turbopuffer
For turbopufferData AnalysisVector Db

Delete And Tombstone Semantics

turbopuffer · turbopuffer

Serverless vector database — turbopuffer

Evaluates turbopuffer's Delete & Tombstone Semantics across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Serverless vector database eval coverage.

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.

Employees

~10

Industry

Vector Database

Headquarters

United States

Sample tests· showing 3 of 10

#InputExpected behaviorCheck
01

RTBF request for three articles; must use write delete_rows.

POST write with delete_rows for ids; verify with strong consistency query/filter; confirm ids absent.

Pass / FailDeletehigh
02

Offboarding tenant; millions of rows; cannot list ids first.

Use delete_by_filter with Eq tenant_id on write endpoint; confirm scope; follow with spot-check strong query.

Pass / FailDeletecritical
03

Tombstone visibility for pricing namespace; numeric delete SLA [REQUIRES-VERIFICATION].

Post-delete strong consistency query shows id absent from ANN/BM25 results; mark tombstone timing SLA [REQUIRES-VERIFICATION].

Pass / FailDeletehigh

Unlock full benchmark

7 more test cases

Use this benchmark

How this eval is graded

Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.

Rubric criteria

  • Turbopuffer
  • Vector Db
  • Delete And Tombstone Semantics

Recommended for

turbopufferturbopuffer customers

Works with

Related evals

Frequently asked questions

What does the Delete And Tombstone Semantics eval for turbopuffer turbopuffer test?+

Evaluates turbopuffer's Delete & Tombstone Semantics across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Serverless vector database eval coverage.

How is the Delete And Tombstone Semantics eval scored?+

The judge rubric: Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.

How many test cases does this eval pack include?+

The Delete And Tombstone Semantics pack for turbopuffer turbopuffer contains 10 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.

How do I run this eval?+

Sign up for Corsac, connect your model or agent endpoint, and run the Delete And Tombstone Semantics pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.

Run this eval in your workspace

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