Verifiable Linear Regression

In this tutorial you will learn how to use the Giza stack though a Linear Regression model.

Installation

To follow this tutorial, you must first proceed with the following installation.

Handling Python versions with Pyenv

You should install Giza tools in a virtual environment. If you’re unfamiliar with Python virtual environments, take a look at this guide. A virtual environment makes it easier to manage different projects and avoid compatibility issues between dependencies.

Install Python 3.11 using pyenv

pyenv install 3.11.0

Set Python 3.11 as local Python version:

pyenv local 3.11.0

Create a virtual environment using Python 3.11:

pyenv virtualenv 3.11.0 my-env

Activate the virtual environment:

pyenv activate my-env

Now, your terminal session will use Python 3.11 for this project.

Install Giza

Install Giza CLI

Install the CLI from PyPi

pipx install giza-cli

Install Agent SDK

Install the Agents package from from PyPi

pip install giza-agents

You'll find more options for installing Giza in the installation guide.

Install Dependencies

You must also install the following dependencies:

pip install scikit-learn skl2onnx numpy

Setup

From your terminal, create a Giza user through our CLI in order to access the Giza Platform:

giza users create

After creating your user, log into Giza:

giza users login

Optional: you can create an API Key for your user in order to not regenerate your access token every few hours.

giza users create-api-key

Create and Train a Linear Regression Model

We'll start by creating a simple linear regression model using Scikit-Learn and train it with some dummy data.

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

# Generate some dummy data
X = np.random.rand(100, 1) * 10  # 100 samples, 1 feature
y = 2 * X + 1 + np.random.randn(100, 1) * 2  # y = 2x + 1 + noise

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Create a linear regression model
model = LinearRegression()

# Train the model
model.fit(X_train, y_train)

Convert the Model to ONNX Format

Giza supports ONNX models so you'll need to convert the model to ONNX format. After the model is trained, you can convert it to ONNX format using the skl2onnx library.

from skl2onnx import convert_sklearn
from skl2onnx.common.data_types import FloatTensorType

# Define the initial types for the ONNX model
initial_type = [('float_input', FloatTensorType([None, X_train.shape[1]]))]

# Convert the scikit-learn model to ONNX
onnx_model = convert_sklearn(model, initial_types=initial_type)

# Save the ONNX model to a file
with open("linear_regression.onnx", "wb") as f:
    f.write(onnx_model.SerializeToString())

Transpile your model to Orion Cairo

For more detailed information on transpilation, please consult the Transpiler resource.

We will use Giza-CLI to transpile our ONNX model to Orion Cairo.

$ giza transpile linear_regression.onnx --output-path verifiable_lr
>>>>
[giza][2024-03-19 10:43:11.351] No model id provided, checking if model exists βœ…
[giza][2024-03-19 10:43:11.354] Model name is: linear_regression
[giza][2024-03-19 10:43:11.586] Model Created with id -> 447! βœ…
[giza][2024-03-19 10:43:12.093] Version Created with id -> 1! βœ…
[giza][2024-03-19 10:43:12.094] Sending model for transpilation βœ… 
[giza][2024-03-19 10:43:43.185] Transpilation is fully compatible. Version compiled and Sierra is saved at Giza βœ…
β § Transpiling Model...
[giza][2024-03-19 10:43:43.723] Downloading model βœ…
[giza][2024-03-19 10:43:43.731] model saved at: verifiable_lr

Deploy an inference endpoint

For more detailed information on inference endpoint, please consult the Endpoint resource.

Now that our model is transpiled to Cairo we can deploy an endpoint to run verifiable inferences. We will use Giza CLI again to deploy an endpoint. Ensure to replace model-id and version-id with your ids provided during transpilation.

