Upload 2 files

app.py

@@ -21,7 +21,10 @@ import numpy as np
 import pdb
 # This repository's directory
 REPO_DIR = Path(__file__).parent
-subprocess.Popen(["uvicorn", "server:app"], cwd=REPO_DIR)
+# subprocess.Popen(["uvicorn", "server:app"], cwd=REPO_DIR)
+
+
+subprocess.Popen(["uvicorn", "server:app", "--port", "3000"], cwd=REPO_DIR)
 
 # if not exists, create a directory for the FHE keys called .fhe_keys
 if not os.path.exists(".fhe_keys"):
@@ -146,7 +149,7 @@ def run_fhe(user_id):
     headers = {"Content-type": "application/json"}
 
     response = requests.post(
-        "http://localhost:8000/predict",
+        "http://localhost:3000/predict",
         data=json.dumps(query),
         headers=headers,
     )
@@ -177,7 +180,6 @@ def decrypt_prediction(user_id):
     return predictions
 
 
-
 def process_pipeline(test_file):
 
     eval_key = keygen()
@@ -205,4 +207,4 @@ if __name__ == "__main__":
         description="This is a FHE Model",
     )
 
-    app.launch(share=True)
+    app.launch() #share=True)

server.py

@@ -5,6 +5,8 @@ from concrete.ml.deployment import FHEModelServer
 from pydantic import BaseModel
 import base64
 from pathlib import Path
+import uvicorn
+
 
 current_dir = Path(__file__).parent
 
@@ -35,4 +37,7 @@ def predict(query: PredictRequest):
 
     # Encode base64 the prediction
     encoded_prediction = base64.b64encode(prediction).decode()
-    return {"encrypted_prediction": encoded_prediction}
+    return {"encrypted_prediction": encoded_prediction}
+
+#if __name__ == "__main__":
+#    uvicorn.run(app, host="0.0.0.0", port=3000)