basic setup

app.py

@@ -1,7 +1,66 @@
 import gradio as gr
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.decomposition import PCA
+from sklearn.manifold import TSNE
 
-def greet(name):
+def greet(name, name2, name3):
     return "Hello " + name + "!!"
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+# Dummy function to simulate getting embeddings from different models
+def get_embeddings(model_name, data):
+    np.random.seed(0)  # For reproducibility
+    return np.random.rand(len(data), 128)  # Simulate 128-dimensional embeddings
+
+def visualize_embeddings(model1, model2, data):
+    # Convert input data to list
+    data = data.split(',')
+    data = [item.strip() for item in data]
+    
+    # Get embeddings
+    embeddings1 = get_embeddings(model1, data)
+    embeddings2 = get_embeddings(model2, data)
+    
+    # Combine embeddings
+    combined_embeddings = np.concatenate((embeddings1, embeddings2), axis=0)
+    
+    # Reduce dimensions using PCA for initial dimensionality reduction
+    pca = PCA(n_components=2) #, svd_solver='randomized')
+    pca_embeddings = pca.fit_transform(combined_embeddings)
+    tsne_embeddings = pca_embeddings
+    
+    # Further reduce dimensions using t-SNE
+    # tsne = TSNE(n_components=2, random_state=0)
+    # tsne_embeddings = tsne.fit_transform(pca_embeddings)
+    
+    # Plot the embeddings
+    plt.figure(figsize=(10, 5))
+    plt.scatter(tsne_embeddings[:len(data), 0], tsne_embeddings[:len(data), 1], label=model1, alpha=0.5)
+    plt.scatter(tsne_embeddings[len(data):, 0], tsne_embeddings[len(data):, 1], label=model2, alpha=0.5)
+    plt.legend()
+    plt.title('Embeddings Visualization')
+    plt.xlabel('Dimension 1')
+    plt.ylabel('Dimension 2')
+    
+    # Save the plot to a file and return the file path
+    plt.savefig('embeddings_plot.png')
+    plt.close()
+    
+    return 'embeddings_plot.png'
+
+# demo = gr.Interface(fn=greet, inputs="text", outputs="text")
+# Define Gradio interface
+# Model 1 - sentence-transformers/sentence-t5-large
+# Model 2 - nomic-ai/nomic-embed-text-v1
+demo = gr.Interface(
+    fn=visualize_embeddings,
+    inputs=[
+        gr.Textbox(label="Model 1 Name"),
+        gr.Textbox(label="Model 2 Name"),
+        gr.Textbox(lines=2, label="Data (comma-separated)")
+    ],
+    outputs="image",
+    title="Embeddings Visualizer",
+    description="Visualize embeddings from different models"
+)
 demo.launch()