Update web_crawler.py

Set NoExtractionStrategy for FetchPages
This commit is contained in:
UncleCode
2024-05-16 22:06:33 +08:00
committed by GitHub
parent 5ce1dc1622
commit a856319499

View File

@@ -184,7 +184,7 @@ class WebCrawler:
extract_blocks_flag: bool = True,
word_count_threshold=MIN_WORD_THRESHOLD,
use_cached_html: bool = False,
extraction_strategy: ExtractionStrategy = LLMExtractionStrategy(),
extraction_strategy: ExtractionStrategy = NoExtractionStrategy(),
chunking_strategy: ChunkingStrategy = RegexChunking(),
**kwargs,
) -> List[CrawlResult]: