Update app.py

app.py

@@ -26,7 +26,7 @@ We will load our environment variables here.
 """
 HF_LLM_ENDPOINT = os.environ["HF_LLM_ENDPOINT"]
 HF_EMBED_ENDPOINT = os.environ["HF_EMBED_ENDPOINT"]
-HF_TOKEN = os.environ["HF_TOKEN"]
+HF_TOKEN = os.environ["HF_API_KEY"]
 
 # ---- GLOBAL DECLARATIONS ---- #
 
@@ -37,7 +37,7 @@ HF_TOKEN = os.environ["HF_TOKEN"]
 3. Load HuggingFace Embeddings (remember to use the URL we set above)
 4. Index Files if they do not exist, otherwise load the vectorstore
 """
-document_loader = TextLoader("./data/paul_graham_essays.txt")
+document_loader = TextLoader("paul_graham_essays.txt")
 documents = document_loader.load()
 
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
@@ -49,9 +49,9 @@ 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.
     )
@@ -59,7 +59,7 @@ 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)
     for i in range(0, len(split_documents), 32):
         if i == 0:
             vectorstore = FAISS.from_documents(
@@ -67,7 +67,7 @@ else:
             )
             continue
         vectorstore.add_documents(split_documents[i : i + 32])
-    vectorstore.save_local("./data/vectorstore")
+    vectorstore.save_local("vectorstore")
 
 hf_retriever = vectorstore.as_retriever()