st.py

from __future__ import annotations
from google.oauth2 import service_account

from vertexai.language_models import TextGenerationModel,TextEmbeddingModel
import vertexai
import streamlit as st
# st.title("Product Description Enhancer")
# with st.form(key="Product"):
#

import os
import openai
from langchain.prompts import PromptTemplate
# from langchain.chat_models import ChatOpenAI
from typing import Any
from langchain.base_language import BaseLanguageModel
from langchain.chains.llm import LLMChain
import gradio as gr
# from google.cloud import auth
# auth.authenticate_user()

# OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
# OPENAI_API_KEY='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'

PROJECT_ID = "agileai-poc"
vertexai.init(project=PROJECT_ID, location="us-central1")


generation_model = TextGenerationModel.from_pretrained("text-bison@001")
# embedding_model = TextEmbeddingModel.from_pretrained("textembedding-gecko@001")
# prompt_file = "prompt_template.txt"


# class ProductDescGen(LLMChain):
#     """LLM Chain specifically for generating multi paragraph rich text product description using emojis."""

#     @classmethod
#     def from_llm(
#         cls, llm: BaseLanguageModel, prompt: str, **kwargs: Any
#     ) -> ProductDescGen:
#         """Load ProductDescGen Chain from LLM."""
#         return cls(llm=llm, prompt=prompt, **kwargs)


# def product_desc_generator(product_name, keywords, style):
#     with open(prompt_file, "r") as file:
#         prompt_template = file.read()

#     PROMPT = PromptTemplate(
#         input_variables=["product_name", "keywords"], template=prompt_template
#     )
#     # llm = ChatOpenAI(
#     #     model_name="gpt-3.5-turbo",
#     #     temperature=0.7,
#     #     openai_api_key=OPENAI_API_KEY,
#     # )

#     llm = vertexai(
#         model_name="text-bison@001",
#         max_output_tokens=500,
#         temperature=0.1,
#         top_p=0.8,
#         top_k=40,
#     )

#     ProductDescGen_chain = ProductDescGen.from_llm(llm=llm, prompt=PROMPT)
#     ProductDescGen_query = ProductDescGen_chain.apply_and_parse(
#         [{"product_name": product_name, "keywords": keywords}]
#     )
#     Writing_Style = st.selectbox([{"Select a Writing Style": style}])

#     response = generation_model.predict(
#         "Generate a product description that is creative and SEO compliant. Emojis should be added to make product description look appealing. Begin!", **llm)
#     return ProductDescGen_query[0]["text"], Writing_Style, {response.text}


# prod_nm = st.text_input("Product Name")
# keywords = st.text_input("Filters")
# style = st.selectbox("Select the response style", [
#                      "Funny", "Sarcastic", "Casual"])
# generate = st.button("Generate Product Description")

# if generate:
#     message = st.empty()
#     message.text("Describing...")
#     content = product_desc_generator(prod_nm, keywords, style)
#     message.text("")
#     st.write(content)