POST /v1/embeddings to get one vector per input back. The examples use a client created as in Installation.
const embedding = await client.generateEmbedding({
model: "openai/text-embedding-3-large",
input: "Sample text",
});
embedding = client.generate_embedding({
"model": "openai/text-embedding-3-large",
"input": "Sample text",
})
resp, err := client.GenerateEmbedding(context.Background(), map[string]interface{}{
"model": "openai/text-embedding-3-large",
"input": "Sample text",
})
if err != nil {
panic(err)
}
fmt.Println(resp["data"])
var response = await client.CreateEmbedding(new Dictionary<string, object>
{
["model"] = "openai/text-embedding-3-large",
["input"] = "Sample text",
});
$response = $client->generateEmbedding([
'model' => 'openai/text-embedding-3-large',
'input' => 'Sample text',
]);
response = client.generate_embedding(
model: 'openai/text-embedding-3-large',
input: 'Sample text'
)
String body = """
{
"model": "openai/text-embedding-3-large",
"input": "Sample text"
}
""";
Object response = client.createEmbedding(new com.fasterxml.jackson.databind.ObjectMapper().readTree(body));
System.out.println(String.valueOf(response));
// No embeddings method yet: post() sends JSON to any Phaseo path.
let response = client.post("/embeddings", &json!({
"model": "openai/text-embedding-3-large",
"input": "Sample text"
}))?;
| Language | Method | Returns |
|---|---|---|
| TypeScript | client.generateEmbedding(request) | The typed response |
| Python | client.generate_embedding(request) or client.embeddings.create(request) | A dict |
| Go | client.GenerateEmbedding(ctx, req), alias CreateEmbedding | map[string]interface{} |
| C# | client.CreateEmbedding(request) | Dictionary<string, object>? |
| PHP | $client->generateEmbedding($request), alias createEmbedding() | An array |
| Ruby | client.generate_embedding(...), alias create_embedding | A Hash |
| Java | client.createEmbedding(jsonNode) | Object |
| Rust | client.post("/embeddings", &request) | PhaseoResponse, with the JSON in body |
Parameters
Field names are the JSON body fields in every SDK.| Field | Notes |
|---|---|
model | Required. An embedding model ID. |
input | Required. A string, an array of strings, or multimodal content parts (text, image, audio, video) for models that accept them. |
encoding_format | float (default), base64, base64_int8 or base64_binary. |
dimensions | A positive integer that shortens each vector, on models that support it. |
provider_options | Provider settings, such as Google’s task_type and title or Mistral’s output_dtype. |
user | End-user tag. |
Response
{
"data": [
{
"embedding": [0.1, 0.2, 0.3],
"index": 0
}
],
"usage": {
"input_tokens": 5,
"output_tokens": 0,
"total_tokens": 5,
"embedding_tokens": 5
}
}