Spaces:
Sleeping
Sleeping
File size: 5,235 Bytes
2057158 547cbaa 2057158 547cbaa 2057158 560feb8 c87e7b9 2057158 547cbaa |
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 |
import streamlit as st
import os
from PyPDF2 import PdfReader
import openpyxl
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import GooglePalmEmbeddings
from langchain.llms import GooglePalm
from langchain.vectorstores import FAISS
from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
os.environ['GOOGLE_API_KEY'] = 'your_google_api_key_here'
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_excel_text(excel_docs):
text = ""
for excel_doc in excel_docs:
workbook = openpyxl.load_workbook(filename=excel_doc)
for sheet in workbook:
for row in sheet:
for cell in row:
text += str(cell.value) + " "
return text.strip()
def get_text_chunks(text):
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=20)
chunks = text_splitter.split_text(text)
return chunks
def get_vector_store(text_chunks):
embeddings = GooglePalmEmbeddings()
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
return vector_store
def get_conversational_chain(vector_store):
llm = GooglePalm()
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
conversation_chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=vector_store.as_retriever(), memory=memory)
return conversation_chain
def get_user_input(user_question):
with st.container():
response = st.session_state.conversation({'question': user_question})
st.session_state.chatHistory = response['chat_history']
file_contents = ""
left , right = st.columns((2,1))
with left:
for i, message in enumerate(st.session_state.chatHistory):
if i % 2 == 0:
st.markdown(f'<div style="background-color: rgb(30 24 17 / 77%); border-radius: 10px; padding: 10px; margin-bottom: 5px; text-align: end;"><span style="text-align: end;">User:</span> {message.content}</div>', unsafe_allow_html=True)
else:
st.markdown(f'<div style="background-color: rgb(145 74 1 / 25%); border-radius: 10px; padding: 10px; margin-bottom: 5px; ">Bot: {message.content}</div>', unsafe_allow_html=True)
with right:
for message in st.session_state.chatHistory:
file_contents += f"{message.content}\n"
file_name = "Chat_History.txt"
def main():
st.set_page_config("DocChat")
# Define Streamlit app layout
st.markdown("<style>body { background-color: black; color: white; }</style>", unsafe_allow_html=True)
st.markdown("<h3 style='color: orange;'>🧾 DocChat - Chat with multiple documents</h3>", unsafe_allow_html=True)
st.caption("🚀 Chat bot developed By :- [Dinesh Abeysinghe](https://www.linkedin.com/in/dinesh-abeysinghe-bb773293) | [GitHub Source Code](https://github.com/dineshabey/AI-Chat_with_document)")
st.markdown("<div style= 'text-align: center;'>First need to upload PDF file or Excel file. Then click PROCESS PDF file / PROCESS EXCEL file and next you can start chat with document related things <span style='color: orange;'>Please click like button</span>❤️ and support me and enjoy it.</div>", unsafe_allow_html=True)
st.write("---")
with st.container():
with st.sidebar:
st.title("Settings")
st.subheader("Upload Documents")
st.markdown("**PDF files:**")
pdf_docs = st.file_uploader("Upload PDF Files", accept_multiple_files=True)
if st.button("Process PDF file"):
with st.spinner("Processing PDFs..."):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
vector_store = get_vector_store(text_chunks)
st.session_state.conversation = get_conversational_chain(vector_store)
st.success("PDF processed successfully!")
st.markdown("**Excel files:**")
excel_docs = st.file_uploader("Upload Excel Files", accept_multiple_files=True)
if st.button("Process Excel file"):
with st.spinner("Processing Excel files..."):
raw_text = get_excel_text(excel_docs)
text_chunks = get_text_chunks(raw_text)
vector_store = get_vector_store(text_chunks)
st.session_state.conversation = get_conversational_chain(vector_store)
st.success("Excel file processed successfully!")
with st.container():
st.subheader("Document Q&A")
user_question = st.text_input("Ask a Question from the document")
if "conversation" not in st.session_state:
st.session_state.conversation = None
if "chatHistory" not in st.session_state:
st.session_state.chatHistory = None
if user_question:
get_user_input(user_question)
if __name__ == "__main__":
main()
|