Update app.py

app.py

@@ -1,9 +1,10 @@
-import gradio as gr
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
 from datasets import load_dataset
 
-# Load the model and tokenizer
+# Model details
 MODEL_NAME = "Pisethan/sangapac-math"
+
+# Load model and tokenizer
 try:
     tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
     model = AutoModelForSequenceClassification.from_pretrained(MODEL_NAME)
@@ -12,10 +13,10 @@ except Exception as e:
     classifier = None
     print(f"Error loading model or tokenizer: {e}")
 
-# Load dataset
+# Load dataset dynamically from Hugging Face or locally
 try:
-    dataset = load_dataset("Pisethan/sangapac-math-dataset")["train"]
-    dataset_dict = {entry["input"]: entry for entry in dataset}
+    dataset = load_dataset("Pisethan/sangapac-math-dataset")["train"]  # Load your dataset
+    dataset_dict = {entry["input"]: entry for entry in dataset}  # Create a dictionary for lookup
 except Exception as e:
     dataset_dict = {}
     print(f"Error loading dataset: {e}")
@@ -26,18 +27,22 @@ def predict(input_text):
         return "Model not loaded properly.", {"Error": "Model not loaded properly."}
 
     try:
+        # Predict the category
         result = classifier(input_text)
         label = result[0]["label"]
         score = result[0]["score"]
 
+        # Retrieve output and metadata dynamically from the dataset
         data = dataset_dict.get(input_text, {"output": "Unknown", "metadata": {}})
         output = data["output"]
         metadata = data["metadata"]
 
+        # Extract metadata details
         difficulty = metadata.get("difficulty", "Unknown")
         steps = metadata.get("steps", ["No steps available"])
 
-        steps_text = "\n".join(steps)
+        # Create a simple result string without dashes
+        steps_text = "\n".join(steps)  # No dash or prefix for each step
         simple_result = (
             f"Category: {label}\n"
             f"Confidence: {score:.2f}\n"
@@ -46,6 +51,7 @@ def predict(input_text):
             f"Steps:\n{steps_text}"
         )
 
+        # Create the full JSON output
         detailed_result = {
             "Category": label,
             "Confidence": score,
@@ -57,6 +63,8 @@ def predict(input_text):
     except Exception as e:
         return "An error occurred.", {"Error": str(e)}
 
+# Gradio interface
+import gradio as gr
 
 # Define sample inputs
 sample_inputs = [
@@ -66,51 +74,17 @@ sample_inputs = [
     ["Solve for x: x + 5 = 10"],
 ]
 
-# Define Gradio interface
 interface = gr.Interface(
     fn=predict,
     inputs=gr.Textbox(lines=2, placeholder="Enter a math problem..."),
     outputs=[
-        gr.Textbox(label="Simple Output"),
-        gr.JSON(label="Detailed JSON Output"),
+        gr.Textbox(label="Simple Output"),  # Display only the result
+        gr.JSON(label="Detailed JSON Output"),  # Display full JSON
     ],
     title="Sangapac Math Model",
     description="A model to classify math problems into categories like Arithmetic, Multiplication, Division, Algebra, and Geometry.",
-    examples=sample_inputs,
-    allow_flagging="never",
+    examples=sample_inputs,  # Add examples below the Clear and Submit buttons
 )
 
-# Custom HTML for buttons next to Clear/Submit
-custom_js = """
-<script>
-    function addSampleButtons() {
-        const buttonsContainer = document.createElement('div');
-        buttonsContainer.style.display = 'flex';
-        buttonsContainer.style.justifyContent = 'center';
-        buttonsContainer.style.marginTop = '10px';
-
-        const examples = [
-            "1 + 1 = ?",
-            "(5 + 3) × 2 = ?",
-            "12 ÷ 4 = ?",
-            "Solve for x: x + 5 = 10"
-        ];
-
-        examples.forEach((example, index) => {
-            const button = document.createElement('button');
-            button.innerHTML = example;
-            button.style.margin = '0 10px';
-            button.onclick = function() {
-                document.querySelector('textarea').value = example;
-            };
-            buttonsContainer.appendChild(button);
-        });
-
-        document.querySelector('body > div').appendChild(buttonsContainer);
-    }
-    window.onload = addSampleButtons;
-</script>
-"""
-
-# Launch Gradio app with custom JavaScript
-interface.launch(components=custom_js)
+# Launch the app
+interface.launch()