tomcat commited on
Commit
2591fef
1 Parent(s): c2d3e70

Create new file

Browse files
Files changed (1) hide show
  1. app.py +29 -0
app.py ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import gradio as gr
2
+ from transformers import pipeline
3
+
4
+ pp_en = pipeline("question-answering",model="deepset/roberta-base-squad2")
5
+ pp_ch = pipeline("question-answering",model="luhua/chinese_pretrain_mrc_roberta_wwm_ext_large")
6
+
7
+ def qa_fn(ask,ctxt,model):
8
+ pp = (pp_en if model=="deepset" else pp_ch);
9
+ ret = pp(context=ctxt, question=ask);
10
+ ret['entity']='Answer';
11
+ return {"text":ctxt,"entities":[ret]}, ret['answer'], ret['score']
12
+ #注意HighlightedText的用法。有两种不同用法:https://gradio.app/named_entity_recognition/
13
+ # 一种是list of dict ,一种是list of tuple. 详细用法参考https://gradio.app/named_entity_recognition/吧
14
+
15
+ samples= [["乔治的哥哥叫什么名字?","我是小猪佩奇,我是乔治的哥哥,我家住在北京"],["乔治住在哪里呀?","我是小猪佩奇,我是乔治的哥哥,我的家在北京颐和园"]];
16
+ introStr = "用于演示使用人工智能自动寻找问题答案,这将是一种更加高效便捷的新型信息检索方式。";
17
+ titleStr ="智能问答演示程序";
18
+
19
+ demo = gr.Interface(qa_fn,
20
+ inputs=[gr.Textbox(label="Question",placeholder='请输入问题'),
21
+ gr.Textbox(label="Context",lines=10,placeholder="请输入一段文本"),
22
+ gr.Radio(["deepset","chinese"],label="Select Model", value="deepset"),
23
+ ],
24
+ outputs=[gr.HighlightedText(label='答案位置'),gr.Textbox(label="答案"),gr.Number(label="Score")],
25
+ examples=samples,
26
+ description=introStr,
27
+ title=titleStr);
28
+
29
+ demo.launch()