File size: 3,244 Bytes
d473e6d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e217eee
 
 
 
d473e6d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e217eee
 
d473e6d
 
 
 
e217eee
d473e6d
e217eee
d473e6d
 
 
e217eee
d473e6d
 
e217eee
d473e6d
 
 
 
 
 
 
 
e217eee
d473e6d
 
 
 
 
 
 
 
 
 
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
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


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=1000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks


def get_vector_stores(text_chunks, api_key):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", api_key=api_key)
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")


def conversation_chain(api_key):
    prompt_template = """
    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context,
    just say, "answer is not available in the context", don't provide the wrong answer or give answers by yourself.\n\n
    Context:\n{context}\n
    Question:\n{question}\n
    Answer:
    """
    model = ChatGoogleGenerativeAI(model="gemini-pro", api_key=api_key, 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_q, api_key):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001", api_key=api_key)
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
    docs = new_db.similarity_search(user_q)

    chain = conversation_chain(api_key)
    response = chain({"input_documents": docs, "question": user_q}, return_only_outputs=True)

    st.write("Reply ->", response["output_text"])


def main():
    st.set_page_config("Chat PDF")
    st.header("Chat with PDF using Gemini 💁")

    # Ask for API key input
    api_key = st.text_input("Enter your Gemini API Key", type="password")

    if api_key:
        # Configure the API
        genai.configure(api_key=api_key)

        # Input for user questions
        user_question = st.text_input("Ask a Question from the PDF Files")
        if user_question:
            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)
            if st.button("Submit and Process"):
                with st.spinner("Processing..."):
                    raw_text = get_pdf_text(pdf_docs)
                    text_chunks = get_text_chunks(raw_text)
                    get_vector_stores(text_chunks, api_key)
                    st.success("Done")
    else:
        st.warning("Please enter your Gemini API key to proceed.")


if __name__ == "__main__":
    main()