import os import streamlit as st from dotenv import load_dotenv from PyPDF2 import PdfReader from langchain.text_splitter import CharacterTextSplitter from langchain.embeddings import HuggingFaceBgeEmbeddings from langchain.vectorstores import FAISS from langchain.chat_models import ChatOpenAI from langchain.memory import ConversationBufferMemory from langchain.chains import ConversationalRetrievalChain from htmlTemplates import css, bot_template, user_template from langchain.llms import HuggingFaceHub from deep_translator import GoogleTranslator # set this key as an environment variable os.environ["HUGGINGFACEHUB_API_TOKEN"] = st.secrets['huggingface_token'] ########################################################################################### def get_pdf_text(pdf_docs : list) -> str: text = "" for pdf in pdf_docs: pdf_reader = PdfReader(pdf) for page in pdf_reader.pages: text += page.extract_text() return text ########################################### def load_file(): loader = TextLoader('d2.txt') documents = loader.load() return documents ###################################### def get_text_chunks(text:str) ->list: text_splitter = CharacterTextSplitter( separator="\n", chunk_size=1500, chunk_overlap=300, length_function=len ) chunks = text_splitter.split_text(text) return chunks def get_vectorstore(text_chunks : list) -> FAISS: model = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2" encode_kwargs = { "normalize_embeddings": True } # set True to compute cosine similarity embeddings = HuggingFaceBgeEmbeddings( model_name=model, encode_kwargs=encode_kwargs, model_kwargs={"device": "cpu"} ) vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings) return vectorstore def get_conversation_chain(vectorstore:FAISS) -> ConversationalRetrievalChain: # llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613") llm = HuggingFaceHub( repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", #repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF" model_kwargs={"temperature": 0.5, "max_length": 2048}, ) 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:str): 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: text2=message.content translator = GoogleTranslator(source='english', target='persian') result = translator.translate(text2) st.write("سوال کاربر: "+result) else: text1=message.content translator = GoogleTranslator(source='english', target='persian') result = translator.translate(text1) st.write("پاسخ ربات: "+result) ############################################################################################################# def read_pdf_pr_en(pdf_file_path): from deep_translator import GoogleTranslator import PyPDF2 # مسیر فایل PDF را تعیین کنید #pdf_file_path = '/content/d2en.pdf' # باز کردن فایل PDF with open(pdf_file_path, 'rb') as pdf_file: pdf_reader = PyPDF2.PdfReader(pdf_file) # خواندن محتوای صفحه‌ها full_text = '' for page in pdf_reader.pages: page_pdf=page.extract_text() translator = GoogleTranslator(source='persian', target='english') result = translator.translate(page_pdf) full_text +=result st.write(full_text) return(full_text) ################################################################################################################# def get_pdf_text(pdf_docs): text = "" for pdf in pdf_docs: pdf_reader = PdfReader(pdf) for page in pdf_reader.pages: txt_page=page.extract_text() text += txt_page return text ################################33333333333333333333333333333333333333333333333333333333 def main(): st.set_page_config( page_title="Chat Bot PDFs", page_icon=":books:", ) #st.markdown("# Chat with a Bot") #st.markdown("This bot tries to answer questions about multiple PDFs. Let the processing of the PDF finish before adding your question. 🙏🏾") 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("Chat Bot PDFs :books:") user_question1 = st.text_input("Ask a question about your documents:") translator = GoogleTranslator(source='persian', target='english') user_question = translator.translate(user_question1) if st.button("Answer"): with st.spinner("Answering"): handle_userinput(user_question) if st.button("CLEAR"): with st.spinner("CLEARING"): st.cache_data.clear() with st.sidebar: st.subheader("Your documents") pdf_docs = st.file_uploader( "Upload your PDFs here and click on 'Process'", accept_multiple_files=True ) file_path = pdf_docs.name st.write( file_path) full_text=read_pdf_pr_en(pdf_file_path=file_path) if st.button("Process"): with st.spinner("Processing"): st.write(pdf_docs) # get pdf text raw_text = get_pdf_text(pdf_docs) # get the text chunks text_chunks = get_text_chunks(raw_text) # create vector store vectorstore = get_vectorstore(text_chunks) # create conversation chain st.session_state.conversation = get_conversation_chain(vectorstore) #compelete build model st.write("compelete build model") if __name__ == "__main__": main()