rag.py

# +
import streamlit as st

# Set up the document loader
from langchain_community.document_loaders import PyPDFLoader
loader = PyPDFLoader("ca30x30-2024.pdf")
docs = loader.load()

# Set up the language model
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(model = "llama3", api_key=st.secrets["LITELLM_KEY"], base_url = "https://llm.nrp-nautilus.io",  temperature=0)

# Set up the embedding model
from langchain_openai import OpenAIEmbeddings
embedding = OpenAIEmbeddings(
    model = "embed-mistral", 
    api_key=st.secrets["LITELLM_KEY"], 
    base_url = "https://llm.nrp-nautilus.io"
)

# Build a retrival agent
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_text_splitters import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
vectorstore = InMemoryVectorStore.from_documents(documents=splits, embedding=embedding)
retriever = vectorstore.as_retriever()

from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
system_prompt = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Use three sentences maximum and keep the "
    "answer concise."
    "\n\n"
    "{context}"
)
prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system_prompt),
        ("human", "{input}"),
    ]
)
question_answer_chain = create_stuff_documents_chain(llm, prompt)
rag_chain = create_retrieval_chain(retriever, question_answer_chain)

# agent is ready to test:
#results = rag_chain.invoke({"input": "What is the goal of CA 30x30?"})
#results['answer']


# Place agent inside a streamlit application:
st.title("RAG Demo")

if prompt := st.chat_input("What is the goal of CA 30x30?"):
    with st.chat_message("user"):
        st.markdown(prompt)

    with st.chat_message("assistant"):
        results = rag_chain.invoke({"input": prompt})
        st.write(results['answer'])

        st.write('**Context metadata:**\n')
        st.write(results['context'][0]['metadata'])

# adapt for memory / multi-question interaction with:
# https://python.langchain.com/docs/tutorials/qa_chat_history/

# Also see structured outputs.