cURL
curl --request POST \ --url https://api.veryfront.com/projects/{project_reference}/embeddings \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "chunk_ids": [ "3c90c3cc-0d44-4b50-8888-8dd25736052a" ], "vectors": [ [ 123 ] ], "model": { "name": "<string>", "provider": "<string>", "dimension": 123 } } '
{ "embeddings": [ { "id": "<string>", "model": "<string>", "status": "ready", "created_at": "<string>" } ], "created": 123, "updated": 123 }
Upsert embeddings for file chunks. The app generates vectors (e.g., via OpenAI), API stores them for search.
Authentication via JWT token or API key. JWT: Get from Veryfront dashboard. API Key: Format "vf__" - create via /api-keys endpoint.
Project ID or slug
1 - 100
Show child attributes
Upsert results