diff --git a/dialog_lib/loaders/csv.py b/dialog_lib/loaders/csv.py
index f3ffe96..d441081 100644
--- a/dialog_lib/loaders/csv.py
+++ b/dialog_lib/loaders/csv.py
@@ -1,3 +1,4 @@
+import logging
 from dialog_lib.db import get_session
 from dialog_lib.db.models import CompanyContent
 from dialog_lib.embeddings.generate import generate_embedding
@@ -6,6 +7,9 @@
 from langchain_community.document_loaders.csv_loader import CSVLoader
 
 
+logger = logging.getLogger(__name__)
+
+
 def load_csv(
         file_path, dbsession=get_session, embeddings_model_instance=None,
         embedding_llm_model=None, embedding_llm_api_key=None, company_id=None
@@ -28,6 +32,10 @@ def load_csv(
                 values = line.split(": ")
                 content[values[0]] = values[1]
 
+
+        if not dbsession.query(CompanyContent).filter(
+            CompanyContent.question == content["question"], CompanyContent.content == content["content"]
+        ).first():
             company_content = CompanyContent(
                 category="csv",
                 subcategory="csv-content",
@@ -37,5 +45,5 @@ def load_csv(
                 embedding=generate_embedding(csv_content.page_content, embeddings_model_instance)
             )
             session.add(company_content)
-
-    return company_content
\ No newline at end of file
+        else:
+            logger.warning(f"Question: {content['question']} already exists in the database. Skipping.")
\ No newline at end of file
diff --git a/dialog_lib/loaders/gsheets.py b/dialog_lib/loaders/gsheets.py
index 6346ec4..c7e17c1 100644
--- a/dialog_lib/loaders/gsheets.py
+++ b/dialog_lib/loaders/gsheets.py
@@ -1,4 +1,5 @@
 import gspread
+import logging
 
 from dialog_lib.db.models import CompanyContent
 from dialog_lib.embeddings.generate import generate_embedding
@@ -11,6 +12,8 @@
 from typing import Any, Dict, Iterator, List, Optional, Sequence, Union
 
 
+logger = logging.getLogger(__name__)
+
 class GoogleSheetsLoader(BaseLoader):
     def __init__(self, credentials_path: Union[str, Path], spreadsheet_url: str, sheet_name: str):
         self.sheet_name = sheet_name
@@ -59,15 +62,19 @@ def load_google_sheets(
                 values = line.split(": ")
                 content[values[0]] = values[1]
 
-        company_content = CompanyContent(
-            category="csv",
-            subcategory="csv-content",
-            question=content["question"],
-            content=content["content"],
-            dataset=company_id,
-            embedding=generate_embedding(csv_content.page_content, embeddings_model_instance)
-        )
-        dbsession.add(company_content)
+        if not dbsession.query(CompanyContent).filter(
+            CompanyContent.question == content["question"], CompanyContent.content == content["content"]
+        ).first():
+            company_content = CompanyContent(
+                category="csv",
+                subcategory="csv-content",
+                question=content["question"],
+                content=content["content"],
+                dataset=company_id,
+                embedding=generate_embedding(csv_content.page_content, embeddings_model_instance)
+            )
+            dbsession.add(company_content)
+        else:
+            logger.warning(f"Question: {content['question']} already exists in the database. Skipping.")
 
-    dbsession.commit()
-    return company_content
\ No newline at end of file
+    dbsession.commit()
\ No newline at end of file