- Step1: Install Crawlr via pip or download the binary from GitHub releases.
- Step2: Configure your OpenAI API key in the environment variable or config file.
- Step3: Define target URLs or domains and crawl parameters in the settings file.
- Step4: Run `crawlr start` to begin crawling, summarizing, and embedding content.
- Step5: Connect to your vector database (e.g., Pinecone, Weaviate, SQLite) and load the output index.
- Step6: Query the generated knowledge base using semantic search or integrate it into chatbots.