Create app.py

app.py

@@ -0,0 +1,75 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+
+# Load the model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def load_csv(file):
+    df = pd.read_csv(file.name)
+    return df
+
+def search_similar_queries(query, df, top_k=5):
+    # Encode the query
+    query_embedding = model.encode([query])
+
+    # Encode all queries in the DataFrame
+    all_embeddings = model.encode(df['query'].tolist())
+
+    # Calculate cosine similarity
+    similarities = cosine_similarity(query_embedding, all_embeddings)[0]
+
+    # Get top-k similar queries
+    top_indices = np.argsort(similarities)[-top_k:][::-1]
+
+    results = []
+    for idx in top_indices:
+        result = {
+            'query': df.iloc[idx]['query'],
+            'similarity': similarities[idx],
+            'uber_intent': df.iloc[idx]['uber_intent'],
+            'common_intent': df.iloc[idx]['common_intent'],
+            'sub_common_intent': df.iloc[idx]['sub_common_intent'],
+            'fsc': df.iloc[idx]['fsc'],
+            'language': df.iloc[idx]['language'],
+            'Name': df.iloc[idx]['Name']
+        }
+        results.append(result)
+
+    return results
+
+def gradio_interface(csv_file, query, top_k):
+    df = load_csv(csv_file)
+    results = search_similar_queries(query, df, top_k)
+    
+    output = ""
+    for i, result in enumerate(results, 1):
+        output += f"Result {i}:\n"
+        output += f"Query: {result['query']}\n"
+        output += f"Similarity: {result['similarity']:.4f}\n"
+        output += f"Uber Intent: {result['uber_intent']}\n"
+        output += f"Common Intent: {result['common_intent']}\n"
+        output += f"Sub-Common Intent: {result['sub_common_intent']}\n"
+        output += f"FSC: {result['fsc']}\n"
+        output += f"Language: {result['language']}\n"
+        output += f"Name: {result['Name']}\n\n"
+    
+    return output
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=gradio_interface,
+    inputs=[
+        gr.File(label="Upload CSV file"),
+        gr.Textbox(label="Enter your query"),
+        gr.Slider(minimum=1, maximum=10, step=1, label="Top-K results", value=5)
+    ],
+    outputs=gr.Textbox(label="Results"),
+    title="Query Similarity Search",
+    description="Upload a CSV file, enter a query, and find similar queries with associated metadata."
+)
+
+# Launch the interface
+iface.launch()