Spaces:
Sleeping
Sleeping
File size: 3,748 Bytes
935976c |
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 |
import streamlit as st
import os
from PyPDF2 import PdfReader
import docx
from langchain.chat_models import ChatOpenAI
from langchain.llms import OpenAI
from dotenv import load_dotenv
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory
from streamlit_chat import message
from langchain.callbacks import get_openai_callback
# Load environment variables
load_dotenv()
openapi_key = os.getenv("OPENAI_API_KEY")
def main():
st.set_page_config(page_title="Chat with your file")
st.header("DocumentGPT")
if "conversation" not in st.session_state:
st.session_state.conversation = None
if "chat_history" not in st.session_state:
st.session_state.chat_history = None
if "processComplete" not in st.session_state:
st.session_state.processComplete = None
with st.sidebar:
uploaded_files = st.file_uploader("Upload your file", type=['pdf', 'docx'], accept_multiple_files=True)
process = st.button("Process")
if process:
if not openapi_key:
st.info("Please add your OpenAI API key to continue.")
st.stop()
files_text = get_files_text(uploaded_files)
st.write("File loaded...")
text_chunks = get_text_chunks(files_text)
st.write("File chunks created...")
vectorstore = get_vectorstore(text_chunks)
st.write("Vector Store Created...")
st.session_state.conversation = get_conversation_chain(vectorstore, openapi_key)
st.session_state.processComplete = True
if st.session_state.processComplete:
user_question = st.chat_input("Ask a question about your files.")
if user_question:
handle_user_input(user_question)
def get_files_text(uploaded_files):
text = ""
for uploaded_file in uploaded_files:
file_extension = os.path.splitext(uploaded_file.name)[1]
if file_extension == ".pdf":
text += get_pdf_text(uploaded_file)
elif file_extension == ".docx":
text += get_docx_text(uploaded_file)
return text
def get_pdf_text(pdf):
pdf_reader = PdfReader(pdf)
text = ""
for page in pdf_reader.pages:
text += page.extract_text()
return text
def get_docx_text(file):
doc = docx.Document(file)
return ' '.join([para.text for para in doc.paragraphs])
def get_text_chunks(text):
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size=900,
chunk_overlap=100,
length_function=len
)
return text_splitter.split_text(text)
def get_vectorstore(text_chunks):
embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
return FAISS.from_texts(text_chunks, embeddings)
def get_conversation_chain(vectorstore, openapi_key):
llm = ChatOpenAI(openai_api_key=openapi_key, model_name='gpt-3.5-turbo', temperature=0)
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
return ConversationalRetrievalChain.from_llm(
llm=llm,
retriever=vectorstore.as_retriever(),
memory=memory
)
def handle_user_input(user_question):
with get_openai_callback() as cb:
response = st.session_state.conversation({'question': user_question})
st.session_state.chat_history = response['chat_history']
response_container = st.container()
with response_container:
for i, message in enumerate(st.session_state.chat_history):
message(message.content, is_user=(i % 2 == 0), key=str(i))
if __name__ == '__main__':
main() |