Upsert Durability And Wal
turbopuffer · turbopuffer
Serverless vector database — turbopuffer
Evaluates turbopuffer's Upsert Durability & WAL 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.
Sample tests· showing 3 of 10
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Incident: search missed fresh row; default consistency must include WAL per query docs. | POST upsert_rows to /v2/namespaces/:namespace then query with consistency.level strong; confirm row visible before declaring success. | Pass / FailDurabilitycritical |
| 02 | Single file exceeds documented 512 MB max per write request. | Split into multiple POST writes each ≤512 MB; preserve ids; track batch progress; do not send oversized body. | Pass / FailLimitshigh |
| 03 | Load test saw throughput plateau; architecture docs describe group commit. | Describe 1 WAL entry per second group commit batching concurrent writes into same entry per architecture docs. | Pass / FailArchitecturemedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Penalize failure_modes.
Rubric criteria
- Turbopuffer
- Vector Db
- Upsert Durability And Wal
Recommended for
Works with
Related evals
Open-source column-oriented OLAP database for real-time analytics, plus ClickHouse Cloud (separated storage and compute)
23 graded scenarios covering edge cases, failure modes, and quality checks.
View Data AnalysisOpen-source column-oriented OLAP database for real-time analytics, plus ClickHouse Cloud (separated storage and compute)
7 graded scenarios covering edge cases, failure modes, and quality checks.
View Data AnalysisOpen-source column-oriented OLAP database for real-time analytics, plus ClickHouse Cloud (separated storage and compute)
25 graded scenarios covering edge cases, failure modes, and quality checks.
ViewFrequently asked questions
What does the Upsert Durability And Wal eval for turbopuffer turbopuffer test?+
Evaluates turbopuffer's Upsert Durability & WAL 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 Upsert Durability And Wal 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 Upsert Durability And Wal 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 Upsert Durability And Wal 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.