Find Similar Semantic Neighbors
Exa · Exa Labs
Exa Labs evals — Find Similar & Semantic Neighbors (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.
Sample tests· showing 3 of 8
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | User provides seed URL https://example.com/blog/post-1 and wants related reading. | Note /findSimilar deprecated but functional; prefer documented alternatives when available; use findSimilar for URL-seeded semantic neighbors with excludeSourceDomain. | Pass / FailSimilaritymedium |
| 02 | SKU ABC-123 appears in unrelated retailers; user asks for similar pages to Amazon listing. | Explain findSimilar is semantic neural similarity on page content, not SKU equality; use search with SKU query for lexical needs. | Pass / FailSimilarityhigh |
| 03 | Seed is Japanese; team expects English-only neighbors. | Do not guarantee language match; apply query/filters if needed; disclose semantic neighbors may differ in language. | Pass / FailSimilaritylow |
Rubric criteria
- Exa Labs
- Search
- Find Similar Semantic Neighbors
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.