Spaces:
Running
Running
File size: 4,988 Bytes
d02c555 2ec3bd5 d02c555 0e30719 d02c555 4f14541 fe9e680 4f14541 d02c555 7fe73eb 2ec3bd5 7e5e56e b714b43 c24c097 7fe73eb b714b43 d02c555 7fe73eb d02c555 dcfb64b 293a762 d02c555 dcfb64b fe9e680 cc17fdc dcfb64b d02c555 cc17fdc d02c555 cc17fdc d02c555 dcfb64b cc17fdc dcfb64b cc17fdc dcfb64b d02c555 dcfb64b 05d63de d02c555 827df7b d02c555 cc17fdc |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 |
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
#load_dotenv()
#os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=st.secrets["GOOGLE_API_KEY"])
footer="""<style>
a:link , a:visited{
color: blue;
background-color: transparent;
text-decoration: underline;
}
a:hover, a:active {
color: red;
background-color: transparent;
text-decoration: underline;
}
.footer {
position: fixed;
left: 0;
bottom: 0;
width: 100%;
color: black;
text-align: center;
}
</style>
<div class="footer">
<p>powered by google gemini<a style='display: block; text-align: center;' href="https://www.linkedin.com/in/shubhendu-ghosh-423092205/" target="_blank">Developer</a></p>
</div>
"""
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):
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=0.3)
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):
embeddings = GoogleGenerativeAIEmbeddings(model = "models/embedding-001")
try:
new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
docs = new_db.similarity_search(user_question)
except Exception as e:
st.markdown(f"""<p style="color: #e80000;font-size: 15px;font-family: sans-serif; text-align:left;margin-bottom: 0px; height: 5px">Document not submitted. Please upload a pdf and then click on 'submit'. Only then we can answer your question</p>""", unsafe_allow_html=True)
return None
#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)
print(response)
st.markdown(f"""<p style="color: #000000;font-size: 15px;font-family: sans-serif; text-align:left;margin-bottom: 0px; height: 5px">{response["output_text"]}</p>""", unsafe_allow_html=True)
def main():
# Set page config and header
st.set_page_config("Chat PDF")
st.markdown("""<p style="color: #0352ff;font-size: 70px;font-family: arial; text-align:center; margin-bottom: 0px;" ><b>POLY</b><span style="color: #ec11f7;font-size: 70px;font-family: arial;"><b>DOCS</b></span></p>""", unsafe_allow_html=True)
st.markdown("""<p style="color: #0352ff;font-size: 30px;font-family: sans-serif; text-align:center; margin-bottom: 50px;">Chat with your PDF</p>""", unsafe_allow_html=True)
# Text input for user question
st.markdown("""<p style="color: #0352ff;font-size: 15px;font-family: sans-serif; text-align:left;margin-bottom: 0px; height: 5px">Ask a Question from the PDF Files </p>""", unsafe_allow_html=True)
user_question = st.text_input("")
# If user inputs a question, process it
if user_question:
user_input(user_question)
# Sidebar menu
with st.sidebar:
st.title("Menu")
# File uploader for PDF files
pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit Button", accept_multiple_files=True)
# Button to submit and process PDF files
if st.button("Submit"):
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("Uploaded")
st.markdown(footer,unsafe_allow_html=True)
if __name__ == "__main__":
main()
|