Skip to content

Conversation

@ZeeshanAdilButt
Copy link

Description

Add Olostep tools, utilities, and document loader for AI-powered web search, scraping, and crawling capabilities.

Olostep is the most reliable and cost-effective web search, scraping and crawling API for AI. Build intelligent agents that can search, scrape, analyze, and structure data from any website.

New components

  • OlostepAPIWrapper: Full API wrapper with sync/async methods for all Olostep endpoints
  • OlostepScrape: Tool for scraping web content with JavaScript rendering support
  • OlostepAnswers: Tool for AI-powered web search with structured output and sources
  • OlostepMap: Tool for extracting all URLs from a website (up to ~100,000 URLs)
  • OlostepCrawl: Tool for autonomous website crawling
  • OlostepLoader: Document loader with scrape/crawl/map modes

Features

  • Scrape: Extract clean, LLM-ready content from any website
  • Crawl: Autonomously discover and scrape entire websites
  • Map: Discover complete website structure
  • Batch: Process up to 10,000 URLs in parallel
  • Answers: AI-powered web search with natural language queries

Includes unit tests and integration tests.

Issue

N/A

Dependencies

None (uses requests and aiohttp which are already available)

Add Olostep tools, utilities, and document loader for AI-powered web search,
scraping, and crawling capabilities.

New components:
- OlostepAPIWrapper: Full API wrapper with sync/async methods
- OlostepScrape: Tool for scraping web content
- OlostepAnswers: Tool for AI-powered web search with structured output
- OlostepMap: Tool for extracting all URLs from a website
- OlostepCrawl: Tool for autonomous website crawling
- OlostepLoader: Document loader with scrape/crawl/map modes

Features:
- Scrape: Extract clean, LLM-ready content from any website
- Crawl: Autonomously discover and scrape entire websites
- Map: Extract up to ~100,000 URLs from a website
- Batch: Process up to 10,000 URLs in parallel
- Answers: AI-powered web search with natural language queries

Includes unit tests and integration tests.
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.

1 participant