hosting
POST /v1/vector/indexes/{indexId}/query
Find the nearest vectors.
Ìfàṣẹ́pọ̀
Fi bọ́ọ̀lù (bearer token) ranṣẹ gẹ́gẹ́ bí kọ́kọ́rọ́ API. Kọ́kọ́rọ́ náà gbọ́dọ̀ ní ìyọ̀ǹda vector.manage; a ó kọ̀ ọ́ silẹ pẹlu 403, kii ṣe 404, ti kọ́kọ́rọ́ náà kò bá ní i.
Ojú abánisọ̀rọ̀ yìí kò gba id ajọ kankan. Kọ́kọ́rọ́ rẹ ti mọ ajọ ti o jẹ ti e, a o si fèsì nipa rẹ̀.
Gbiyanju rẹ
Rọ́pọ̀ èyíkéyìí nínú àwọn àmì ìtọ́ka < > pẹ̀lú iye tirẹ̀, àti àmì ìdánimọ̀ bọ́tìnnì náà pẹ̀lú bọ́tìnnì kan láti inú dásibọ̀ọ̀dù rẹ.
curl -X POST https://api.zinndigital.com/v1/vector/indexes/{indexId}/query \
-H "Authorization: Bearer zdk_live_…" \
-H "Content-Type: application/json" \
-d '{ "values": <number[]> }'Ṣé o ti wọlé? Iwọ̀n api ní nú ìgbékalẹ̀ rẹ kún id àjọ gidi rẹ ati bọtini tirẹ, o si nṣiṣẹ ibeere na lòdì si api gidi ki o le rii esi gidi na. Ṣí ojú abáná yìí sílẹ̀ nínú kọnsólù API
Àwọn kúlẹ̀kúlẹ̀
Returns the top_k nearest vectors, nearest first, optionally restricted to those whose metadata contains filter. distance is in the index's own metric, so smaller is always nearer whichever metric you chose. ⛔ A query spends the plan's monthly query allowance, which is why it requires vector.manage rather than vector.view — a read that costs money is not a read.
Àwọn ìpìlẹ̀
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
indexId (path) | string | Bẹẹni | The index's id. |
Akoonu ibeere naa
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
values | number[] | Bẹẹni | The query vector — exactly dimension values. |
top_k | integer | Bẹẹkọ | — |
filter | object | Bẹẹkọ | Restrict the search to vectors whose metadata contains these keys and values. Containment, not equality of the whole object, so a filter naming one key matches a vector carrying… |
Idahun
| Orúkọ | Iru | Tí a nílò | Kini o jẹ |
|---|---|---|---|
matches | object[] | Bẹẹni | — |
Awọn aṣiṣe ti ibudo ipari yii le da pada
401 · 403 · 404 · 422 · 429