File size: 3,370 Bytes
0a5815c 34da4cb 0a5815c |
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 |
# Import necessary libraries
import streamlit as st
from streamlit_chat import message
import tempfile
from langchain.document_loaders.csv_loader import CSVLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import CTransformers
from langchain.chains import ConversationalRetrievalChain
import sys
sys.path.append(r"vectorstore/db_faiss")
import dataset_utils
# Define the path for generated embeddings
DB_FAISS_PATH = 'vectorstore/db_faiss'
# Load the model of choice
def load_llm():
llm = CTransformers(
model="meta-llama/Llama-2-7b",
model_type="llama",
max_new_tokens=512,
temperature=0.5
)
return llm
# Set the title for the Streamlit app
st.title("Llama2 Chat CSV - 🦜🦙")
# Create a file uploader in the sidebar
uploaded_file = st.sidebar.file_uploader("Upload File", type="csv")
# Handle file upload
if uploaded_file:
with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
tmp_file.write(uploaded_file.getvalue())
tmp_file_path = tmp_file.name
# Load CSV data using CSVLoader
loader = CSVLoader(file_path=tmp_file_path, encoding="utf-8", csv_args={'delimiter': ','})
data = loader.load()
# Create embeddings using Sentence Transformers
embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2', model_kwargs={'device': 'cpu'})
# Create a FAISS vector store and save embeddings
db = FAISS.from_documents(data, embeddings)
db.save_local(DB_FAISS_PATH)
# Load the language model
llm = load_llm()
# Create a conversational chain
chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=db.as_retriever())
# Function for conversational chat
def conversational_chat(query):
result = chain({"question": query, "chat_history": st.session_state['history']})
st.session_state['history'].append((query, result["answer"]))
return result["answer"]
# Initialize chat history
if 'history' not in st.session_state:
st.session_state['history'] = []
# Initialize messages
if 'generated' not in st.session_state:
st.session_state['generated'] = ["Hello ! Ask me(LLAMA2) about " + uploaded_file.name + " 🤗"]
if 'past' not in st.session_state:
st.session_state['past'] = ["Hey ! 👋"]
# Create containers for chat history and user input
response_container = st.container()
container = st.container()
# User input form
with container:
with st.form(key='my_form', clear_on_submit=True):
user_input = st.text_input("Query:", placeholder="Talk to csv data 👉 (:", key='input')
submit_button = st.form_submit_button(label='Send')
if submit_button and user_input:
output = conversational_chat(user_input)
st.session_state['past'].append(user_input)
st.session_state['generated'].append(output)
# Display chat history
if st.session_state['generated']:
with response_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="big-smile")
message(st.session_state["generated"][i], key=str(i), avatar_style="thumbs") |