|
import streamlit as st |
|
from dotenv import load_dotenv |
|
from langchain.text_splitter import CharacterTextSplitter, RecursiveCharacterTextSplitter |
|
from langchain.vectorstores import FAISS |
|
from langchain.embeddings import HuggingFaceEmbeddings |
|
from langchain.memory import ConversationBufferMemory |
|
from langchain.chains import ConversationalRetrievalChain |
|
from htmlTemplates import css, bot_template, user_template |
|
from langchain.llms import LlamaCpp |
|
from langchain.document_loaders import PyPDFLoader, TextLoader, JSONLoader, CSVLoader |
|
import tempfile |
|
import os |
|
from huggingface_hub import hf_hub_download |
|
|
|
|
|
def get_pdf_text(pdf_docs): |
|
temp_dir = tempfile.TemporaryDirectory() |
|
temp_filepath = os.path.join(temp_dir.name, pdf_docs.name) |
|
with open(temp_filepath, "wb") as f: |
|
f.write(pdf_docs.getvalue()) |
|
pdf_loader = PyPDFLoader(temp_filepath) |
|
pdf_doc = pdf_loader.load() |
|
return pdf_doc |
|
|
|
|
|
|
|
def get_text_file(text_docs): |
|
temp_dir = tempfile.TemporaryDirectory() |
|
temp_filepath = os.path.join(temp_dir.name, text_docs.name) |
|
with open(temp_filepath, "wb") as f: |
|
f.write(text_docs.getvalue()) |
|
text_loader = DirectoryLoader(temp_filepath) |
|
text_doc = text_loader.load() |
|
return text_doc |
|
|
|
def get_csv_file(csv_docs): |
|
temp_dir = tempfile.TemporaryDirectory() |
|
temp_filepath = os.path.join(temp_dir.name, csv_docs.name) |
|
with open(temp_filepath, "wb") as f: |
|
f.write(csv_docs.getvalue()) |
|
csv_loader = CSVLoader(temp_filepath) |
|
csv_doc = csv_loader.load() |
|
return csv_doc |
|
|
|
def get_json_file(json_docs): |
|
temp_dir = tempfile.TemporaryDirectory() |
|
temp_filepath = os.path.join(temp_dir.name, json_docs.name) |
|
with open(temp_filepath, "wb") as f: |
|
f.write(json_docs.getvalue()) |
|
json_loader = JSONLoader(temp_filepath) |
|
json_doc = json_loader.load() |
|
return json_doc |
|
|
|
|
|
def get_text_chunks(documents): |
|
text_splitter = RecursiveCharacterTextSplitter( |
|
chunk_size=1000, |
|
chunk_overlap=200, |
|
length_function=len |
|
) |
|
|
|
documents = text_splitter.split_documents(documents) |
|
return documents |
|
|
|
|
|
|
|
def get_vectorstore(text_chunks): |
|
|
|
embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L12-v2', |
|
model_kwargs={'device': 'cpu'}) |
|
vectorstore = FAISS.from_documents(text_chunks, embeddings) |
|
return vectorstore |
|
|
|
|
|
def get_conversation_chain(vectorstore): |
|
if vectorstore is None: |
|
return None |
|
|
|
model_name_or_path = 'TheBloke/Llama-2-7B-chat-GGUF' |
|
model_basename = 'llama-2-7b-chat.Q2_K.gguf' |
|
model_path = hf_hub_download(repo_id=model_name_or_path, filename=model_basename) |
|
|
|
llm = LlamaCpp(model_path=model_path, |
|
n_ctx=4086, |
|
input={"temperature": 0.75, "max_length": 2000, "top_p": 1}, |
|
verbose=True, ) |
|
|
|
memory = ConversationBufferMemory( |
|
memory_key='chat_history', return_messages=True) |
|
|
|
|
|
retriever = vectorstore.as_retriever() if hasattr(vectorstore, 'as_retriever') else None |
|
|
|
if retriever is None: |
|
return None |
|
|
|
conversation_chain = ConversationalRetrievalChain.from_llm( |
|
llm=llm, |
|
retriever=vectorstore.as_retriever(), |
|
memory=memory |
|
) |
|
return conversation_chain |
|
|
|
|
|
def handle_userinput(user_question): |
|
print('user_question => ', 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 Files", |
|
page_icon=":books:") |
|
st.write(css, unsafe_allow_html=True) |
|
|
|
if "conversation" not in st.session_state: |
|
st.session_state.conversation = get_conversation_chain(None) |
|
if "chat_history" not in st.session_state: |
|
st.session_state.chat_history = None |
|
|
|
st.header("Chat with multiple Files:") |
|
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") |
|
docs = st.file_uploader( |
|
"Upload your PDFs here and click on 'Process'", accept_multiple_files=True) |
|
if st.button("Process"): |
|
with st.spinner("Processing"): |
|
|
|
doc_list = [] |
|
|
|
for file in docs: |
|
print('file - type : ', file.type) |
|
if file.type == 'text/plain': |
|
|
|
doc_list.extend(get_text_file(file)) |
|
elif file.type in ['application/octet-stream', 'application/pdf']: |
|
|
|
doc_list.extend(get_pdf_text(file)) |
|
elif file.type == 'text/csv': |
|
|
|
doc_list.extend(get_csv_file(file)) |
|
elif file.type == 'application/json': |
|
|
|
doc_list.extend(get_json_file(file)) |
|
|
|
|
|
text_chunks = get_text_chunks(doc_list) |
|
|
|
|
|
vectorstore = get_vectorstore(text_chunks) |
|
|
|
|
|
st.session_state.conversation = get_conversation_chain( |
|
vectorstore) |
|
|
|
|
|
if __name__ == '__main__': |
|
main() |