Spaces:
Sleeping
Sleeping
File size: 3,866 Bytes
01ab79d ac83e83 01ab79d 69ffbc4 01ab79d 031fa3d 69ffbc4 031fa3d 01ab79d 031fa3d 01ab79d 9a62241 01ab79d f4e486c 01ab79d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
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_community.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 pdf2image import convert_from_bytes
from PIL import Image
import pytesseract
import io
load_dotenv()
os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
def get_pdf_text(pdf_docs):
text = ""
for uploaded_file in pdf_docs:
if uploaded_file.name.endswith(".pdf"):
# Process actual PDF files
pdf_reader = PdfReader(uploaded_file)
for page in pdf_reader.pages:
page_text = page.extract_text()
if page_text:
text += page_text
# If no text extracted, try OCR
if not text.strip():
images = convert_from_bytes(uploaded_file.read())
for img in images:
text += pytesseract.image_to_string(img)
else:
# Process image files
image = Image.open(uploaded_file)
text += pytesseract.image_to_string(image)
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):
if not text_chunks:
raise ValueError("No text chunks generated from PDF. Please check the uploaded file.")
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
vector_store.save_local("faiss_index")
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=0.7)
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):
embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
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"])
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() |