Update app.py

app.py

@@ -13,22 +13,6 @@ from langchain.prompts.chat import (
 )
 import chainlit as cl
 
-# ---------------------------------------------------for backend looks, example file:----------------------------------
-import os
-
-with open('/home/user/.local/lib/python3.10/site-packages/chainlit/config.py', 'r') as file: # line 622
-    content = file.read()
-    print("config.py:", content)
-
-# /home/user/.local/bin/chainlit
-# /home/user/app/.chainlit/config.toml
-
-
-#app_path = os.path.abspath(__file__)
-#print("[email protected]:", app_path)
-
-# ------------------------------------------------------the end--------------------------------------------------------
-
 
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
 
@@ -71,26 +55,19 @@ async def init():
     msg = cl.Message(content=f"Building Index...")
     await msg.send()
 
-    # --builds FAISS index from csv
     loader = CSVLoader(file_path="./data/total_faq.csv", source_column="Answer") 
     data = loader.load()
 
-    # --adding spec. metadata-------------------------------------------------------------------------------------------------
     for i, doc in enumerate(data):
-        doc.metadata["row_index"] = i + 1  # --row index (1-based)
+        doc.metadata["row_index"] = i + 1  
         doc.metadata["source"] = doc.metadata.get("Info_Url", "") 
-    # ------------------------------------------------------------------------------------------------------------------------
 
-    # --pull some q's & dotted i's for menu ==================================================================================
-    questions = [doc.page_content for doc in data[:5]]
-    # ========================================================================================================================
     documents = text_splitter.transform_documents(data)
     store = LocalFileStore("./cache/")
     core_embeddings_model = OpenAIEmbeddings()
     embedder = CacheBackedEmbeddings.from_bytes_store(
         core_embeddings_model, store, namespace=core_embeddings_model.model
     )
-    # --make async docsearch
     docsearch = await cl.make_async(FAISS.from_documents)(documents, embedder)
 
     chain = RetrievalQA.from_chain_type(
@@ -101,19 +78,12 @@ async def init():
         chain_type_kwargs = {"prompt": prompt}
     )
 
-    #menu_message = (
-        #"Index built! Bare spør ivei..\n\n"
-        #"Her er noen spørsmål vi ofte ser i forbindelse med DaysOff firmahytteordning:\n"
-        #+ "\n".join([f"- {q}" for q in questions])
-    #)
-
-    #msg.content = menu_message
     msg.content = f"Index built! Bare spør ivei..🤓"
     await msg.send()
 
-
     cl.user_session.set("chain", chain)
 
+
 @cl.on_message
 async def main(message):
     chain = cl.user_session.get("chain")
@@ -129,12 +99,10 @@ async def main(message):
     source_elements = []
     visited_sources = set()
 
-    # --documents, user session
     docs = res.get("source_documents", [])
     metadatas = [doc.metadata for doc in docs]
-    #all_sources = [m["source"] for m in metadatas]
+  
 
-    # --append source(s), specific rows only
     for doc, metadata in zip(docs, metadatas):
         row_index = metadata.get("row_index", -1) 
         source = metadata.get("source", "")