Quickstart Guide

This guide will help you quickly integrate and use the Techsolut platform for your computer vision projects. Follow these simple steps to start leveraging the power of our AI tools.

Prerequisites

Before getting started, make sure you have the following:

  • An active Techsolut account. Create an account if you don't have one yet.
  • An API key to access Techsolut services. You can get one in your profile settings.
  • Image or video data for analysis (supported formats: JPG, PNG, MP4, MOV).

Step 1: Setup

1
Install the SDK
Python
JavaScript
PHP
pip 
pip install techsolut-sdk
npm 
npm install techsolut-sdk
composer 
composer require techsolut/techsolut-sdk
2
Configure Authentication
Python
JavaScript
PHP
Python 
from techsolut import Client

# Initialiser le client avec votre clé API
client = Client(api_key="votre_clé_api")

# Vérifier la connexion
status = client.check_auth()
print(f"Statut de connexion: {status}")
JavaScript 
const { TechsolutClient } = require('techsolut-sdk');

// Initialiser le client avec votre clé API
const client = new TechsolutClient({
  apiKey: "votre_clé_api"
});

// Vérifier la connexion
client.checkAuth()
  .then(status => console.log(`Statut de connexion: ${status}`))
  .catch(error => console.error(error));
PHP 
<?php
require_once 'vendor/autoload.php';

use Techsolut\Client;

// Initialiser le client avec votre clé API
$client = new Client('votre_clé_api');

// Vérifier la connexion
$status = $client->checkAuth();
echo "Statut de connexion: " . $status;
?>

Tip: Store your API key in an environment variable rather than directly in your code to enhance security.

Step 2: First Usage

3
Object Detection

Let's start with a simple example of object detection in an image:

Python
JavaScript
PHP
Python 
from techsolut import Client

client = Client(api_key="votre_clé_api")

# Détecter des objets dans une image locale
results = client.detect_objects(
    image_path="chemin/vers/votre/image.jpg",
    confidence=0.5  # Seuil de confiance minimum
)

# Afficher les résultats
for obj in results:
    print(f"Objet: {obj.label}, Confiance: {obj.confidence:.2f}, Position: {obj.box}")
JavaScript 
const { TechsolutClient } = require('techsolut-sdk');
const fs = require('fs');

const client = new TechsolutClient({
  apiKey: "votre_clé_api"
});

// Lire l'image comme un Buffer
const imageBuffer = fs.readFileSync('chemin/vers/votre/image.jpg');

// Détecter des objets
client.detectObjects({
  image: imageBuffer,
  confidence: 0.5  // Seuil de confiance minimum
})
.then(results => {
  // Afficher les résultats
  results.forEach(obj => {
    console.log(`Objet: ${obj.label}, Confiance: ${obj.confidence.toFixed(2)}, Position: `, obj.box);
  });
})
.catch(error => console.error(error));
PHP 
<?php
require_once 'vendor/autoload.php';

use Techsolut\Client;

$client = new Client('votre_clé_api');

// Détecter des objets dans une image locale
$results = $client->detectObjects([
    'image_path' => 'chemin/vers/votre/image.jpg',
    'confidence' => 0.5  // Seuil de confiance minimum
]);

// Afficher les résultats
foreach ($results as $obj) {
    echo "Objet: " . $obj->label . ", Confiance: " . 
         number_format($obj->confidence, 2) . ", Position: " . 
         json_encode($obj->box) . "\n";
}
?>

Note: The confidence parameter allows you to set the minimum confidence threshold for detections. Recommended value between 0.4 and 0.6.

Step 3: Advanced Features

4
Using Your Custom Models

You can use your own models trained on the Techsolut platform:

Python 
from techsolut import Client

client = Client(api_key="votre_clé_api")

# Charger votre modèle personnalisé par ID
model_id = "votre_id_modele"  # Exemple : "model_12345"

# Faire une prédiction avec votre modèle
results = client.predict_with_model(
    model_id=model_id,
    image_path="chemin/vers/votre/image.jpg"
)

print(f"Résultats: {results}")
5
Batch Processing

Process multiple images in a single request for better efficiency:

Python 
from techsolut import Client

client = Client(api_key="votre_clé_api")

# Liste de chemins d'images
image_paths = [
    "chemin/vers/image1.jpg",
    "chemin/vers/image2.jpg",
    "chemin/vers/image3.jpg"
]

# Traitement par lots
batch_results = client.batch_process(
    operation="detect_objects",
    image_paths=image_paths,
    confidence=0.5
)

# Afficher les résultats pour chaque image
for i, results in enumerate(batch_results):
    print(f"Résultats pour image {i+1}:")
    for obj in results:
        print(f"  - {obj.label}: {obj.confidence:.2f}")

Warning: Batch processing is limited to 20 images per request for standard accounts and 50 images for premium accounts.

Troubleshooting

Common Issues

If you receive an authentication error:

  • Check that your API key is correct and active
  • Make sure your account has not exceeded usage limits
  • Renew your API key in your account settings if necessary

If you have issues with image format:

  • Supported formats are: JPG, JPEG, PNG, BMP
  • Maximum image size: 10 MB
  • Recommended resolution: between 640×480 and 4096×4096 pixels
  • If the image is too large, resize it before sending

If you encounter timeout errors:

  • Increase the timeout in the client configuration (default: 30 seconds)
  • Use smaller or reduced quality images
  • Avoid making too many simultaneous requests
  • For long processing, use asynchronous operations
client = Client(api_key="your_api_key", timeout=60)

Next Steps

Now that you've started using the Techsolut platform, here are some additional resources to deepen your knowledge:

Complete Documentation

Check out our detailed documentation to explore all available features.

View Documentation
API Reference

Explore the complete API reference with all available endpoints and parameters.

API Reference
Tutorials & Examples

Discover concrete examples and tutorials to go further with the platform.

View Tutorials
Assistant IA Techsolut
Historique des conversations

Vous n'avez pas encore de conversations enregistrées.

Analyser une image

Glissez-déposez une image ici
ou cliquez pour choisir un fichier