Update app.py

app.py

@@ -1,140 +1,80 @@
 import pandas as pd
+import numpy as np
 import gradio as gr
-import re
 from sentence_transformers import SentenceTransformer
-from sklearn.neighbors import NearestNeighbors
+from sklearn.metrics.pairwise import cosine_similarity
 
-# -------------------------------
-# Load dataset
-# -------------------------------
+# -----------------------------
+# LOAD DATA & MODEL
+# -----------------------------
 df = pd.read_csv("food_order_cleaned.csv")
-df['rating'] = pd.to_numeric(df['rating'], errors='coerce')
-df['search_text'] = (
-    df['restaurant_name'].astype(str) +
-    " | " + df['cuisine_type'].astype(str) +
-    " | " + df['rating'].astype(str)
-)
-
-# -------------------------------
-# Rule-based functions
-# -------------------------------
-def find_by_cuisine(cuisine, limit=10):
-    mask = df['cuisine_type'].str.strip().str.lower() == cuisine.strip().lower()
-    cols = ['restaurant_name','cuisine_type','cost_of_the_order','rating']
-    return df.loc[mask, cols].head(limit)
-
-def best_rated_by_cuisine(cuisine, top_n=10):
-    mask = df['cuisine_type'].str.strip().str.lower() == cuisine.strip().lower()
-    subset = df[mask].dropna(subset=['rating']).sort_values('rating', ascending=False)
-    cols = ['restaurant_name','cuisine_type','cost_of_the_order','rating']
-    return subset[cols].head(top_n)
-
-def cheapest_high_rated(max_cost=None, min_rating=4.0, top_n=10):
-    subset = df.dropna(subset=['rating'])
-    subset = subset[subset['rating'] >= min_rating]
-    if max_cost:
-        subset = subset[subset['cost_of_the_order'] <= max_cost]
-    subset = subset.sort_values('cost_of_the_order')
-    cols = ['restaurant_name','cuisine_type','cost_of_the_order','rating']
-    return subset[cols].head(top_n)
-
-def personalized_recall(customer_id, day):
-    mask = (
-        df['customer_id'].astype(str) == str(customer_id)
-    ) & (
-        df['day_of_the_week'].str.lower() == day.lower()
-    )
-    cols = ['order_id','restaurant_name','cuisine_type','cost_of_the_order','rating','day_of_the_week']
-    return df.loc[mask, cols]
 
-# -------------------------------
-# Semantic Search
-# -------------------------------
 model = SentenceTransformer("all-MiniLM-L6-v2")
-corpus_embeddings = model.encode(df["search_text"].tolist(), show_progress_bar=True)
-nn = NearestNeighbors(n_neighbors=10, metric="cosine").fit(corpus_embeddings)
-
-def semantic_search(query, k=5):
-    q_emb = model.encode([query])
-    dists, idxs = nn.kneighbors(q_emb, n_neighbors=k)
-    results = df.iloc[idxs[0]].copy()
-    results["score"] = 1 - dists[0]
-    cols = ['restaurant_name','cuisine_type','cost_of_the_order','rating','score']
-    return results[cols]
-
-# -------------------------------
-# Query Router
-# -------------------------------
-def handle_query(message, customer_id=""):
-    text = message.lower()
-
-    # 1. cuisine search
-    if "find" in text and "restaurant" in text:
-        for cuisine in df["cuisine_type"].str.lower().unique():
-            if cuisine in text:
-                return find_by_cuisine(cuisine).to_html(index=False)
-        return semantic_search(message).to_html(index=False)
-
-    # 2. best-rated query
-    if "best" in text:
-        for cuisine in df["cuisine_type"].str.lower().unique():
-            if cuisine in text:
-                return best_rated_by_cuisine(cuisine).to_html(index=False)
-        return semantic_search(message).to_html(index=False)
-
-    # 3. cheap places
-    if "cheap" in text or "value" in text:
-        return cheapest_high_rated().to_html(index=False)
-
-    # 4. personalized recall
-    if "what did i order" in text:
-        m = re.search(r"on (\w+)", text)
-        if not customer_id:
-            return "Please enter customer_id."
-        if not m:
-            return "Please specify the day (e.g., Tuesday)"
-        day = m.group(1)
-        r = personalized_recall(customer_id, day)
-        if r.empty:
-            return "No matching records."
-        return r.to_html(index=False)
-
-    return semantic_search(message).to_html(index=False)
-
-
-# -------------------------------
-# CHATBOT FUNCTION (DICTIONARY FORMAT)
-# -------------------------------
-def chatbot_fn(history, message, customer_id):
-    reply_html = handle_query(message, customer_id)
-
-    # append user message
-    history.append({"role": "user", "content": message})
-
-    # append assistant message
-    history.append({"role": "assistant", "content": "Here are the results 👇"})
-
-    return history, "", reply_html
-
-
-# -------------------------------
-# INTERFACE
-# -------------------------------
-with gr.Blocks() as demo:
-    gr.Markdown("## 🍽️ Restaurant Guide Chatbot")
-
-    chat = gr.Chatbot(label="Chat History")   # no type arg
-    html_out = gr.HTML(label="Search Results")
 
