add apps

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+. filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,217 @@
+import os
+from groq import Groq
+import gradio as gr
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import sqlite3
+import pandas as pd
+from tqdm import tqdm
+
+# Get the Groq API key from environment variables (in Hugging Face, this is stored as a secret)
+client = Groq(
+    # This is the default and can be omitted
+    api_key=os.environ.get("GROQ_API_KEY"),
+)
+
+
+con = sqlite3.connect("file::memory:?cache=shared", check_same_thread=False)
+con.row_factory = sqlite3.Row
+cur = con.cursor()
+
+# create table if not exists
+
+cur.execute("""
+            CREATE TABLE IF NOT EXISTS places (
+                Place_Id INTEGER PRIMARY KEY,  -- SQLite auto-increments INTEGER PRIMARY KEY automatically
+                Place_Name TEXT NOT NULL,      -- SQLite uses TEXT instead of VARCHAR
+                Description TEXT,
+                Category TEXT,
+                City TEXT,
+                Price REAL,                    -- SQLite uses REAL instead of DECIMAL or FLOAT
+                Rating REAL,
+                Embedding TEXT
+            );
+            """)
+
+
+data = pd.read_csv('dataset/tourism_place.csv')
+
+
+# check if the table is empty
+cur.execute("SELECT * FROM places")
+
+if cur.fetchone() is None:
+    # Store the places in the database
+    for i in tqdm(range(len(data))):
+        cur.execute("""
+            INSERT INTO places (Place_Name, Description, Category, City, Price, Rating) 
+            VALUES (?, ?, ?, ?, ?, ?)
+            """, (data['Place_Name'][i], data['Description'][i], data['Category'][i], data['City'][i], float(data['Price'][i]), float(data['Rating'][i]))
+    )
+
+    # Commit the changes to the database
+    con.commit()
+
+# Compute and store embeddings
+def compute_and_store_embeddings():
+    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')  
+    
+    # Select all places from the database
+    cur.execute("SELECT Place_Id, Place_Name, Category, Description, City FROM places")
+    places = cur.fetchall()
+    
+    for place in places:
+        # Combine PlaceName, Category, Description, and City into one string
+        text = f"{place[1]} {place[2]} {place[3]} {place[4]}"
+        
+        # Generate embedding for the combined text
+        embedding = model.encode(text)
+        
+        # Convert embedding to a string format to store in the database
+        embedding_str = ','.join([str(x) for x in embedding])
+        
+        # Update the place in the database with the embedding
+        cur.execute(
+            "UPDATE places SET Embedding = ? WHERE Place_Id = ?", 
+            (embedding_str, place[0])
+        )
+    
+    # Commit the changes to the database
+    con.commit()
+# Run the function to compute and store embeddings
+compute_and_store_embeddings()
+
+
+# Load Hugging Face model for generating embeddings
+model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
+
+# Normalize user query using Groq VM
+def normalize_query(user_query):
+    try:
+        response = client.chat.completions.create(
+            model="llama-3.1-70b-versatile",
+            messages=[{
+                "role": "user",
+                "content": f"""
+                    Please analyze the query: \"{user_query}\", extract Place name, Category, Description, and City. 
+                    Return the response as: "Place name, Category, Description, City".
+                """
+            }]
+        )
+        normalized_user_query = response.choices[0].message.content.split('\n')[-1].strip()
+        return normalized_user_query
+    except Exception as e:
+        print(f"Error normalizing query: {e}")
+        return ""
+
+# Generate user embedding using Hugging Face model
+def get_user_embedding(query):
+    try:
+        return model.encode(query)
+    except Exception as e:
+        print(f"Error generating embedding: {e}")
+        return np.zeros(512)  # Assuming 384 as default embedding size
+
+# Find similar places based on cosine similarity
+def get_similar_places(user_embedding):
+    similarities = []
+    # Select all places from the database
+    res = cur.execute("SELECT * FROM places").fetchall()
+    
+    for place in res:
+        embedding_str = place['Embedding']  # Assuming embeddings are stored as comma-separated strings in the database
+        embedding = np.array([float(x) for x in embedding_str.split(',')])  # Convert the string back to a numpy array
+        
+        # Compute cosine similarity
+        similarity = cosine_similarity([user_embedding], [embedding])[0][0]
+        similarities.append((place, similarity))
+    
+    # Sort results based on similarity and then by rating
+    ranked_results = sorted(similarities, key=lambda x: (x[1], x[0]['Rating']), reverse=True)
+    
+    # Return top places
+    return ranked_results
+
+# Main function to get top 5 destinations
+def get_top_5_destinations(user_query):
+    normalized_query = normalize_query(user_query)
+    user_embedding = get_user_embedding(normalized_query)
+    similar_places = get_similar_places(user_embedding)
+
+    if not similar_places:
+        return "Tidak ada tempat yang ditemukan."
+
+    top_places = []
+    for i, (place, similarity) in enumerate(similar_places):
+        top_places.append({
+            'name': place['Place_Name'],
+            'city': place['City'],
+            'category': place['Category'],
+            'rating': place['Rating'],
+            'description': place['Description'],
+            'similarity': similarity
+        })
+    
+    return top_places
+
+# Generate response to user using Groq VM
+def generate_response(user_query, top_places):
+    try:
+        # Prepare the destinations data in JSON format for the model to use directly
+        destinations_data = ", ".join([
+            f'{{"name": "{place["name"]}", "city": "{place["city"]}", "category": "{place["category"]}", "rating": {place["rating"]}, "description": "{place["description"]}"}}'
+            for place in top_places
+        ])
+
+        # System prompt: Simplified and focused on returning only the recommendations
+        system_prompt = """
+            You are a tour guide assistant. Your task is to present the following tourism recommendations to the user in Bahasa Indonesia.
