Skip to content

Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.

fix: default LLMExtractionStrategy extraction_type to schema

unclecodeec560f13d298
diff --git a/crawl4ai/extraction_strategy.py b/crawl4ai/extraction_strategy.py
index 494ddc07..ed039890 100644
--- a/crawl4ai/extraction_strategy.py
+++ b/crawl4ai/extraction_strategy.py
@@ -558,7 +558,7 @@ class LLMExtractionStrategy(ExtractionStrategy):
llm_config: 'LLMConfig' = None,
instruction: str = None,
schema: Dict = None,
- extraction_type="block",
+ extraction_type="schema",
chunk_token_threshold=CHUNK_TOKEN_THRESHOLD,
overlap_rate=OVERLAP_RATE,
word_token_rate=WORD_TOKEN_RATE,