Spaces:
Runtime error
Runtime error
tabito12345678910
commited on
Commit
·
df2aef5
1
Parent(s):
45c2088
Create new README.md with proper Hugging Face Spaces YAML configuration for Gohan API
Browse files
README.md
DELETED
|
@@ -1,34 +0,0 @@
|
|
| 1 |
-
# Gohan FastAPI
|
| 2 |
-
|
| 3 |
-
This is a FastAPI-based product recommendation API deployed on Hugging Face Spaces.
|
| 4 |
-
|
| 5 |
-
## Endpoints
|
| 6 |
-
|
| 7 |
-
- `GET /` - Root endpoint with API information
|
| 8 |
-
- `GET /status` - Health check and model status
|
| 9 |
-
- `POST /predict` - Main prediction endpoint with topK parameter
|
| 10 |
-
- `POST /predict_simple` - Simple prediction endpoint
|
| 11 |
-
|
| 12 |
-
## Usage
|
| 13 |
-
|
| 14 |
-
### Check API Status
|
| 15 |
-
```bash
|
| 16 |
-
curl "https://your-space-url.hf.space/status"
|
| 17 |
-
```
|
| 18 |
-
|
| 19 |
-
### Make Predictions
|
| 20 |
-
```bash
|
| 21 |
-
curl -X POST "https://your-space-url.hf.space/predict" \
|
| 22 |
-
-H "Content-Type: application/json" \
|
| 23 |
-
-d '{"company_data_json": "{...}", "topK": 10}'
|
| 24 |
-
```
|
| 25 |
-
|
| 26 |
-
## Model Loading
|
| 27 |
-
|
| 28 |
-
The API uses FastAPI's lifespan events to load models only once during startup, providing efficient cold start handling.
|
| 29 |
-
|
| 30 |
-
## Required Model Files
|
| 31 |
-
|
| 32 |
-
- `model/gohan/epoch_*.pt` (PyTorch model)
|
| 33 |
-
- `model/gohan/*.json` (encoder files)
|
| 34 |
-
- `model/gohan/gohan_pm.csv` (product master data)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|