Update app.py

app.py

@@ -3,22 +3,19 @@ from langchain.prompts import ChatPromptTemplate
 from langchain.schema import StrOutputParser
 from langchain.schema.runnable import Runnable
 from langchain.schema.runnable.config import RunnableConfig
-from typing import cast
 from dotenv import load_dotenv
 import os
 from langchain_community.document_loaders import PyMuPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_openai.embeddings import OpenAIEmbeddings
 from langchain_community.vectorstores import Qdrant
-from langchain_core.runnables import RunnablePassthrough, RunnableParallel
 import chainlit as cl
-from pathlib import Path
 from sentence_transformers import SentenceTransformer
 
+# Load environment variables
 load_dotenv()
-
 os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
 
+# Custom embedding class for SentenceTransformer
 class SentenceTransformerEmbedding:
     def __init__(self, model_name):
         self.model = SentenceTransformer(model_name)
@@ -29,7 +26,7 @@ class SentenceTransformerEmbedding:
     def __call__(self, texts):
         return self.embed_documents(texts)  # Make it callable
 
-@cl.on_chat_start
+@cl.on_chat_start  # Marks the function to be executed at the start of a user session
 async def on_chat_start():
     model = ChatOpenAI(streaming=True)
 
@@ -62,20 +59,19 @@ async def on_chat_start():
     sentence_blueprint = metadata_generator(ai_blueprint_document, "AI Blueprint", sentence_text_splitter)
 
     sentence_combined_documents = sentence_framework + sentence_blueprint
-    from langchain_community.embeddings import HuggingFaceEmbeddings  # Use HuggingFaceEmbeddings if needed
-
 
-    # Initialize the custom embedding class
+    # Initialize the embedding model instance
     embedding_model = SentenceTransformerEmbedding('Cheselle/finetuned-arctic-sentence')
 
-    # Create the Qdrant vector store using the custom embedding model
+    # Create the Qdrant vector store using the embedding instance
     sentence_vectorstore = Qdrant.from_documents(
         documents=sentence_combined_documents,
-        embedding_function=embedding_model,  # Ensure this is an instance
+        embedding=embedding_model,  # Pass the embedding instance correctly
         location=":memory:",
         collection_name="AI Policy"
     )
 
+    # Create retriever from the vector store
     sentence_retriever = sentence_vectorstore.as_retriever()
 
     # Check if retriever is initialized correctly
@@ -87,11 +83,10 @@ async def on_chat_start():
     cl.user_session.set("retriever", sentence_retriever)
     cl.user_session.set("prompt_template", rag_prompt)
 
-
-@cl.on_message
+@cl.on_message  # Marks a function to run each time a message is received
 async def on_message(message: cl.Message):
     # Get the stored model, retriever, and prompt
-    model = cast(ChatOpenAI, cl.user_session.get("runnable"))
+    model = cl.user_session.get("runnable")
     retriever = cl.user_session.get("retriever")
     prompt_template = cl.user_session.get("prompt_template")