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: Spider web scraper & crawler tool #5725

Merged
merged 12 commits into from
Jul 18, 2024
Merged

Conversation

WilliamEspegren
Copy link
Contributor

Description

Add Spider, the fastest open source scraper & crawler that returns LLM-ready data.

Twitter: @WilliamEspegren

Type of Change

Please delete options that are not relevant.

  • New feature (non-breaking change which adds functionality)

How Has This Been Tested?

I have created a new workflow in the UI then tested it manually with all the different parameters.

image

Suggested Checklist:

  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • My changes generate no new warnings
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

This PR was inspired by #3819

@WilliamEspegren WilliamEspegren marked this pull request as ready for review June 28, 2024 20:57
@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. 🔨 feat:tools Tools for agent, function call related stuff. labels Jun 28, 2024
@WilliamEspegren WilliamEspegren changed the title Add new tool: Spider feat: Jul 2, 2024
@WilliamEspegren WilliamEspegren changed the title feat: feat: Spider web scraper & crawler tool Jul 2, 2024
@WilliamEspegren
Copy link
Contributor Author

@bowenliang123 could you check this one out? Let me know if you want any changes or help otherwise :)

@takatost takatost requested a review from laipz8200 July 5, 2024 10:39
@takatost
Copy link
Collaborator

takatost commented Jul 8, 2024

Hi @WilliamEspegren, I tried out Spider, but neither the SIGN IN nor REGISTER buttons are bringing up the login screen as expected. It's happening on both Chrome and Safari.

@WilliamEspegren
Copy link
Contributor Author

Hi @WilliamEspegren, I tried out Spider, but neither the SIGN IN nor REGISTER buttons are bringing up the login screen as expected. It's happening on both Chrome and Safari.

Hi @TakaTos! Thank you for mentioning this issue. Here is the link instead: https://spider.cloud/login

@crazywoola crazywoola requested a review from takatost July 8, 2024 10:15
@WilliamEspegren
Copy link
Contributor Author

@crazywoola @takatost just checking the status on this, if you want any help just ping me :)

Copy link
Collaborator

@takatost takatost left a comment

Choose a reason for hiding this comment

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

Thanks!!

@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Jul 18, 2024
@takatost takatost merged commit 588615b into langgenius:main Jul 18, 2024
5 checks passed
@takatost takatost mentioned this pull request Jul 23, 2024
@ivuai
Copy link

ivuai commented Jul 30, 2024

@WilliamEspegren is this tool still working in latest version? because it doesn't work for me when I enter API key it gives me this error: argument of type 'NoneType' is not iterable

@WilliamEspegren
Copy link
Contributor Author

Hey @ivuai! How does your parameters look like, and what nodes are you using?

@ivuai
Copy link

ivuai commented Jul 30, 2024

I don't use any node, I'm just simply trying to add API key in tools and I don't use any parameters. Here is the screenshot.
Capture987

@WilliamEspegren
Copy link
Contributor Author

Thank you @ivuai! Weird, I will look and test it out tomorrow :)

@WilliamEspegren
Copy link
Contributor Author

@ivuai the API was somehow down. I have added error checks to display this more clearly if that ever happens again, thanks for mentioning this 👏

cuiks pushed a commit to cuiks/dify that referenced this pull request Aug 6, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
🔨 feat:tools Tools for agent, function call related stuff. lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants