Add application file

Dockerfile

@@ -0,0 +1,16 @@
+# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.11
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "5001"]

app.py

@@ -0,0 +1,141 @@
+import openai
+import logging
+from openai import OpenAI
+import uvicorn
+import sys
+import base64
+import requests
+import json
+from fastapi import FastAPI, Request, Form,UploadFile,File
+from fastapi.responses import HTMLResponse, RedirectResponse,JSONResponse,RedirectResponse
+from fastapi.templating import Jinja2Templates
+from fastapi.staticfiles import StaticFiles
+
+from pydantic_settings import BaseSettings
+import io
+import torch
+from PIL import Image
+from torchvision import transforms
+from torchmetrics.multimodal.clip_iqa import CLIPImageQualityAssessment
+
+
+class Settings(BaseSettings):
+    OPENAI_API_KEY: str = 'OPENAI_API_KEY'
+    FLASK_APP: str = 'FLASK_APP'
+    FLASK_ENV: str = 'FLASK_ENV'
+    
+    class Config:
+        env_file = '.env'
+
+settings = Settings()
+client = OpenAI(api_key=settings.OPENAI_API_KEY)
+app = FastAPI()
+
+templates = Jinja2Templates(directory="templates")
+app.mount("/static", StaticFiles(directory="static"), name="static")
+
+# Function to encode the image
+def encode_image(image_path:str)->base64:
+    with open(image_path, "rb") as image_file:
+        return base64.b64encode(image_file.read()).decode('utf-8')
+
+def get_json(
+    img_bytes:base64
+)->dict:
+    # Getting the base64 string
+    # base64_image = encode_image(file_name)
+    headers = {
+        "Content-Type": "application/json",
+        "Authorization": f"Bearer {settings.OPENAI_API_KEY}"
+    }
+
+    payload = {
+        "model": "gpt-4o-mini",
+        "response_format": {"type": "json_object"},
+        "messages": [
+            {
+                "role": "user",
+                "content": [
+                    {
+                    "type": "text",
+                    "text": "You are an intelligent system api that reads the texts from an image and outputs the texts as key values pairs in JSON format. Given an image, output the texts in JSON format."
+                },
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": f"data:image/jpeg;base64,{img_bytes}"
+                        }
+                }
+            ]
+        }
+    ],
+        "max_tokens": 1000
+    }
+    
+    response = requests.post("https://api.openai.com/v1/chat/completions", headers=headers, json=payload)
+    return response.json()
+    # return templates.TemplateResponse("json_out.html", {"request": request, "data": response.json()})
+
+
+@app.get("/", response_class=HTMLResponse)
+def index(request: Request):
+    return templates.TemplateResponse("upload_image.html", {"request": request})
+
+
+@app.post("/output_iqa")
+async def create_upload_file(
+    request:Request,
+    file: UploadFile = File(...),
+    choice: str = Form(...), 
+)->dict:
+    pairs = {
+        'quality': ("Good photo", "Bad photo"),
+        'sharpness': ("Sharp photo", "Blurry photo"),
+        'noisiness': ("Clean photo", "Noisy photo"),
+    }
+    classes = pairs[choice.lower()]
+    
+    _ = torch.manual_seed(42)
+    transform = transforms.Compose([
+        transforms.ToTensor(),  # Converts the image to a PyTorch tensor
+        # transforms.Normalize(mean=0,std=255)
+        transforms.Normalize(mean=[0.485, 0.456, 0.406],  # Normalize for pre-trained models
+                            std=[0.229, 0.224, 0.225])
+    ])
+    
+    # Read the image file into a PIL Image
+    image_content = await file.read()
+    image = Image.open(io.BytesIO(image_content)).convert('RGB')
+    img = transform(image)
+    metric = CLIPImageQualityAssessment(
+        # model_name_or_path='openai/clip-vit-large-patch14',
+        prompts=(classes, choice)
+    )
+    out = {
+        'filename':file.filename,
+        'on':choice,
+        "prompts":classes,
+        "score": metric(img)[choice].item(),
+    }
+    if out['score'] > 0.75:
+        # return RedirectResponse(url=f'/get_json/?filename={file.filename}')
+        to_gpt = base64.b64encode(image.tobytes()).decode('utf-8')
+        info = get_json(to_gpt)
+        if info.get('choices') is not None:
+            out.update(json.loads(info['choices'][0]['message']['content']))
+        else:
+            info['error']['mb'] = f"{sys.getsizeof(to_gpt)/1000000} MB?"
+            info['error']['refer_article'] = 'https://community.openai.com/t/400-errors-on-gpt-vision-api-since-today/534538/4'
+            out.update(info['error'])
+        return out
+    return out
+
+
+if __name__ == "__main__":
+    # Disable uvicorn access logger
+    uvicorn_access = logging.getLogger("uvicorn.access")
+    uvicorn_access.disabled = True
+
+    logger = logging.getLogger("uvicorn")
+    logger.setLevel(logging.getLevelName(logging.DEBUG))
+    uvicorn.run('app:app', host="0.0.0.0", port=5001, reload=True)

