https://github.com/apify/actor-rag-web-browser
RAG Web Browser is an Apify Actor to feed your LLM applications and RAG pipelines with up-to-date text content scraped from the web.
https://github.com/apify/actor-rag-web-browser
ai crawling llm rag scraper serp
Last synced: 14 days ago
JSON representation
RAG Web Browser is an Apify Actor to feed your LLM applications and RAG pipelines with up-to-date text content scraped from the web.
- Host: GitHub
- URL: https://github.com/apify/actor-rag-web-browser
- Owner: apify
- License: apache-2.0
- Created: 2024-08-15T10:57:04.000Z (almost 2 years ago)
- Default Branch: master
- Last Pushed: 2026-07-24T11:33:56.000Z (14 days ago)
- Last Synced: 2026-07-24T13:10:20.382Z (14 days ago)
- Topics: ai, crawling, llm, rag, scraper, serp
- Language: TypeScript
- Homepage: https://apify.com/apify/rag-web-browser
- Size: 1.26 MB
- Stars: 74
- Watchers: 2
- Forks: 18
- Open Issues: 29
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# actor-rag-web-browser
This monorepo contains the source code for two Apify Actors:
- **[RAG Web Browser](https://console.apify.com/actors/3ox4R101TgZz67sLr)** — Web browser for RAG pipelines that accepts a search query or URL list, searches the web or loads specific URLs, and returns cleaned content as Markdown.
- **[URL to Markdown](https://console.apify.com/actors/oK4fp52ayRqNayFTw)** — Converts web pages to clean Markdown content.
For detailed documentation on each Actor, see their READMEs in the [`actors/`](./actors) folder:
- [`actors/apify_rag-web-browser/README.md`](./actors/apify_rag-web-browser/README.md)
- [`actors/apify_url-to-markdown/README.md`](./actors/apify_url-to-markdown/README.md)