Spaces:
Runtime error
Runtime error
File size: 4,419 Bytes
d6626e6 337ce72 d6626e6 bf65290 d6626e6 337ce72 d6626e6 264f598 d6626e6 337ce72 d6626e6 |
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 |
import streamlit as st
import openai
import os
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.chat_models import ChatOpenAI
from htmlTemplates import css, bot_template, user_template
from PIL import Image
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
# documentation for CharacterTextSplitter:
# https://python.langchain.com/en/latest/modules/indexes/text_splitters/examples/character_text_splitter.html
def get_text_chunk(text):
text_splitter = CharacterTextSplitter(
separator="\n",
chunk_size = 1000,
chunk_overlap = 200,
length_function = len
)
chunks = text_splitter.split_text(text)
return chunks
#embedding using openAI embedding. Warn: This will cost you money
def get_vectorstore_openAI(text_chunks):
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
return vectorstore
#embedding using instructor-xl with your local machine for free
#you can find more details at: https://huggingface.co/hkunlp/instructor-xl
def get_vectorstore(text_chunks):
embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
return vectorstore
def get_conversation_chain(vectorstore):
llm = ChatOpenAI()
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
conversation_chain = ConversationalRetrievalChain.from_llm(
llm=llm,
retriever=vectorstore.as_retriever(),
memory = memory
)
return conversation_chain
def handle_userinput(user_question):
response = st.session_state.conversation({'question': user_question})
st.session_state.chat_history = response['chat_history']
for i, message in enumerate(st.session_state.chat_history):
if i%2 == 0:
st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
else:
st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
def main():
##############################################################################
#load openai api_key from .evn
# load_dotenv()
openai.api_key = os.getenv("OPENAI_API_KEY")
##############################################################################
#set up basic page
st.set_page_config(page_title="Chat With multiple PDFs", page_icon=":books:")
st.write(css, unsafe_allow_html=True)
#initial session_state in order to avoid refresh
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
st.header("Chat based on PDF you provided :books:")
user_question = st.text_input("Ask a question about your documents:")
if user_question:
handle_userinput(user_question)
# Define the templates
with st.sidebar:
st.subheader("Your PDF documents")
pdf_docs = st.file_uploader("Upload your pdfs here and click on 'Proces'", accept_multiple_files= True)
#if the button is pressed
if st.button("Process"):
with st.spinner("Processing"):
#get pdf text
raw_text = get_pdf_text(pdf_docs)
print('raw_text is created')
#get the text chunks
text_chunks = get_text_chunk(raw_text)
print('text_chunks are generated')
#create vector store
vectorstore = get_vectorstore_openAI(text_chunks)
print('vectorstore is created')
#create converstion chain
st.session_state.conversation = get_conversation_chain(vectorstore)
print('conversation chain created')
# to run this application, you need to run "streamlit run app.py"
if __name__ == '__main__':
main() |