
RAG Web Browser
Pricing
Pay per usage
Go to Store

RAG Web Browser
Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in ChatGPT. It queries Google Search, scrapes the top N pages, and returns their content as Markdown for further processing by an LLM. It can also scrape individual URLs. Supports Model Context Protocol (MCP).
0.0 (0)
Pricing
Pay per usage
0
Total users
1
Monthly users
1
Runs succeeded
>99%
Last modified
2 months ago
This changelog summarizes all changes of the RAG Web Browser
1.0.15 (2025-03-27)
🐛 Bug Fixes
- Cancel requests only in standby mode
1.0.13 (2025-03-27)
🐛 Bug Fixes
- Cancel crawling requests from timed-out search queries
1.0.12 (2025-03-24)
🐛 Bug Fixes
- Updated selector for organic search results and places
1.0.11 (2025-03-21)
🐛 Bug Fixes
- Selector for organic search results
1.0.10 (2025-03-19)
🚀 Features
- Handle all query parameters in the standby mode (including proxy)
1.0.9 (2025-03-14)
🚀 Features
- Change default value for
scrapingTool
from 'browser-playwright' to 'raw-http' to improve latency.
1.0.8 (2025-03-07)
🚀 Features
- Add a new
scrapingTool
input to allow users to choose between Browser scraper and raw HTTP scraper
1.0.7 (2025-02-20)
🚀 Features
- Update Readme.md to include information about MCP
1.0.6 (2025-02-04)
🚀 Features
- Handle double encoding of URLs
1.0.5 (2025-01-17)
🐛 Bug Fixes
- Change default value of input query
- Retry search if no results are found
1.0.4 (2025-01-04)
🚀 Features
- Include Model Context Protocol in Standby Mode
1.0.3 (2024-11-13)
🚀 Features
- Improve README.md and simplify configuration
- Add an AWS Lambda function
- Hide variables initialConcurrency, minConcurrency, and maxConcurrency in the Actor input and remove them from README.md
- Remove requestTimeoutContentCrawlSecs and use only requestTimeoutSecs
- Ensure there is enough time left to wait for dynamic content before the Actor timeout (normal mode)
- Rename googleSearchResults to searchResults and searchProxyGroup to serpProxyGroup
- Implement input validation
0.1.4 (2024-11-08)
🚀 Features
- Add functionality to extract content from a specific URL
- Update README.md to include new functionality and provide examples
0.0.32 (2024-10-17)
🚀 Features
- Handle errors when request is added to Playwright queue. This will prevent the Cheerio crawler from repeating the same request multiple times.
- Silence error: Could not parse CSS stylesheet as there is no way to fix it at our end
- Set logLevel to INFO (debug level can be set using the
debugMode=true
input)
2024-10-11
🚀 Features
- Increase the maximum number of results (
maxResults
) from 50 to 100 - Explain better how to search a specific website using "llm site:apify.com"
2024-10-07
🚀 Features
- Add a short description how to create a custom action
2024-09-24
🚀 Features
- Updated README.md to include tips on improving latency
- Set initialConcurrency to 5
- Set minConcurrency to 3
2024-09-20
🐛 Bug Fixes
- Fix response format when crawler fails
2024-09-24
🚀 Features
- Add ability to create new crawlers using query parameters
- Update Dockerfile to node version 22
🐛 Bug Fixes
- Fix playwright key creation
2024-09-11
🚀 Features
- Initial version of the RAG Web Browser