Create app.py

app.py

@@ -0,0 +1,42 @@
+import gradio as gr
+from keybert import KeyBERT
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import nltk
+nltk.download('punkt_tab')
+
+device="cuda"
+kw_model = KeyBERT()
+tokenizer = AutoTokenizer.from_pretrained("itskavya/t5-small-finetuned-titlegen2") # this is where the model is saved on hf, can load it n use it
+model = AutoModelForSeq2SeqLM.from_pretrained("itskavya/t5-small-finetuned-titlegen2")
+model.to(device)
+max_input_length=512
+
+def predict(text):
+  inputs = ["summarize: " + text]
+
+  inputs = tokenizer(inputs, max_length=max_input_length, truncation=True, return_tensors="pt").to(device)
+  output = model.generate(**inputs, num_beams=8, do_sample=True, min_length=10, max_length=64) # num beans 8 means explore 8 sequences, sample introduces randomness
+  decoded_output = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
+  predicted_title = nltk.sent_tokenize(decoded_output.strip())[0]
+
+  keywords = kw_model.extract_keywords(text, keyphrase_ngram_range=(1, 2), top_n=5)
+  formatted_keywords = ", ".join([kw[0] for kw in keywords])
+
+  return predicted_title, formatted_keywords
+
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=predict, # function to call for prediction
+    inputs=[ # inputs that user will provide
+        gr.Textbox(label="Enter abstract..."),
+
+
+    ],
+    outputs=[gr.Textbox(label="Title"), # outputs for title n keyword
+             gr.Textbox(label="Keywords"),],
+    title="Automated Title and Keyword Extraction from Research Abstracts",
+    description="This app uses the abstract of a scientific research article to automatically generate relevant and impactful titles and keywords!"
+)
+
+# Launch the app
+interface.launch()