Update app.py

app.py

@@ -1,49 +1,69 @@
 import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-# Set up the device to use CPU only
-device = torch.device("cpu")
-
-# Load model and tokenizer, then move the model to the appropriate device
-model = AutoModelForCausalLM.from_pretrained("adi2606/MenstrualQA").to(device)
-tokenizer = AutoTokenizer.from_pretrained("adi2606/MenstrualQA")
-
-# Function to generate a response from the chatbot
-def generate_response(message: str, temperature: float = 0.4, repetition_penalty: float = 1.1) -> str:
-    # Apply the chat template and convert to PyTorch tensors
-    messages = [
-        {"role": "system", "content": "You are a helpful assistant."},
-        {"role": "user", "content": message}
-    ]
-    input_ids = tokenizer.apply_chat_template(
-        messages, add_generation_prompt=True, return_tensors="pt"
-    ).to(device)
-
-    # Generate the response
-    output = model.generate(
-        input_ids,
-        max_length=512,
-        temperature=temperature,
-        repetition_penalty=repetition_penalty,
-        do_sample=True
-    ) 
-
-    # Decode the generated output
-    generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-    return generated_text
-
-# Streamlit app layout
-st.title("Menstrual QA Chatbot")
-st.write("Ask any question related to menstrual health.")
-
-# User input
-user_input = st.text_input("You:", "")
-
-if st.button("Send"):
-    if user_input:
-        with st.spinner("Generating response..."):
+from PIL import Image
+import base64
+
+
+st.set_page_config(page_title="Menstrual Health Chatbot 💬", layout="centered")
+
+
+@st.cache_resource
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained("adi2606/Menstrual-Health-Awareness-Chatbot")
+    model = AutoModelForSeq2SeqLM.from_pretrained("adi2606/Menstrual-Health-Awareness-Chatbot").to("cpu")
+    return tokenizer, model
+
+tokenizer, model = load_model()
+
+
+def generate_response(input_text):
+    inputs = tokenizer(input_text, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=128)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return response
+
+
+def set_background(image_path):
+    with open(image_path, "rb") as f:
+        encoded_string = base64.b64encode(f.read()).decode()
+        st.markdown(
+            f"""
+            <style>
+            .stApp {{
+                background-image: url("data:image/png;base64,{encoded_string}");
+                background-size: cover;
+            }}
+            </style>
+            """,
+            unsafe_allow_html=True
+        )
+
+
+set_background("background.jpg") 
+
+
+banner = Image.open("banner.png")  
+st.image(banner, use_column_width=True)
+
+
+st.markdown("<h1 style='text-align: center;'>🩸 Menstrual Health Awareness Chatbot 💬</h1>", unsafe_allow_html=True)
+st.markdown("<h4 style='text-align: center;'>Ask anything about periods, PMS, hygiene, and more!</h4>", unsafe_allow_html=True)
+
+
+st.markdown("### 🤔 Your Question")
+user_input = st.text_input("", placeholder="E.g., What are the symptoms of PMS?")
+
+
+if st.button("🚀 Ask"):
+    if user_input.strip():
+        with st.spinner("Generating a helpful response..."):
             response = generate_response(user_input)
-        st.write(f"Chatbot: {response}")
+        st.success("✅ Here's what I found:")
+        st.markdown(f"**💬 Chatbot:** {response}")
     else:
-        st.write("Please enter a question.")
+        st.warning("⚠️ Please enter a question to get started.")
+
+
+st.markdown("---")
+st.markdown("<small style='color: gray;'>Made with ❤️ to spread awareness.</small>", unsafe_allow_html=True)