REST API Quickstart

Integrate SeeMe.ai with any programming language using our REST API. This guide covers authentication and common endpoints.

What You’ll Accomplish

Authenticate with the API
Make predictions via HTTP
List and manage resources
Handle API responses

Prerequisites

A SeeMe.ai account (sign up)
An API key (generate at app.seeme.ai/settings/api-keys)
HTTP client (curl, Postman, or your language’s HTTP library)

Base URL

All API requests use this base URL:

https://api.seeme.ai/api/v1

Authentication

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Test Your Connection

curl -X GET "https://api.seeme.ai/api/v1/me" \
  -H "Authorization: Bearer YOUR_API_KEY"

import requests

headers = {"Authorization": "Bearer YOUR_API_KEY"}
response = requests.get("https://api.seeme.ai/api/v1/me", headers=headers)
print(response.json())

const response = await fetch("https://api.seeme.ai/api/v1/me", {
  headers: {
    "Authorization": "Bearer YOUR_API_KEY"
  }
});
const user = await response.json();
console.log(user);

req, _ := http.NewRequest("GET", "https://api.seeme.ai/api/v1/me", nil)
req.Header.Set("Authorization", "Bearer YOUR_API_KEY")

client := &http.Client{}
resp, _ := client.Do(req)

Make a Prediction

The most common operation: send data to a model and get predictions.

Image Prediction

curl -X POST "https://api.seeme.ai/api/v1/models/MODEL_ID/predict" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@/path/to/image.jpg"

import requests

url = "https://api.seeme.ai/api/v1/models/MODEL_ID/predict"
headers = {"Authorization": "Bearer YOUR_API_KEY"}

with open("image.jpg", "rb") as f:
    files = {"file": f}
    response = requests.post(url, headers=headers, files=files)

predictions = response.json()["predictions"]
for p in predictions:
    print(f"{p['label']}: {p['confidence']:.2%}")

const formData = new FormData();
formData.append('file', imageFile);

const response = await fetch(
  `https://api.seeme.ai/api/v1/models/${modelId}/predict`,
  {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${apiKey}`
    },
    body: formData
  }
);

const { predictions } = await response.json();
predictions.forEach(p => {
  console.log(`${p.label}: ${(p.confidence * 100).toFixed(2)}%`);
});

Response Format

{
  "id": "pred_abc123",
  "model_id": "model_xyz",
  "predictions": [
    {
      "label": "cat",
      "confidence": 0.9432
    },
    {
      "label": "dog",
      "confidence": 0.0321
    }
  ],
  "inference_time_ms": 45,
  "created_at": "2024-01-15T10:30:00Z"
}

Common Endpoints

Models

Method	Endpoint	Description
GET	`/models`	List your models
GET	`/models/{id}`	Get model details
GET	`/models/{id}/versions`	List model versions
POST	`/models/{id}/predict`	Make a prediction

Datasets

Method	Endpoint	Description
GET	`/datasets`	List your datasets
POST	`/datasets`	Create a dataset
GET	`/datasets/{id}`	Get dataset details
DELETE	`/datasets/{id}`	Delete a dataset
POST	`/datasets/{id}/versions/{vid}/upload`	Upload data

Jobs

Method	Endpoint	Description
GET	`/jobs`	List training jobs
POST	`/jobs`	Create a training job
GET	`/jobs/{id}`	Get job status
POST	`/jobs/{id}/cancel`	Cancel a job

List Models Example

curl -X GET "https://api.seeme.ai/api/v1/models" \
  -H "Authorization: Bearer YOUR_API_KEY"

import requests

headers = {"Authorization": "Bearer YOUR_API_KEY"}
response = requests.get("https://api.seeme.ai/api/v1/models", headers=headers)

for model in response.json()["models"]:
    print(f"{model['name']} ({model['application']})")

const response = await fetch("https://api.seeme.ai/api/v1/models", {
  headers: { "Authorization": `Bearer ${apiKey}` }
});

const { models } = await response.json();
models.forEach(m => console.log(`${m.name} (${m.application})`));

Create a Training Job

curl -X POST "https://api.seeme.ai/api/v1/jobs" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "dataset_id": "ds_abc123",
    "dataset_version_id": "dsv_xyz789",
    "framework": "fastai",
    "application": "image_classification",
    "config": {
      "epochs": 10,
      "image_size": 224
    }
  }'

import requests

url = "https://api.seeme.ai/api/v1/jobs"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "dataset_id": "ds_abc123",
    "dataset_version_id": "dsv_xyz789",
    "framework": "fastai",
    "application": "image_classification",
    "config": {
        "epochs": 10,
        "image_size": 224
    }
}

response = requests.post(url, headers=headers, json=data)
job = response.json()
print(f"Job started: {job['id']}")

Error Handling

The API returns standard HTTP status codes:

Code	Meaning
200	Success
201	Created
400	Bad request (check your parameters)
401	Unauthorized (check your API key)
403	Forbidden (insufficient permissions)
404	Not found
429	Rate limited (slow down)
500	Server error

Error Response Format

{
  "error": {
    "code": "invalid_request",
    "message": "The 'file' field is required",
    "details": {
      "field": "file"
    }
  }
}

Handle Errors in Code

import requests

response = requests.post(url, headers=headers, files=files)

if response.status_code == 200:
    predictions = response.json()["predictions"]
elif response.status_code == 401:
    print("Invalid API key")
elif response.status_code == 404:
    print("Model not found")
elif response.status_code == 429:
    print("Rate limited - wait and retry")
else:
    error = response.json().get("error", {})
    print(f"Error: {error.get('message', 'Unknown error')}")

Rate Limits

Plan	Requests/minute	Requests/day
Free	60	1,000
Pro	300	50,000
Enterprise	Custom	Unlimited

Rate limit headers are included in every response:

X-RateLimit-Limit: 60
X-RateLimit-Remaining: 45
X-RateLimit-Reset: 1705312800

Pagination

List endpoints support pagination:

GET /models?limit=20&offset=0

Response includes pagination info:

{
  "models": [...],
  "pagination": {
    "total": 45,
    "limit": 20,
    "offset": 0,
    "has_more": true
  }
}

What’s Next?

More REST API Examples

These pages include detailed REST API examples alongside Python SDK code:

Graphs API Workflows API API Keys

Continue Learning

Python SDK Build Something

Python SDK Quickstart Mobile Quickstart