From e737c3895c3c6b1ec60e67b3b391134ecce56c3e Mon Sep 17 00:00:00 2001
From: Niklas Mueller <n.mueller@ibm.com>
Date: Wed, 3 Jul 2024 10:14:23 +0200
Subject: [PATCH] generalize logging

---
 .../src/common_packages/logging.py            |  2 +-
 rag-chat-backend/src/preprocessing/pdf.py     | 27 +++++++------------
 2 files changed, 10 insertions(+), 19 deletions(-)

diff --git a/rag-chat-backend/src/common_packages/logging.py b/rag-chat-backend/src/common_packages/logging.py
index 5b3e870..2cdc2f8 100644
--- a/rag-chat-backend/src/common_packages/logging.py
+++ b/rag-chat-backend/src/common_packages/logging.py
@@ -35,7 +35,7 @@ def create_logger(log_level: str, logger_name: str = "custom_logger"):
 
     # Create a formatter and set it for the console handler
     formatter = logging.Formatter(
-        "%(asctime)s - %(levelname)s [%(name)s] - %(message)s",
+        "%(asctime)s [%(name)s] | %(levelname)s\t - %(message)s",
         datefmt="%Y-%m-%d %H:%M:%S",
     )
     console_handler.setFormatter(formatter)
diff --git a/rag-chat-backend/src/preprocessing/pdf.py b/rag-chat-backend/src/preprocessing/pdf.py
index 4a38df1..75ac3ba 100644
--- a/rag-chat-backend/src/preprocessing/pdf.py
+++ b/rag-chat-backend/src/preprocessing/pdf.py
@@ -1,26 +1,17 @@
 """Module for tools to process PDF documents"""
 
 import os
-import sys
 import io
 import PyPDF2
 
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-import logging
-import datetime as dt
-from datetime import datetime
-import traceback
+from common_packages import logging
 
-# Setup Logging
-logging.basicConfig(
-    level=logging.DEBUG,
-    # level=logging.INFO,
-    format="Start: " + str(dt.datetime.now()).replace(" ", "_") + " | %(asctime)s [%(levelname)s] %(message)s",
-    handlers=[
-        logging.FileHandler("/<path>-_" + str(datetime.today().strftime('%Y-%m-%d')) + "_-_debug.log"),
-        logging.StreamHandler(sys.stdout)
-    ]
+# instantiate logger
+logger = logging.create_logger(
+    log_level=os.getenv("LOGGING_LEVEL", "INFO"),
+    logger_name=__name__,
 )
 
 
@@ -73,11 +64,11 @@ def read_pdf(pdf_bytes: io.BytesIO) -> tuple:
     Returns:
         tuple of lists: (List of chunked text, List of corresponding page numbers).
     """
-    logging.info("Reading PDF document")
+    logger.info("Reading PDF document")
     pdf_reader = PyPDF2.PdfReader(io.BytesIO(pdf_bytes))
 
     num_pages = len(pdf_reader.pages)
-    logging.info("Read PDF document with '%s' pages", num_pages)
+    logger.info("Read PDF document with '%s' pages", num_pages)
 
     text_pages = []
     for i in range(num_pages):
@@ -86,12 +77,12 @@ def read_pdf(pdf_bytes: io.BytesIO) -> tuple:
         if text:
             text_pages.append((text, i + 1))
 
-    logging.info("Processing PDF content")
+    logger.info("Processing PDF content")
     pdf_processor = PDFProcessor()
     processed_chunks = pdf_processor.chunk_text(text_pages)
 
     chunks = [chunk for chunk, _ in processed_chunks]
     pages = [page for _, page in processed_chunks]
-    logging.info("PDF processed. Number of chunks: %s", len(chunks))
+    logger.info("PDF processed. Number of chunks: %s", len(chunks))
 
     return chunks, pages