llm-context
Pre-extracted web content optimized for LLM RAG inputs.
Developer Setup
Setup & Installation
npx skills add https://github.com/brave/brave-search-skills --skill llm-contextnpx skills add https://github.com/brave/brave-search-skills --skill llm-contextOverview
What This Skill Does
Delivers token-budgeted, relevance-ranked web page content (including text, tables, and code) directly to LLM prompts.
Application
When to use this Skill
- When you are building a custom RAG (Retrieval-Augmented Generation) pipeline for an LLM.
- When you need pre-extracted, token-budgeted main body text rather than generic search snippets.
- When you want to reduce LLM prompt token counts by adjusting max_tokens or max_urls filters.
- When you need to extract structured elements like tables or code blocks directly from web pages.
- When you want to apply custom Goggles ranking rules to prioritize certain knowledge bases.
Documentation
Show Skills.md file
LLM Context
Requires API Key: Get one at https://api.search.brave.com
Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe
Brave LLM Context API delivers pre-extracted, relevance-ranked web content optimized for grounding LLM responses in real-time search results. Unlike traditional web search APIs that return links and snippets, LLM Context extracts the actual page content—text chunks, tables, code blocks, and structured data—so your LLM or AI agent can reason over it directly.
LLM Context vs AI Grounding
| Feature | LLM Context (this) | AI Grounding (answers) |
|---|---|---|
| Output | Raw extracted content for YOUR LLM | End-to-end AI answers with citations |
| Interface | REST API (GET/POST) | OpenAI-compatible /chat/completions |
| Searches | Single search per request | Multi-search (iterative research) |
| Speed | Fast (<1s) | Slower |
| Plan | Search | Answers |
| Endpoint | /res/v1/llm/context |
/res/v1/chat/completions |
| Best for | AI agents, RAG pipelines, tool calls | Chat interfaces, research mode |
Endpoint
GET https://api.search.brave.com/res/v1/llm/context
POST https://api.search.brave.com/res/v1/llm/context
Recommendations