app.py

import gradio as gr


import os 
token=os.environ.get("TOKEN") 
os.environ["GOOGLE_API_KEY"] = token

safe = [
    {
        "category": "HARM_CATEGORY_HARASSMENT",
        "threshold": "BLOCK_NONE",
    },
    {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "threshold": "BLOCK_NONE",
    },
    {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "threshold": "BLOCK_NONE",
    },
    {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "threshold": "BLOCK_NONE",
    },
]
from llama_index.llms.gemini import Gemini
from llama_index.multi_modal_llms.gemini import GeminiMultiModal

from llama_index.core.multi_modal_llms.generic_utils import load_image_urls


# Chargez l'image

gemini_pro = GeminiMultiModal(model_name="models/gemini-pro-vision")

llm = Gemini(model="models/gemini-pro")

e =""
# Fonction pour générer le contenu
async def generate_content(pro,image):
    global e

    if not image:
        response = await llm.acomplete(pro,safety_settings=safe)
        print(response)
        e = response.text
        print(e)

    else:
        #response = model.generate_content([pro, image])
        response_acomplete = await gemini_pro.acomplete(prompt=pro, image_documents=image,)
        print(response_acomplete)
        e = response_acomplete
    return e


markdown = r"""
e
""".format(e)
# Interface Gradio
iface = gr.Interface(fn=generate_content, inputs=[gr.Textbox(),gr.Image(type='pil')], outputs= gr.Markdown(markdown, latex_delimiters=[{ "left":"$$", "right":"$$", "display": True }]))

iface.launch()