+            - For each destination, include the name, city, category, rating, and a short description.
+            - Do not provide any additional commentary.
+            - Only return the provided data in a clear and concise format.
+            """
+
+        # Generate the response using the model
+        response = client.chat.completions.create(
+            model="llama-3.1-70b-versatile",
+            messages=[
+                {"role": "system", "content": system_prompt},  # System prompt defines behavior
+                {"role": "user", "content": f"Berikut adalah rekomendasi berdasarkan data: {destinations_data}"}
+            ]
+        )
+
+        # Return the response content generated by the model
+        return response.choices[0].message.content
+    except Exception as e:
+        print(f"Error generating response: {e}")
+        return "Maaf, terjadi kesalahan dalam menghasilkan rekomendasi."
+
+# Gradio Interface - User Input and Output
+def chatbot(user_query):
+    # Step 1: Get the top 5 destinations
+    top_places = get_top_5_destinations(user_query)
+
+    if isinstance(top_places, str):  # Error case, e.g. "No places found"
+        return top_places
+
+    # Step 2: Generate the chatbot's response
+    # response = generate_response(user_query, top_places)
+
+    # only the first 5 element of top_places
+    response = generate_response(user_query, top_places[:5])
+
+    return response
+
+# Define Gradio Interface
+iface = gr.Interface(
+    fn=chatbot,
+    inputs="text",  
+    outputs="text",  
+    title="Tourism Recommendation Chatbot",
+    description="Masukkan pertanyaan wisata Anda dan dapatkan rekomendasi tempat terbaik!"
+)
+
+# Launch the Gradio App
+if __name__ == "__main__":
+    iface.launch(share=True)

dataset/user.csv

@@ -0,0 +1,301 @@
+User_Id,Location,Age
+1,"Semarang, Jawa Tengah",20
+2,"Bekasi, Jawa Barat",21
+3,"Cirebon, Jawa Barat",23
+4,"Bekasi, Jawa Barat",21
+5,"Lampung, Sumatera Selatan",20
+6,"Jakarta Utara, DKI Jakarta",18
+7,"Jakarta Selatan, DKI Jakarta",39
+8,"Bandung, Jawa Barat",40
+9,"Surabaya, Jawa Timur",38
+10,"Bekasi, Jawa Barat",39
+11,"Yogyakarta, DIY",20
+12,"Bogor, Jawa Barat",37
+13,"Depok, Jawa Barat",18
+14,"Jakarta Pusat, DKI Jakarta",26
+15,"Jakarta Timur, DKI Jakarta",34
+16,"Bekasi, Jawa Barat",40
+17,"Semarang, Jawa Tengah",31
+18,"Yogyakarta, DIY",39
+19,"Cirebon, Jawa Barat",26
+20,"Lampung, Sumatera Selatan",30
+21,"Semarang, Jawa Tengah",30
+22,"Subang, Jawa Barat",25
+23,"Jakarta Barat, DKI Jakarta",37
+24,"Bekasi, Jawa Barat",36
+25,"Lampung, Sumatera Selatan",40
+26,"Palembang, Sumatera Selatan",38
+27,"Bogor, Jawa Barat",22
+28,"Sragen, Jawa Tengah",38
+29,"Ponorogo, Jawa Timur",34
+30,"Depok, Jawa Barat",30
+31,"Jakarta Selatan, DKI Jakarta",26
+32,"Bekasi, Jawa Barat",34
+33,"Ponorogo, Jawa Timur",24
+34,"Sragen, Jawa Tengah",31
+35,"Klaten, Jawa Tengah",24
+36,"Solo, Jawa Tengah",20
+37,"Tanggerang, Banten",21
+38,"Serang, Banten",26
+39,"Cilacap, Jawa Tengah",32
+40,"Semarang, Jawa Tengah",27
+41,"Yogyakarta, DIY",24
+42,"Kota Gede, DIY",37
+43,"Cirebon, Jawa Barat",33
+44,"Subang, Jawa Barat",21
+45,"Karawang, Jawa Barat",25
+46,"Purwakarat, Jawa Barat",38
+47,"Jakarta Utara, DKI Jakarta",31
+48,"Jakarta Selatan, DKI Jakarta",35
+49,"Jakarta Pusat, DKI Jakarta",24
+50,"Bekasi, Jawa Barat",19
+51,"Bogor, Jawa Barat",29
+52,"Karawang, Jawa Barat",18
+53,"Subang, Jawa Barat",28
+54,"Serang, Banten",31
+55,"Tanggerang, Banten",19
+56,"Kota Gede, DIY",18
+57,"Yogyakarta, DIY",21
+58,"Lampung, Sumatera Selatan",21
+59,"Ponorogo, Jawa Timur",26
+60,"Surabaya, Jawa Timur",25
+61,"Nganjuk, Jawa Timur",23
+62,"Madura, Jawa Timur",36
+63,"Semarang, Jawa Tengah",35
+64,"Bandung, Jawa Barat",38
+65,"Yogyakarta, DIY",22
+66,"Bekasi, Jawa Barat",33
+67,"Surabaya, Jawa Timur",25
+68,"Kota Gede, DIY",37
+69,"Bekasi, Jawa Barat",24
+70,"Bogor, Jawa Barat",21
+71,"Depok, Jawa Barat",39
+72,"Tanggerang, Banten",19
+73,"Serang, Banten",29
+74,"Semarang, Jawa Tengah",30
+75,"Bekasi, Jawa Barat",19
+76,"Cirebon, Jawa Barat",19
+77,"Bekasi, Jawa Barat",34
+78,"Lampung, Sumatera Selatan",22
+79,"Jakarta Utara, DKI Jakarta",31
+80,"Jakarta Selatan, DKI Jakarta",32
+81,"Bandung, Jawa Barat",29
+82,"Surabaya, Jawa Timur",24
+83,"Bekasi, Jawa Barat",32
+84,"Yogyakarta, DIY",35
+85,"Bogor, Jawa Barat",31
+86,"Depok, Jawa Barat",32
+87,"Jakarta Pusat, DKI Jakarta",30
+88,"Jakarta Timur, DKI Jakarta",27
+89,"Bekasi, Jawa Barat",35
+90,"Semarang, Jawa Tengah",29
+91,"Yogyakarta, DIY",32
+92,"Cirebon, Jawa Barat",39
+93,"Lampung, Sumatera Selatan",18
+94,"Semarang, Jawa Tengah",34
+95,"Subang, Jawa Barat",27
+96,"Jakarta Barat, DKI Jakarta",19
+97,"Bekasi, Jawa Barat",38
+98,"Lampung, Sumatera Selatan",28
+99,"Palembang, Sumatera Selatan",33
+100,"Bogor, Jawa Barat",28
+101,"Sragen, Jawa Tengah",39
+102,"Ponorogo, Jawa Timur",21
