Trying Don Branson solution

app.py

@@ -53,9 +53,9 @@ hf_embeddings = HuggingFaceEndpointEmbeddings(
     huggingfacehub_api_token=HF_TOKEN,
 )
 
-if os.path.exists("./data/vectorstore"):
+if os.path.exists("./vectorstore"):
     vectorstore = FAISS.load_local(
-        "./data/vectorstore", 
+        "./vectorstore", 
         hf_embeddings, 
         allow_dangerous_deserialization=True # this is necessary to load the vectorstore from disk as it's stored as a `.pkl` file.
     )
@@ -63,7 +63,7 @@ if os.path.exists("./data/vectorstore"):
     print("Loaded Vectorstore")
 else:
     print("Indexing Files")
-    os.makedirs("./data/vectorstore", exist_ok=True)
+    os.makedirs("./vectorstore", exist_ok=True)
     ### 4. INDEX FILES
     ### NOTE: REMEMBER TO BATCH THE DOCUMENTS WITH MAXIMUM BATCH SIZE = 32
     for i in range(0, len(split_documents), 32):
@@ -71,7 +71,7 @@ else:
             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")
+    vectorstore.save_local("./vectorstore")
 
 hf_retriever = vectorstore.as_retriever()
 
@@ -104,7 +104,7 @@ rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
 """
 ### 1. CREATE HUGGINGFACE ENDPOINT FOR LLM
 hf_llm = HuggingFaceEndpoint(
-    endpoint_url=f"{HF_LLM_ENDPOINT}",
+    endpoint_url=HF_LLM_ENDPOINT,
     max_new_tokens=512,
     top_k=10,
     top_p=0.95,