Project: Conversational RAG

Project 2: Conversational RAG with chat memory using LangChain's `ConversationalRetrievalChain`.

from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
import os

os.environ["OPENAI_API_KEY"] = "your-key-here"

# Load, chunk, embed, store (same as before)
loader = PyPDFLoader("document.pdf")
documents = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
chunks = splitter.split_documents(documents)
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(chunks, embeddings)

# Conversational chain
llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
qa_chain = ConversationalRetrievalChain.from_llm(
    llm, retriever=vectorstore.as_retriever(), memory=memory
)

# Interactive chat
print("Chat with your PDF (type 'exit' to stop)")
while True:
    query = input("nYou: ")
    if query.lower() == "exit": break
    result = qa_chain({"question": query})
    print(f"Bot: {result['answer']}")

python chat_rag.py

• Adding conversation memory with `ConversationBufferMemory`.
• Using `ConversationalRetrievalChain` for chat.
• Handling multi‑turn conversations.