ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: Update pip installation command and requirements, add new dependencies

Browse Source
This commit is contained in:
unclecode
2024-05-17 16:53:03 +08:00
parent d7b37e849d
commit 1cc67df301
5 changed files with 46 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
docs/examples/quickstart.py
View File

@@ -170,22 +170,11 @@ def main():
cprint("If this is the first time you're running Crawl4ai, this might take a few seconds to load required model files.")
crawler = create_crawler()
cprint("For the rest of this guide, I set crawler.always_by_pass_cache to True to force the crawler to bypass the cache. This is to ensure that we get fresh results for each run.")
crawler.always_by_pass_cache = True
cprint("\n🔍 [bold cyan]Time to explore another chunking strategy: NlpSentenceChunking![/bold cyan]", True)
cprint("NlpSentenceChunking uses NLP techniques to split the text into sentences. Let's see how it performs!")
result = crawler.run(
url="https://www.nbcnews.com/business",
chunking_strategy=NlpSentenceChunking()
)
cprint("[LOG] 📦 [bold yellow]NlpSentenceChunking result:[/bold yellow]")
print_result(result)
basic_usage(crawler)
understanding_parameters(crawler)
crawler.always_by_pass_cache = True
add_chunking_strategy(crawler)
add_extraction_strategy(crawler)
add_llm_extraction_strategy(crawler)