app.py

import gradio as gr
from typing import List
from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai
from langchain_community.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
import re


genai.configure(api_key="AIzaSyD2o8vjePJb6z8vT_PVe82lVWMD3_cBL0g")


def format_gemini_response(text):

  bold_pattern = r"\*\*(.*?)\*\*"
  italic_pattern = r"\*(.*?)\*"
  code_pattern = r"```(.*?)```"
  text = text.replace('\n', '<br>')
  formatted_text = re.sub(code_pattern,"<pre><code>\\1</code></pre>",text)
  formatted_text = re.sub(bold_pattern, "<b>\\1</b>", formatted_text)
  formatted_text = re.sub(italic_pattern, "<i>\\1</i>", formatted_text)

  return formatted_text
def predict(message :str , chat_his ,d ) -> str:
    model = genai.GenerativeModel("gemini-pro")
    his = []
    # for i,j in history:
    #     his.extend([
    #         {"role": "user", "parts": i},
    #         {"role": "model", "parts": j},
    #     ])
    chat = model.start_chat(
        history=his
    )
    response = chat.send_message(message)
    return format_gemini_response(response.text),chat_his, d
iface = gr.Interface(fn = predict,inputs = ["text","list","json"],outputs = "text")
iface.launch()