Update app.py

app.py

@@ -1,29 +1,28 @@
-from fastapi import FastAPI
-from fastapi.middleware.cors import CORSMiddleware
-import numpy as np
-from onnxruntime import InferenceSession
 from transformers import AutoTokenizer
-import os
+from onnxruntime import InferenceSession
+import numpy as np
+import json
+from fastapi import FastAPI
 
 app = FastAPI()
 
-# CORS setup
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_methods=["*"],
-    allow_headers=["*"],
+# Initialize components
+tokenizer = AutoTokenizer.from_pretrained(
+    "Xenova/multi-qa-mpnet-base-dot-v1",
+    use_fast=False  # Avoids framework dependencies
 )
-
-# Load model
 session = InferenceSession("model.onnx")
-tokenizer = AutoTokenizer.from_pretrained("Xenova/multi-qa-mpnet-base-dot-v1")
+
+def cosine_similarity(a, b):
+    return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b))
 
 @app.post("/predict")
 async def predict(query: str):
+    # Tokenize
     inputs = tokenizer(query, return_tensors="np")
     inputs = {k: v.astype(np.int64) for k, v in inputs.items()}
-    outputs = session.run(None, inputs)
-    embedding = outputs[0][0].tolist()
     
-    return {"embedding": embedding}
+    # Get embedding
+    embedding = session.run(None, inputs)[0][0]
+    
+    return {"embedding": embedding.tolist()}