61ae2de841
- default (most frequent mode) - torch - transformers - all 2/ Update Docker file 3/ Update documentation as well.
2.6 KiB
Installation 💻
There are three ways to use Crawl4AI:
- As a library (Recommended)
- As a local server (Docker) or using the REST API
- As a Google Colab notebook.
Library Installation
Crawl4AI offers flexible installation options to suit various use cases. Choose the option that best fits your needs:
-
Default Installation (Basic functionality):
virtualenv venv source venv/bin/activate pip install "crawl4ai @ git+https://github.com/unclecode/crawl4ai.git"Use this for basic web crawling and scraping tasks.
-
Installation with PyTorch (For advanced text clustering):
virtualenv venv source venv/bin/activate pip install "crawl4ai[torch] @ git+https://github.com/unclecode/crawl4ai.git"Choose this if you need the CosineSimilarity cluster strategy.
-
Installation with Transformers (For summarization and Hugging Face models):
virtualenv venv source venv/bin/activate pip install "crawl4ai[transformer] @ git+https://github.com/unclecode/crawl4ai.git"Opt for this if you require text summarization or plan to use Hugging Face models.
-
Full Installation (All features):
virtualenv venv source venv/bin/activate pip install "crawl4ai[all] @ git+https://github.com/unclecode/crawl4ai.git"This installs all dependencies for full functionality.
-
Development Installation (For contributors):
virtualenv venv source venv/bin/activate git clone https://github.com/unclecode/crawl4ai.git cd crawl4ai pip install -e ".[all]"Use this if you plan to modify the source code.
💡 After installation, it's recommended to run the following CLI command to load the required models. This is optional but will boost the performance and speed of the crawler. You need to do this only once:
crawl4ai-download-models
Using Docker for Local Server
To run Crawl4AI as a local server using Docker:
# For Mac users
# docker build --platform linux/amd64 -t crawl4ai .
# For other users
# docker build -t crawl4ai .
docker run -d -p 8000:80 crawl4ai
Using Google Colab
You can also use Crawl4AI in a Google Colab notebook for easy setup and experimentation. Simply open the following Colab notebook and follow the instructions: