Create app.py

app.py

@@ -0,0 +1,43 @@
+import gradio as gr
+import random
+import time
+from transformers import pipeline,AutoModelForSeq2SeqLM,AutoTokenizer
+
+model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+
+context=""
+
+def generate_answer(question):
+  prompt = question +". \nAnswer this question given context in next line if answer is present in context otherwise say I don't know about that. Context: \n "+context
+  inputs = tokenizer(prompt , return_tensors="pt")
+  outputs = model.generate(**inputs)
+  return (tokenizer.batch_decode(outputs, skip_special_tokens=True))
+
+def upload_file(file):
+    global context
+    with open(file.name, encoding="utf-8") as f:
+      context = f.read()
+
+with gr.Blocks() as demo:
+    file_output = gr.File()
+    upload_button = gr.UploadButton("Click to Upload a File", file_types=["txt", "pdf"])
+    upload_button.upload(upload_file, upload_button, file_output)
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.ClearButton([msg, chatbot,upload_button])
+
+    def respond(message, chat_history):
+        ans=generate_answer(message)
+
+        chat_history.append((message, f"\n {ans} "))
+        return "", chat_history
+
+    msg.submit(respond, [msg, chatbot], [msg, chatbot])
+
+    with gr.Row(visible=True) as button_row:
+        upvote_btn = gr.Button(value="👍  Upvote", interactive=True)
+        downvote_btn = gr.Button(value="👎  Downvote", interactive=True)
+
+demo.queue()
+demo.launch(debug=True)