app.py

import gradio as gr
import torch
import transformers
from transformers import AutoTokenizer
from langchain import LLMChain, HuggingFacePipeline, PromptTemplate


def greet(text):

 model = "meta-llama/Llama-2-7b-chat-hf"
 tokenizer = AutoTokenizer.from_pretrained(model, token=llama2)
 
 pipeline = transformers.pipeline(
 "text-generation",
 model=model,
 tokenizer=tokenizer,
 torch_dtype=torch.bfloat16,
 trust_remote_code=True,
 device_map="auto",
 max_length=1000,
 do_sample=True,
 top_k=10,
 num_return_sequences=1,
 eos_token_id=tokenizer.eos_token_id
 )

 llm = HuggingFacePipeline(pipeline = pipeline, model_kwargs = {'temperature':0})

 template = """
 Write a summary of the following text delimited by triple backticks.
 Return your response which covers the key points of the text.
 ```{text}```
 SUMMARY:
 """
 
 prompt = PromptTemplate(template=template, input_variables=["text"])
 llm_chain = LLMChain(prompt=prompt, llm=llm)

 summary = llm_chain.run(text)
 
 return summary

with gr.Blocks() as demo:
 
 text = gr.Textbox(label="Text")
 summary = gr.Textbox(label="Summary")
 greet_btn = gr.Button("Submit")
 greet_btn.click(fn=greet, inputs=text, outputs=summary, api_name="greet")

demo.launch()