Upload 2 files

app.py

@@ -0,0 +1,58 @@
+import gradio as gr
+import torch
+from transformers import BartTokenizer, BartForConditionalGeneration
+
+# Initialize tokenizers and models for both healthcare and AI
+healthcare_model_name = 'facebook/bart-large-cnn'
+ai_model_name = 'facebook/bart-large-xsum'
+
+healthcare_tokenizer = BartTokenizer.from_pretrained(healthcare_model_name)
+ai_tokenizer = BartTokenizer.from_pretrained(ai_model_name)
+
+healthcare_model = BartForConditionalGeneration.from_pretrained(healthcare_model_name)
+ai_model = BartForConditionalGeneration.from_pretrained(ai_model_name)
+
+# Summarization function
+def generate_summary(text, tokenizer, model):
+    inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True, padding="max_length")
+    with torch.no_grad():
+        outputs = model.generate(inputs["input_ids"], max_length=150, num_beams=5, no_repeat_ngram_size=2, early_stopping=True)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Functions for each agent
+def healthcare_agent(abstract):
+    return generate_summary(abstract, healthcare_tokenizer, healthcare_model)
+
+def ai_agent(abstract):
+    return generate_summary(abstract, ai_tokenizer, ai_model)
+
+# Function to generate implications based on both agents' insights
+def generate_implications(healthcare_summary, ai_summary):
+    healthcare_implication = f"Healthcare Implications: {healthcare_summary} The healthcare sector can leverage these findings to improve patient care and treatment outcomes."
+    ai_implication = f"AI Implications: {ai_summary} These insights can further enhance AI models, making them more applicable in real-world healthcare scenarios."
+    combined_implications = f"{healthcare_implication}\n\n{ai_implication}"
+    return combined_implications
+
+# Gradio Interface function
+def summarize_and_generate_implications(abstract):
+    healthcare_summary = healthcare_agent(abstract)
+    ai_summary = ai_agent(abstract)
+    implications = generate_implications(healthcare_summary, ai_summary)
+    return healthcare_summary, ai_summary, implications
+
+# Creating the Gradio interface
+interface = gr.Interface(
+    fn=summarize_and_generate_implications, 
+    inputs=gr.Textbox(label="Abstract", placeholder="Enter the abstract of a research paper..."), 
+    outputs=[
+        gr.Textbox(label="Healthcare Summary"), 
+        gr.Textbox(label="AI Summary"),
+        gr.Textbox(label="Implications")
+    ],
+    live=True,
+    title="Research Paper Summarization and Implications",
+    description="This app generates summaries for healthcare and AI domains and provides implications for each."
+)
+
+# Launch the Gradio interface
+interface.launch(share=True)  # share=True will generate a public link

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+gradio
+pandas