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

feat: update firecrawl tool with additional features #1445

Open
wants to merge 4 commits into
base: main
Choose a base branch
from

Conversation

AbhishekRP2002
Copy link

@AbhishekRP2002
Copy link
Author

@manthanguptaa any updates on this ?

@manthanguptaa
Copy link
Contributor

Ran into this issue while running the code

Screenshot 2024-11-19 at 2 38 18 PM

reasoning=True,
markdown=True,
)
agent.print_response(f"Crawl and analyze the main use cases and insights using asynchronous crawling: {url}")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

extra whitespace in the middle of the sentence



if __name__ == "__main__":
url = "https://www.firecrawl.dev/blog"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

replace the link with https://docs.phidata.com/agents

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you not have Agents in functions and then call them? I think you can have only 1 Agent with the following config

Agent(
        tools=[FirecrawlTools(scrape=True, crawl=True, async_crawl=True, limit=25)],
        show_tool_calls=True,
        reasoning=True,
        markdown=True,
    )

and then ask the agent to do it synchronously or asynchronously

)
agent.print_response(f"Fetch all the blog links from the website: {url}")
agent.print_response(
"scrape and summarize the following website: https://www.firecrawl.dev/blog/using-structured-output-and-json-strict-mode-openai"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Replace this link with https://docs.phidata.com/workflows

if async_crawl:
self.register(self.async_crawl_website)
if crawl or async_crawl:
self.register(self.check_crawl_status)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should this be here? What if only async_crawl is True

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

if only async_crawl is True then also the code block will execute @manthanguptaa

@AbhishekRP2002
Copy link
Author

Ran into this issue while running the code

Screenshot 2024-11-19 at 2 38 18 PM

@manthanguptaa did u encounter it while running the cookbook script ?
what is the openai model being used by default ?
This is most likely due to stochastic nature of the llm model, as a result of which it could parse the exact tool params . I wasn't able to reproduce it.

PFA for ref:
image
image
image
image

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

Successfully merging this pull request may close these issues.

Update Firecrawl tool with Async Crawling and Map functionality.
3 participants