app.py

import streamlit as st
import time
from langchain_community.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import GoogleGenerativeAIEmbeddings
from langchain_chroma import Chroma
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.prompts import ChatPromptTemplate
import pdfplumber
from langchain_community.document_loaders import PDFPlumberLoader

#https://mrmaheshrajput.medium.com/how-to-productionize-large-language-models-llms-060a4cb1a169
import traceback
api_key = "AIzaSyBAzG1ck9Pn81THl8CBgXmYabklRMIrJCM"

from dotenv import load_dotenv
load_dotenv()


st.title("RAG and Gemini Model")



# Load data from PDF
pdf_path = "100340.pdf"
loader = PDFPlumberLoader(pdf_path)
data = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000)
docs = text_splitter.split_documents(data)

vectorstore = Chroma.from_documents(documents=docs, embedding=GoogleGenerativeAIEmbeddings(model="models/embedding-001"))

retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 30})

llm = ChatGoogleGenerativeAI(model="gemini-1.5-pro",temperature=0,max_tokens=None,timeout=None)


query = st.chat_input("Say something: ") 
prompt = query

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}"),
    ]
)

if query:
    question_answer_chain = create_stuff_documents_chain(llm, prompt)
    rag_chain = create_retrieval_chain(retriever, question_answer_chain)

    response = rag_chain.invoke({"input": query})
    #print(response["answer"])

    st.write(response["answer"])