Update app.py

app.py

@@ -1,12 +1,13 @@
-# 安装依赖
-!pip install datasets sentence-transformers transformers torch
-
-# 导入库
+# 导入必要的库
+import gradio as gr
 from datasets import load_dataset
 import numpy as np
 from sentence_transformers import SentenceTransformer, util
 from transformers import pipeline
 
+# 安装依赖（在Hugging Face Spaces中可省略，若空间环境未预装相关库可保留）
+#!pip install datasets sentence-transformers transformers torch
+
 # 加载数据集
 dataset = load_dataset("Pradeep016/career-guidance-qa-dataset", split="train")
 # 过滤无效数据（确保question和answer非空）
@@ -31,6 +32,7 @@ embedder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
 # 预计算知识库嵌入向量
 knowledge_embeddings = embedder.encode(knowledge_base, convert_to_tensor=True)
 
+# 智能问答函数
 def career_qa(user_input):
     # 1. 语义搜索匹配相关职位
     input_embedding = embedder.encode(user_input, convert_to_tensor=True)
@@ -55,13 +57,18 @@ def career_qa(user_input):
         })
     return results
 
-# 用户输入职业关键词
-user_query = "零售经理"
-results = career_qa(user_query)
+# Gradio界面定义
+def demo(user_input):
+    results = career_qa(user_input)
+    output = "\n".join([f"📌 {res['职位名称']}\n{res['简介']}\n" for res in results])
+    return output
 
-# 输出结果
-for res in results:
-    print(f"职位：{res['职位名称']}")
-    print(f"简介：{res['简介']}")
-    print(f"置信度：{res['置信度']:.2f}\n")
+iface = gr.Interface(
+    fn=demo,
+    inputs=gr.Textbox(label="输入职业关键词（如：零售经理）"),
+    outputs=gr.Textbox(label="职位介绍"),
+    title="职业咨询智能问答",
+)
 
+if __name__ == "__main__":
+    iface.launch()