Integrate with Sindri

Sindri offers a zero-knowledge developer cloud for end-to-end encrypted inference. It ensures that user inputs are never visible to anyone, including Sindri itself, thus maintaining strong privacy guarantees. With this integration, you can build infrastructure that protects user confidentiality and data integrity while enabling context-aware AI without exposing sensitive data.

From the perspective of working within the DeepFellow framework, Sindri integration is no different from operating on a local DeepFellow infrastructure. The data is encrypted and sent to Sindri, where computations take place on their trusted execution environment (TEE). The results return to the DeepFellow server and are then decrypted for the user.

The integration can be simply done using DeepFellow Infra Web Panel.

Integration Guide

Requirements:

• DF Server and DeepFellow Infra - see our installation guide.
• Sindri's API Key

1. Open DeepFellow Infra Web Panel.
2. Locate "sindri" tab and click "Install".
3. Enter Sindri's API URL: https://sindri.app/api/ai/v1/openai, and Sindri's API Key.

1. After installing Sindri service, click "Models" on Sindri's service tab.
2. Install the desired model by clicking "Install" button. Optionally enter model alias in the pop-up window.

Test if the installation was successful:

curl -X 'POST' \
 'https://deepfellow-server-host/v1/chat/completions' \
 -H 'Content-Type: application/json' \
 -H 'Authorization: Bearer DEEPFELLOW-PROJECT-API-KEY' \
 -d '{
  "messages": [
    {
      "content": "Hello Sindri!",
      "role": "user"
    }
  ],
  "model": "gemma3:27b"
}'

from openai import OpenAI

client = OpenAI(
    api_key="DEEPFELLOW-PROJECT-API-KEY",
    base_url="https://deepfellow-server-host/v1",
)

response = client.chat.completions.create(
    model="gemma3:27b",
    messages=[
        {
            "content": "Hello Sindri!",
            "role": "user"
        }
    ]
)

print(response.model_dump_json())

import OpenAI from 'openai';

const openai = new OpenAI({
    apiKey: 'DEEPFELLOW-PROJECT-API-KEY',
    baseURL: 'https://deepfellow-server-host/v1'
});

const response = await openai.chat.completions.create({
    model: 'gemma3:27b',
    messages: [
        {
            content: 'Hello Sindri!',
            role: 'user'
        }
    ]
});

console.log(response);

Successful response:

{
    "id": "chatcmpl-640",
    "object": "chat.completion",
    "created": 1759754890,
    "model": "gemma3:27b",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "Hello there! How can I help you today? 😊"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 13,
        "completion_tokens": 11,
        "total_tokens": 24
    }
}