Spaces:
Sleeping
Sleeping
import os | |
import streamlit as st | |
import google.generativeai as genai | |
from dotenv import load_dotenv | |
from PyPDF2 import PdfReader # read the PDF file | |
from langchain.text_splitter import RecursiveCharacterTextSplitter | |
from langchain_google_genai import GoogleGenerativeAIEmbeddings # converting text to vectors | |
from langchain.vectorstores import FAISS # for vector embeddings | |
from langchain_google_genai import ChatGoogleGenerativeAI | |
from langchain.chains.question_answering import load_qa_chain # helps for prompts | |
from langchain.prompts import PromptTemplate | |
load_dotenv() | |
genai.configure(api_key=os.getenv('GOOGLE_API_KEY')) | |
# read the pdf, and extract the text | |
def get_pdf_text(pdf_docs): | |
text = "" | |
for pdf in pdf_docs: | |
pdf_reader = PdfReader(pdf) | |
for page in pdf_reader.pages: | |
text += page.extract_text() | |
return text | |
# divide the text into chunks | |
def get_text_chunks(text): | |
text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000) | |
chunks = text_splitter.split_text(text) | |
return chunks | |
# convert the text to vectors | |
def get_vector_store(text_chunks): | |
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001") | |
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings) | |
vector_store.save_local("faiss_index") # save the vector as local, can also save it on Pinecone, DataStax | |
# creating chain for conversational | |
def get_conversational_chain(): | |
prompt_template = """ | |
Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in | |
provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n | |
Context:\n {context}?\n | |
Question: \n{question}\n | |
Answer: | |
""" | |
model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.8) | |
prompt = PromptTemplate(template=prompt_template, input_variables=['context','question']) | |
chain = load_qa_chain(model, chain_type='stuff',prompt=prompt) #stuff for internal summerization | |
return chain | |
# user question besed on the textbox and calling the other functions | |
def user_input(user_question): | |
embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001") | |
new_db = FAISS.load_local("faiss_index",embeddings) # load the embedding from local | |
docs = new_db.similarity_search(user_question) | |
chain = get_conversational_chain() | |
response = chain( | |
{'input_documents': docs, "question": user_question}, | |
return_only_outputs=True | |
) | |
print(response) | |
st.write("Reply: ", response["output_text"]) | |
# creating the streamlit Application | |
def main(): | |
st.set_page_config("Chat PDF") | |
st.header("Chat with PDF using Gemini💁") | |
user_question = st.text_input("Ask a Question from the PDF Files") | |
if user_question: | |
user_input(user_question) | |
with st.sidebar: | |
st.title("Menu:") | |
pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True) | |
if st.button("Submit & Process"): | |
with st.spinner("Processing..."): | |
raw_text = get_pdf_text(pdf_docs) | |
text_chunks = get_text_chunks(raw_text) | |
get_vector_store(text_chunks) | |
st.success("Done") | |
if __name__ == "__main__": | |
main() | |