+103,"Depok, Jawa Barat",30
+104,"Jakarta Selatan, DKI Jakarta",27
+105,"Bekasi, Jawa Barat",37
+106,"Ponorogo, Jawa Timur",32
+107,"Sragen, Jawa Tengah",24
+108,"Klaten, Jawa Tengah",33
+109,"Solo, Jawa Tengah",18
+110,"Tanggerang, Banten",39
+111,"Serang, Banten",38
+112,"Cilacap, Jawa Tengah",18
+113,"Semarang, Jawa Tengah",38
+114,"Yogyakarta, DIY",39
+115,"Kota Gede, DIY",26
+116,"Cirebon, Jawa Barat",23
+117,"Subang, Jawa Barat",30
+118,"Karawang, Jawa Barat",32
+119,"Purwakarat, Jawa Barat",25
+120,"Jakarta Utara, DKI Jakarta",32
+121,"Jakarta Selatan, DKI Jakarta",35
+122,"Jakarta Pusat, DKI Jakarta",24
+123,"Bekasi, Jawa Barat",32
+124,"Bogor, Jawa Barat",22
+125,"Karawang, Jawa Barat",24
+126,"Subang, Jawa Barat",32
+127,"Serang, Banten",38
+128,"Tanggerang, Banten",28
+129,"Kota Gede, DIY",29
+130,"Yogyakarta, DIY",27
+131,"Lampung, Sumatera Selatan",21
+132,"Ponorogo, Jawa Timur",31
+133,"Surabaya, Jawa Timur",29
+134,"Nganjuk, Jawa Timur",27
+135,"Madura, Jawa Timur",22
+136,"Semarang, Jawa Tengah",35
+137,"Bandung, Jawa Barat",28
+138,"Yogyakarta, DIY",25
+139,"Bekasi, Jawa Barat",33
+140,"Surabaya, Jawa Timur",25
+141,"Kota Gede, DIY",34
+142,"Bekasi, Jawa Barat",29
+143,"Bogor, Jawa Barat",25
+144,"Depok, Jawa Barat",18
+145,"Tanggerang, Banten",37
+146,"Serang, Banten",38
+147,"Semarang, Jawa Tengah",18
+148,"Bekasi, Jawa Barat",33
+149,"Cirebon, Jawa Barat",30
+150,"Bekasi, Jawa Barat",40
+151,"Lampung, Sumatera Selatan",36
+152,"Jakarta Utara, DKI Jakarta",25
+153,"Jakarta Selatan, DKI Jakarta",39
+154,"Bandung, Jawa Barat",31
+155,"Surabaya, Jawa Timur",37
+156,"Bekasi, Jawa Barat",31
+157,"Yogyakarta, DIY",28
+158,"Bogor, Jawa Barat",23
+159,"Depok, Jawa Barat",20
+160,"Jakarta Pusat, DKI Jakarta",36
+161,"Jakarta Timur, DKI Jakarta",33
+162,"Bekasi, Jawa Barat",25
+163,"Semarang, Jawa Tengah",40
+164,"Yogyakarta, DIY",19
+165,"Cirebon, Jawa Barat",23
+166,"Lampung, Sumatera Selatan",26
+167,"Semarang, Jawa Tengah",19
+168,"Subang, Jawa Barat",38
+169,"Jakarta Barat, DKI Jakarta",18
+170,"Bekasi, Jawa Barat",19
+171,"Lampung, Sumatera Selatan",33
+172,"Palembang, Sumatera Selatan",34
+173,"Bogor, Jawa Barat",29
+174,"Sragen, Jawa Tengah",32
+175,"Ponorogo, Jawa Timur",36
+176,"Depok, Jawa Barat",31
+177,"Jakarta Selatan, DKI Jakarta",35
+178,"Bekasi, Jawa Barat",33
+179,"Ponorogo, Jawa Timur",27
+180,"Sragen, Jawa Tengah",24
+181,"Klaten, Jawa Tengah",29
+182,"Solo, Jawa Tengah",34
+183,"Tanggerang, Banten",37
+184,"Serang, Banten",30
+185,"Cilacap, Jawa Tengah",33
+186,"Semarang, Jawa Tengah",28
+187,"Yogyakarta, DIY",25
+188,"Kota Gede, DIY",37
+189,"Cirebon, Jawa Barat",21
+190,"Subang, Jawa Barat",18
+191,"Karawang, Jawa Barat",32
+192,"Purwakarat, Jawa Barat",37
+193,"Jakarta Utara, DKI Jakarta",20
+194,"Jakarta Selatan, DKI Jakarta",31
+195,"Jakarta Pusat, DKI Jakarta",29
+196,"Bekasi, Jawa Barat",28
+197,"Bogor, Jawa Barat",27
+198,"Karawang, Jawa Barat",26
+199,"Subang, Jawa Barat",18
+200,"Serang, Banten",34
+201,"Bekasi, Jawa Barat",21
+202,"Lampung, Sumatera Selatan",21
+203,"Jakarta Utara, DKI Jakarta",24
+204,"Jakarta Selatan, DKI Jakarta",21
+205,"Bandung, Jawa Barat",24
+206,"Surabaya, Jawa Timur",30
+207,"Bekasi, Jawa Barat",20
+208,"Yogyakarta, DIY",27
+209,"Bogor, Jawa Barat",19
+210,"Depok, Jawa Barat",18
+211,"Jakarta Pusat, DKI Jakarta",22
+212,"Jakarta Timur, DKI Jakarta",28
+213,"Bekasi, Jawa Barat",20
+214,"Semarang, Jawa Tengah",30
+215,"Yogyakarta, DIY",23
+216,"Cirebon, Jawa Barat",28
+217,"Lampung, Sumatera Selatan",20
+218,"Semarang, Jawa Tengah",29
+219,"Subang, Jawa Barat",24
+220,"Jakarta Barat, DKI Jakarta",23
+221,"Bekasi, Jawa Barat",30
+222,"Lampung, Sumatera Selatan",30
+223,"Palembang, Sumatera Selatan",20
+224,"Bogor, Jawa Barat",28
+225,"Sragen, Jawa Tengah",19
+226,"Ponorogo, Jawa Timur",23
+227,"Depok, Jawa Barat",25
+228,"Jakarta Selatan, DKI Jakarta",18
+229,"Bekasi, Jawa Barat",20
+230,"Ponorogo, Jawa Timur",20
+231,"Sragen, Jawa Tengah",28
+232,"Klaten, Jawa Tengah",30
+233,"Solo, Jawa Tengah",23
+234,"Tanggerang, Banten",27
+235,"Serang, Banten",18
+236,"Cilacap, Jawa Tengah",23
+237,"Semarang, Jawa Tengah",20
+238,"Yogyakarta, DIY",30
+239,"Kota Gede, DIY",23
+240,"Cirebon, Jawa Barat",22
+241,"Subang, Jawa Barat",20
+242,"Karawang, Jawa Barat",20
+243,"Purwakarat, Jawa Barat",20
+244,"Jakarta Utara, DKI Jakarta",27
+245,"Jakarta Selatan, DKI Jakarta",27
+246,"Jakarta Pusat, DKI Jakarta",28
+247,"Bekasi, Jawa Barat",28
+248,"Bogor, Jawa Barat",29
+249,"Karawang, Jawa Barat",19
+250,"Subang, Jawa Barat",27
+251,"Semarang, Jawa Tengah",29
+252,"Bekasi, Jawa Barat",30
+253,"Cirebon, Jawa Barat",34
+254,"Bekasi, Jawa Barat",34
+255,"Lampung, Sumatera Selatan",30
+256,"Jakarta Utara, DKI Jakarta",39
+257,"Jakarta Selatan, DKI Jakarta",25
+258,"Bandung, Jawa Barat",38
+259,"Surabaya, Jawa Timur",27
+260,"Bekasi, Jawa Barat",33
+261,"Yogyakarta, DIY",38
