Skip to content

Conversation

@srilaasya
Copy link
Collaborator

📥 Pull Request

📘 Description
Updated Firecrawl tool with added functonalities:

  • retrieve_web_crawl: Gets the results of a previously initiated web crawl using its crawl ID
  • batch_scrape: Scrapes multiple URLs simultaneously, returning content in specified formats (markdown/HTML)
  • check_batch_status: Checks the completion status and results of an asynchronous batch scraping job
  • extract_data: Extracts structured data from URLs using LLMs based on a schema or natural language prompt
  • map_website: Discovers and returns all accessible URLs on a website, with optional search filtering
  • batch_extract: Performs structured data extraction across multiple URLs in a single batch operation

[TODO] Populate scraped data to a vectordb
#273

@codecov
Copy link

codecov bot commented Feb 13, 2025

Codecov Report

Attention: Patch coverage is 0% with 25 lines in your changes missing coverage. Please review.

Files with missing lines Patch % Lines
agentstack/_tools/firecrawl/__init__.py 0.00% 25 Missing ⚠️

📢 Thoughts on this report? Let us know!

# Conflicts:
#	agentstack/_tools/vision/__init__.py
#	agentstack/_tools/vision/config.json
@bboynton97
Copy link
Contributor

made a few small fixes, merged main in, and cleaned it up.

in the future, please be sure to make new feature branches off of main.

git checkout main
git pull origin main
git branch <feature-branch-name>

@bboynton97
Copy link
Contributor

there was a mypy type error as well.

please be sure to manually test all of your code, as well as run mypy agentstack for type checking

@bboynton97 bboynton97 merged commit eafff89 into main Feb 14, 2025
9 of 10 checks passed
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.

3 participants