embedding
Zembed 1
Zembed 1ZeroEntropy’s flagship, state-of-the-art, open-weight, multilingual embedding model.
Model details
Example usage
Input
1import os
2from openai import OpenAI
3
4model_id = "" #Add Model ID from Baseten dashboard
5
6client = OpenAI(
7 api_key=os.environ["BASETEN_API_KEY"],
8 base_url=f"https://model-{model_id}.api.baseten.co/environments/production/sync"
9)
10
11response = client.embeddings.create(
12 model="zembed-1",
13 input=[
14 "query: What is the capital of France?",
15 "passage: Paris is the capital of France.",
16 ],
17 dimensions=2048,
18)JSON output
1{
2 "data": [
3 {
4 "embedding": [
5 "<EMBEDDING VECTOR>"
6 ],
7 "index": 0,
8 "object": "embedding"
9 },
10 {
11 "embedding": [
12 "<EMBEDDING VECTOR>"
13 ],
14 "index": 1,
15 "object": "embedding"
16 }
17 ],
18 "model": "zembed-1",
19 "object": "list",
20 "usage": {
21 "prompt_tokens": 37,
22 "total_tokens": 37
23 }
24}
