Go SDK

JFrog ML Documentation

Products
JFrog ML
Content Type
User Guide

After you deploy a FrogML-based model, your Go-based client applications can use this module to get inferences from the model hosted as a real-time endpoint.

Installation

To install the SDK and its dependencies, run the following Go command:

go get github.com/qwak-ai/go-sdk/qwak

Inference Examples

The following example invokes the model test_model which accepts one feature vector which contains three fields and produces one output field named "score".

package main

import (
    "fmt"
    "github.com/qwak-ai/go-sdk/qwak"
)


func main() {
    client, err := qwak.NewRealTimeClient(qwak.RealTimeClientConfig{
        ApiKey:      "api-key",
        Environment: "env-name",
    })

    if err != nil {
        fmt.Println("Errors occurred, Error: ", err)
    }

    predictionRequest := qwak.NewPredictionRequest("test_model").AddFeatureVector(
        qwak.NewFeatureVector().
            WithFeature("feature_a", "feature_value").
            WithFeature("feature_b", 1).
            WithFeature("feature_c", 0.5),
    )

    response, err := client.Predict(predictionRequest)
    if err != nil {
        fmt.Println("Errors occurred, Error: ", err)
    }

    val , err := response.GetSinglePrediction().GetValueAsInt("score")
    if err != nil {
        fmt.Println("Errors occurred, Error: ", err)
    }

    fmt.Println(val)
}