app.py

import gradio as gr
from langchain import PromptTemplate, LLMChain
from langchain.llms import GPT4All
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler


def func(prompt):
        
    template = """Question: {question}
    
    Answer: Let's think step by step."""
    
    prompt = PromptTemplate(template=template, input_variables=["question"])
    
    local_path = (
        "https://tommy24-llm.hf.space/file=nous-hermes-13b.ggmlv3.q4_0.bin"  # replace with your desired local file path
    )
    
    # Callbacks support token-wise streaming
    callbacks = [StreamingStdOutCallbackHandler()]
    
    # Verbose is required to pass to the callback manager
    llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)
    
    # If you want to use a custom model add the backend parameter
    # Check https://docs.gpt4all.io/gpt4all_python.html for supported backends
    llm = GPT4All(model=local_path, backend="gptj", callbacks=callbacks, verbose=True)
    
    llm_chain = LLMChain(prompt=prompt, llm=llm)
    question = prompt

    return llm_chain.run(question)

iface = gr.Interface(fn=func, inputs="text", outputs="text")
iface.launch()