diff --git a/WebServer/AIPython/ai-trainer.py b/WebServer/AIPython/ai-trainer.py
index 3e2a0885..9763ab8a 100644
--- a/WebServer/AIPython/ai-trainer.py
+++ b/WebServer/AIPython/ai-trainer.py
@@ -1,73 +1,78 @@
 import pandas as pd
 import numpy as np
 import matplotlib.pyplot as plt
+import datapuller
 import os
 from sklearn.model_selection import train_test_split
 from keras import Sequential, layers, optimizers
 
-# Get the CWD for pathing due to being called from C# now
-SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
-DATA_DIR = os.path.join(SCRIPT_DIR, "data")
+def TrainAI():
+    # Pull New Data
+    datapuller.pull()
 
-# Load the dataset
-dataset = pd.read_parquet(os.path.join(DATA_DIR, "stocks.parquet"))
-X = dataset.drop('Volatility_5', axis=1)
-Y = dataset['Volatility_5']
+    # Get the CWD for pathing due to being called from C# now
+    SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+    DATA_DIR = os.path.join(SCRIPT_DIR, "data")
 
-# Show the datatypes
-print(dataset.dtypes)
+    # Load the dataset
+    dataset = pd.read_parquet(os.path.join(DATA_DIR, "stocks.parquet"))
+    X = dataset.drop('Volatility_5', axis=1)
+    Y = dataset['Volatility_5']
 
-# Split out the test and train
-train_features, test_features, train_labels, test_labels = train_test_split(X, Y, test_size=0.2)
+    # Show the datatypes
+    print(dataset.dtypes)
 
-# Create a normalizer to nomralize the data
-normalizer = layers.Normalization(axis=-1)
-normalizer.adapt(np.array(train_features))
+    # Split out the test and train
+    train_features, test_features, train_labels, test_labels = train_test_split(X, Y, test_size=0.2)
 
-# Start with a linear model
-dnn_linear_model = Sequential([
-    layers.Input(shape=(9,)), # Explicitly tell Keras there are 9 features
-    normalizer,
-    layers.Dense(64, activation='relu'),
-    layers.Dense(64, activation='relu'),
-    layers.Dense(1)
-])
+    # Create a normalizer to nomralize the data
+    normalizer = layers.Normalization(axis=-1)
+    normalizer.adapt(np.array(train_features))
 
-# Configure the model
-dnn_linear_model.compile(
-    optimizer=optimizers.Adam(learning_rate=0.001),
-    loss='mean_absolute_error'
-)
+    # Start with a linear model
+    dnn_linear_model = Sequential([
+        layers.Input(shape=(9,)), # Explicitly tell Keras there are 9 features
+        normalizer,
+        layers.Dense(64, activation='relu'),
+        layers.Dense(64, activation='relu'),
+        layers.Dense(1)
+    ])
 
-# Show the summary before training the model
-dnn_linear_model.summary()
+    # Configure the model
+    dnn_linear_model.compile(
+        optimizer=optimizers.Adam(learning_rate=0.001),
+        loss='mean_absolute_error'
+    )
 
-# Train the model
-Training_Data = dnn_linear_model.fit( 
-    train_features,
-    train_labels,
-    epochs=100,
-    # Show progress
-    verbose=1,
-    # Calculate validation results on 20% of the training data.
-    validation_split = 0.2
-)
+    # Show the summary before training the model
+    dnn_linear_model.summary()
 
-# Predict
-test_predictions = dnn_linear_model.predict(test_features).flatten()
-a = plt.axes(aspect='equal')
-plt.scatter(test_labels, test_predictions)
-plt.xlabel('True Values')
-plt.ylabel('Predictions')
-lims = [0, 50]
-plt.xlim(lims)
-plt.ylim(lims)
-_ = plt.plot(lims, lims)
+    # Train the model
+    Training_Data = dnn_linear_model.fit( 
+        train_features,
+        train_labels,
+        epochs=100,
+        # Show progress
+        verbose=1,
+        # Calculate validation results on 20% of the training data.
+        validation_split = 0.2
+    )
+
+    # Predict
+    test_predictions = dnn_linear_model.predict(test_features).flatten()
+    a = plt.axes(aspect='equal')
+    plt.scatter(test_labels, test_predictions)
+    plt.xlabel('True Values')
+    plt.ylabel('Predictions')
+    lims = [0, 50]
+    plt.xlim(lims)
+    plt.ylim(lims)
+    _ = plt.plot(lims, lims)
 
 
-test_results = dnn_linear_model.evaluate(
-    test_features, test_labels, verbose=0
-)
+    test_results = dnn_linear_model.evaluate(
+        test_features, test_labels, verbose=0
+    )
 
-# Save the model
-dnn_linear_model.save(os.path.join(DATA_DIR, "model.keras"))
\ No newline at end of file
+    # Save the model
+    dnn_linear_model.save(os.path.join(DATA_DIR, "model.keras"))
\ No newline at end of file