Update app/core/summarizer.py

app/core/summarizer.py

@@ -1,29 +1,33 @@
 from transformers import pipeline
 
-# Load the summarization pipeline
 summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
-def get_summary(text: str) -> str:
-    max_chunk_chars = 3000  # ~1024 tokens, safe limit for BART
-    overlap = 200  # overlap to avoid cutting in middle of sentence
+def chunk_text(text, max_len=700):
+    words = text.split()
+    chunks = []
+    current = []
+
+    for word in words:
+        current.append(word)
+        if len(" ".join(current)) >= max_len:
+            chunks.append(" ".join(current))
+            current = []
+
+    if current:
+        chunks.append(" ".join(current))
+
+    return chunks[:3]  # Limit to first 3 chunks
+
+def get_summary(text):
+    print("Input length:", len(text))
+
     summaries = []
+    for chunk in chunk_text(text):
+        try:
+            result = summarizer(chunk, max_length=150, min_length=30, do_sample=False)
+            summaries.append(result[0]['summary_text'])
+        except Exception as e:
+            print("Summarization failed:", e)
+            summaries.append("...")
 
-    # Generate chunks
-    i = 0
-    while i < len(text):
-        end = i + max_chunk_chars
-        chunk = text[i:end]
-        if len(chunk.strip()) > 50:  # avoid empty/short segments
-            try:
-                summary = summarizer(
-                    chunk,
-                    max_length=150,
-                    min_length=30,
-                    do_sample=False
-                )
-                summaries.append(summary[0]['summary_text'])
-            except Exception as e:
-                summaries.append(f"[Error summarizing chunk: {e}]")
-        i += max_chunk_chars - overlap
-
-    return "\n\n".join(summaries)
+    return "\n".join(summaries)