app.py

from transformers import AutoModelForCausalLM, AutoTokenizer

from langchain.chat_models import ChatOpenAI
from langchain.chains import ConversationChain
from langchain.chains.conversation.memory import ConversationBufferWindowMemory
from langchain.prompts import PromptTemplate

import gradio as gr

REPO_ID = "ksh-nyp/llama-2-7b-chat-TCMKB"

# Load the model and tokenizer from Hugging Face's model hub
model = AutoModelForCausalLM.from_pretrained(REPO_ID)
tokenizer = AutoTokenizer.from_pretrained(REPO_ID)

llm = ChatOpenAI(model=model, tokenizer=tokenizer)

if 'buffer_memory' not in st.session_state:
    st.session_state.buffer_memory = ConversationBufferWindowMemory(k=3)

conversation = ConversationChain(
    llm=llm,
    memory=st.session_state.buffer_memory,
    verbose=True
)

context = """ 
Act as an OrderBot, you work collecting orders in a delivery only fast food restaurant called My Dear Frankfurt. \
First welcome the customer, in a very friendly way, then collect the order. \
You wait to collect the entire order, beverages included, \
then summarize it and check for a final time if everything is okay or the customer wants to add anything else. \
Finally, you collect the payment. \
Make sure to clarify all options, extras, and sizes to uniquely identify the item from the menu. \
You respond in a short, very friendly style. \
The menu includes:
burgers 12.95, 10.00, 7.00
frankfurts 10.95, 9.25, 6.50
sandwiches 11.95, 9.75, 6.75
fries 4.50, 3.50
salad 7.25
Toppings:
extra cheese 2.00,
mushrooms 1.50
martra sausage 3.00
canadian bacon 3.50
romesco sauce 1.50
peppers 1.00
Drinks:
coke 3.00, 2.00, 1.00
sprite 3.00, 2.00, 1.00
vichy catalan 5.00
"""

prompt_template = PromptTemplate.from_template('''system role :{context} \
        user:{query}\
        assistance: 
        ''')

# Define Gradio Interface
iface = gr.Interface(
    fn=lambda query: conversation.run(prompt_template.format(context=context, query=query)),
    inputs=gr.Textbox(),
    outputs=gr.Textbox(),
    live=True,
    capture_session=True
)

# Launch Gradio Interface
iface.launch()