add model

app.py

@@ -1,8 +1,91 @@
-from fastapi import FastAPI
+import logging
+from typing import List
+import numpy as np
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel, HttpUrl
+from sentence_transformers import SentenceTransformer
+from PIL import Image
+import requests
+from io import BytesIO
 
-app = FastAPI()
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = FastAPI(title="CLIP ViT-B/32 Image Embedding API", version="1.0.0")
+
+# Initialize the CLIP model
+logger.info("Loading CLIP ViT-B/32 model...")
+model = SentenceTransformer("clip-ViT-B-32")
+logger.info("Model loaded successfully")
+
+
+class ImageUrlRequest(BaseModel):
+    """Request model for image URL embedding."""
+
+    image_url: HttpUrl
+
+
+class EmbeddingResponse(BaseModel):
+    """Response model for image embeddings."""
+
+    embedding: List[float]
+    embedding_dimension: int
 
 
 @app.get("/")
 def greet_json():
-    return {"Hello": "World!"}
+    """Health check endpoint."""
+    return {"Hello": "World!", "service": "CLIP ViT-B/32 Image Embedding API"}
+
+
+@app.post("/embed-image", response_model=EmbeddingResponse)
+def embed_image(request: ImageUrlRequest) -> EmbeddingResponse:
+    """
+    Generate embeddings for an image from URL using CLIP ViT-B/32 model.
+
+    Args:
+        request: ImageUrlRequest containing the image URL
+
+    Returns:
+        EmbeddingResponse containing the image embedding and its dimension
+
+    Raises:
+        HTTPException: If image cannot be downloaded or processed
+    """
+    try:
+        logger.info(f"Processing image from URL: {request.image_url}")
+
+        # Download the image from URL
+        response = requests.get(str(request.image_url), timeout=30)
+        response.raise_for_status()
+
+        # Open and process the image
+        image = Image.open(BytesIO(response.content))
+
+        # Convert to RGB if necessary (CLIP expects RGB format)
+        if image.mode != "RGB":
+            image = image.convert("RGB")
+
+        # Generate embedding using CLIP model
+        embedding = model.encode(image)
+
+        # Convert numpy array to list for JSON serialization
+        embedding_list = embedding.tolist()
+
+        logger.info(
+            f"Successfully generated embedding with dimension: {len(embedding_list)}"
+        )
+
+        return EmbeddingResponse(
+            embedding=embedding_list, embedding_dimension=len(embedding_list)
+        )
+
+    except requests.exceptions.RequestException as e:
+        logger.error(f"Failed to download image from URL: {e}")
+        raise HTTPException(
+            status_code=400, detail=f"Failed to download image from URL: {str(e)}"
+        )
+    except Exception as e:
+        logger.error(f"Error processing image: {e}")
+        raise HTTPException(status_code=500, detail=f"Error processing image: {str(e)}")

requirements.txt

@@ -1,2 +1,6 @@
 fastapi
 uvicorn[standard]
+numpy==2.1.3
+sentence-transformers==3.2.1
+pillow
+requests