Create app.py

app.py

@@ -0,0 +1,37 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the summarization model pipeline
+summarizer = pipeline("summarization", model="Falconsai/text_summarization")
+
+# Define the function to handle dynamic chunking of text
+def summarize_text(text):
+    # Calculate dynamic chunk size (for example, we assume a max chunk of 1024 characters)
+    max_chunk_size = 1024  # Can be adjusted based on model's token limit (often 1024-2048 tokens)
+    
+    # Split the text into chunks if it's longer than the max chunk size
+    text_chunks = []
+    if len(text) > max_chunk_size:
+        # Calculate chunk size dynamically based on input length
+        chunk_size = max_chunk_size if len(text) > max_chunk_size else len(text)
+        text_chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size)]
+    else:
+        # If the text is small enough, use it as one chunk
+        text_chunks = [text]
+    
+    # Summarize each chunk
+    summaries = [summarizer(chunk)[0]['summary_text'] for chunk in text_chunks]
+    
+    # Combine all summaries into one
+    full_summary = " ".join(summaries)
+    return full_summary
+
+# Set up the Gradio interface
+interface = gr.Interface(fn=summarize_text, 
+                         inputs="text", 
+                         outputs="text",
+                         title="Text Summarizer", 
+                         description="Enter long text to get a detailed summarized version.")
+
+# Launch the Gradio interface
+interface.launch(share=True)