Update app.py

app.py

@@ -1,43 +1,50 @@
+
 import streamlit as st
-import pandas as pd
-from transformers import pipeline, AutoTokenizer, AutoModelForQuestionAnswering
+from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
 
 @st.cache(allow_output_mutation=True)
 def load_qa_model():
-    model_name = "google/mobilebert-uncased"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model_name = "mrm8488/mobilebert-uncased-finetuned-squadv2"
     model = AutoModelForQuestionAnswering.from_pretrained(model_name)
-    qa_pipeline = pipeline("question-answering", model=model, tokenizer=tokenizer)
-    return qa_pipeline
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    qa = pipeline("question-answering", model=model, tokenizer=tokenizer)
+    return qa
+
+def preprocess_text(text):
+    # Remove special characters and punctuation
+    text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
+    # Convert to lowercase
+    text = text.lower()
+    return text
+
+def format_answer(answer):
+    # Add answer formatting logic here
+    # For example, add bold formatting
+    return f**{answer}**
+
+def get_answers(qa, question, text, max, min, do_sample):
+    try:
+        answers = qa(question=question, context=text, max_answer_len=max, min_answer_len=min, do_sample=do_sample)
+        return format_answer(answers['answer'])
+    except Exception as e:
+        st.error(f"Error: {str(e)}")
 
 qa = load_qa_model()
 
-def process_batch(data):
-    results = []
-    for index, row in data.iterrows():
-        answer = qa(question=row['Question'], context=row['Article'])
-        results.append({
-            'Question': row['Question'],
-            'Article': row['Article'],
-            'Answer': answer['answer'],
-            'Score': answer['score']
-        })
-    return results
-
-st.title("Batch Question Answering App")
-
-uploaded_file = st.file_uploader("Upload a CSV file", type="csv")
-
-if uploaded_file is not None:
-    data = pd.read_csv(uploaded_file)
-
-    if st.button("Process Batch"):
-        with st.spinner("Processing Batch..."):
-            results = process_batch(data)
-            st.write("Batch Processing Results:")
-            for result in results:
-                st.write("Question:", result['Question'])
-                st.write("Article:", result['Article'])
-                st.write("Answer:", result['Answer'])
-                st.write("Score:", result['Score'])
-                st.write("------")
+st.title("Ask Questions about your Text")
+sentence = st.text_area('Please paste your article :', height=30)
+question = st.text_input("Questions from this article?")
+button = st.button("Get me Answers")
+
+with st.sidebar:
+    max = st.slider('Select max answer length', 50, 500, step=10, value=150)
+    min = st.slider('Select min answer length', 10, 450, step=10, value=50)
+    do_sample = st.checkbox("Do sample", value=False)
+
+if button and sentence and question:
+    with st.spinner("Discovering Answers.."):
+        text = preprocess_text(sentence)
+        answer = get_answers(qa, question, text, max, min, do_sample)
+        st.write(answer)
+else:
+    st.error("Please enter a question and text!")