Update app.py

app.py

@@ -4,17 +4,12 @@ import os
 
 app = FastAPI()
 
-hf_token = os.getenv('HUGGINGFACE_HUB_TOKEN')
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
 
-model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.3", use_auth_token=hf_token)
-tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.3")
 
-@app.post("/inference")
-async def inference(prompt: str):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(**inputs)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return {"response": response}
+def t5(input):
+    output = pipe_flan(input)
+    return {"output": output[0]["generated_text"]}
 
 
 @app.get("/")