Spaces:
Build error
Build error
File size: 2,755 Bytes
6c14dd8 |
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 |
import streamlit as st
import os
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain_mistralai.chat_models import ChatMistralAI
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmltemp import css, botTemp, userTemp
def get_text(docs):
text= ""
for pdf in docs:
pdf_reader=PdfReader(pdf)
for page in pdf_reader.pages:
text+=page.extract_text()
return text
def get_chunks(rawtxt):
splitter=CharacterTextSplitter(
separator="\n",
chunk_size=1000,
chunk_overlap=200,
length_function=len
)
chunks=splitter.split_text(rawtxt)
return chunks
def get_vectorstore(chunks):
openai_api_key = os.environ.get('OPENAI_API_KEY')
embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
vectors=FAISS.from_texts(texts=chunks,embedding=embeddings)
return vectors
def get_convo_chain(vector):
llm = ChatMistralAI() # Use ChatMistralAI instead of ChatOpenAI
memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
convo_chain = ConversationalRetrievalChain.from_llm(
llm=llm,
retriever=vector.as_retriever(),
memory=memory
)
return convo_chain
def handle_inp(inp):
response=st.session_state.conversation({'question':inp})
st.session_state.chat_history= response['chat_history']
for i, msg in enumerate(st.session_state.chat_history):
if i%2==0:
st.write(userTemp.replace("{{MSG}}",msg.content),unsafe_allow_html=True)
else:
st.write(botTemp.replace("{{MSG}}",msg.content),unsafe_allow_html=True)
def main():
load_dotenv()
st.set_page_config(page_title="PDF Chat", page_icon=":books:")
st.write(css,unsafe_allow_html=True)
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("PDF Chat :books:")
inp= st.text_input("Ask a question about the PDF:")
if inp:
handle_inp(inp)
with st.sidebar:
st.subheader("Your PDFs")
docs=st.file_uploader("Upload your PDFs here",accept_multiple_files=True)
if st.button("Upload"):
with st.spinner("Processing"):
rawtxt=get_text(docs)
chunks=get_chunks(rawtxt)
vectors=get_vectorstore(chunks)
st.session_state.conversation=get_convo_chain(vectors)
if __name__ == "__main__":
main() |