Update api.py

api.py

@@ -1,32 +1,58 @@
 from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
-from inference import predict
+from transformers import pipeline
+import uvicorn
 
-app = FastAPI(title="Your Model API", version="1.0.0")
+# Initialize app
+app = FastAPI(title="OrcaleSeek API", version="1.0.0")
+
+# CORS for web access
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Change this to your website domain
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Load model
+classifier = pipeline(
+    "text-classification",
+    model="your-username/OrcaleSeek",
+    tokenizer="your-username/OrcaleSeek"
+)
 
 class PredictionRequest(BaseModel):
     text: str
+    max_length: int = 128
 
 class PredictionResponse(BaseModel):
-    prediction: dict
+    prediction: list
     status: str
+    model: str = "OrcaleSeek"
 
 @app.get("/")
-def read_root():
-    return {"message": "Your Model API is running!"}
+def home():
+    return {"message": "OrcaleSeek API is running! 🚀"}
+
+@app.get("/health")
+def health_check():
+    return {"status": "healthy"}
 
 @app.post("/predict", response_model=PredictionResponse)
-async def predict_endpoint(request: PredictionRequest):
+async def predict(request: PredictionRequest):
     try:
-        result = predict(request.text)
+        result = classifier(request.text)
         return PredictionResponse(
             prediction=result,
             status="success"
         )
     except Exception as e:
         return PredictionResponse(
-            prediction={},
+            prediction=[],
             status=f"error: {str(e)}"
         )
 
-# Run with: uvicorn api:app --host 0.0.0.0 --port 8000
+# Run with: uvicorn api:app --host 0.0.0.0 --port 8000 --reload
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=8000)