+262,"Bogor, Jawa Barat",38
+263,"Depok, Jawa Barat",27
+264,"Jakarta Pusat, DKI Jakarta",37
+265,"Jakarta Timur, DKI Jakarta",30
+266,"Bekasi, Jawa Barat",32
+267,"Semarang, Jawa Tengah",31
+268,"Yogyakarta, DIY",32
+269,"Cirebon, Jawa Barat",36
+270,"Lampung, Sumatera Selatan",25
+271,"Semarang, Jawa Tengah",37
+272,"Subang, Jawa Barat",30
+273,"Jakarta Barat, DKI Jakarta",33
+274,"Bekasi, Jawa Barat",38
+275,"Lampung, Sumatera Selatan",34
+276,"Lampung, Sumatera Selatan",39
+277,"Jakarta Utara, DKI Jakarta",29
+278,"Jakarta Selatan, DKI Jakarta",40
+279,"Bandung, Jawa Barat",28
+280,"Surabaya, Jawa Timur",40
+281,"Bekasi, Jawa Barat",30
+282,"Yogyakarta, DIY",39
+283,"Bogor, Jawa Barat",37
+284,"Depok, Jawa Barat",29
+285,"Jakarta Pusat, DKI Jakarta",29
+286,"Jakarta Timur, DKI Jakarta",35
+287,"Bekasi, Jawa Barat",27
+288,"Semarang, Jawa Tengah",30
+289,"Yogyakarta, DIY",35
+290,"Cirebon, Jawa Barat",34
+291,"Lampung, Sumatera Selatan",25
+292,"Semarang, Jawa Tengah",29
+293,"Subang, Jawa Barat",34
+294,"Jakarta Barat, DKI Jakarta",28
+295,"Bekasi, Jawa Barat",31
+296,"Lampung, Sumatera Selatan",31
+297,"Palembang, Sumatera Selatan",39
+298,"Bogor, Jawa Barat",38
+299,"Sragen, Jawa Tengah",27
+300,"Ponorogo, Jawa Timur",26

exploration-LlamaRecommender.ipynb

@@ -0,0 +1,844 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Berhasil terkoneksi ke MySQL Server\n",
+      "Database 'tourism_destination' berhasil dibuat!\n",
+      "Koneksi ke MySQL ditutup\n"
+     ]
+    }
+   ],
+   "source": [
+    "import mysql.connector\n",
+    "from mysql.connector import Error\n",
+    "\n",
+    "# Fungsi untuk membuat koneksi ke MySQL dan membuat database\n",
+    "def create_database(host_name, user_name, user_password, db_name):\n",
+    "    try:\n",
+    "        # Koneksi ke server MySQL\n",
+    "        connection = mysql.connector.connect(\n",
+    "            host=host_name,\n",
+    "            user=user_name,\n",
+    "            password=user_password\n",
+    "        )\n",
+    "        \n",
+    "        if connection.is_connected():\n",
+    "            print(\"Berhasil terkoneksi ke MySQL Server\")\n",
+    "            cursor = connection.cursor()\n",
+    "            # Membuat database baru\n",
+    "            cursor.execute(f\"CREATE DATABASE {db_name}\")\n",
+    "            print(f\"Database '{db_name}' berhasil dibuat!\")\n",
+    "    \n",
+    "    except Error as e:\n",
+    "        print(f\"Error: '{e}' terjadi\")\n",
+    "    \n",
+    "    finally:\n",
+    "        # Menutup koneksi\n",
+    "        if connection.is_connected():\n",
+    "            cursor.close()\n",
+    "            connection.close()\n",
+    "            print(\"Koneksi ke MySQL ditutup\")\n",
+    "\n",
+    "# Contoh penggunaan\n",
+    "host = \"localhost\"\n",
+    "user = \"root\"\n",
+    "password = \"admin123\"\n",
+    "database_name = \"tourism_destination\"\n",
+    "\n",
+    "create_database(host, user, password, database_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Berhasil terkoneksi ke database 'tourism_destination'\n",
+      "Tabel 'places' berhasil dibuat!\n",
+      "Koneksi ke MySQL ditutup\n"
+     ]
+    }
+   ],
+   "source": [
+    "def create_table(host_name, user_name, user_password, db_name):\n",
+    "    try:\n",
+    "        # Koneksi ke MySQL dan pilih database\n",
+    "        connection = mysql.connector.connect(\n",
+    "            host=host_name,\n",
+    "            user=user_name,\n",
+    "            password=user_password,\n",
+    "            database=db_name\n",
+    "        )\n",
+    "        \n",
+    "        if connection.is_connected():\n",
+    "            print(f\"Berhasil terkoneksi ke database '{db_name}'\")\n",
+    "            cursor = connection.cursor()\n",
+    "            \n",
+    "            # Membuat tabel dengan kolom sesuai format yang diberikan\n",
+    "            create_table_query = \"\"\"\n",
+    "            CREATE TABLE places (\n",
+    "                Place_Id INT AUTO_INCREMENT PRIMARY KEY,\n",
+    "                Place_Name VARCHAR(255) NOT NULL,\n",
+    "                Description TEXT,\n",
+    "                Category VARCHAR(100),\n",
+    "                City VARCHAR(100),\n",
+    "                Price DECIMAL(10, 2),  \n",
+    "                Rating FLOAT \n",
+    "            );\n",
+    "            \"\"\"\n",
+    "            cursor.execute(create_table_query)\n",
+    "            print(\"Tabel 'places' berhasil dibuat!\")\n",
+    "    \n",
+    "    except Error as e:\n",
+    "        print(f\"Error: '{e}' terjadi\")\n",
+    "    \n",
+    "    finally:\n",
+    "        # Menutup koneksi\n",
+    "        if connection.is_connected():\n",
+    "            cursor.close()\n",
+    "            connection.close()\n",
+    "            print(\"Koneksi ke MySQL ditutup\")\n",
