Update app.py

app.py

@@ -1,42 +1,57 @@
+import gradio as gr
 from transformers import pipeline
-from fastapi import FastAPI, Request
-from pydantic import BaseModel
-import uvicorn
 
-# Load classifier
-classifier = pipeline("text-classification", model="WarTitan2077/Number-Classifier", tokenizer="WarTitan2077/Number-Classifier", top_k=None)
+# Load your fine-tuned multi-label classification model
+classifier = pipeline(
+    "text-classification",
+    model="your-username/your-model-name",
+    tokenizer="your-username/your-model-name",
+    top_k=None
+)
 
-# Define labels (same as during training)
+# Define labels in the correct order
 labels = ["Symbolic", "Numeric", "Natural", "Integer", "Rational", "Irrational", "Real", "Prime", "Composite"]
-
-# Map label IDs back to names
 label_map = {f"LABEL_{i}": label for i, label in enumerate(labels)}
 
-# Input schema
-class Inputs(BaseModel):
-    Input1: str
-    Input2: str
-    Input3: str
-
-# App
-app = FastAPI()
-
-@app.post("/predict")
-async def predict(data: Inputs):
+# Define the prediction function
+def classify_numbers(input1, input2, input3):
     inputs = {
-        "Input1": data.Input1,
-        "Input2": data.Input2,
-        "Input3": data.Input3
+        "Input1": input1,
+        "Input2": input2,
+        "Input3": input3
     }
 
-    response = {}
+    results = {}
 
-    for key, value in inputs.items():
-        if value.strip():  # only classify non-empty inputs
-            result = classifier(value)
-            preds = {label_map[item["label"]]: round(item["score"], 3) for item in result[0]}
-            response[key] = preds
+    for name, value in inputs.items():
+        if value.strip():  # only process non-empty input
+            output = classifier(value)[0]  # list of dicts for each label
+            result = {
+                label_map[item["label"]]: round(item["score"], 3)
+                for item in output
+            }
+            results[name] = result
         else:
-            response[key] = {}
+            results[name] = {}
+
+    return results
+
+# Define Gradio interface
+inputs = [
+    gr.Textbox(label="Input 1"),
+    gr.Textbox(label="Input 2"),
+    gr.Textbox(label="Input 3")
+]
+
+output = gr.JSON(label="Predictions")
+
+demo = gr.Interface(
+    fn=classify_numbers,
+    inputs=inputs,
+    outputs=output,
+    title="Number Classifier",
+    description="Enter up to three inputs to classify them as Symbolic, Numeric, Prime, etc."
+)
 
-    return response
+if __name__ == "__main__":
+    demo.launch()