Update app.py

app.py

@@ -49,31 +49,23 @@ hf_embeddings = HuggingFaceEndpointEmbeddings(
     huggingfacehub_api_token=HF_TOKEN,
 )
 
-vectorstore_path = "./data/vectorstore"
-index_file = os.path.join(vectorstore_path, "index.faiss")
-
-if os.path.exists(index_file):
+if os.path.exists("./data/vectorstore"):
     vectorstore = FAISS.load_local(
-        vectorstore_path, 
+        "./data/vectorstore", 
         hf_embeddings, 
-        allow_dangerous_deserialization=True
+        allow_dangerous_deserialization=True # this is necessary to load the vectorstore from disk as it's stored as a `.pkl` file.
     )
     hf_retriever = vectorstore.as_retriever()
     print("Loaded Vectorstore")
 else:
     print("Indexing Files")
-    os.makedirs(vectorstore_path, exist_ok=True)
-    ### 4. INDEX FILES
-    vectorstore = None
+    os.makedirs("./data/vectorstore", exist_ok=True)
     for i in range(0, len(split_documents), 32):
-        batch = split_documents[i:i+32]
-        if vectorstore is None:
-            vectorstore = FAISS.from_documents(batch, hf_embeddings)
-        else:
-            vectorstore.add_documents(batch)
-    vectorstore.save_local(vectorstore_path)
-    print("Vectorstore created and saved")
-
+        if i == 0:
+            vectorstore = FAISS.from_documents(split_documents[i:i+32], hf_embeddings)
+            continue
+        vectorstore.add_documents(split_documents[i:i+32])
+    vectorstore.save_local("./data/vectorstore")
 
 hf_retriever = vectorstore.as_retriever()