$ giza endpoints deploy --model-id 447 --version-id 1

β–°β–±β–±β–±β–±β–±β–± Creating endpoint!
[giza][2024-03-19 10:51:48.551] Endpoint is successful βœ…
[giza][2024-03-19 10:51:48.557] Endpoint created with id -> 109 βœ…
[giza][2024-03-19 10:51:48.558] Endpoint created with endpoint URL: https://endpoint-raphael-doukhan-447-1-a09e4e6f-7i3yxzspbq-ew.a.run.app πŸŽ‰

Run a verifiable inference

To streamline verifiable inference, you might consider using the endpoint URL obtained after transpilation. However, this approach requires manual serialization of the input for the Cairo program and handling the deserialization process. To make this process more user-friendly and keep you within a Python environment, we've introduced a Python SDK designed to facilitate the creation of ML workflows and execution of verifiable predictions. When you initiate a prediction, our system automatically retrieves the endpoint URL you deployed earlier, converts your input into Cairo-compatible format, executes the prediction, and then converts the output back into a numpy object.

from giza.agents.model import GizaModel

MODEL_ID = 447  # Update with your model ID
VERSION_ID = 1  # Update with your version ID

def prediction(input, model_id, version_id):
    model = GizaModel(id=model_id, version=version_id)

    (result, proof_id) = model.predict(
        input_feed={'input': input}, verifiable=True
    )

    return result, proof_id

def execution():
    # The input data type should match the model's expected input
    input = np.array([[5.5]]).astype(np.float32)

    (result, proof_id) = prediction(input, MODEL_ID, VERSION_ID)

    print(
        f"Predicted value for input {input.flatten()[0]} is {result[0].flatten()[0]}")

    return result, proof_id


execution()
11:34:04.423 | INFO    | Created flow run 'proud-perch' for flow 'ExectuteCairoLR'
11:34:04.424 | INFO    | Action run 'proud-perch' - View at https://actions-server-raphael-doukhan-dblzzhtf5q-ew.a.run.app/flow-runs/flow-run/637bd0e0-d7e8-4d89-8c07-a266e6c280ce
11:34:04.746 | INFO    | Action run 'proud-perch' - Created task run 'PredictLRModel-0' for task 'PredictLRModel'
11:34:04.748 | INFO    | Action run 'proud-perch' - Executing 'PredictLRModel-0' immediately...
πŸš€ Starting deserialization process...
βœ… Deserialization completed! πŸŽ‰
11:34:08.194 | INFO    | Task run 'PredictLRModel-0' - Finished in state Completed()
11:34:08.197 | INFO    | Action run 'proud-perch' - Predicted value for input 5.5 is 12.208511352539062
11:34:08.313 | INFO    | Action run 'proud-perch' - Finished in state Completed()
(array([[12.20851135]]), '"3a15bca06d1f4788b36c1c54fa71ba07"')

Download the proof

For more detailed information on proving, please consult the Prove resource.

Initiating a verifiable inference sets off a proving job on our server, sparing you the complexities of installing and configuring the prover yourself. Upon completion, you can download your proof.

First, let's check the status of the proving job to ensure that it has been completed.

Remember to substitute endpoint-id and proof-id with the specific IDs assigned to you throughout this tutorial.

$ giza endpoints get-proof --endpoint-id 109 --proof-id "3a15bca06d1f4788b36c1c54fa71ba07"

>>>
[giza][2024-03-19 11:51:45.470] Getting proof from endpoint 109 βœ… 
{
  "id": 664,
  "job_id": 831,
  "metrics": {
    "proving_time": 15.083126
  },
  "created_date": "2024-03-19T10:41:11.120310"
}

Once the proof is ready, you can download it.

$ giza endpoints download-proof --endpoint-id 109 --proof-id "3a15bca06d1f4788b36c1c54fa71ba07" --output-path zklr.proof

>>>>
[giza][2024-03-19 11:55:49.713] Getting proof from endpoint 109 βœ… 
[giza][2024-03-19 11:55:50.493] Proof downloaded to zklr.proof βœ… 

Better to surround the proof-id in double quotes (") when using the alphanumerical id

Verify the proof

Finally you can verify the proof.

$ giza verify --proof-id 664

>>>>
[giza][2024-05-21 10:08:59.315] Verifying proof...
[giza][2024-05-21 10:09:00.268] Verification result: True
[giza][2024-05-21 10:09:00.270] Verification time: 0.437505093

Last updated