File size: 2,381 Bytes
0dc0782 e7b14e0 0dc0782 fa5b702 0dc0782 bd481ed 0dc0782 fa5b702 0dc0782 fa5b702 0dc0782 fa5b702 0dc0782 fa5b702 0dc0782 fa5b702 0dc0782 fa5b702 |
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 |
# Import necessary libraries
import streamlit as st
import os
from openai import OpenAI
import json
working_dir = os.path.dirname(os.path.abspath(__file__))
endpoint_data = json.load(open(f"{working_dir}/model_info.json"))
def clear_chat():
st.session_state.messages = []
st.title("Intel® AI for Enterprise Inference")
st.header("LLM chatbot")
# Extract the keys (model names) from the JSON data
# model_names = list(endpoint_data.keys())
with st.sidebar:
#Enter openai_api key under "Secrets " in HF settings
#Enter base_url under "Variables" in HF settings
api_key = st.session_state.api_key = st.secrets["openai_apikey"]
base_url = st.session_state.base_url = os.environ.get("base_url")
client = OpenAI(api_key=api_key, base_url=base_url)
model_names = client.models.list()
modelname = st.selectbox("Select LLM model (Running on Intel® Gaudi®) ", model_names)
st.write(f"You selected: {modelname}")
st.button("Start New Chat", on_click=clear_chat)
try:
if "messages" not in st.session_state:
st.session_state.messages = []
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
if prompt := st.chat_input("What is up?"):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.markdown(prompt)
with st.chat_message("assistant"):
try:
stream = client.chat.completions.create(
model=modelname,
messages=[
{"role": m["role"], "content": m["content"]}
for m in st.session_state.messages
],
max_tokens=4096,
stream=True,
)
response = st.write_stream(stream)
except Exception as e:
st.error(f"An error occurred while generating the response: {e}")
response = "An error occurred while generating the response."
st.session_state.messages.append({"role": "assistant", "content": response})
except KeyError as e:
st.error(f"Key error: {e}")
except Exception as e:
st.error(f"An unexpected error occurred: {e}") |