Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+from transformers.pipelines import pipeline
+import PyPDF2
+
+# Load T5 model and tokenizer
+model_name = "t5-large"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+qa_pipeline = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
+
+def read_pdf(file):
+    reader = PyPDF2.PdfFileReader(file)
+    text = ""
+    for page_num in range(reader.numPages):
+        page = reader.getPage(page_num)
+        text += page.extract_text()
+    return text
+
+def answer_question(pdf, question):
+    context = read_pdf(pdf)
+    input_text = f"question: {question} context: {context}"
+    response = qa_pipeline(input_text, max_length=512, do_sample=False)
+    return response[0]['generated_text']
+
+# Define Gradio interface
+iface = gr.Interface(
+    fn=answer_question,
+    inputs=[gr.inputs.File(type="file", label="Upload PDF"), gr.inputs.Textbox(lines=2, placeholder="Ask a question")],
+    outputs=gr.outputs.Textbox(label="Answer"),
+    title="PDF Q&A with T5"
+)
+
+if __name__ == "__main__":
+    iface.launch()