hosting

POST `/v1/vector/indexes`

Create a vector index.

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 \
  -H "Authorization: Bearer zdk_live_…" \
  -H "Content-Type: application/json" \
  -d '{ "name": <string>, "dimension": <integer> }'

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

Creates an index of a fixed width and distance function. `dimension` is whatever your embedding model emits, from 1 to 3072 — it does not have to be a round number, and a width we do not store natively is held exactly rather than approximately. Above 2000 dimensions the index is stored at half precision, because pgvector's HNSW index does not accept a full-precision column wider than that. Requires `vector.manage`, and is refused if the plan's `vector_indexes` allowance is full.

Akoonu ibeere naa

Orúkọ	Iru	Tí a nílò	Kini o jẹ
`name`	`string`	Bẹẹni	—
`dimension`	`integer`	Bẹẹni	—
`metric`	`string<cosine, l2, inner_product>`	Bẹẹkọ	—

Idahun

Orúkọ	Iru	Tí a nílò	Kini o jẹ
`id`	`string`	Bẹẹni	—
`name`	`string`	Bẹẹni	Lower-case, hyphenated, unique within the organisation.
`dimension`	`integer`	Bẹẹni	The width your embedding model emits, and the width reads return. Fixed at creation.
`metric`	`string<cosine, l2, inner_product>`	Bẹẹni	The distance function. Fixed at creation.
`status`	`string<ready, deleting>`	Bẹẹni	—
`vectors`	`integer`	Bẹẹni	How many vectors the index holds.
`storage_bytes`	`integer`	Bẹẹni	What the index counts for against `vector_index_gb`. A published formula rather than a physical table size, so it is reproducible: 96 bytes of row overhead, plus the stored widt…
`created_at`	`string`	Bẹẹni	—

Awọn aṣiṣe ti ibudo ipari yii le da pada

401 · 403 · 422 · 429

POST /v1/vector/indexes