+    "\n",
+    "# Contoh penggunaan\n",
+    "host = \"localhost\"\n",
+    "user = \"root\"\n",
+    "password = \"admin123\"\n",
+    "database_name = \"tourism_destination\"\n",
+    "\n",
+    "create_table(host, user, password, database_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Place_Id</th>\n",
+       "      <th>Place_Name</th>\n",
+       "      <th>Description</th>\n",
+       "      <th>Category</th>\n",
+       "      <th>City</th>\n",
+       "      <th>Price</th>\n",
+       "      <th>Rating</th>\n",
+       "      <th>Time_Minutes</th>\n",
+       "      <th>Coordinate</th>\n",
+       "      <th>Lat</th>\n",
+       "      <th>Long</th>\n",
+       "      <th>Unnamed: 11</th>\n",
+       "      <th>Unnamed: 12</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Monumen Nasional</td>\n",
+       "      <td>Monumen Nasional atau yang populer disingkat d...</td>\n",
+       "      <td>Budaya</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>20000</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>{'lat': -6.1753924, 'lng': 106.8271528}</td>\n",
+       "      <td>-6.175392</td>\n",
+       "      <td>106.827153</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Kota Tua</td>\n",
+       "      <td>Kota tua di Jakarta, yang juga bernama Kota Tu...</td>\n",
+       "      <td>Budaya</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>{'lat': -6.137644799999999, 'lng': 106.8171245}</td>\n",
+       "      <td>-6.137645</td>\n",
+       "      <td>106.817125</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Dunia Fantasi</td>\n",
+       "      <td>Dunia Fantasi atau disebut juga Dufan adalah t...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>270000</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>360.0</td>\n",
+       "      <td>{'lat': -6.125312399999999, 'lng': 106.8335377}</td>\n",
+       "      <td>-6.125312</td>\n",
+       "      <td>106.833538</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Taman Mini Indonesia Indah (TMII)</td>\n",
+       "      <td>Taman Mini Indonesia Indah merupakan suatu kaw...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>10000</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>{'lat': -6.302445899999999, 'lng': 106.8951559}</td>\n",
+       "      <td>-6.302446</td>\n",
+       "      <td>106.895156</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Atlantis Water Adventure</td>\n",
+       "      <td>Atlantis Water Adventure atau dikenal dengan A...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>94000</td>\n",
+       "      <td>4.5</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>{'lat': -6.12419, 'lng': 106.839134}</td>\n",
+       "      <td>-6.124190</td>\n",
+       "      <td>106.839134</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Place_Id                         Place_Name  \\\n",
+       "0         1                   Monumen Nasional   \n",
+       "1         2                           Kota Tua   \n",
+       "2         3                      Dunia Fantasi   \n",
+       "3         4  Taman Mini Indonesia Indah (TMII)   \n",
+       "4         5           Atlantis Water Adventure   \n",
+       "\n",
+       "                                         Description       Category     City  \\\n",
+       "0  Monumen Nasional atau yang populer disingkat d...         Budaya  Jakarta   \n",
+       "1  Kota tua di Jakarta, yang juga bernama Kota Tu...         Budaya  Jakarta   \n",
+       "2  Dunia Fantasi atau disebut juga Dufan adalah t...  Taman Hiburan  Jakarta   \n",
+       "3  Taman Mini Indonesia Indah merupakan suatu kaw...  Taman Hiburan  Jakarta   \n",
+       "4  Atlantis Water Adventure atau dikenal dengan A...  Taman Hiburan  Jakarta   \n",
+       "\n",
+       "    Price  Rating  Time_Minutes  \\\n",
+       "0   20000     4.6          15.0   \n",
+       "1       0     4.6          90.0   \n",
+       "2  270000     4.6         360.0   \n",
+       "3   10000     4.5           NaN   \n",
+       "4   94000     4.5          60.0   \n",
+       "\n",
+       "                                        Coordinate       Lat        Long  \\\n",
+       "0          {'lat': -6.1753924, 'lng': 106.8271528} -6.175392  106.827153   \n",
+       "1  {'lat': -6.137644799999999, 'lng': 106.8171245} -6.137645  106.817125   \n",
+       "2  {'lat': -6.125312399999999, 'lng': 106.8335377} -6.125312  106.833538   \n",
+       "3  {'lat': -6.302445899999999, 'lng': 106.8951559} -6.302446  106.895156   \n",
+       "4             {'lat': -6.12419, 'lng': 106.839134} -6.124190  106.839134   \n",
+       "\n",
+       "   Unnamed: 11  Unnamed: 12  \n",
+       "0          NaN            1  \n",
+       "1          NaN            2  \n",
+       "2          NaN            3  \n",
+       "3          NaN            4  \n",
+       "4          NaN            5  "
