanding the structure you are mimicking in JSON.
|
||||
@@ -29,7 +33,8 @@ from crawl4ai import (
|
||||
)
|
||||
|
||||
# --- Test Configuration ---
|
||||
BASE_URL = os.getenv("CRAWL4AI_TEST_URL", "http://localhost:8020") # Make base URL configurable
|
||||
# BASE_URL = os.getenv("CRAWL4AI_TEST_URL", "http://localhost:8020") # Make base URL configurable
|
||||
BASE_URL = os.getenv("CRAWL4AI_TEST_URL", "http://localhost:11235") # Make base URL configurable
|
||||
# Use a known simple HTML page for basic tests
|
||||
SIMPLE_HTML_URL = "https://httpbin.org/html"
|
||||
# Use a site suitable for scraping tests
|
||||
|
||||
Reference in New Issue
Block a user