Summary
Moving and fixing the user input placeholder to the bottom of the page.
Steps to reproduce
Code snippet:
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
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()
I have provided the link to the whole repository as well.
Expected behavior:
I am creating a chatbot using to retrieve the responses from my own PDF files. The code that I have found puts the user input on top of the page. I want to fix the user input box at the “bottom” of the page while the last response appears on top of it (exactly as we see in ChatGPT).
Actual behavior:
In the main part of the page, the user input placeholder is on the top of the page and chat history appears under it. It is uncomfortable, particularly in long chats where the last response goes all down the page and I have to scroll down a long way to read it. It should be repeated for each new response over and over again.
Debug info
- Streamlit version: (get it with
$ streamlit version) - Python version: (get it with
$ python --version) - Using Conda? PipEnv? PyEnv? Pex?
- OS version:
- Browser version:
Requirements file
Using Conda? PipEnv? PyEnv? Pex? Share the contents of your requirements file here.
Not sure what a requirements file is? Check out this doc and add a requirements file to your app.
Links
- Link to your GitHub repo: GitHub - HesamSalehiACN/Langchain_Pdf
- Link to your deployed app:
Additional information
If needed, add any other context about the problem here.