translator.py

import gradio as gr
from pydantic import BaseModel, Field
from langchain.prompts import HumanMessagePromptTemplate, ChatPromptTemplate
from langchain.output_parsers import PydanticOutputParser
from langchain_openai import ChatOpenAI

chat = ChatOpenAI()

# Define the Pydantic Model (updated for Pydantic v2)
class TextTranslator(BaseModel):
    output: str = Field(description="Python string containing the output text translated in the desired language")

# Use PydanticOutputParser (no need for response_schemas)
output_parser = PydanticOutputParser(pydantic_object=TextTranslator)

def text_translator(input_text: str, language: str) -> str:
    human_template = """Enter the text that you want to translate: 
                {input_text}, and enter the language that you want it to translate to {language}."""
    human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
    chat_prompt = ChatPromptTemplate.from_messages([human_message_prompt])
    prompt = chat_prompt.format_prompt(input_text=input_text, language=language)
    messages = prompt.to_messages()
    response = chat(messages=messages)
    
    # Use output_parser to parse the response
    output = output_parser.parse(response.content)
    return output.output

def text_translator_ui():
    gr.Markdown("### Text Translator\nTranslate text into any language using AI.")
    input_text = gr.Textbox(label="Enter the text that you want to translate")
    input_lang = gr.Textbox(label="Enter the language that you want it to translate to", placeholder="Example: Hindi, French, Bengali, etc.")
    output_text = gr.Textbox(label="Translated text")
    translate_button = gr.Button("Translate")
    translate_button.click(fn=text_translator, inputs=[input_text, input_lang], outputs=output_text)