Create app.py

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import numpy as np
+import h5py
+import faiss
+import json
+from sentence_transformers import SentenceTransformer
+
+# Load embeddings and metadata
+def load_data():
+    with h5py.File('patent_embeddings.h5', 'r') as f:
+        embeddings = f['embeddings'][:]
+        patent_numbers = f['patent_numbers'][:]
+    
+    metadata = {}
+    with open('patent_metadata.jsonl', 'r') as f:
+        for line in f:
+            data = json.loads(line)
+            metadata[data['patent_number']] = data
+    
+    return embeddings, patent_numbers, metadata
+
+embeddings, patent_numbers, metadata = load_data()
+
+# Create FAISS index
+index = faiss.IndexFlatL2(embeddings.shape[1])
+index.add(embeddings)
+
+# Load BERT model for encoding search queries
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def search(query, top_k=5):
+    # Encode the query
+    query_embedding = model.encode([query])[0]
+    
+    # Perform similarity search
+    distances, indices = index.search(np.array([query_embedding]), top_k)
+    
+    results = []
+    for i, idx in enumerate(indices[0]):
+        patent_number = patent_numbers[idx]
+        patent_data = metadata[patent_number]
+        result = f"Patent Number: {patent_number}\n"
+        result += f"Abstract: {patent_data['abstract'][:200]}...\n"
+        result += f"Similarity Score: {1 - distances[0][i]:.4f}\n\n"
+        results.append(result)
+    
+    return "\n".join(results)
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=search,
+    inputs=gr.Textbox(lines=2, placeholder="Enter your search query here..."),
+    outputs=gr.Textbox(lines=10, label="Search Results"),
+    title="Patent Similarity Search",
+    description="Enter a query to find similar patents based on their embeddings."
+)
+
+iface.launch()