chore: Update configuration values for chunk token threshold, overlap rate, and minimum word threshold. Create a new example for LLMExtraction Strategy, update Dockerfile, and README

2024-06-19 18:32:20 +08:00
parent 3f0e265baf
commit 539263a8ba
11 changed files with 212 additions and 130 deletions
--- a/crawl4ai/web_crawler.py
+++ b/crawl4ai/web_crawler.py
@@ -42,7 +42,7 @@ class WebCrawler:
    def warmup(self):
        print("[LOG] 🌤️  Warming up the WebCrawler")
        result = self.run(
-            url='https://crawl4ai.uccode.io/',
+            url='https://google.com/',
            word_count_threshold=5,
            extraction_strategy= NoExtractionStrategy(),
            bypass_cache=False,