logging

app.py

@@ -20,6 +20,17 @@ item_id = ""
 item = {}
 LIMIT = 1000  # Limit to 1000 reviews so that processing does not take too long
 
+import logging
+
+# Configure logging
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s [%(levelname)s] %(message)s",
+    handlers=[logging.StreamHandler()],
+)
+
+logger = logging.getLogger(__name__)
+
 
 def scrape(product_id, max_reviews=LIMIT):
     all_reviews = []
@@ -37,7 +48,7 @@ def scrape(product_id, max_reviews=LIMIT):
     reviews_df = pd.json_normalize(all_reviews)
     reviews_df.rename(columns={"message": "comment"}, inplace=True)
     reviews_df = reviews_df[["comment"]]
-    print(reviews_df.head())
+    logger.info(reviews_df.head())
     return reviews_df
 
 
@@ -47,7 +58,7 @@ def get_product_id(URL):
     product_id = request_product_id(SHOP, PRODUCT_KEY).json()["data"]["pdpGetLayout"][
         "basicInfo"
     ]["id"]
-    print(product_id)
+    logger.info(product_id)
     return product_id
 
 
@@ -57,7 +68,7 @@ def clean(df):
     df = df[df["comment"] != ""].reset_index(drop=True)  # remove empty reviews
     df["comment"] = df["comment"].apply(lambda x: clean_text(x))  # clean text
     df = df[df["comment"] != ""].reset_index(drop=True)  # remove empty reviews
-    print("cleaned")
+    logger.info("cleaned")
     return df
 
 
@@ -107,7 +118,7 @@ async def generate(URL, query):
                         chunk_size=1000, chunk_overlap=50
                     )
                     docs = text_splitter.split_documents(documents)
-                    print("split")
+                    logger.info("split")
                     cache_URL = URL
                     # Vector store
                     db = FAISS.from_documents(docs, embeddings)
@@ -116,7 +127,7 @@ async def generate(URL, query):
                         llm=llm, retriever=db.as_retriever()
                     )
                     res = await qa.ainvoke(query)
-                    print("generated")
+                    logger.info("generated")
                     # Process result
                     return res["result"]
         except: