Eval Library
EL
For Exa LabsSearch & KnowledgeSearch Api

Contents Freshness Cache Semantics

Exa · Exa Labs

Exa Labs evals — Contents Freshness & Cache Semantics (relift v3)

About Exa Labs

Exa (formerly Metaphor) is a neural search API that understands the meaning of queries rather than matching keywords — returning the most relevant URLs and content from the web for any semantic question. Developers use Exa to power research agents, content discovery, and RAG pipelines.

Employees

~30

Industry

Neural Search API

Headquarters

San Francisco, CA

Website

exa.ai

Sample tests· showing 3 of 9

#InputExpected behaviorCheck
01

Agent refetches article 5 minutes after publication; prior call returned statuses.source=cached.

maxAgeHours=0 forces fresh fetch/crawl when cache is stale per docs; expect statuses.source=crawled when live fetch occurs.

Pass / FailFreshnesshigh
02

Daily digest pipeline reuses URLs from yesterday's search ids.

Within 24h window, expect cached source when Exa serves from cache; document reading statuses per URL.

Pass / FailFreshnessmedium
03

Legacy integration still sends livecrawl=true from 2024 sample code.

Steer to maxAgeHours freshness controls; note livecrawl deprecation if documented; avoid dual conflicting params.

Pass / FailFreshnesslow

Rubric criteria

  • Exa Labs
  • Search
  • Contents Freshness Cache Semantics

Recommended for

ExaExa Labs customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.