Developers

API

Embeddings

POST /v1/embeddings

Generates vector embeddings for the given text input. The request and response formats are identical to the OpenAI embeddings API.

Request

curl https://janus.neboloop.com/v1/embeddings \
  -H "Authorization: Bearer $NEBO_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "neboloop/nebo-embed-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Parameters

Parameter Type Required Description
model string Yes Embedding model ID. See Available Models.
input string or array Yes Text to embed. Can be a single string or array of strings.
encoding_format string No "float" (default) or "base64".

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0152, ...]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 9,
    "total_tokens": 9
  }
}

Available Models

Nebo Model Underlying Model Dimensions Use Case
neboloop/nebo-embed-small text-embedding-3-small 1536 General purpose, lower cost
neboloop/nebo-embed-large text-embedding-3-large 3072 Higher accuracy, larger vectors

Both models are served via OpenAI's embedding API. The Nebo model names are mapped transparently — you can use either the Nebo name or the underlying OpenAI name.

Using with the OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://janus.neboloop.com/v1",
    api_key="<your-jwt-token>"
)

response = client.embeddings.create(
    model="neboloop/nebo-embed-small",
    input="Search query text"
)

embedding = response.data[0].embedding
print(f"Dimensions: {len(embedding)}")

Batch Embedding

response = client.embeddings.create(
    model="neboloop/nebo-embed-small",
    input=[
        "First document to embed",
        "Second document to embed",
        "Third document to embed"
    ]
)

for item in response.data:
    print(f"Index {item.index}: {len(item.embedding)} dimensions")

Headers

Header Required Description
Authorization Yes Bearer <jwt-token>
Content-Type Yes application/json
X-Bot-ID No Application identifier for usage tracking. Defaults to "default".

Next Steps

Models Usage & Limits