GLM-5.2 Fast is now available. Learn more
embedding

ZeroEntropyZerank 2

Zerank 2 is our state-of-the-art reranker. Get dramatically more accurate retrieval with one line of code.

Model details

Example usage

Input
1import requests
2import os
3
4headers = {
5    f"Authorization": f"Api-Key {os.environ['BASETEN_API_KEY']}"
6}
7
8MODEL_ID = "" # Get from Baseten Dashboard
9
10response = requests.post(
11    headers=headers,
12    url=f"https://model-{MODEL_ID}.api.baseten.co/environments/production/sync/predict",
13    json={
14        "inputs": [
15          ["Baseten is a fast inference provider"], 
16          ["classify this separately."]
17        ],
18        "raw_scores": True,
19        "truncate": True,
20        "truncation_direction": "Right"
21    }
22)
23
24print(response.json())

JSON output
1[
2    [
3        {
4            "score": 3.375,
5            "label": "Yes"
6        }
7    ],
8    [
9        {
10            "score": 3.40625,
11            "label": "Yes"
12        }
13    ]
14]

🔥 Trending models