Initial commit

test_app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import tensorflow as tf
+import pandas as pd
+from transformers import AutoTokenizer, TFAutoModelForQuestionAnswering
+
+# Load the pre-trained model and tokenizer
+# Import required libraries
+# Load the tokenizer and model
+model_name = "distilbert-base-uncased-distilled-squad"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = TFAutoModelForQuestionAnswering.from_pretrained(model_name)
+
+def read_text_file(file):
+    with open(file.name) as f:
+        content = f.read()
+    return content
+
+
+# Define a function to perform the question answering
+def answer_question(doc, question):
+    # context = doc.read().decode('utf-8')
+    context = read_text_file(doc)
+
+    # Tokenize the context and question
+    inputs = tokenizer(question, context, return_tensors="tf")
+
+    # Get the answer span
+    start_scores = model(inputs)[0]
+    end_scores = model(inputs)[1]
+    answer_start = tf.argmax(start_scores, axis=1).numpy()[0]
+    answer_end = tf.argmax(end_scores, axis=1).numpy()[0] + 1
+    answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][answer_start:answer_end]))
+    return answer
+
+# Create a Gradio interface
+interface = gr.Interface(
+    fn=answer_question,
+    inputs=[
+        gr.inputs.File(label="doc"),
+        gr.inputs.Textbox(label="question")
+    ],
+    outputs=gr.outputs.Textbox(label="answer"),
+    title="Document Question Answering",
+    description="Upload a document and ask a question about its contents.",
+    theme="default"
+)
+
+# Launch the interface
+interface.launch()