TAKAHE

Runtime error

App Files Files Community

TAKAHE / app.py

steve7909

updated prompt wording issue

682747c 3 months ago

raw history blame contribute delete

No virus

5.18 kB

	import requests
	import gradio as gr
	from dotenv import load_dotenv
	import os
	#from openai import OpenAI
	from langchain_openai import OpenAI
	import spacy
	#from langchain.chat_models import ChatOpenAI
	from langchain_openai import ChatOpenAI
	from langchain.schema import AIMessage, HumanMessage
	import pandas as pd
	import uuid
	import json

	# Load environment variables from .env file
	load_dotenv()

	# Access the env
	HF_TOKEN = os.getenv('HUGGING_FACE_TOKEN')

	GITHUB_TOKEN = "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" # move to env

	# openai setup
	# client = OpenAI(
	# api_key=os.getenv('OPENAI_API_KEY')
	# )

	# hugging face setup
	#model_name = "mmnga/ELYZA-japanese-Llama-2-7b-instruct-gguf"
	API_URL = f"https://api-inference.huggingface.co/models/"
	#API_URL = f"https://api-inference.huggingface.co/models/{model_name}"
	headers = {"Authorization": f"Bearer {HF_TOKEN}"}

	# Global variable to control debug printing
	DEBUG_MODE = True


	def share_to_gist(content, public=False):
	url = "https://api.github.com/gists"
	headers = {
	"Authorization": f"token {os.getenv(GITHUB_TOKEN)}",
	"Accept": "application/vnd.github.v3+json",
	}
	data = {
	"public": public,
	"description": "Chat history",
	"files": {
	"chat.txt": {
	"content": content
	}
	}
	}
	response = requests.post(url, headers=headers, data=json.dumps(data))
	gist_url = response.json().get('html_url', '')
	return gist_url

	def generate_unique_id():
	return str(uuid.uuid4())

	def debug_print(args, *kwargs):
	if DEBUG_MODE:
	print(args, *kwargs)

	def split_sentences_ginza(input_text):
	nlp = spacy.load("ja_core_news_sm")
	doc = nlp(input_text)
	sentences = [sent.text for sent in doc.sents]
	return sentences


	file_path = 'anki_japanese_english_pairs.csv'

	def load_csv(file_path):
	# Load the CSV file into a DataFrame
	df = pd.read_csv(file_path)

	return df

	def get_sentence_pair(df):

	# Get a random row from the DataFrame
	random_row = df.sample(1)
	#debug_print("### random_row:", random_row)

	#print(random_row.shape)

	japanese_sentence = str(random_row.iloc[0, 0])
	english_sentence = str(random_row.iloc[0, 1])

	debug_print("### Japanese sentence:", japanese_sentence)
	debug_print("### English sentence:", english_sentence)


	return japanese_sentence, english_sentence


	japanese_sentence, english_sentence = get_sentence_pair(load_csv(file_path))


	llm = ChatOpenAI(temperature=0.7, model='gpt-3.5-turbo')

	def predict(message, history):

	# Define your initial setup prompt here
	initial_setup = f'''
	Japanese students are learning to translate Japanese text to English text. They will be given a Japanese sentence to translate, and will provide an English translation attempt.
	Based on the feedback you provide, they will revise their translation. This process will continue until their translation is accurate.

	Encourage the student by specifying the strengths of their writing.
	DO NOT PROVIDE THE CORRECT ENGLISH TRANSLATION until the student gets the correct translation. Let the student work it out.
	Provide your feedback as a list in the format: a, b, c etc.
	Do not respond in Japanese - always respond in English even if the student uses Japanese with you.

	Execute the following tasks step by step:
	1. Ask the student to translate the following sentence from Japanese to English: {japanese_sentence}. Here is the English translation for reference: {english_sentence}
	2. Suggest only mechanical corrections (i.e., spelling, grammar, and punctuation) for the student. Ask for another translation attempt.

	Start by asking the student to translate the Japanese sentence.
	'''

	# removed from prompt
	# The student's translation need not match the provided English translation exactly, but it should be accurate to the Japanese text.

	# Start your history with a SystemMessage containing the setup prompt
	history_langchain_format = [AIMessage(content=initial_setup)]
	#history_langchain_format.append(HumanMessage(content="Let's start."))


	for human, ai in history:
	if human is not None:
	history_langchain_format.append(HumanMessage(content=human)) # convert to str to avoid error; not compatible with multimodal
	if ai is not None:
	history_langchain_format.append(AIMessage(content=ai))

	history_langchain_format.append(HumanMessage(content=message))

	#debug_print("### Full history: ", history_langchain_format)
	gpt_response = llm(history_langchain_format)
	return gpt_response.content

	welcome_message = "Hi! 👋. Are you ready to practise translation?"

	# with gr.Blocks() as app:
	# chatbot = gr.Chatbot()
	# message = gr.Textbox()
	# clear = gr.ClearButton([message, chatbot])
	# message.submit(predict, [message, chatbot], [message, chatbot])

	app = gr.ChatInterface(fn=predict, title="Translation Chatbot", chatbot=gr.Chatbot(value=[(None, welcome_message)],),)#, multimodal=True) # chatbot=gr.Chatbot(value=[["Welcome 👋. I am an assistant",]])



	app.launch()