rag_web_browser
Fetch web pages and convert them into clean LLM-ready text for RAG pipelines. Use when an agent needs readable page content from the web without HTML noise — a lightweight browser alternative for retrieval. Returns per-page cleaned text with metadata. Pricing: $0.003 per page crawled.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lang | No | Language code for search results (e.g. en, fr, de) | en |
| urls | No | Direct page URLs to extract content from (instead of searching). Example: ["https://example.com/article"] | |
| query | No | Google search query. Top results are fetched and extracted. Example: 'best crm software 2026' | |
| maxResults | No | Maximum number of search results / pages to process | |
| outputFormat | No | Content format: markdown (best for LLM/RAG) or plain text | markdown |