Update app.py

app.py

@@ -8,39 +8,35 @@ import gradio as gr
 import openai
 import re
 
-# 設置OpenAI API密鑰
 openai.api_key = 'sk-zK6OrDxP5DvDdAQqnR_nEuUL3UrZf_4W7qvYj1uphjT3BlbkFJdmZAxlxUCFv92NnnMwSB15FhpmiDZSfG2QPueobSQA'
 
 def load_or_create_model_and_embeddings(model_name, data_file, output_dir):
     model_path = os.path.join(output_dir, 'saved_model')
     embeddings_path = os.path.join(output_dir, 'corpus_embeddings.pt')
     if os.path.exists(model_path) and os.path.exists(embeddings_path):
-        print("載入已保存的模型和嵌入...")
         model = SentenceTransformer(model_path)
         embeddings = torch.load(embeddings_path)
         with open(data_file, 'r', encoding='utf-8') as f:
             data = json.load(f)
     else:
-        print("創建新的模型和嵌入...")
         model = SentenceTransformer(model_name)
         with open(data_file, 'r', encoding='utf-8') as f:
             data = json.load(f)
         texts = [item['text'] for item in data]
         embeddings = model.encode(texts, convert_to_tensor=True)
-        print("保存模型和嵌入...")
         model.save(model_path)
         torch.save(embeddings, embeddings_path)
     return model, embeddings, data
 
-# 設置參數
+
 model_name = 'sentence-transformers/all-MiniLM-L6-v2'
 data_file = 'labeled_cti_data.json'
 output_dir = '.'
 
-# 載入或創建模型和嵌入
+
 model, embeddings, data = load_or_create_model_and_embeddings(model_name, data_file, output_dir)
 
-# 創建 Faiss 索引
+
 dimension = embeddings.shape[1]
 index = faiss.IndexFlatL2(dimension)
 index.add(embeddings.cpu().numpy().astype('float32'))
@@ -73,7 +69,7 @@ def semantic_search(query, top_k=5):
     results = []
     for distance, idx in zip(distances[0], indices[0]):
         similarity_score = 1 - distance / 2  # 將距離轉換為相似度分數
-        if similarity_score >= 0.45:  # 只添加相似度大於等於0.3的結果
+        if similarity_score >= 0.45:  # 只添加相似度大於等於0.45的結果
             results.append({
                 'text': data[idx]['text'],
                 'entities': data[idx]['entities'],
@@ -177,7 +173,7 @@ def audio_to_search(audio):
     combined_output = f""
     return combined_output, transcription
 
-# 示例問題
+# 範例問題
 example_queries = [
     "Tell me about recent cyber attacks from Russia",
     "What APT groups are targeting Ukraine?",
@@ -205,7 +201,7 @@ footer {display:none !important}
 # 創建Gradio界面
 with gr.Blocks(css=custom_css) as iface:
     gr.Markdown("# AskCTI", elem_classes=["text-3xl"])
-    gr.Markdown("使用文字或使用語音輸入問題或關鍵字查詢相關情資威脅情報，結果將顯示前5個最相關的結果。", elem_classes=["text-xl"])
+    gr.Markdown("使用文字或使用語音輸入問題或關鍵字查詢相關情資威脅情報，結果將顯示前 5 個最相關的結果。", elem_classes=["text-xl"])
     
     with gr.Row(equal_height=True):
         with gr.Column(scale=1, min_width=300):