|
import streamlit as st
|
|
from PyPDF2 import PdfReader
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
import os
|
|
from langchain_google_genai import GoogleGenerativeAIEmbeddings
|
|
import google.generativeai as genai
|
|
from langchain.vectorstores import FAISS
|
|
from langchain_google_genai import ChatGoogleGenerativeAI
|
|
from langchain.chains.question_answering import load_qa_chain
|
|
from langchain.prompts import PromptTemplate
|
|
from dotenv import load_dotenv
|
|
from PIL import Image
|
|
import io
|
|
|
|
|
|
load_dotenv()
|
|
os.getenv("GOOGLE_API_KEY")
|
|
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
|
|
|
|
|
|
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
|
|
|
|
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
|
|
|
|
def get_image_text(image_files):
|
|
|
|
|
|
text = ""
|
|
for image in image_files:
|
|
|
|
text += "Extracted text from image.\n"
|
|
return text
|
|
|
|
def get_text_chunks(text):
|
|
text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
|
|
chunks = text_splitter.split_text(text)
|
|
return chunks
|
|
|
|
def get_vector_store(text_chunks):
|
|
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
|
|
vector_store.save_local("faiss_index")
|
|
|
|
def load_faiss_index():
|
|
return FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
|
|
|
|
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=0.3)
|
|
prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
|
|
chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
|
|
return chain
|
|
|
|
def user_input(user_question):
|
|
new_db = load_faiss_index()
|
|
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"])
|
|
st.snow()
|
|
|
|
def main():
|
|
st.set_page_config("Chat with Documents and Images", page_icon="π")
|
|
st.header("Chat with Multi Docs and Images π")
|
|
|
|
user_question = st.text_input("Ask a Question from the PDF Files or Uploaded Images")
|
|
|
|
if user_question:
|
|
user_input(user_question)
|
|
|
|
with st.sidebar:
|
|
st.title("Menu:")
|
|
|
|
pdf_docs = st.file_uploader("Upload your PDF Files", accept_multiple_files=True, type=["pdf"])
|
|
image_files = st.file_uploader("Upload your Image Files", accept_multiple_files=True, type=["jpg", "jpeg", "png"])
|
|
|
|
if st.button("Submit & Process"):
|
|
with st.spinner("Processing..."):
|
|
raw_text = get_pdf_text(pdf_docs) + get_image_text(image_files)
|
|
text_chunks = get_text_chunks(raw_text)
|
|
get_vector_store(text_chunks)
|
|
st.success("Done")
|
|
st.balloons()
|
|
|
|
if __name__ == "__main__":
|
|
main()
|
|
|
|
|