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = pd.read_csv(r'dataset_recommendation_tourism\\tourism_with_id.csv')\n",
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Place_Id', 'Place_Name', 'Description', 'Category', 'City', 'Price',\n",
+       "       'Rating', 'Time_Minutes', 'Coordinate', 'Lat', 'Long', 'Unnamed: 11',\n",
+       "       'Unnamed: 12'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Index(['Place_Id', 'Place_Name', 'Description', 'Category', 'City', 'Price',\n",
+       "       'Rating'],\n",
+       "      dtype='object')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data = data.drop(['Time_Minutes', 'Coordinate',\n",
+    "                'Lat', 'Long', 'Unnamed: 11',\n",
+    "                'Unnamed: 12'], axis=1)\n",
+    "data.columns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data.to_csv('tourism_place.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 437 entries, 0 to 436\n",
+      "Data columns (total 7 columns):\n",
+      " #   Column       Non-Null Count  Dtype  \n",
+      "---  ------       --------------  -----  \n",
+      " 0   Place_Id     437 non-null    int64  \n",
+      " 1   Place_Name   437 non-null    object \n",
+      " 2   Description  437 non-null    object \n",
+      " 3   Category     437 non-null    object \n",
+      " 4   City         437 non-null    object \n",
+      " 5   Price        437 non-null    int64  \n",
+      " 6   Rating       437 non-null    float64\n",
+      "dtypes: float64(1), int64(2), object(4)\n",
+      "memory usage: 24.0+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "data.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Place_Id</th>\n",
+       "      <th>Place_Name</th>\n",
+       "      <th>Description</th>\n",
+       "      <th>Category</th>\n",
+       "      <th>City</th>\n",
+       "      <th>Price</th>\n",
+       "      <th>Rating</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>Monumen Nasional</td>\n",
+       "      <td>Monumen Nasional atau yang populer disingkat d...</td>\n",
+       "      <td>Budaya</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>20000</td>\n",
+       "      <td>4.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Kota Tua</td>\n",
+       "      <td>Kota tua di Jakarta, yang juga bernama Kota Tu...</td>\n",
+       "      <td>Budaya</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>Dunia Fantasi</td>\n",
+       "      <td>Dunia Fantasi atau disebut juga Dufan adalah t...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>270000</td>\n",
+       "      <td>4.6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Taman Mini Indonesia Indah (TMII)</td>\n",
+       "      <td>Taman Mini Indonesia Indah merupakan suatu kaw...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>10000</td>\n",
+       "      <td>4.5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Atlantis Water Adventure</td>\n",
+       "      <td>Atlantis Water Adventure atau dikenal dengan A...</td>\n",
+       "      <td>Taman Hiburan</td>\n",
+       "      <td>Jakarta</td>\n",
+       "      <td>94000</td>\n",
+       "      <td>4.5</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   Place_Id                         Place_Name  \\\n",
+       "0         1                   Monumen Nasional   \n",
+       "1         2                           Kota Tua   \n",
+       "2         3                      Dunia Fantasi   \n",
+       "3         4  Taman Mini Indonesia Indah (TMII)   \n",
+       "4         5           Atlantis Water Adventure   \n",
+       "\n",
+       "                                         Description       Category     City  \\\n",
+       "0  Monumen Nasional atau yang populer disingkat d...         Budaya  Jakarta   \n",
+       "1  Kota tua di Jakarta, yang juga bernama Kota Tu...         Budaya  Jakarta   \n",
+       "2  Dunia Fantasi atau disebut juga Dufan adalah t...  Taman Hiburan  Jakarta   \n",
+       "3  Taman Mini Indonesia Indah merupakan suatu kaw...  Taman Hiburan  Jakarta   \n",
+       "4  Atlantis Water Adventure atau dikenal dengan A...  Taman Hiburan  Jakarta   \n",
+       "\n",
+       "    Price  Rating  \n",
+       "0   20000     4.6  \n",
+       "1       0     4.6  \n",
+       "2  270000     4.6  \n",
+       "3   10000     4.5  \n",
+       "4   94000     4.5  "
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\Data Science\\HACKATHON\\GEN AI LLAMA HACKTIV8\\llama_venv\\Lib\\site-packages\\sentence_transformers\\cross_encoder\\CrossEncoder.py:11: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from tqdm.autonotebook import tqdm, trange\n"
+     ]
+    }
+   ],
+   "source": [
+    "import mysql.connector\n",
+    "from mysql.connector import Error\n",
+    "import ollama\n",
+    "from sentence_transformers import SentenceTransformer\n",
+    "from sklearn.metrics.pairwise import cosine_similarity\n",
