pplx-decider-v1-27b - SGLang Documentation

Deployment

Install SGLang

Until a release includes pplx-decider support, use a nightly build. The nightly image carries it:

Command

docker pull lmsysorg/sglang:dev

The recipe below serves the model in BF16 on one H200 with no extra flag. SGLang reads the checkpoint’s decision_config.json, loads its decision readout, and answers on /v1/systemone with the prompt, answer codes, and calibrated temperature the model was trained with.

1. Model Introduction

pplx-decider-v1-27b is a decision model from Perplexity, fine-tuned from Qwen3.8-27B under the Apache-2.0 license. It replaces the language model head with a readout over 255 answer codes, and answers choice, yes or no (noul), and score questions about a text state and optional images with a probability for every option, without generating text. Resources: HuggingFace.

2. Configuration Tips

Route. Send requests to /v1/systemone, the System One API the checkpoint was trained for. /v1/decisions refuses this checkpoint because its labels and prompt are not the ones the readout learned, and chat or generation requests are not meaningful without a language model head.
Clients. Clients of the System One API, including the TypeSafe SDKs, work by pointing their base URL at the server. See System One compatible API for the request and response reference.
Images. Pass each image in images as base64 bytes or a URL. They precede the text in every question, as in the checkpoint’s reference code.

3. Advanced Usage

3.1 Text Decisions

Text Decision Example (Python)

Example

import requests

response = requests.post(
    "http://localhost:30000/v1/systemone",
    json={
        "model": "perplexity-ai/pplx-decider-v1-27b",
        "state": "My Stripe integration keeps failing. I'm losing sales. Please help ASAP.",
        "questions": {
            "routing": {
                "type": "choice",
                "instructions": "Which team should handle this request?",
                "criteria": {
                    "billing": "Charges and refunds",
                    "technical_support": "Integration errors",
                    "sales": "Questions about buying a product",
                },
            },
            "urgency": {"type": "noul", "instructions": "Does this message express urgency?"},
        },
    },
    timeout=60,
)
response.raise_for_status()
for name, answer in response.json()["answers"].items():
    print(name, answer)

Example Output

Output

routing {'type': 'choice', 'choice': 'technical_support', 'confidence': 0.987854396908662, 'probabilities': {'billing': 0.004840538662952211, 'technical_support': 0.9919029312724412, 'sales': 0.0032565300646064375}}
urgency {'type': 'noul', 'noul': 0.9929980993021188}

3.2 Image Decisions

The example output below came from a mostly red test image.

Image Decision Example (Python)

Example

import base64
from pathlib import Path

import requests

image = base64.b64encode(Path("screenshot.png").read_bytes()).decode("ascii")
response = requests.post(
    "http://localhost:30000/v1/systemone",
    json={
        "model": "perplexity-ai/pplx-decider-v1-27b",
        "state": "Look at the supplied image.",
        "images": [image],
        "questions": {
            "color": {
                "type": "choice",
                "instructions": "What is the dominant color?",
                "criteria": {"red": "Red", "green": "Green", "blue": "Blue", "other": "Another color"},
            }
        },
    },
    timeout=60,
)
response.raise_for_status()
print(response.json()["answers"]["color"])

Example Output

Output

{'type': 'choice', 'choice': 'red', 'confidence': 0.9498445161931509, 'probabilities': {'red': 0.9623833871448632, 'green': 0.009006826727044857, 'blue': 0.00926546931819573, 'other': 0.01934431680989631}}

​Deployment

​1. Model Introduction

​2. Configuration Tips

​3. Advanced Usage

​3.1 Text Decisions

​3.2 Image Decisions