Create utils/summarizer.py

utils/summarizer.py

@@ -0,0 +1,28 @@
+from transformers import pipeline
+from config import SUMMARIZATION_MODEL
+import textwrap
+
+# Use Pegasus model for better abstractive summarization
+summarizer = pipeline("summarization", model=SUMMARIZATION_MODEL)
+
+MAX_CHARS = 800  # Adjust based on model token limit
+
+def chunk_text(text, max_chunk_size=MAX_CHARS):
+    return textwrap.wrap(text, max_chunk_size)
+
+def summarize_text(text):
+    chunks = chunk_text(text)
+    summaries = []
+    for chunk in chunks:
+        try:
+            summary = summarizer(
+                chunk,
+                max_length=60,     # Force concise summary
+                min_length=20,
+                do_sample=False,   # No randomness
+                clean_up_tokenization_spaces=True
+            )[0]['summary_text']
+            summaries.append(summary)
+        except Exception as e:
+            summaries.append(f"[Error: {e}]")
+    return " ".join(summaries)