+    "from tqdm import tqdm\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def connect_to_database():\n",
+    "    try:\n",
+    "        connection = mysql.connector.connect(\n",
+    "            host=\"localhost\",\n",
+    "            user=\"root\",\n",
+    "            password=\"admin123\",\n",
+    "            database=\"tourism_destination\"\n",
+    "        )\n",
+    "        return connection\n",
+    "    except Error as e:\n",
+    "        print(f\"Error: '{e}'\")\n",
+    "        return None\n",
+    "    \n",
+    "    # Function to check if a column exists, and add it if necessary\n",
+    "def add_embedding_column_if_not_exists(cursor):\n",
+    "    # Check if the 'Embedding' column exists\n",
+    "    cursor.execute(\"SHOW COLUMNS FROM places LIKE 'Embedding'\")\n",
+    "    result = cursor.fetchone()\n",
+    "    \n",
+    "    # If the 'Embedding' column does not exist, add it\n",
+    "    if not result:\n",
+    "        print(\"Adding 'Embedding' column to the table...\")\n",
+    "        cursor.execute(\"ALTER TABLE places ADD COLUMN Embedding TEXT\")\n",
+    "        print(\"'Embedding' column added.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Adding 'Embedding' column to the table...\n"
+     ]
+    }
+   ],
+   "source": [
+    "connection = connect_to_database()\n",
+    "cursor = connection.cursor()\n",
+    "add_embedding_column_if_not_exists(cursor)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\Data Science\\HACKATHON\\GEN AI LLAMA HACKTIV8\\llama_venv\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Koneksi ke MySQL\n",
+    "def connect_to_database():\n",
+    "    try:\n",
+    "        connection = mysql.connector.connect(\n",
+    "            host=\"localhost\",\n",
+    "            user=\"root\",\n",
+    "            password=\"admin123\",\n",
+    "            database=\"tourism_destination\"\n",
+    "        )\n",
+    "        return connection\n",
+    "    except Error as e:\n",
+    "        print(f\"Error: '{e}'\")\n",
+    "        return None\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Compute and store embeddings\n",
+    "def compute_and_store_embeddings():\n",
+    "    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')  \n",
+    "\n",
+    "    # Connect to the database\n",
+    "    connection = connect_to_database()\n",
+    "    if connection is None:\n",
+    "        return\n",
+    "    \n",
+    "    cursor = connection.cursor(dictionary=True)\n",
+    "    \n",
+    "    # Select all places from the database\n",
+    "    cursor.execute(\"SELECT Place_Id, Place_Name, Category, Description, City FROM places\")\n",
+    "    places = cursor.fetchall()\n",
+    "    \n",
+    "    for place in places:\n",
+    "        # Combine PlaceName, Category, Description, and City into one string\n",
+    "        text = f\"{place['Place_Name']} {place['Category']} {place['Description']} {place['City']}\"\n",
+    "        \n",
+    "        # Generate embedding for the combined text\n",
+    "        embedding = model.encode(text)\n",
+    "        \n",
+    "        # Convert embedding to a string format to store in the database\n",
+    "        embedding_str = ','.join([str(x) for x in embedding])\n",
+    "        \n",
+    "        # Update the place in the database with the embedding\n",
+    "        cursor.execute(\n",
+    "            \"UPDATE places SET Embedding = %s WHERE Place_Id = %s\", \n",
+    "            (embedding_str, place['Place_Id'])\n",
+    "        )\n",
+    "    \n",
+    "    # Commit the changes and close the connection\n",
+    "    connection.commit()\n",
+    "    cursor.close()\n",
+    "    connection.close()\n",
+    "\n",
+    "# Run the function to compute and store embeddings\n",
+    "compute_and_store_embeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\Data Science\\HACKATHON\\GEN AI LLAMA HACKTIV8\\llama_venv\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Top 5 Ranked Destinations:\n",
+      "\n",
+      "Pulau Semak Daun (Rating: 4.0, Similarity Score: 0.6861)\n",
+      "Wisata Batu Kuda (Rating: 4.4, Similarity Score: 0.6839)\n",
+      "Gedung Agung Yogyakarta (Rating: 4.6, Similarity Score: 0.6727)\n",
+      "Taman Sungai Mudal (Rating: 4.6, Similarity Score: 0.6595)\n",
+      "Grand Maerakaca (Rating: 4.4, Similarity Score: 0.6581)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Koneksi ke MySQL\n",
+    "def query_database():\n",
+    "    try:\n",
+    "        connection = mysql.connector.connect(\n",
+    "            host=\"localhost\",\n",
+    "            user=\"root\",\n",
+    "            password=\"admin123\",\n",
+    "            database=\"tourism_destination\"\n",
+    "        )\n",
+    "\n",
+    "        if connection.is_connected():\n",
+    "            cursor = connection.cursor(dictionary=True)\n",
