app.py

import os
from huggingface_hub import InferenceClient, login
from transformers import AutoTokenizer
from langchain.chat_models import ChatOpenAI

# access token with permission to access the model and PRO subscription
HUGGINGFACEHUB_API_TOKEN = os.getenv("HF_ACCESS_READ")
OAI_API_KEY=os.getenv("OPENAI_API_KEY")
login(token=HUGGINGFACEHUB_API_TOKEN)

# tokenizer for generating prompt
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")

# inference client
client = InferenceClient("https://api-inference.huggingface.co/models/meta-llama/Llama-2-70b-chat-hf")

# generate function
def generate(text):
    payload = tokenizer.apply_chat_template([{"role":"user","content":text}],tokenize=False)
    res = client.text_generation(
                    payload,
                    do_sample=True,
                    return_full_text=False,
                    max_new_tokens=2048,
                    top_p=0.9,
                    temperature=0.6,
                )
    return res.strip()

# test client
#assert generate("What is 2+2?") == "The answer to 2+2 is 4."

# create evaluator
#assert OAI_API_KEY is not None, "Please set OPENAI_API_KEY environment variable"

evaluation_llm = ChatOpenAI(model="gpt-4")

################################################
#GUI
###############################################
#Beschreibung oben in GUI
################################################



chatbot_stream = gr.Chatbot()

chat_interface_stream = gr.ChatInterface(fn=generate, 
                title = "ChatGPT vom LI",
                theme="soft",
                chatbot=chatbot_stream,
                retry_btn="🔄 Wiederholen",
                undo_btn="↩️ Letztes löschen",
                clear_btn="🗑️ Verlauf löschen",
                submit_btn = "Abschicken",
                ) 

with gr.Blocks() as demo:
    with gr.Tab("Chatbot"):
        #chatbot_stream.like(vote, None, None)
        chat_interface_stream.queue().launch()