Pagination And Export
turbopuffer · turbopuffer
turbopuffer evals — Pagination & Export (relift v3)
About turbopuffer
turbopuffer is a serverless vector database designed for high-performance approximate nearest neighbor search at scale. It handles ingest, indexing, and hybrid queries with a simple HTTP API and charges only for storage and queries — no always-on infrastructure.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Compliance export terabyte-scale; POST /v2/namespaces/:namespace/export. | Use export endpoint with cursor from last response; loop until exhausted; do not re-fetch from start only. | Pass / FailExporthigh |
| 02 | Reranker stage already has ids; second hop needs skinny rows. | Set include_attributes to id and title only on query; keep top_k modest; avoid returning vec unless needed. | Pass / FailQuerylow |
| 03 | Engineer confused about pagination fields on query response. | Clarify top_k/per-result limits vs limit.total cap (10k documented); paginate UI client-side within returned batch or adjust query. | Pass / FailLimitsmedium |
Rubric criteria
- Turbopuffer
- Vector Db
- Pagination And Export
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.