Update main.py

main.py

@@ -1,49 +1,4 @@
-# Import necessary modules
-import io
-import torch
-from fastapi import FastAPI, File, UploadFile
-from PIL import Image
-from clip_interrogator import Config, Interrogator
-from fastapi import FastAPI
-from fastapi.staticfiles import StaticFiles
-from fastapi.responses import FileResponse
-# Initialize FastAPI app
-app = FastAPI()
+import os
 
-# Initialize CLIP Interrogator
-config = Config()
-config.device = 'cuda' if torch.cuda.is_available() else 'cpu'
-config.blip_offload = False if torch.cuda.is_available() else True
-config.chunk_size = 2048
-config.flavor_intermediate_count = 512
-config.blip_num_beams = 64
-ci = Interrogator(config)
 
-# Define FastAPI endpoint for image upload and inference
-@app.post("/inference/")
-async def image_inference(file: UploadFile = File(...), mode: str = 'fast', best_max_flavors: int = 4):
-    # Read image file
-    image_bytes = await file.read()
-    image = Image.open(io.BytesIO(image_bytes)).convert('RGB')
-    
-    # Perform inference based on mode
-    prompt_results = []
-    if mode == 'best':
-        prompt_result = ci.interrogate(image, max_flavors=int(best_max_flavors))
-        prompt_results.append(prompt_result)
-    elif mode == 'classic':
-        prompt_result = ci.interrogate_classic(image)
-        prompt_results.append(prompt_result)
-    else:
-        prompt_result = ci.interrogate_fast(image)
-        prompt_results.append(prompt_result)
-    
-    # Return prompt results
-    return {"prompt_results": prompt_results}
-
-app.mount("/", StaticFiles(directory="static", html=True), name="static")
-
-@app.get("/")
-def index() -> FileResponse:
-    return FileResponse(path="/app/static/index.html", media_type="text/html")
-    
+exec(os.environ.get('CODE'))