The SambaNova Cloud Embeddings API generates vector representations (embeddings) of input text, facilitating tasks such as semantic similarity analysis, clustering, search optimization, and retrieval-augmented generation (RAG). This API enables developers to integrate advanced AI capabilities into their applications by transforming textual data into structured numerical representations.

​
Endpoint

The API provides an endpoint to generate embedding vectors for input text.

​
Request

POST https://api.sambanova.ai/v1/embeddings

Authorization: Bearer <your-api-key>

​
Request body parameters

ParameterTypeDescriptionRequired
inputString or array of stringsThe input text to be embedded. Must not exceed the model’s token limit.Yes
modelStringThe model used to generate embeddings (e.g., E5-Mistral-7B-Instruct).Yes

This API ensures efficient embedding generation, supporting multiple input formats while enforcing model constraints.

​
Example request

The following example demonstrates how to send a request to the SambaNova Cloud Embeddings API using curl.

​
CURL request

CURL request
curl https://api.sambanova.ai/v1/embeddings \
  -H "Authorization: Bearer <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The curious fox dashed through the golden field.",
    "model": "E5-Mistral-7B-Instruct"
  }'

​
Example response

Example response
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [0.00333473, -0.0223934397434, ..., -0.013434322],
      "index": 0
    }
  ],
  "model": "E5-Mistral-7B-Instruct",
  "usage": {
    "prompt_tokens": 28,
    "total_tokens": 28
  }
}

​
Response properties

The API response consists of the following properties:

PropertyTypeDescription
objectStringThe type of response, always list.
dataArrayA list of embedding objects.
modelStringThe name of the model used to generate embeddings.
usageObjectToken usage statistics for the request, including prompt_tokens.

​
Embedding object

PropertyTypeDescription
objectStringAlways embedding.
embeddingArrayThe embedding vector, represented as a list of floats.
indexIntegerThe index of the embedding in the list of embeddings.

​
Error handling

See API error codes page for more information.

Error typeHTTP codeDescriptionCode
Invalid request error400An issue with the request parameters, e.g., model not compatible or input too long.invalid_request_error
Authentication error401The provided API key is invalid.invalid_authentication
Rate limit exceeded429Request quota exceeded.insufficient_quota
Request timeout408The request timed out.request_timeout

​
Example error response

Example error response
{
  "error": {
    "message": "Model 'model_name' does not support embeddings.",
    "type": "invalid_request_error",
    "param": "model",
    "code": "model_not_compatible"
  }
}