Inovacc Developer

API reference / Knowledge and vector search

Ingest documents

POSThttps://ai.inovacc.dev/v1/vector/ingest

Store passages in your organization's Vector Database, embedded and ready to be searched by meaning.

Body params

  • scope"shared" | "local"required

    shared: visible to every service of your workspace. local: visible only to the API key that writes it.

  • documentsarrayrequired

    1 to 100 passages. A passage that cannot be stored is listed in skipped with a reason; the others are stored.

  • documents[].idstringrequired

    Your id for the passage, 1 to 256 bytes. Ingesting an existing id in the same scope replaces it.

  • documents[].textstringrequired

    The passage, returned by queries. With id and metadata it must fit in 10 KiB.

  • documents[].metadataobject

    Flat values: strings, numbers, booleans or arrays of strings. kind, source, category, tag, language and created_at can be filtered on.

  • documents[].document_idstring

    Groups passages into one document that can be deleted or replaced as a whole.

  • documents[].generationinteger

    Your version of the document. A higher generation replaces the older one; a deleted document only accepts a higher one.

  • documents[].content_sha256string

    Your SHA-256 of the document's content, 64 lowercase hex characters, given back by GET /v1/vector/documents.

Headers

  • Authorizationstringrequired

    Bearer <API key>

  • X-Operation-Idstringrequired

    a unique id you choose, on every call except GET

  • Content-Typestringrequired

    application/json, on a call with a body

See also

Source details

Catalogue entry

Id
identity/component-taxonomy/capabilities#knowledge
Repository
identity
Path
contracts/component-taxonomy/catalog/capabilities.json
Commit
08ef3cd75d82

Contract section

Id
ai/ai/contract#post-v1vectoringest
Repository
ai
Path
apps/cloudflare/workers/api/ai/CONTRACT.md
Commit
972a1c15b9d5
Version documented
2.37.0
Version live
2.14.0
Updated 2026-10-10.