diff --git a/emotion_detection.py b/emotion_detection.py
new file mode 100644
index 000000000..c371ce1ad
--- /dev/null
+++ b/emotion_detection.py
@@ -0,0 +1,39 @@
+import requests
+import json
+
+def emotion_detector(text_to_analyse):
+    url = 'https://sn-watson-emotion.labs.skills.network/v1/watson.runtime.nlp.v1/NlpService/EmotionPredict'
+    headers = {"grpc-metadata-mm-model-id": "emotion_aggregated-workflow_lang_en_stock"}
+    myobj = {"raw_document": { "text": text_to_analyse }}
+
+    try:
+        response = requests.post(url, json=myobj, headers=headers)
+        response.raise_for_status()  # Lanza una excepción para errores HTTP
+        res = response.json()  # Parsea directamente el JSON de la respuesta
+        
+        # Extraer emociones relevantes
+        emotions = res.get('emotionPredictions', [{}])[0].get('emotion', {})
+        extracted_emotions = {
+            'anger': emotions.get('anger', 0),
+            'disgust': emotions.get('disgust', 0),
+            'fear': emotions.get('fear', 0),
+            'joy': emotions.get('joy', 0),
+            'sadness': emotions.get('sadness', 0)
+        }
+
+        # Determinar la emoción dominante
+        dominant_emotion = max(extracted_emotions, key=extracted_emotions.get)
+        extracted_emotions['dominant_emotion'] = dominant_emotion
+
+        return extracted_emotions
+
+    except requests.exceptions.RequestException as e:
+        return {"error": f"Request failed: {e}"}
+
+# Ejemplo de uso
+text = "I am extremely happy today!"
+result = emotion_detector(text)
+print(result)
+
+
+
diff --git a/server.py b/server.py
new file mode 100644
index 000000000..140e53f96
--- /dev/null
+++ b/server.py
@@ -0,0 +1,82 @@
+"""
+Flask application for detecting emotions from text input using an external API.
+"""
+from flask import Flask, render_template, request, jsonify
+import requests
+# Initialize Flask app
+app = Flask(__name__)
+def emotion_detector(text_to_analyze):
+    """
+    Sends the given text to the Watson Emotion API for analysis and extracts emotions.
+
+    Args:
+        text_to_analyze (str): The text to be analyzed for emotions.
+
+    Returns:
+        dict: Dictionary containing detected emotions and the dominant emotion.
+              Returns an error message if no emotions are detected or if there is an issue.
+    """
+    url = (
+    "https://sn-watson-emotion.labs.skills.network/v1/"
+    "watson.runtime.nlp.v1/NlpService/EmotionPredict"
+    )
+
+    headers = {"grpc-metadata-mm-model-id": "emotion_aggregated-workflow_lang_en_stock"}
+    input_json = {"raw_document": {"text": text_to_analyze}}
+
+    try:
+        response = requests.post(url, json=input_json, headers=headers, timeout=10)
+        response.raise_for_status()
+        response_data = response.json()
+
+        if "emotion_predictions" not in response_data or not response_data["emotion_predictions"]:
+            return None
+
+        emotions = response_data["emotion_predictions"][0]
+        extracted_emotions = {
+            "anger": emotions.get("anger", 0),
+            "disgust": emotions.get("disgust", 0),
+            "fear": emotions.get("fear", 0),
+            "joy": emotions.get("joy", 0),
+            "sadness": emotions.get("sadness", 0),
+        }
+
+        dominant_emotion = max(extracted_emotions, key=extracted_emotions.get)
+        extracted_emotions["dominant_emotion"] = dominant_emotion
+
+        return extracted_emotions
+
+    except requests.exceptions.Timeout:
+        return {"error": "Request timed out"}
+    except requests.exceptions.RequestException as err:
+        return {"error": str(err)}
+
+@app.route('/')
+def index():
+    """
+    Serves the index page.
+    """
+    return render_template('index.html')
+
+@app.route('/detect_emotion', methods=['POST'])
+def detect_emotion():
+    """
+    API endpoint that receives text input, analyzes its emotions, and returns the results.
+
+    Returns:
+        JSON response containing detected emotions or an error message.
+    """
+    text = request.json.get("text", "").strip()
+
+    if not text:
+        return jsonify({"error": "No text provided"})
+
+    result = emotion_detector(text)
+
+    if result and result.get("dominant_emotion"):
+        return jsonify(result)
+
+    return jsonify({"error": "Invalid text! Please try again!"})
+
+if __name__ == '__main__':
+    app.run(debug=True)
diff --git a/setup.py b/setup.py
new file mode 100644
index 000000000..aacc3035a
--- /dev/null
+++ b/setup.py
@@ -0,0 +1,20 @@
+from setuptools import setup, find_packages
+
+setup(
+    name="EmotionDetection",
+    version="1.0.0",
+    packages=find_packages(),
+    install_requires=[
+        "requests",
+    ],
+    author="Edson Ramirez",
+    author_email="ramirez_edson@hotmail.com",
+    description="A package for detecting emotions from text using Watson API",
+    url="https://github.com/yourusername/EmotionDetection",
+    classifiers=[
+        "Programming Language :: Python :: 3",
+        "License :: OSI Approved :: MIT License",
+        "Operating System :: OS Independent",
+    ],
+    python_requires=">=3.6",
+)
diff --git a/test_emotion_detection.py b/test_emotion_detection.py
new file mode 100644
index 000000000..e1d3762bf
--- /dev/null
+++ b/test_emotion_detection.py
@@ -0,0 +1,33 @@
+import unittest
+from emotion_detection import emotion_detector
+
+class TestEmotionDetection(unittest.TestCase):
+
+    def test_joy(self):
+        text = "I am glad this happened"
+        result = emotion_detector(text)
+        self.assertEqual(result["dominant_emotion"], "joy")
+
+    def test_anger(self):
+        text = "I am really mad about this"
+        result = emotion_detector(text)
+        self.assertEqual(result["dominant_emotion"], "anger")
+
+    def test_disgust(self):
+        text = "I feel disgusted just hearing about this"
+        result = emotion_detector(text)
+        self.assertEqual(result["dominant_emotion"], "disgust")
+
+    def test_sadness(self):
+        text = "I am so sad about this"
+        result = emotion_detector(text)
+        self.assertEqual(result["dominant_emotion"], "sadness")
+
+    def test_fear(self):
+        text = "I am really afraid that this will happen"
+        result = emotion_detector(text)
+        self.assertEqual(result["dominant_emotion"], "fear")
+
+if __name__ == "__main__":
+    unittest.main()
+