Update app.py

app.py

@@ -37,43 +37,30 @@ 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")
-documents = document_loader.load()
-
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=30)
-split_documents = text_splitter.split_documents(documents)
 
+vectorstore_path = "./data/vectorstore"
+index_file = os.path.join(vectorstore_path, "index.faiss")
 hf_embeddings = HuggingFaceEndpointEmbeddings(
     model=HF_EMBED_ENDPOINT,
     task="feature-extraction",
     huggingfacehub_api_token=HF_TOKEN,
 )
 
-if os.path.exists("./data/vectorstore"):
-    vectorstore = FAISS.load_local(
-        "./data/vectorstore", 
+vectorstore = FAISS.load_local(
+        vectorstore_path, 
         hf_embeddings, 
-        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("./data/vectorstore", exist_ok=True)
-    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")
-
+        allow_dangerous_deserialization=True
+)
 hf_retriever = vectorstore.as_retriever()
+print("Loaded Vectorstore")
+    
 
 # -- AUGMENTED -- #
 """
 1. Define a String Template
 2. Create a Prompt Template from the String Template
 """
+### 1. DEFINE STRING TEMPLATE
 RAG_PROMPT_TEMPLATE = """\
 <|start_header_id|>system<|end_header_id|>
 You are a helpful assistant. You answer user questions based on provided context. If you can't answer the question with the provided context, say you don't know.<|eot_id|>
@@ -88,19 +75,21 @@ Context:
 <|start_header_id|>assistant<|end_header_id|>
 """
 
+### 2. CREATE PROMPT TEMPLATE
 rag_prompt = PromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
 
 # -- GENERATION -- #
 """
 1. Create a HuggingFaceEndpoint for the LLM
 """
+### 1. CREATE HUGGINGFACE ENDPOINT FOR LLM
 hf_llm = HuggingFaceEndpoint(
     endpoint_url=HF_LLM_ENDPOINT,
     max_new_tokens=512,
     top_k=10,
     top_p=0.95,
-    temperature=0.3,
-    repetition_penalty=1.15,
+    temperature=0.1,
+    repetition_penalty=1.0,
     huggingfacehub_api_token=HF_TOKEN,
 )
 
@@ -126,6 +115,7 @@ async def start_chat():
     The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
     """
 
+    ### BUILD LCEL RAG CHAIN THAT ONLY RETURNS TEXT
     lcel_rag_chain = (
         {"context": itemgetter("query") | hf_retriever, "query": itemgetter("query")}
         | rag_prompt | hf_llm
@@ -146,7 +136,7 @@ async def main(message: cl.Message):
 
     msg = cl.Message(content="")
 
-    for chunk in await cl.make_async(lcel_rag_chain.stream)(
+    async for chunk in lcel_rag_chain.astream(
         {"query": message.content},
         config=RunnableConfig(callbacks=[cl.LangchainCallbackHandler()]),
     ):