Create app/model.py

app/model.py

@@ -0,0 +1,31 @@
+from fastapi import FastAPI, Request
+from pydantic import BaseModel
+from app.model import load_model, generate_response
+import uvicorn
+
+app = FastAPI()
+
+# Load model at startup
+model, tokenizer = load_model()
+
+class QueryRequest(BaseModel):
+    prompt: str
+    max_new_tokens: int = 512
+    temperature: float = 0.7
+    top_p: float = 0.95
+
+@app.post("/generate")
+async def generate_text(request: QueryRequest):
+    output = generate_response(
+        model=model,
+        tokenizer=tokenizer,
+        prompt=request.prompt,
+        max_new_tokens=request.max_new_tokens,
+        temperature=request.temperature,
+        top_p=request.top_p
+    )
+    return {"response": output}
+
+@app.get("/")
+def read_root():
+    return {"message": "AyurEze LLaMA3 Ayurveda API is running"}