diff --git a/api.py b/api.py
new file mode 100644
index 000000000..55fe2af76
--- /dev/null
+++ b/api.py
@@ -0,0 +1,47 @@
+from flask import Flask, request, jsonify
+import psycopg2
+
+app = Flask(__name__)
+
+# Database connection
+DB_CONFIG = {
+    "dbname": "your_db",
+    "user": "your_user",
+    "password": "your_password",
+    "host": "your_host",
+    "port": "your_port"
+}
+
+def connect_db():
+    try:
+        conn = psycopg2.connect(**DB_CONFIG)
+        cursor = conn.cursor()
+        return conn, cursor
+    except Exception as e:
+        print(f"Database connection error: {e}")
+        return None, None
+
+@app.route('/conversation-summary', methods=['GET'])
+def conversation_summary():
+    conn, cursor = connect_db()
+    if conn is None:
+        return jsonify({"error": "Database connection failed"}), 500
+
+    cursor.execute("SELECT user_id, COUNT(*) FROM conversations GROUP BY user_id")
+    data = cursor.fetchall()
+    conn.close()
+    return jsonify({"summary": data})
+
+@app.route('/data-stats', methods=['GET'])
+def data_stats():
+    conn, cursor = connect_db()
+    if conn is None:
+        return jsonify({"error": "Database connection failed"}), 500
+
+    cursor.execute("SELECT COUNT(*) FROM conversations")
+    count = cursor.fetchone()
+    conn.close()
+    return jsonify({"total_conversations": count[0]})
+
+if __name__ == '__main__':
+    app.run(debug=True)
diff --git a/data_pipeline.py b/data_pipeline.py
new file mode 100644
index 000000000..a33a1e21e
--- /dev/null
+++ b/data_pipeline.py
@@ -0,0 +1,70 @@
+# Task 1: Data Pipeline Setup (data_pipeline.py)
+import psycopg2
+import pandas as pd
+import requests
+
+# Database connection
+DB_CONFIG = {
+    "dbname": "your_db",
+    "user": "your_user",
+    "password": "your_password",
+    "host": "your_host",
+    "port": "your_port"
+}
+
+def connect_db():
+    try:
+        conn = psycopg2.connect(**DB_CONFIG)
+        cursor = conn.cursor()
+        return conn, cursor
+    except Exception as e:
+        print(f"Database connection error: {e}")
+        return None, None
+
+# Create table
+def setup_database():
+    conn, cursor = connect_db()
+    if conn is None:
+        return
+    
+    cursor.execute('''
+    CREATE TABLE IF NOT EXISTS conversations (
+        id SERIAL PRIMARY KEY,
+        user_id VARCHAR(50),
+        timestamp TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
+        query TEXT,
+        generated_response TEXT
+    );
+    ''')
+    conn.commit()
+    conn.close()
+    print("Database setup completed.")
+
+# ETL Pipeline
+def etl_pipeline():
+    url = "https://example.com/amazon_reviews.json"  # Replace with actual dataset link
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        data = response.json()
+        df = pd.DataFrame(data)
+    except Exception as e:
+        print(f"Error fetching data: {e}")
+        return
+    
+    conn, cursor = connect_db()
+    if conn is None:
+        return
+    
+    for _, row in df.iterrows():
+        cursor.execute("""
+            INSERT INTO conversations (user_id, query, generated_response)
+            VALUES (%s, %s, %s)
+        """, (row['user_id'], row['review_text'], row['response_text']))
+    conn.commit()
+    conn.close()
+    print("ETL Process Completed")
+
+if __name__ == "__main__":
+    setup_database()
+    etl_pipeline()
diff --git a/web_crawler.py b/web_crawler.py
new file mode 100644
index 000000000..512aaa844
--- /dev/null
+++ b/web_crawler.py
@@ -0,0 +1,19 @@
+import requests
+from bs4 import BeautifulSoup
+
+def crawl_wikipedia():
+    url = "https://en.wikipedia.org/wiki/Natural_language_processing"
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, 'html.parser')
+        text = soup.get_text()
+        return text[:1000]  # Return only first 1000 characters for preview
+    except Exception as e:
+        print(f"Error fetching Wikipedia data: {e}")
+        return None
+
+if __name__ == "__main__":
+    data = crawl_wikipedia()
+    if data:
+        print("Extracted Wikipedia Data:", data)
\ No newline at end of file