File size: 4,194 Bytes
6350811 |
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 |
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
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
import os
# Load the environment variables from .env file
load_dotenv()
# Fetch the Google API key from the .env file
api_key = os.getenv("GOOGLE_API_KEY")
st.set_page_config(page_title="Document Genie", layout="wide")
st.markdown("""
## Document Genie: Get instant insights from your Documents
This chatbot is built using the Retrieval-Augmented Generation (RAG) framework, leveraging Google's Generative AI model Gemini-PRO. It processes uploaded PDF documents by breaking them down into manageable chunks, creates a searchable vector store, and generates accurate answers to user queries. This advanced approach ensures high-quality, contextually relevant responses for an efficient and effective user experience.
### How It Works
Follow these simple steps to interact with the chatbot:
1. **Upload Your Documents**: The system accepts multiple PDF files at once, analyzing the content to provide comprehensive insights.
2. **Ask a Question**: After processing the documents, ask any question related to the content of your uploaded documents for a precise answer.
""")
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_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, api_key):
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
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=0.3, google_api_key=api_key)
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, api_key):
embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", google_api_key=api_key)
new_db = FAISS.load_local("faiss_index", embeddings)
docs = new_db.similarity_search(user_question)
chain = get_conversational_chain()
response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
st.write("Reply: ", response["output_text"])
def main():
st.header("AI clone chatbot💁")
user_question = st.text_input("Ask a Question from the PDF Files", key="user_question")
if user_question: # Only check for the user question now
user_input(user_question, api_key)
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, key="pdf_uploader")
if st.button("Submit & Process", key="process_button"): # No need to check for API key here
with st.spinner("Processing..."):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
get_vector_store(text_chunks, api_key)
st.success("Done")
if __name__ == "__main__":
main()
|