-    with gr.Row():
-        msg = gr.Textbox(placeholder="Ask me anything…")
-        cid = gr.Textbox(label="Customer ID (optional)")
-        btn = gr.Button("Send")
-
-    btn.click(
-        chatbot_fn,
-        inputs=[chat, msg, cid],
-        outputs=[chat, msg, html_out]
+TEXT_FIELDS = ["restaurant_name", "cuisine_type", "rating", "cost_of_the_order"]
+
+def create_text(row):
+    text = (
+        f"Restaurant: {row['restaurant_name']}. "
+        f"Cuisine: {row['cuisine_type']}. "
+        f"Rating: {row['rating']}. "
+        f"Cost: {row['cost_of_the_order']}."
+    )
+    return text
+
+df["text"] = df.apply(create_text, axis=1)
+corpus_embeddings = model.encode(df["text"].tolist(), normalize_embeddings=True)
+
+# -----------------------------
+# CHAT LOGIC
+# -----------------------------
+def bot_reply(user_query, history):
+    if not user_query.strip():
+        return history + [("","Please enter a valid question.")]
+
+    # Encode query
+    q_emb = model.encode([user_query], normalize_embeddings=True)
+    sims = cosine_similarity(q_emb, corpus_embeddings)[0]
+    idx = np.argmax(sims)
+    best_match = df.iloc[idx]
+
+    # Prepare clean response
+    response = (
+        f"🍽 **Recommended Restaurant**\n\n"
+        f"**Name:** {best_match['restaurant_name']}\n"
+        f"**Cuisine:** {best_match['cuisine_type']}\n"
+        f"**Rating:** ⭐ {best_match['rating']}\n"
+        f"**Avg Cost:** {best_match['cost_of_the_order']}\n\n"
+        f"Let me know if you want more options!"
+    )
+
+    # Update chat
+    history = history + [(user_query, response)]
+    return history
+
+
+# -----------------------------
+# GRADIO UI (MODERN + CLEAN)
+# -----------------------------
+with gr.Blocks(theme=gr.themes.Soft(primary_hue="indigo")) as demo:
+
+    gr.Markdown(
+        """
+        # 🍴 Restaurant Guide Chatbot  
+        Ask me for restaurant recommendations!
+        """
     )
 
+    chat = gr.Chatbot(label="Chat with Restaurant Guide", height=500)
+
+    with gr.Row():
+        user_in = gr.Textbox(
+            placeholder="Ask: Find me a Thai restaurant, show me cheap Italian...",
+            label="Your Question"
+        )
+        clear = gr.Button("Clear Chat")
+
+    user_in.submit(bot_reply, [user_in, chat], chat)
+    clear.click(lambda: [], None, chat)
+
 demo.launch()