Spaces:
Runtime error
Runtime error
File size: 2,729 Bytes
3265841 39729db 3265841 39729db 3265841 39729db 3265841 7d04a4b 39729db 3265841 |
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 |
import streamlit as st
import tempfile
import pandas as pd
from langchain import HuggingFacePipeline
from transformers import AutoTokenizer
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.document_loaders.csv_loader import CSVLoader
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA
import transformers
import torch
import textwrap
def main():
st.set_page_config(page_title="👨💻 Talk with BORROWER data")
st.title("👨💻 Talk with BORROWER data")
uploaded_file = st.sidebar.file_uploader("Upload your Data", type="csv")
query = st.text_input("Send a Message")
if st.button("Submit Query", type="primary"):
DB_FAISS_PATH = "vectorstore/db_faiss"
if uploaded_file :
#use tempfile because CSVLoader only accepts a file_path
with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
tmp_file.write(uploaded_file.getvalue())
tmp_file_path = tmp_file.name
loader = CSVLoader(file_path=tmp_file_path, encoding="utf-8", csv_args={
'delimiter': ','})
data = loader.load()
st.write(data)
model = "daryl149/llama-2-7b-chat-hf"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline("text-generation", #task
model=model,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
trust_remote_code=True,
device_map="auto",
max_length=1000,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id
)
llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0})
embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
vectorstore = FAISS.from_documents(data, embeddings)
vectorstore.save_local(DB_FAISS_PATH)
chain = RetrievalQA.from_chain_type(llm=llm, chain_type = "stuff",return_source_documents=True, retriever=vectorstore.as_retriever())
result=chain(query)
wrapped_text = textwrap.fill(result['result'], width=500)
st.write(wrapped_text)
if __name__ == '__main__':
main()
|