Create app.py

app.py

@@ -0,0 +1,57 @@
+import gradio as gr
+from sentence_transformers import SentenceTransformer, util
+import ast
+
+# Load the SentenceTransformer model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def compare_embeddings(query, text_lists):
+    # Convert string representation of lists to actual lists
+    try:
+        lists = ast.literal_eval(text_lists)
+    except:
+        return "Error: Invalid input format for text lists."
+
+    # Encode the query
+    query_embedding = model.encode(query, convert_to_tensor=True)
+
+    results = []
+    for i, lst in enumerate(lists):
+        # Encode the list items
+        list_embeddings = model.encode(lst, convert_to_tensor=True)
+
+        # Calculate cosine similarity
+        similarities = util.pytorch_cos_sim(query_embedding, list_embeddings)[0]
+
+        # Calculate average similarity for the list
+        avg_similarity = similarities.mean().item()
+
+        results.append((i, avg_similarity))
+
+    # Sort results by similarity score (descending)
+    results.sort(key=lambda x: x[1], reverse=True)
+
+    # Format the output
+    output = ""
+    for i, score in results:
+        output += f"List {i}: Similarity score {score:.4f}\n"
+        for j, item in enumerate(lists[i]):
+            output += f"  Element {j}: {item}\n"
+        output += "\n"
+
+    return output
+
+# Create the Gradio interface
+iface = gr.Interface(
+    fn=compare_embeddings,
+    inputs=[
+        gr.Textbox(label="Query"),
+        gr.Textbox(label="Text Lists (in format [['', ''], ['', ''], ['', '']])"),
+    ],
+    outputs=gr.Textbox(label="Results"),
+    title="Embedding Comparison App",
+    description="Compare a query with multiple lists of text and find the most relevant list."
+)
+
+# Launch the app
+iface.launch()