Create app.py

app.py

@@ -0,0 +1,66 @@
+import gradio as gr
+from transformers import pipeline
+import re
+
+# Load a Hugging Face pipeline for zero-shot classification
+classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+# Define categories for classification
+categories = ["Saving", "Need", "Want", "Investment"]
+
+# Helper function to extract information from input
+def extract_info(user_input):
+    # Remove Vietnamese accents (khong dau processing)
+    normalized_input = re.sub(r'[àáạảãâầấậẩẫăằắặẳẵèéẹẻẽêềếệểễìíịỉĩòóọỏõôồốộổỗơờớợởỡùúụủũưừứựửữỳýỵỷỹđ]', '', user_input)
+    normalized_input = normalized_input.replace("đ", "d")
+
+    # Predefined rules for classification and information extraction
+    if "gui tiet kiem" in normalized_input:
+        return classify_saving(normalized_input)
+    else:
+        return classify_other(normalized_input)
+
+# Function to classify saving-related expenditure
+def classify_saving(input_text):
+    details = {}
+    # Extract potential fields from input text using regex
+    term_match = re.search(r'(\d+)\s*thang', input_text)
+    details['term'] = term_match.group(1) + " tháng" if term_match else None
+
+    # Ask for missing fields
+    if not details.get('term'):
+        return "Ban gui tiet kiem bao nhieu thang?"
+
+    return "Saving: {}".format(details)
+
+# Function to classify other expenditures
+def classify_other(input_text):
+    result = classifier(input_text, candidate_labels=categories)
+    classification = result['labels'][0]  # Take the top classification
+
+    # Ask for amount and other details if not mentioned
+    amount_match = re.search(r'(\d+\.?\d*)', input_text)
+    if not amount_match:
+        return "Ban chi tieu nay het bao nhieu tien?"
+    
+    # Extract sub-category
+    sub_category = input_text.lower()
+    return {
+        "classification": classification,
+        "amount": amount_match.group(0),
+        "sub_category": sub_category
+    }
+
+# Define the Gradio interface
+def process_user_input(user_input):
+    return extract_info(user_input)
+
+iface = gr.Interface(
+    fn=process_user_input,
+    inputs="text",
+    outputs="text",
+    title="Expenditure Classification",
+    description="Classify expenditures into Need, Want, Saving, or Investment based on the 50-30-20 rule. Type in Vietnamese (không dấu)!"
+)
+
+iface.launch()