bottleneck

app.py

@@ -2,9 +2,14 @@ from fastapi import FastAPI
 from pydantic import BaseModel
 from transformers import pipeline, AutoTokenizer
 from typing import List
+import logging
 
 app = FastAPI()
 
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger("summarizer")
+
 # Faster and lighter summarization model
 model_name = "sshleifer/distilbart-cnn-12-6"
 summarizer = pipeline("summarization", model=model_name)
@@ -48,6 +53,7 @@ async def summarize_batch(request: BatchSummarizationRequest):
 
     for item in request.inputs:
         chunks = chunk_text(item.text)
+        logger.info(f"[CHUNKING] content_id={item.content_id} original_len={len(item.text)} num_chunks={len(chunks)}")
         all_chunks.extend(chunks)
         chunk_map.extend([item.content_id] * len(chunks))