Create app.py

app.py

@@ -0,0 +1,14 @@
+from fastapi import FastAPI
+from transformers import pipeline
+
+app = FastAPI()
+generator = pipeline("text-generation", model="gpt2")  # Replace with Mistral later
+
+@app.get("/")
+def root():
+    return {"message": "SpeedAI LLM server is live!"}
+
+@app.get("/generate")
+def generate(prompt: str):
+    result = generator(prompt, max_length=100, num_return_sequences=1)
+    return {"output": result[0]['generated_text']}