Spaces:

uyen13
/

chatgirl

Sleeping

App Files Files Community

chatgirl / app.py

uyen13

Update app.py

c3579f9 9 months ago

raw history blame contribute delete

No virus

4.2 kB

	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
	from ctransformers import AutoModelForCausalLM
	from langchain_g4f import G4FLLM
	from g4f import Provider, models
	import requests
	# Define the path for generated embeddings
	DB_FAISS_PATH = 'vectorstore/db_faiss'

	# Load the model of choice
	def load_llm():
	# url = "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML/blob/main/llama-2-7b-chat.ggmlv3.q4_K_M.bin" # 2.87G

	# model_loc, file_size = dl_hf_model(url)

	# llm = CTransformers(
	# model=model_loc,
	# temperature=0.2,
	# model_type="llama",
	# top_k=10,
	# top_p=0.9,
	# repetition_penalty=1.0,
	# max_new_tokens=512, # adjust as needed
	# seed=42,
	# reset=True, # reset history (cache)
	# stream=False,
	# # threads=cpu_count,
	# # stop=prompt_prefix[1:2],


	# )
	llm = G4FLLM(
	model=models.gpt_35_turbo,
	provider=Provider.DeepAi,
	)
	return llm
	hide_streamlit_style = """
	<style>
	#MainMenu {visibility: hidden;}
	footer {visibility: hidden;}
	</style>
	"""
	st.markdown(hide_streamlit_style, unsafe_allow_html=True)

	# Set the title for the Streamlit app
	st.title("Coloring Anime ChatBot")

	csv_url = "https://huggingface.co/spaces/uyen13/chatgirl/raw/main/testchatdata.csv"
	# csv_url="https://docs.google.com/uc?export=download&id=1fQ2v2n9zQcoi6JoOU3lCBDHRt3a1PmaE"

	# Define the path where you want to save the downloaded file
	tmp_file_path = "testchatdata.csv"

	# Download the CSV file
	response = requests.get(csv_url)
	if response.status_code == 200:
	with open(tmp_file_path, 'wb') as file:
	file.write(response.content)
	else:
	raise Exception(f"Failed to download the CSV file from {csv_url}")

	# 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 about this page like coloring book,how to buy ... 🤗"]

	if 'past' not in st.session_state:
	st.session_state['past'] = ["your chat here"]

	# 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("ChatBox", placeholder="Ask anything... ", 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")