Spaces:
Sleeping
Sleeping
File size: 3,784 Bytes
554d4a4 |
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 |
import streamlit as st
from streamlit_chat import message
from langchain.chains import ConversationalRetrievalChain
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.llms import LlamaCpp
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.document_loaders import PyPDFLoader
import os
import tempfile
from langchain.document_loaders import PyPDFDirectoryLoader
from langchain.chains import RetrievalQA
def initialize_session_state():
if 'history' not in st.session_state:
st.session_state['history'] = []
if 'generated' not in st.session_state:
st.session_state['generated'] = ["Hello! Ask me anything about 🤗"]
if 'past' not in st.session_state:
st.session_state['past'] = ["Hey! 👋"]
def conversation_chat(query, chain, history):
result = chain({"question": query, "chat_history": history})
history.append((query, result["answer"]))
return result["answer"]
def display_chat_history(chain):
reply_container = st.container()
container = st.container()
with container:
with st.form(key='my_form', clear_on_submit=True):
user_input = st.text_input("Question:", placeholder="Ask about your PDF", key='input')
submit_button = st.form_submit_button(label='Send')
if submit_button and user_input:
with st.spinner('Generating response...'):
output = conversation_chat(user_input, chain, st.session_state['history'])
st.session_state['past'].append(user_input)
st.session_state['generated'].append(output)
if st.session_state['generated']:
with reply_container:
for i in range(len(st.session_state['generated'])):
message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
def create_conversational_chain(vector_store):
# Create llm
# Importing the Model
llm = LlamaCpp(
streaming = True,
model_path = "model/mistral-7b-instruct-v0.2.Q4_K_M.gguf",
temperature = 0.75,
top_p = 1,
verbose = True,
n_ctx = 4096
)
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
memory=memory)
return chain
def main():
# Initialize session state
initialize_session_state()
st.title("Multi-PDF ChatBot using Mistral-7B-Instruct :books:")
# Initialize Streamlit
# st.sidebar.title("Document Processing")
# uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
# Loading the file directory using PyPDF Directory
loader = PyPDFDirectoryLoader("data_pdf/")
data = loader.load()
# Splitting extracted text data into chunks for easier processing
text_splitter = RecursiveCharacterTextSplitter(chunk_size = 100000, chunk_overlap = 20)
text_chunks = text_splitter.split_documents(data)
# Downloading Embessings
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
# Creating Embeddings for each of the text chunk
vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
# Create the chain object
chain = create_conversational_chain(vector_store)
display_chat_history(chain)
if __name__ == "__main__":
main() |