+    "            sql = \"SELECT * FROM places\"\n",
+    "            cursor.execute(sql)\n",
+    "            results = cursor.fetchall()\n",
+    "            return results\n",
+    "\n",
+    "    except Error as e:\n",
+    "        print(f\"Error: '{e}'\")\n",
+    "    \n",
+    "    finally:\n",
+    "        if connection.is_connected():\n",
+    "            cursor.close()\n",
+    "            connection.close()\n",
+    "\n",
+    "# Get embedding from the database and calculate cosine similarity\n",
+    "def get_similar_places(user_embedding, db_results):\n",
+    "    similarities = []\n",
+    "    \n",
+    "    for place in db_results:\n",
+    "        embedding_str = place['Embedding']  # Assuming embeddings are stored as comma-separated strings in the database\n",
+    "        embedding = np.array([float(x) for x in embedding_str.split(',')])  # Convert the string back to a numpy array\n",
+    "        \n",
+    "        # Compute cosine similarity\n",
+    "        similarity = cosine_similarity([user_embedding], [embedding])[0][0]\n",
+    "        similarities.append((place, similarity))\n",
+    "    \n",
+    "    # Sort results based on similarity and then by rating\n",
+    "    ranked_results = sorted(similarities, key=lambda x: (x[1], x[0]['Rating']), reverse=True)\n",
+    "    \n",
+    "    # Return top 5 places\n",
+    "    return ranked_results[:5]\n",
+    "\n",
+    "# Ollama - Generate possible places (Retrieval Augmented Generation)\n",
+    "def generate_rag_result(user_query):\n",
+    "    prompt = f\"User Query: {user_query}\\n\\nPlease list 10 potential destinations based on user query:\"\n",
+    "    \n",
+    "    print(\"\\nGenerating results using Ollama (RAG)...\\n\")\n",
+    "    with tqdm(total=10, desc=\"Processing RAG\") as pbar:\n",
+    "        response = ollama.generate(model=\"llama3.1\", prompt=prompt)\n",
+    "        pbar.update(5)\n",
+    "    \n",
+    "    # Process the response (assuming response structure is consistent)\n",
+    "    print(\"Full response:\", response)\n",
+    "    return response  # For now, we don't need to extract specific places, as similarity search will handle that\n",
+    "\n",
+    "# Main function to find the top 5 destinations\n",
+    "def get_top_5_destinations(user_query):\n",
+    "    # Step 1: Generate embedding for user query\n",
+    "    model = SentenceTransformer('paraphrase-MiniLM-L6-v2')\n",
+    "    user_embedding = model.encode(user_query)\n",
+    "    \n",
+    "    # Step 2: Fetch all places from the database\n",
+    "    db_results = query_database()\n",
+    "    if not db_results or len(db_results) == 0:\n",
+    "        print(\"No data returned from database.\")\n",
+    "        return\n",
+    "    \n",
+    "    # Step 3: Find the most similar places\n",
+    "    top_5_places = get_similar_places(user_embedding, db_results)\n",
+    "    \n",
+    "    # Step 4: Display top 5 destinations\n",
+    "    print(\"\\nTop 5 Ranked Destinations:\\n\")\n",
+    "    for place, score in top_5_places:\n",
+    "        print(f\"{place['Place_Name']} (Rating: {place['Rating']}, Similarity Score: {score:.4f})\")\n",
+    "\n",
+    "# Example user query\n",
+    "user_query = \"Saya ingin ke Jogjakarta dan saya suka dengan pemandangan alam. kemana saya harus pergi?\"\n",
+    "get_top_5_destinations(user_query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# prompt= \"do u know about LLM?\"\n",
+    "# response = ollama.generate(model=\"llama3.1\", prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# response['response'].strip().split('\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "d:\\Data Science\\HACKATHON\\GEN AI LLAMA HACKTIV8\\llama_venv\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:1601: FutureWarning: `clean_up_tokenization_spaces` was not set. It will be set to `True` by default. This behavior will be depracted in transformers v4.45, and will be then set to `False` by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Top 5 Ranked Destinations:\n",
+      "\n",
+      "Pulau Semak Daun (Rating: 4.0, Similarity Score: 0.6407)\n",
+      "Jembatan Merah (Rating: 4.5, Similarity Score: 0.6401)\n",
+      "Pasar Beringharjo (Rating: 4.5, Similarity Score: 0.6331)\n",
+      "Gereja Perawan Maria Tak Berdosa Surabaya (Rating: 4.8, Similarity Score: 0.6286)\n",
+      "Perpustakaan Nasional (Rating: 4.7, Similarity Score: 0.6256)\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Example user query\n",
+    "user_query = \"Saya ingin ke Surabaya dan ingin berbelanja. kemana saya harus pergi?\"\n",
+    "get_top_5_destinations(user_query)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "llama_venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

requirements.txt

@@ -0,0 +1,5 @@
+gradio==2.6.4
+sentence-transformers==2.2.2
+scikit-learn==1.2.2
+groq
+numpy==1.23.5