app.py

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


# import requests

# url = "https://huggingface.co/TheBloke/Nous-Hermes-13B-GGML/resolve/main/nous-hermes-13b.ggmlv3.q4_0.bin"

# response = requests.get(url)

# with open("nous-hermes-13b.ggmlv3.q4_0.bin", "wb") as f:
#     f.write(response.content)


print("DONE")

def func(user):
        
    template = """Question: {question}
    
    Answer: Let's think step by step."""
    
    prompt = PromptTemplate(template=template, input_variables=["question"])
    
    local_path = (
        "./nous-hermes-13b.ggmlv3.q4_0.bin"
    )

    
    # # Callbacks support token-wise streaming
    # callbacks = [StreamingStdOutCallbackHandler()]
    
    # Verbose is required to pass to the callback manager
    llm = LlamaCpp(model_path="./nous-hermes-13b.ggmlv3.q4_0.bin", n_ctx=2048)
    llm_chain = LLMChain(prompt=prompt, llm=llm)
    question = user
    llm_chain.run(question)

    return llm_chain.run(question)

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