Getting Started
Your First AI Prediction in 5 Minutes

Your First AI Prediction in 5 Minutes

This is the fastest path to seeing SeeMe.ai in action. You’ll use a public model and make a prediction via the SDK.

What You’ll Accomplish

  • Connect to SeeMe.ai
  • Find a public model
  • Make an inference call
  • See results in real-time

Prerequisites

  • A SeeMe.ai account (sign up)
  • Python 3.8+ installed

Step 1: Install the SDK 

pip install seeme

Step 2: Create Your Client 

from seeme import Client

# Initialize the client with your credentials
client = Client(username="your-username", apikey="your-api-key")
ℹ️
You can also store your credentials in a .env file with username, apikey, and optionally backend variables. Then simply call Client() without arguments.

Step 3: Find a Public Model

SeeMe.ai has public models you can use immediately:

# Get all models (includes public, owned, and shared)
models = client.get_models()

# Filter for public image classification models
public_models = [m for m in models if m.public and m.kind == "image_classification"]

for model in public_models:
    print(f"{model.name}: {model.id}")

Step 4: Make a Prediction 

from seeme.types import ApplicationType

# Make a prediction on an image
result = client.predict(
    model_id=model.id,
    item="./your-image.jpg",
    application_type=ApplicationType.IMAGE_CLASSIFICATION
)

# View the results
for item in result.inference_items:
    print(f"{item.prediction}: {item.confidence:.2%}")

Example output:

cat: 94.32%
dog: 3.21%
rabbit: 1.47%

Step 5: Explore the Web Interface

  1. Go to app.seeme.ai
  2. Navigate to Models
  3. Click on your model
  4. Use the built-in Try It interface

Complete Example

Here’s the full code in one block:

from seeme import Client
from seeme.types import ApplicationType

# Initialize
client = Client(username="your-username", apikey="your-api-key")

# Get a public image classification model
models = client.get_models()
model = next(m for m in models if m.public and m.kind == "image_classification")

# Make prediction
result = client.predict(
    model_id=model.id,
    item="./test-image.jpg",
    application_type=ApplicationType.IMAGE_CLASSIFICATION
)

# Print results
print(f"Model: {model.name}")
print(f"Predictions:")
for item in result.inference_items:
    print(f"  {item.prediction}: {item.confidence:.2%}")

What’s Next?

Now that you’ve made your first prediction, choose your next step:

Train Your Own Model Explore the SDK Build Workflows

Video Script Outline

Hook (0:00-0:10) “What if you could go from zero to AI predictions in under 5 minutes? Let me show you.”

What You’ll Learn (0:10-0:30)

  • Install the SeeMe.ai Python SDK
  • Authenticate with your account
  • Make your first prediction
  • View results in the web interface

Demo Steps (0:30-4:00)

  1. Show pip install (0:30)
  2. Create client, show auth flow (1:00)
  3. Find public model (1:30)
  4. Make prediction, show results (2:30)
  5. Switch to web UI, show Try It (3:30)

Call to Action (4:00-5:00) “Now you’ve made your first prediction. Head to docs.seeme.ai to learn how to train your own custom models.”

No-Code Quickstart