requirements.txt

@@ -0,0 +1,154 @@
+annotated-types==0.7.0
+anyio==4.4.0
+aplus==0.11.0
+astropy==6.1.1
+astropy-iers-data==0.2024.7.8.0.31.19
+asttokens==2.4.1
+azure-core==1.30.2
+azure-storage-blob==12.20.0
+azure-storage-file-datalake==12.15.0
+blake3==0.4.1
+bqplot==0.12.43
+branca==0.7.2
+cachetools==5.3.3
+certifi==2024.7.4
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+cloudpickle==3.0.0
+colorama==0.4.6
+comm==0.2.2
+contourpy==1.2.1
+cryptography==42.0.8
+cycler==0.12.1
+dask==2024.7.0
+debugpy==1.8.2
+decorator==5.1.1
+distro==1.9.0
+dnspython==2.6.1
+email_validator==2.2.0
+exceptiongroup==1.2.1
+executing==2.0.1
+fastapi==0.111.0
+fastapi-cli==0.0.4
+filelock==3.15.4
+fonttools==4.53.1
+frozendict==2.4.4
+fsspec==2024.6.1
+future==1.0.0
+h11==0.14.0
+h5py==3.11.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.24.0
+idna==3.7
+# importlib
+# importlib_metadata==8.0.0
+intel-openmp==2021.4.0
+ipydatawidgets==4.3.5
+ipykernel==6.29.5
+ipyleaflet==0.19.1
+ipympl==0.9.4
+ipython==8.26.0
+ipython-genutils==0.2.0
+ipyvolume==0.6.3
+ipyvue==1.11.1
+ipyvuetify==1.9.4
+ipywebrtc==0.6.0
+ipywidgets==8.1.3
+isodate==0.6.1
+jedi==0.19.1
+Jinja2==3.1.4
+jupyter-leaflet==0.19.1
+jupyter_client==8.6.2
+jupyter_core==5.7.2
+jupyterlab_widgets==3.0.11
+kiwisolver==1.4.5
+lightning-utilities==0.11.5
+llvmlite==0.43.0
+locket==1.0.0
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.9.1
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mkl==2021.4.0
+mpmath==1.3.0
+nest-asyncio==1.6.0
+networkx==3.3
+numba==0.60.0
+numpy==1.26.4
+openai==1.37.0
+orjson==3.10.6
+packaging==24.1
+pandas==2.2.2
+parso==0.8.4
+partd==1.4.2
+pillow==10.4.0
+piq==0.8.0
+platformdirs==4.2.2
+progressbar2==4.4.2
+prompt_toolkit==3.0.47
+psutil==6.0.0
+pure-eval==0.2.2
+pyarrow==16.1.0
+pycparser==2.22
+pydantic==2.8.2
+pydantic-settings==2.3.4
+pydantic_core==2.20.1
+pyerfa==2.0.1.4
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+python-utils==3.8.2
+pythreejs==2.4.2
+pytz==2024.1
+# pywin32==306
+PyYAML==6.0.1
+pyzmq==26.0.3
+regex==2024.5.15
+requests==2.32.3
+rich==13.7.1
+safetensors==0.4.3
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.37.2
+sympy==1.13.1
+tabulate==0.9.0
+tbb==2021.13.0
+tokenizers==0.19.1
+toolz==0.12.1
+torch==2.3.1
+torchmetrics==1.4.0.post0
+torchvision==0.18.1
+tornado==6.4.1
+tqdm==4.66.4
+traitlets==5.14.3
+traittypes==0.2.1
+transformers==4.42.4
+typer==0.12.3
+typing_extensions==4.12.2
+tzdata==2024.1
+ujson==5.10.0
+urllib3==2.2.2
+uvicorn==0.30.1
+vaex==4.17.0
+vaex-astro==0.9.3
+vaex-core==4.17.1
+vaex-hdf5==0.14.1
+vaex-jupyter==0.8.2
+vaex-ml==0.18.3
+vaex-server==0.9.0
+vaex-viz==0.5.4
+watchfiles==0.22.0
+wcwidth==0.2.13
+websockets==12.0
+widgetsnbextension==4.0.11
+xarray==2024.6.0
+xyzservices==2024.6.0
+zipp==3.19.2