RAGwithChatGROQ.py

import streamlit as st
import os
from langchain_groq import ChatGroq
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.embeddings import OllamaEmbeddings
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
from langchain.chains import create_retrieval_chain
from langchain_community.vectorstores import FAISS
import time
from dotenv import load_dotenv


# ENV VARIABLES
load_dotenv()
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY")
os.environ["LANGCHAIN_API_KEY"] = os.getenv("LANGCHAIN_API_KEY")
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["GROQ_API_KEY"] = os.getenv("GROQ_API_KEY")


# load_
groq_api_key = os.getenv("GROQ_API_KEY")

# I'll be using streamlit session_state

if "vector" not in st.session_state:
    st.session_state.embeddings = OllamaEmbeddings()
    st.session_state.loader = WebBaseLoader("https://docs.smith.langchain.com/")
    st.session_state.docs = st.session_state.loader.load()
    st.session_state.text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000, chunk_overlap=200
    )
    st.session_state.final_documents = st.session_state.text_splitter.split_documents(
        st.session_state.docs[:10]
    )
    st.session_state.vectors = FAISS.from_documents(
        st.session_state.final_documents, st.session_state.embeddings
    )

st.title("ChatGropq Demo")
llm = ChatGroq(model_name="Gemma-7b-It")
# print(llm)


prompt = ChatPromptTemplate.from_template(
    """Answer the questions based on the provided context only.
    Please provide the most accurate response based on the question.
    <context>
    {context}
    </context>
    Questions:{input}
    """
)
# create_doc_chain
document_chain = create_stuff_documents_chain(llm, prompt)
retriever = st.session_state.vectors.as_retriever()
retriever_chain = create_retrieval_chain(retriever, document_chain)
prompt = st.text_input("Input your prompt")

if prompt:
    start = time.process_time()
    response = retriever_chain.invoke({"input": prompt})
    print("Response time:", time.process_time() - start)
    st.write(response["answer"])

    # with streamlit expander
    with st.expander("Document Similarity Search"):
        # find relevanr chunks
        for i, doc in enumerate(response["context"]):
            st.write(doc.page_content)
            st.write("--------------------------------")