app.py

import os
from dotenv import load_dotenv
import google.generativeai as genai
from pathlib import Path
import gradio as gr
from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
from PIL import Image
import requests

# Load environment variables from .env file
load_dotenv()

# Get the API key from the environment
API_KEY = os.getenv("GOOGLE_API_KEY")

# Set up the model with the API key
genai.configure(api_key=API_KEY)

# Set up the model
generation_config = {
    "temperature": 0.7,
    "top_p": 0.9,
    "top_k": 40,
    "max_output_tokens": 4000,
}

safety_settings = [
    {
        "category": "HARM_CATEGORY_HARASSMENT",
        "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    },
    {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    },
    {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    },
    {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "threshold": "BLOCK_MEDIUM_AND_ABOVE"
    }
]

model = genai.GenerativeModel(model_name="gemini-1.5-flash-latest",
                              generation_config=generation_config,
                              safety_settings=safety_settings)

def input_image_setup(file_loc):
    if not (img := Path(file_loc)).exists():
        raise FileNotFoundError(f"Could not find image: {img}")

    image_parts = [
        {
            "mime_type": "image/jpeg",
            "data": Path(file_loc).read_bytes()
            }
        ]
    return image_parts

def generate_gemini_response(input_prompt, image_loc):
    image_prompt = input_image_setup(image_loc)
    prompt_parts = [input_prompt, image_prompt[0]]
    response = model.generate_content(prompt_parts)
    return response.text

input_prompt = """ give me the info of the car: 
- plate:
- model:
- color: """

def upload_file(files):
    if not files:
        return None, "Image not uploaded"
    file_paths = [file.name for file in files]
    response = generate_gemini_response(input_prompt, file_paths[0])
    return file_paths[0], response

with gr.Blocks() as demo:
    header = gr.Label("RADARPICK: Vous avez été radarisé!")
    image_output = gr.Image()
    upload_button = gr.UploadButton("Click to upload an image", file_types=["image"], file_count="multiple")
    generate_button = gr.Button("Generer")
    
    file_output = gr.Textbox(label="Generated Caption/Post Content")
    
    def process_generate(files):
        if not files:
            return None, "Image not uploaded"
        return upload_file(files)
    
    upload_button.upload(fn=lambda files: files[0].name if files else None, inputs=[upload_button], outputs=image_output)
    generate_button.click(fn=process_generate, inputs=[upload_button], outputs=[image_output, file_output])

demo.launch()



url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

# you can specify the revision tag if you don't want the timm dependency
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)

# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
    box = [round(i, 2) for i in box.tolist()]
    print(
            f"Detected {model.config.id2label[label.item()]} with confidence "
            f"{round(score.item(), 3)} at location {box}"
    )