Update Gradio to latest secure version 3

README.md

@@ -11,19 +11,19 @@ pinned: false
 
 # 🌸 Iris Detector
 
-A simple Gradio Space that predicts iris species using a K-Nearest Neighbors classifier (k=5).
+A simple Gradio + FastAPI Space that predicts iris species using a K-Nearest Neighbors classifier (k=5).
 
 ## Features
 - 4 numeric inputs: sepal length, sepal width, petal length, petal width
 - Predicts one of 3 classes: `setosa`, `versicolor`, `virginica`
 - Shows probability distribution
-- Exposes API endpoint `/run/predict` for programmatic access
+- Exposes REST API endpoint `/predict` for programmatic access
 
 ## API Usage
 
 **Endpoint:**
 ```
-POST https://huggingface.co/spaces/tofighi/iris-detector/run/predict
+POST https://huggingface.co/spaces/tofighi/iris-detector/predict
 ```
 
 **Request Body Example:**
@@ -49,8 +49,12 @@ POST https://huggingface.co/spaces/tofighi/iris-detector/run/predict
 ```python
 import requests
 
-url = "https://huggingface.co/spaces/tofighi/iris-detector/run/predict"
+url = "https://huggingface.co/spaces/tofighi/iris-detector/predict"
 payload = {"data": [5.1, 3.5, 1.4, 0.2]}
 resp = requests.post(url, json=payload)
 print(resp.json())
-```
+```
+
+## Web Interface
+You can also use the Gradio form in this Space to input iris measurements interactively and get predictions.
+

app.py

@@ -1,27 +1,43 @@
 import gradio as gr
 import numpy as np
 import joblib
+from fastapi import FastAPI
+from pydantic import BaseModel
+from fastapi.middleware.cors import CORSMiddleware
 
-# Load trained model and target names
+# Load trained model
 model, target_names = joblib.load("iris_knn.pkl")
 
-def predict(sepal_length, sepal_width, petal_length, petal_width):
-    """
-    Predict the iris species given 4 numeric inputs.
+# --- FastAPI setup ---
+app = FastAPI(title="Iris Detector API")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
 
-    Returns a dictionary with 'predicted_class' and 'probabilities'.
-    """
-    data = np.array([[sepal_length, sepal_width, petal_length, petal_width]])
-    pred = model.predict(data)[0]
-    proba = model.predict_proba(data)[0]
+class IrisInput(BaseModel):
+    data: list  # [sepal_length, sepal_width, petal_length, petal_width]
+
+@app.post("/predict")
+def predict_api(input_data: IrisInput):
+    arr = np.array([input_data.data])
+    pred = model.predict(arr)[0]
+    proba = model.predict_proba(arr)[0]
     return {
         "predicted_class": str(target_names[pred]),
         "probabilities": {str(target_names[i]): float(proba[i]) for i in range(len(target_names))}
     }
 
+# --- Gradio UI setup ---
+def predict_gradio(sepal_length, sepal_width, petal_length, petal_width):
+    data = [sepal_length, sepal_width, petal_length, petal_width]
+    return predict_api(IrisInput(data=data))
+
 with gr.Blocks() as demo:
     gr.Markdown("# 🌸 Iris Detector — KNN Classifier (k=5)")
-    gr.Markdown("Enter 4 iris flower measurements below to predict the species.")
+    gr.Markdown("Enter 4 iris flower measurements below to predict the species. You can also use the REST API.")
 
     with gr.Row():
         with gr.Column():
@@ -34,7 +50,7 @@ with gr.Blocks() as demo:
             output = gr.JSON(label="Prediction")
 
             predict_btn.click(
-                fn=predict,
+                fn=predict_gradio,
                 inputs=[sepal_length, sepal_width, petal_length, petal_width],
                 outputs=[output]
             )
@@ -42,21 +58,21 @@ with gr.Blocks() as demo:
         with gr.Column():
             gr.Markdown("## 📖 API Usage Guide")
             gr.Markdown("""
-You can access this model programmatically using the Hugging Face Space API.
+You can access this model programmatically using the REST API.
 
 **Endpoint:**
 ```
-POST https://huggingface.co/spaces/tofighi/iris-detector/run/predict
+POST https://huggingface.co/spaces/tofighi/iris-detector/predict
 ```
 
-**Request Body (JSON):**
+**Request Body Example:**
 ```json
 {
   "data": [5.1, 3.5, 1.4, 0.2]
 }
 ```
 
-**Response:**
+**Response Example:**
 ```json
 {
   "predicted_class": "setosa",
@@ -72,11 +88,11 @@ POST https://huggingface.co/spaces/tofighi/iris-detector/run/predict
 ```python
 import requests
 
-url = "https://huggingface.co/spaces/tofighi/iris-detector/run/predict"
+url = "https://huggingface.co/spaces/tofighi/iris-detector/predict"
 payload = {"data": [5.1, 3.5, 1.4, 0.2]}
 resp = requests.post(url, json=payload)
 print(resp.json())
 ```
-""")
+"")
 
-demo.launch(share=True)
+demo.launch(share=True)

requirements.txt

@@ -1,4 +1,6 @@
-gradio>=3.59.0
-scikit-learn
+gradio
+fastapi
+uvicorn
 numpy
-joblib
+scikit-learn
+joblib