Embeddings LLM

POST 
/v1/embeddings

Generate embeddings for the given input text using the specified model.

The model field in the request body specifies the model to use. Check the /models route for complete list of embedding models. You can specify the encoding format (float or np) and the dimensions (up to 1536) of the output embedding vector.

Request

application/json

Body

Embedding generation query

model stringrequired

Model to use for generating embeddings.

input stringrequired

Input text to generate embeddings for.

encoding_format string

Possible values: [float, np]

Format of the output encoding. Only supported by OpenAI

dimensions integer

Possible values: <= 1536

Number of dimensions for the embedding vector. Maximum value is 384-1536 check the models route for max_tokens per model. Only supported by OpenAI

Responses

200

Embedding vector generated successfully

application/json

Schema

Schema

object string
data object[]
Array [
object string
index integer
embedding object
object string
index integer
embedding number[]
]
provider string
model string
usage object
prompt_tokens integer
total_tokens integer
prompt_characters integer
cost string
latency_ms integer

Example (from schema)

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": {
        "object": "embedding",
        "index": 0,
        "embedding": [
          [
            0.015207428,
            -0.0031979256,
            -0.042056903,
            0.03562467,
            0.022221763,
            -0.0012624348,
            0.013301042
          ]
        ]
      }
    }
  ],
  "provider": "openai",
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 6,
    "total_tokens": 6,
    "prompt_characters": 20,
    "cost": "0.0000001260",
    "latency_ms": 349
  }
}

Loading...