update app.py

app.py

@@ -39,7 +39,7 @@ HF_TOKEN = os.environ["HF_TOKEN"]
 """
 ### 1. CREATE TEXT LOADER AND LOAD DOCUMENTS
 ### NOTE: PAY ATTENTION TO THE PATH THEY ARE IN. 
-document_loader = TextLoader("data/paul_graham_essays.txt")
+document_loader = TextLoader("./data/paul_graham_essays.txt")
 documents = document_loader.load()
 
 ### 2. CREATE TEXT SPLITTER AND SPLIT DOCUMENTS
@@ -51,7 +51,7 @@ split_documents = text_splitter.split_documents(documents)
 hf_embeddings = HuggingFaceEndpointEmbeddings(
     model=HF_EMBED_ENDPOINT,
     task="feature-extraction",
-    huggingfacehub_api_token=os.environ["HF_TOKEN"],
+    huggingfacehub_api_token=HF_TOKEN,
 )
 
 if os.path.exists("./data/vectorstore"):
@@ -65,13 +65,12 @@ if os.path.exists("./data/vectorstore"):
 else:
     print("Indexing Files")
     os.makedirs("./data/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):
         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()
 
@@ -103,14 +102,14 @@ 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,
     typical_p=0.95,
     temperature=0.01,
     repetition_penalty=1.03,
-    huggingfacehub_api_token=os.environ["HF_TOKEN"]
+    huggingfacehub_api_token=HF_TOKEN
 )
 
 @cl.author_rename
@@ -136,7 +135,10 @@ async def start_chat():
     """
 
     ### BUILD LCEL RAG CHAIN THAT ONLY RETURNS TEXT
-    lcel_rag_chain = {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}| rag_prompt | hf_llm
+    lcel_rag_chain = (
+        {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
+        | rag_prompt | hf_llm 
+    )
 
     cl.user_session.set("lcel_rag_chain", lcel_rag_chain)