SeeMe.ai Documentation
Build AI Without Giving Up Control
SeeMe.ai is the sovereign AI platform—train, deploy, and manage machine learning models while keeping your data exactly where you want it: on your infrastructure.
Choose Your Path
No-Code Builder
Build AI models using our visual interface. Perfect for domain experts who want results without writing code.
Python Developer
Full programmatic control via our Python SDK. Integrate AI into your applications with a few lines of code.
Enterprise Deployment
Deploy on-premise with complete data sovereignty. GDPR compliant, EU AI Act ready, air-gapped options.
Workflow Automation
Chain models, connect datasets, and build intelligent pipelines. Automate complex AI processes visually.
Mobile Developer
Deploy AI models to iOS and Android. Run inference on-device with offline support and real-time camera processing.
Advanced Techniques
Model distillation, finetuning, automated labeling, knowledge graphs, and production optimization strategies.
What You Can Build
Every major AI task type, one unified platform:
Platform at a Glance
graph TB
subgraph "Data Layer"
D1[Datasets]
D2[Labeling & Annotation]
D3[Versioning]
end
subgraph "Training"
T1[Finetuning]
T2[Distillation]
T3[Optimization]
end
subgraph "Deployment"
P1[Cloud API]
P2[On-Premise]
P3[Edge & Mobile]
end
subgraph "Automation"
W1[Workflows]
W2[Post-Processors]
W3[Knowledge Graphs]
end
D1 --> D2 --> D3
D3 --> T1 --> T2 --> T3
T3 --> P1
T3 --> P2
T3 --> P3
P1 --> W1
W1 --> W2
W2 --> W3Quick Start Examples
Python SDK
from seeme import Client
client = Client()
# Make a prediction
result = client.predict(model_id="your-model", item="image.jpg")
for item in result.inference_items:
print(f"{item.prediction}: {item.confidence:.1%}")REST API
curl -X POST "https://api.seeme.ai/api/v1/inferences/{model_id}" \
-H "Authorization: myusername:my-api-key" \
-F "file=@image.jpg"Deployment Options
| Option | Latency | Data Location | Best For |
|---|---|---|---|
| Cloud API | ~100-500ms | SeeMe.ai managed | Quick start, auto-scaling |
| On-Premise | ~10-50ms | Your data center | Compliance, sovereignty |
| Edge | ~5-30ms | Edge devices | Offline, real-time |
| Mobile | ~5-20ms | iOS/Android | Consumer apps, field work |
Frameworks & Integrations
| Framework | Use Case | Export Formats |
|---|---|---|
| fast.ai / PyTorch | Image classification, transfer learning | PyTorch, ONNX, CoreML, TFLite |
| YOLO v4/v5/v8 | Object detection | Darknet, ONNX, TensorRT |
| spaCy | NER, text processing | spaCy models |
| XGBoost / LightGBM / CatBoost | Tabular data | Native, ONNX |
| Tesseract / PaddleOCR | Document OCR | Built-in |
| Ollama / vLLM | Language models | GGUF, safetensors |