Spaces:
Running
Running
import streamlit as st | |
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.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 | |
import os | |
OPENAI_API_KEY=os.getenv('OPENAI_API_KEY') | |
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_text_chunks(text): | |
text_splitter = CharacterTextSplitter( | |
separator="\n", | |
chunk_size=1000, | |
chunk_overlap=200, | |
length_function=len | |
) | |
chunks = text_splitter.split_text(text) | |
return chunks | |
def get_vectorstore(text_chunks): | |
embeddings = OpenAIEmbeddings() | |
# 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() | |
# llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}) | |
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_dotenv() | |
st.set_page_config(page_title="Chat with multiple PDFs", | |
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("Chat with multiple PDFs :books:") | |
user_question = st.text_input("Ask a question about your documents:") | |
if user_question: | |
handle_userinput(user_question) | |
with st.sidebar: | |
st.subheader("Your documents") | |
pdf_docs = st.file_uploader( | |
"Upload your PDFs here and click on 'Process'", accept_multiple_files=True) | |
if st.button("Process"): | |
with st.spinner("Processing"): | |
# 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) | |
if __name__ == '__main__': | |
main() | |
# Attempting uninstall: tokenizers | |
# Found existing installation: tokenizers 0.15.2 | |
# Uninstalling tokenizers-0.15.2: | |
# Successfully uninstalled tokenizers-0.15.2 | |
# Attempting uninstall: faiss-cpu | |
# Found existing installation: faiss-cpu 1.8.0.post1 | |
# Uninstalling faiss-cpu-1.8.0.post1: | |
# Successfully uninstalled faiss-cpu-1.8.0.post1 | |
# Attempting uninstall: python-dotenv | |
# Found existing installation: python-dotenv 1.0.1 | |
# Uninstalling python-dotenv-1.0.1: | |
# Successfully uninstalled python-dotenv-1.0.1 | |
# Attempting uninstall: pydantic | |
# Found existing installation: pydantic 2.10.2 | |
# Uninstalling pydantic-2.10.2: | |
# Successfully uninstalled pydantic-2.10.2 | |
# Attempting uninstall: protobuf | |
# Found existing installation: protobuf 4.25.5 | |
# Uninstalling protobuf-4.25.5: | |
# Successfully uninstalled protobuf-4.25.5 | |
# Attempting uninstall: torch | |
# Found existing installation: torch 2.1.1 | |
# Uninstalling torch-2.1.1: | |
# Successfully uninstalled torch-2.1.1 | |
# Attempting uninstall: tiktoken | |
# Found existing installation: tiktoken 0.7.0 | |
# Uninstalling tiktoken-0.7.0: | |
# Successfully uninstalled tiktoken-0.7.0 | |
# Attempting uninstall: huggingface-hub | |
# Found existing installation: huggingface-hub 0.23.4 | |
# Uninstalling huggingface-hub-0.23.4: | |
# Successfully uninstalled huggingface-hub-0.23.4 | |
# Attempting uninstall: dataclasses-json | |
# Found existing installation: dataclasses-json 0.6.7 | |
# Uninstalling dataclasses-json-0.6.7: | |
# Successfully uninstalled dataclasses-json-0.6.7 | |
# Attempting uninstall: transformers | |
# Found existing installation: transformers 4.35.2 | |
# Uninstalling transformers-4.35.2: | |
# Successfully uninstalled transformers-4.35.2 | |
# Attempting uninstall: openai | |
# Found existing installation: openai 1.57.4 | |
# Uninstalling openai-1.57.4: | |
# Successfully uninstalled openai-1.57.4 | |
# Attempting uninstall: langchain | |
# Found existing installation: langchain 0.2.5 | |
# Uninstalling langchain-0.2.5: | |
# Successfully uninstalled langchain-0.2.5 | |
# Attempting uninstall: sentence-transformers | |
# Found existing installation: sentence-transformers 3.0.1 | |
# Uninstalling sentence-transformers-3.0.1: | |
# Successfully uninstalled sentence-transformers-3.0.1 | |
# Attempting uninstall: altair | |
# Found existing installation: altair 5.5.0 | |
# Uninstalling altair-5.5.0: | |
# Successfully uninstalled altair-5.5.0 | |
# Attempting uninstall: streamlit | |
# Found existing installation: streamlit 1.41.1 | |
# Uninstalling streamlit-1.41.1: | |
# Successfully uninstalled streamlit-1.41.1 |