app.py

import numpy as np
import pandas as pd
import requests
import os
import gradio as gr
import json
from dotenv import load_dotenv, find_dotenv
_ = load_dotenv(find_dotenv())


databricks_token  = os.getenv('DATABRICKS_TOKEN')
model_uri  = "https://dbc-eb788f31-6c73.cloud.databricks.com/serving-endpoints/Mpt-7b-tester/invocations"

def score_model(model_uri, databricks_token, prompt):
  dataset=pd.DataFrame({
            "prompt":[prompt],
            "temperature": [0.5],
            "max_tokens": [1500]})
  headers = {
    "Authorization": f"Bearer {databricks_token}",
    "Content-Type": "application/json",
  }
  ds_dict = {'dataframe_split': dataset.to_dict(orient='split')} if isinstance(dataset, pd.DataFrame) else create_tf_serving_json(dataset)
  data_json = json.dumps(ds_dict, allow_nan=True)
  print("***ds_dict: ")
  print(ds_dict)
  print("***data_json: ")
  print(data_json)
  response = requests.request(method='POST', headers=headers, url=model_uri, data=data_json)
  if response.status_code != 200:
      raise Exception(f"Request failed with status {response.status_code}, {response.text}")
  return response.json()

def get_completion(prompt):
    return score_model(model_uri, databricks_token, prompt)

def greet(input):
	prompt = f"""
Determine the product or solution, the problem being solved, features, target customer that are being discussed in the \
following text, which is delimited by triple backticks. Then, pretend that you are the target customer. \
State if you would use this product and elaborate on why. Also state if you would pay for it and elaborate on why.\

Format your response as a JSON object with \
'solution', 'problem', 'features', 'target_customer', 'fg_will_use', 'reason_to_use', 'fg_will_pay', 'reason_to_pay' as the keys.\

Text sample: '''{input}'''
	"""

	sys_msg="You are demanding customer."

	instruction = """\\n\
Determine the product or solution, the problem being solved, features, target customer that are being discussed in the \
following user prompt. State if you would use this product and elaborate on why. Also state if you would pay for it and elaborate on why.\
Finally, state if you would invest in it and elaborate on why.\\n\
\\n\
Give a score for the product. Format your response as a JSON object with \
'solution', 'problem', 'features', 'target_customer', 'fg_will_use', 'reason_to_use', 'fg_will_pay', 'reason_to_pay', 'fg_will_invest', 'reason_to_invest', 'score' as the keys.\\n\
	"""

	prompt_template = f"""\\n\
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\\n\
\\n\
### Instruction:\\n\
{sys_msg}\\n\
{instruction}\\n\
\\n\
### Input:\\n\
{input}\\n\
\\n\
### Response:\\n\
	"""

	response = get_completion(prompt_template)
	return json.dumps(response)

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

#iface = gr.Interface(fn=greet, inputs=[gr.Textbox(label="Text to find entities", lines=2)], outputs=[gr.HighlightedText(label="Text with entities")], title="NER with dslim/bert-base-NER", description="Find entities using the `dslim/bert-base-NER` model under the hood!", allow_flagging="never", examples=["My name is Andrew and I live in California", "My name is Poli and work at HuggingFace"])
iface = gr.Interface(fn=greet, inputs=[gr.Textbox(label="Elevator pitch", lines=3)], outputs="json")
iface.launch()