Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improve docs related to Crawl4AI #1683

Open
vanetreg opened this issue Jan 2, 2025 · 1 comment
Open

Improve docs related to Crawl4AI #1683

vanetreg opened this issue Jan 2, 2025 · 1 comment

Comments

@vanetreg
Copy link

vanetreg commented Jan 2, 2025

On page:
https://docs.phidata.com/tools/crawl4ai
specify what max_length means: chars, words or tokens ( I suppose chars but not sure )


I have a weird experience:
phidata: v2.7.6
crawl4ai: v0.4.246

Pls. note I set in example code max_length to 4000

agent = Agent(
    model=Ollama(id="llama3.2:latest", host = ollama_base_url, timeout=180),
    tools=[Crawl4aiTools(max_length=4000)],
    show_tool_calls=True
)

but terminal shows 10000 !!
- Running: web_crawler(max_length=10000, url=https://huggingface.co/blog/smolagents)
note I saved the code before running for sure, I even changed the scraped URL to confirm it... :)

EDIT:
note i tested your hackernews.py example
https://github.com/phidatahq/phidata/blob/main/cookbook/async/hackernews.py
and when running it showed:
Running: get_top_hackernews_stories(num_stories=100)
while 10 was set in the code, so it is the 2nd instance of the same weird stuff.

@manthanguptaa
Copy link
Contributor

Hey @vanetreg you are correct. We are trying hard to update our docs and keep up with our development. We will fix this soon enough

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants