handle multiple requests in your FastAPI endpoint

from fastapi import FastAPI
import uvicorn
import os
from DeepImageSearch import Load_Data, Search_Setup
import shutil

os.environ['KMP_DUPLICATE_LIB_OK']='True'
app = FastAPI()


@app.post("/api/request-similar-images")
async def get_user_image(user_image: dict):
    # Access the data sent by the user
    try :
        img = user_image.get("image")
        # image_list = Load_Data().from_folder(['\image_search\Demo_Data'])
        # go back one directory
        path = os.path.abspath(os.path.join(os.path.dirname( __file__ ), '..'))
        # go to \storage\app\public\image-search
        image_list = os.path.abspath(os.path.join(path, 'storage/app/public/image-search'))

        # Set up the search engine, You can load 'vit_base_patch16_224_in21k', 'resnet50' etc more then 500+ models
        st = Search_Setup(image_list=image_list, model_name='vgg19', pretrained=True, image_count=len(image_list))
        # Get metadata
        metadata = st.get_image_metadata_file()
        st.add_images_to_index([img])
        img_dict , images_and_scores = st.get_similar_images(image_path=img, number_of_images=100)

        paths_list = []
        for index , path in img_dict.items():
            paths_list.append(path)


        scores_list = []
        for index , path in images_and_scores.items():
            scores_list.append(path)


        similarty_list = dict(zip(paths_list, scores_list))
        similarty_list = [{key: value} for key, value in similarty_list.items()]

        for i, d in enumerate(similarty_list):
            mydict = similarty_list[i]
            for key, value in mydict.copy().items():
                if value == 0.0 :
                    del mydict[key]


        while {} in similarty_list:
            similarty_list.remove({})

        transformed_list = [
            {"path": list(item.keys())[0], "score": list(item.values())[0]} for item in similarty_list]


        return transformed_list

    except Exception as e:
        print (e)
        return "No image found."


if __name__ == "__main__":
    uvicorn.run(app, host="127.0.0.1", port=5000)

عندما ارسال اكثر من request من خلال Postman او استخدام ال endpoint في اي مكان اخر.
المشكله انه يجب الانتظار على كل request حتى الانتهاء ليبدا ال request الذي بعدة 
كيف يمكننى حل هذه المشكلة