Update app.py

app.py

@@ -10,7 +10,7 @@ from huggingface_hub import HfApi, HfFolder
 DB_FAISS_PATH = 'vectorstore/db_faiss'
 DATASET_REPO = "GovindRaj/faiss-vectorstore"  # Your Hugging Face Dataset ID
 
-# Function to create FAISS vector DB and upload to Hugging Face
+# Function to create or update FAISS vector DB and upload to Hugging Face
 def create_vector_db(uploaded_files):
     # Create a temporary directory
     with tempfile.TemporaryDirectory() as temp_dir:
@@ -42,8 +42,17 @@ def create_vector_db(uploaded_files):
             model_kwargs={'device': 'cpu'}
         )
 
-        # Create and save FAISS database locally
-        db = FAISS.from_documents(texts, embeddings)
+        # Check if FAISS vectorstore already exists
+        if os.path.exists(DB_FAISS_PATH):
+            # Load existing FAISS database
+            db = FAISS.load_local(DB_FAISS_PATH, embeddings)
+            # Add new documents to the existing database
+            db.add_documents(texts)
+        else:
+            # Create a new FAISS database if none exists
+            db = FAISS.from_documents(texts, embeddings)
+
+        # Save the updated FAISS database locally
         db.save_local(DB_FAISS_PATH)
 
         # Retrieve the token from environment variables (Hugging Face Secrets)
@@ -52,7 +61,7 @@ def create_vector_db(uploaded_files):
         if not hf_token:
             raise ValueError("Hugging Face token not found. Please set the token in Hugging Face secrets.")
 
-        # Push the vector database to Hugging Face Dataset
+        # Push the updated vector database to Hugging Face Dataset
         HfFolder.save_token(hf_token)
         api = HfApi()
         api.upload_folder(
@@ -85,4 +94,4 @@ def main():
                 st.error(f"An error occurred: {str(e)}")
 
 if __name__ == "__main__":
-    main()
+    main()