Upload 3 files

fhe_model/client.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af5402a23b687193c74da8aa5157c7b84728a80009075dd7e252b1fde04a8c57
+size 1593797

fhe_model/server.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90903287cd81228b85e3f41bdc3610c94c8132b5b3fce68075656e44f3f69536
+size 4531

server.py

@@ -0,0 +1,38 @@
+"""Server that will listen for GET requests from the client."""
+from fastapi import FastAPI
+from joblib import load
+from concrete.ml.deployment import FHEModelServer
+from pydantic import BaseModel
+import base64
+from pathlib import Path
+
+current_dir = Path(__file__).parent
+
+# Load the model
+fhe_model_HLM = FHEModelServer(
+    Path.joinpath(current_dir, "fhe_model")
+)
+class PredictRequest(BaseModel):
+    evaluation_key: str
+    encrypted_encoding: str
+
+
+# Initialize an instance of FastAPI
+app = FastAPI()
+
+
+# Define the default route
+@app.get("/")
+def root():
+    return {"message": "Welcome to Your ClairVault!"}
+
+
+@app.post("/predict")
+def predict_HLM(query: PredictRequest):
+    encrypted_encoding = base64.b64decode(query.encrypted_encoding)
+    evaluation_key = base64.b64decode(query.evaluation_key)
+    prediction = fhe_model_HLM.run(encrypted_encoding, evaluation_key)
+
+    # Encode base64 the prediction
+    encoded_prediction = base64.b64encode(prediction).decode()
+    return {"encrypted_prediction": encoded_prediction}