Skip to main content
Nowledge MemNowledge Mem
API ReferenceV1Embeddings

Create embeddings

POST
/v1/embeddings

Generate embeddings with the active search model on this local or self-hosted server. Supports OpenAI-compatible float and base64 responses plus the optional Nowledge input_type extension. The endpoint is not available on Nowledge Cloud. If a remote embedding provider is active, calls are forwarded by this server and count toward that provider's usage.

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/json

application/json

curl -X POST "https://example.com/v1/embeddings" \  -H "Content-Type: application/json" \  -d '{    "input": "string",    "model": "string"  }'
{  "data": [    {      "embedding": [        0.1      ],      "index": 0,      "object": "string"    }  ],  "model": "string",  "object": "string",  "usage": {    "prompt_tokens": 0,    "total_tokens": 0  }}