
Algolia
AI-powered search and discovery platform delivering relevant results with speed and scalability.

The search engine for AI agents that understands what web pages actually mean.

Exa (formerly Metaphor) represents a paradigm shift in web indexing, moving from traditional keyword-based crawling to a fully neural architecture. Unlike Google, which focuses on human-readable snippets, Exa is built specifically for Large Language Models (LLMs) and AI agents. It utilizes a transformer-based encoder to map the entire web into a high-dimensional vector space, allowing users to search by meaning and style rather than exact string matches. This enables 'find similar' capabilities that can locate documents with identical semantic structures across disparate domains. As of 2026, Exa has positioned itself as the essential retrieval layer for RAG (Retrieval-Augmented Generation) pipelines, offering clean Markdown outputs that bypass the noise of traditional HTML. Its architecture handles the heavy lifting of content scraping, boilerplate removal, and embedding-based filtering, providing a 'Search-as-a-Service' model that scales from hobbyist developers to enterprise-grade AI agents requiring high-concurrency access to the live web.
Exa (formerly Metaphor) represents a paradigm shift in web indexing, moving from traditional keyword-based crawling to a fully neural architecture.
Explore all tools that specialize in neural content extraction. This domain focus ensures Exa delivers optimized results for this specific requirement.
Uses a custom transformer model to predict the next relevant link based on a prompt's semantic context.
Server-side HTML parsing that strips ads, navbars, and scripts to return pure Markdown.
Input a URL to find thousands of semantically similar pages using vector clustering.
Near real-time indexing of the web with specialized focus on high-quality technical content.
An LLM-driven layer that rewrites user queries into 'link-prediction' format.
Pre-classified indices for 'Company', 'Research Paper', 'Blog', and 'PDF'.
Filtering of the neural index based on specific 'published' or 'crawled' date ranges.
Create an account at dashboard.exa.ai to obtain your API key.
Install the official SDK via 'npm install exa-js' or 'pip install exa_py'.
Initialize the Exa client with your secure API key environment variable.
Execute a basic neural search using the 'search' method with natural language queries.
Utilize the 'useAutoprompt' flag to let Exa optimize your query for neural retrieval.
Use 'includeDomains' or 'excludeDomains' to restrict search scope to high-authority sources.
Call the 'getContents' method to retrieve cleaned Markdown from specific URLs.
Implement 'findSimilar' to discover pages that match the semantic profile of a seed URL.
Configure rate limit handling and exponential backoff for high-volume agentic workflows.
Integrate results into your LLM prompt as context for RAG-based applications.
All Set
Ready to go
Verified feedback from other users.
"Highly praised for the 'clean' nature of returned content and the superior relevance of its neural search over the Bing/Google Search APIs."
Post questions, share tips, and help other users.

AI-powered search and discovery platform delivering relevant results with speed and scalability.

The privacy-first generative search engine powered by an independent, multi-billion page web index.
Design, document, and build APIs faster.
Digital developers who are actually easy to work with.
Open Source LLM Engineering Platform

The Open-Source Framework for Reinforcement Learning in Quantitative Finance.