Update app.py

app.py

@@ -1,78 +1,140 @@
 import pandas as pd
-import numpy as np
 import gradio as gr
+import re
 from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.neighbors import NearestNeighbors
 
-# -----------------------------
-# LOAD DATA & MODEL
-# -----------------------------
+# -------------------------------
+# Load dataset
+# -------------------------------
 df = pd.read_csv("food_order_cleaned.csv")
-
-model = SentenceTransformer("all-MiniLM-L6-v2")
-
-def create_text(row):
-    return (
-        f"Restaurant: {row['restaurant_name']}. "
-        f"Cuisine: {row['cuisine_type']}. "
-        f"Rating: {row['rating']}. "
-        f"Cost: {row['cost_of_the_order']}."
+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]
 
-df["text"] = df.apply(create_text, axis=1)
-corpus_embeddings = model.encode(df["text"].tolist(), normalize_embeddings=True)
-
-# -----------------------------
-# CHATBOT LOGIC
-# -----------------------------
-def chat_fn(message, history):
-
-    user_msg = {"role": "user", "content": message}
-
-    # Find best match
-    q_emb = model.encode([message], normalize_embeddings=True)
-    sims = cosine_similarity(q_emb, corpus_embeddings)[0]
-    idx = int(np.argmax(sims))
-    best = df.iloc[idx]
-
-    bot_response = (
-        f"🍽 **Recommended Restaurant**\n\n"
-        f"**Name:** {best['restaurant_name']}\n"
-        f"**Cuisine:** {best['cuisine_type']}\n"
-        f"**Rating:** ⭐ {best['rating']}\n"
-        f"**Avg Cost:** {best['cost_of_the_order']}\n\n"
-        f"Ask me for more options anytime!"
-    )
-
-    bot_msg = {"role": "assistant", "content": bot_response}
-
-    # Append messages to history
-    history.append(user_msg)
-    history.append(bot_msg)
-
-    return history, history
-
-
-# -----------------------------
-# GRADIO UI (Gradio 4.x format)
-# -----------------------------
+# -------------------------------
+# 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")
 
-    gr.Markdown("## 🍴 Restaurant Guide Chatbot")
+    chat = gr.Chatbot(label="Chat History")   # no type arg
+    html_out = gr.HTML(label="Search Results")
 
-    chatbot = gr.Chatbot(
-        label="Chat Window",
-        type="messages"
-    )
+    with gr.Row():
+        msg = gr.Textbox(placeholder="Ask me anything…")
+        cid = gr.Textbox(label="Customer ID (optional)")
+        btn = gr.Button("Send")
 
-    user_input = gr.Textbox(
-        placeholder="Ask: Find me a Thai restaurant...",
-        label="Your Message"
+    btn.click(
+        chatbot_fn,
+        inputs=[chat, msg, cid],
+        outputs=[chat, msg, html_out]
     )
 
-    clear = gr.Button("Clear Chat")
-
-    user_input.submit(chat_fn, [user_input, chatbot], [chatbot, chatbot])
-    clear.click(lambda: [], None, chatbot)
-
 demo.launch()