Upload 3 files

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY . /app
+
+RUN pip install --no-cache-dir  -r requirements.txt uvicorn
+
+ENV HF_HOME=/home/user/cache
+ENV TORCH_HOME=/home/user/cache
+RUN mkdir -p /home/user/cache && chmod -R 777 /home/user/cache
+COPY . .
+
+EXPOSE 7860
+
+CMD ["uvicorn","app:app","--host","0.0.0.0","--port","7860"]

app.py

@@ -0,0 +1,47 @@
+from fastapi import FastAPI, File, UploadFile
+import torch
+from transformers import CLIPProcessor, CLIPModel
+from dotenv import load_dotenv
+import logging
+import os
+from PIL import Image
+
+load_dotenv()
+
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = FastAPI(title="Image Embedding API",
+              description="Returns CLIP image embeddings via GET")
+
+
+HF_TOKEN = os.getenv('hf_token')
+
+logger.info("Loading CLIP processor and model...")
+try:
+    processor = CLIPProcessor.from_pretrained(
+        "openai/clip-vit-large-patch14", use_auth_token=HF_TOKEN)
+    clip_model = CLIPModel.from_pretrained(
+        "openai/clip-vit-large-patch14", use_auth_token=HF_TOKEN)
+    clip_model.eval()
+    logger.info("CLIP model loaded successfully")
+except Exception as e:
+    logger.error(f"Failed to load CLIP model: {e}")
+    raise
+
+
+@app.get("/")
+async def root():
+    logger.info("Root endpoint accessed")
+    return {"message": "Welcome to the Image Embedding API."}
+
+
+@app.post("/clip/process")
+async def process_image(file: UploadFile = File(...)):
+    logger.info("Processing image")
+    image = Image.open(file.file).convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+    with torch.no_grad():
+        embeddings = clip_model.get_image_features(**inputs)
+    return {"embedding": embeddings.tolist()}

requirements.txt

@@ -0,0 +1,6 @@
+transformers==4.49.0
+fastapi==0.115.11
+pydantic==2.10.6
+torch==2.6.0
+pillow==11.1.0
+python-dotenv==1.0.1