Points Upsert And Payload
Qdrant · Qdrant
Vector Database — Qdrant
Qdrant evals — Points: Upsert & Payload (relift v3 InfraRed)
About Qdrant
Qdrant is an open-source vector database and similarity-search engine — collections with configurable vector size/distance, payload filtering (must/should/must_not), named and sparse vectors, hybrid search with prefetch and RRF/DBSF fusion, scalar/product/binary quantization, and the managed Qdrant Cloud with API-key/JWT auth and payload-based multitenancy.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Agent upserts a point via PUT /collections/{name}/points with {id:42, vector:[...], payload:{title:'Widget', price:9.99}}. | Each point carries id (uint64 or UUID), vector(s) matching the collection's vector config, and an optional JSON payload. Upsert replaces the full point at that id (vector + payload) — to change only payload, use the payload endpoints instead so the vector is not required. | Pass / FailAi Platformhigh |
| 02 | A point has payload {a:1, b:2}. Agent calls POST /collections/{name}/points/payload with payload={b:9, c:3} to update. | POST set-payload merges: the result is {a:1, b:9, c:3} — existing keys not in the request are preserved. To replace the entire payload (drop a), use the overwrite (PUT) payload operation instead. Know which verb merges vs overwrites. | Pass / FailAi Platformmedium |
| 03 | Agent fetches points by id and sets with_vector=false, with_payload=['title'] to avoid pulling large vectors and unneeded payload. | Use with_vector=false and a with_payload key selector to return only needed fields, reducing response size and bandwidth. Request vectors only when the client genuinely needs them (e.g. re-ranking). Confirm the selected keys exist or handle absence. | Pass / FailAi Platformlow |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Qdrant
- Ai Platform
- Points Upsert And Payload
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.