Updated app code

Dockerfile

@@ -2,7 +2,6 @@ FROM python:3.9
 
 RUN pip install --upgrade pip
 
-# Create a user and set up the environment
 RUN useradd -m -u 1000 user
 USER user
 
@@ -11,7 +10,6 @@ ENV HOME=/home/user \
 
 WORKDIR $HOME/app
 
-# Add this line to copy the data directory
 COPY ./data /home/user/app/data  
 
 # Copy only requirements.txt first to leverage Docker cache

app.py

@@ -1,42 +1,39 @@
 #-----Import Required Libraries-----#
 import os
-from dotenv import load_dotenv
-
+import chainlit as cl
+import tiktoken
 import openai
-import fitz  # PyMuPDF
+import fitz  
 import pandas as pd
+from dotenv import load_dotenv
 from transformers import pipeline
 from qdrant_client import QdrantClient
 from qdrant_client.http import models as qdrant_models
-import chainlit as cl
-import tiktoken
-
-# Specific imports from the libraries
 from langchain.document_loaders import PyMuPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import OpenAIEmbeddings #Note: Old import was - from langchain_openai import OpenAIEmbeddings
+from langchain.embeddings import OpenAIEmbeddings 
 from langchain_community.vectorstores import Qdrant
 from langchain.prompts import ChatPromptTemplate
-from langchain.chat_models import ChatOpenAI #Note: Old import was - from langchain_openai import ChatOpenAI
+from langchain.chat_models import ChatOpenAI 
 from operator import itemgetter
 from langchain.schema.output_parser import StrOutputParser
 from langchain.schema.runnable import RunnablePassthrough
 
-#-----Set Environment Variables-----#
+# Set environment variables
 load_dotenv()
 
 # Load environment variables
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 
-# Initialize OpenAI client after loading the environment variables
+# Initialize OpenAI
 openai.api_key = OPENAI_API_KEY
 
-#-----Document Loading and Processing -----#
+# Load embedding model
+embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+
 loader = PyMuPDFLoader("./data/Airbnb-10k.pdf")
 documents = loader.load()
 
-#Note: I changed the loader file path from one that worked locally only to one that worked with Docker. The old file path is loader = PyMuPDFLoader("/Users/sampazar/AIE3-Midterm/data/airbnb_q1_2024.pdf")
-
 def tiktoken_len(text):
     tokens = tiktoken.encoding_for_model("gpt-4o").encode(text)
     return len(tokens)
@@ -47,37 +44,43 @@ text_splitter = RecursiveCharacterTextSplitter(
     length_function = tiktoken_len
 )
 
-split_chunks = text_splitter.split_documents(documents)
-
-#-----Embedding and Vector Store Setup-----#
-
-# Load OpenAI Embeddings Model
-embeddings = OpenAIEmbeddings(model="text-embedding-3-small")
+split_documents = text_splitter.split_documents(documents)
 
 # Creating a Qdrant Vector Store
 qdrant_vector_store = Qdrant.from_documents(
-    split_chunks,
+    split_documents,
     embeddings,
     location=":memory:",
-    collection_name="Airbnb_Q1_2024",
+    collection_name="Airbnb-10k",
 )
 
 # Create a Retriever
 retriever = qdrant_vector_store.as_retriever()
 
-#-----Prompt Template and Language Model Setup-----#
-# Define the prompt template
-template = """Answer the question based only on the following context. If you cannot answer the question with the context, please respond with 'I don't know':
+# -- 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|>
+<|start_header_id|>user<|end_header_id|>
+User Query:
+{query}
 Context:
-{context}
-Question:
-{question}
+{context}<|eot_id|>
+<|start_header_id|>assistant<|end_header_id|>
 """
+#Note that we do not have the response here. We have assistent, we ONLY start, but not followed by <|eot_id> as we do not have a response YET.
+
+rag_prompt = ChatPromptTemplate.from_template(RAG_PROMPT_TEMPLATE)
 
-prompt = ChatPromptTemplate.from_template(template)
 
-# Define the primary LLM
-primary_llm = ChatOpenAI(model_name="gpt-4o", temperature=0)
+# Define the LLM
+llm = ChatOpenAI(model_name="gpt-4o")
 
 #-----Creating a Retrieval Augmented Generation (RAG) Chain-----#
 # The RAG chain:
@@ -96,20 +99,24 @@ retrieval_augmented_qa_chain = (
     # "response" : the "context" and "question" values are used to format our prompt object and then piped
     #              into the LLM and stored in a key called "response"
     # "context"  : populated by getting the value of the "context" key from the previous step
-    | {"response": prompt | primary_llm, "context": itemgetter("context")}
+    | {"response": rag_prompt | llm, "context": itemgetter("context")}
 )
 
-#-----Chainlit Integration-----#
 # Sets initial chat settings at the start of a user session
 @cl.on_chat_start  
 async def start_chat():
+    """
+    This function will be called at the start of every user session. 
+    We will build our LCEL RAG chain here, and store it in the user session. 
+    The user session is a dictionary that is unique to each user session, and is stored in the memory of the server.
+    """
     settings = {
         "model": "gpt-4o",
         "temperature": 0,
         "max_tokens": 500,
-        "top_p": 1,
         "frequency_penalty": 0,
-        "presence_penalty": 0,
+        "top_p": 1,
+        
     }
     cl.user_session.set("settings", settings)
 
@@ -127,6 +134,6 @@ async def handle_message(message: cl.Message):
 
     # Extracting and sending just the content
     content = response["response"].content
-    pretty_content = content.strip()  # Remove any leading/trailing whitespace
+    pretty_content = content.strip()  
 
     await cl.Message(content=pretty_content).send()

chainlit.md

@@ -4,16 +4,6 @@ Welcome to the Airbnb 10k 2024 RAG application!
 
 This RAG (retrieval augmentation generation) application allows you to query the Airbnb 10k 2024 filing dataset. It utilizes a generalized LLM and uses RAG techniques to retrieve and respond to user queries specific to knowledge of the Airbnb 10k 2024 filing dataset.
 
-Build 🏗️
-
-Data: Airbnb 10-k Filings from Q1, 2024
-LLM: OpenAI
-Embedding Model: OpenAI Embeddings (model="text-embedding-3-small")
-Infrastructure: LangChain
-Vector Store: QDrant
-Deployment: Chainlit, Hugging Face
-
-Ship 🚢
 
 Evaluate your answers to the following questions
 Q1 "What is Airbnb's 'Description of Business'?"

requirements.txt

@@ -3,10 +3,10 @@ langchain==0.2.5
 langchain_community==0.2.5
 langchain_core==0.2.9
 langchain_text_splitters==0.2.1
+PyMuPDF==1.24.5
 python-dotenv==1.0.1
-openai==1.35.3 #Be sure to use the latest version 'pip show openai'
-qdrant-client==1.9.2 #Be sure to use the latest version 'pip show qdrant-client'
-PyMuPDF==1.24.5 #Be sure to use the latest version 'pip show pymupdf'
-tiktoken==0.7.0
+openai==1.35.3 
+qdrant-client==1.9.2 
 transformers==4.37.0
 pandas==2.0.3
+tiktoken==0.7.0