Update app.py

app.py

@@ -1,34 +1,6 @@
-import torch
 import streamlit as st
-from transformers import BertTokenizer, BertForQuestionAnswering
-
-# Utilize BertForQuestionAnswering model for direct start/end logits
-tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
-model = BertForQuestionAnswering.from_pretrained("bert-base-uncased")
-
-def answer_query(question, context):
-    # Preprocess using tokenizer
-    inputs = tokenizer(question, context, return_tensors="pt")
-
-    # Use model for question answering
-    with torch.no_grad():
-        outputs = model(**inputs)
-
-        # Retrieve logits directly
-        start_logits = outputs.start_logits
-        end_logits = outputs.end_logits
-
-    # Find answer span
-    answer_start = torch.argmax(start_logits)
-    answer_end = torch.argmax(end_logits) + 1
-
-    # Extract answer from context
-    answer = tokenizer.convert_tokens_to_string(
-        tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])  # Access original tokens
-    )[answer_start:answer_end]
-
-    return answer
-
+from data_preprocessing import preprocess_csv
+from question_answering import answer_from_csv
 
 # Streamlit app
 st.title("Question Answering App")
@@ -36,19 +8,22 @@ st.title("Question Answering App")
 # Textbox for user query
 user_query = st.text_input("Enter your question:")
 
-# File uploader for context
-uploaded_file = st.file_uploader("Upload a context file (txt):")
+# File uploader for context (Hugging Face specific)
+uploaded_file = st.file_uploader("Upload a CSV file from Hugging Face Hub:", type="text")
 
 if uploaded_file is not None:
-    # Read the uploaded file content
-    context = uploaded_file.read().decode("utf-8")
+  # Extract file URL
+  file_url = uploaded_file.url
+
+  # Preprocess the CSV data
+  context = preprocess_csv(file_url)
 else:
-    # Use default context if no file uploaded
-    context = "This is a sample context for demonstration purposes. You can upload your own text file for context."
+  # Use default context (optional)
+  context = "This is a sample context for demonstration purposes. You can upload your own text file or CSV file for context."
 
 # Answer the query if a question is provided
 if user_query:
-    answer = answer_query(user_query, context)
-    st.write(f"Answer: {answer}")
+  answer = answer_from_csv(user_query, context)
+  st.write(f"Answer: {answer}")
 else:
-    st.write("Please enter a question.")
+  st.write("Please enter a question.")