Update app.py

app.py

@@ -1,30 +1,7 @@
-import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+from fastapi import FastAPI
 
-# Load the pre-trained DistilGPT-2 model and tokenizer
-model_name = "distilgpt2"  # This is a smaller version of GPT-2
-model = AutoModelForCausalLM.from_pretrained(model_name)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
+app = FastAPI()
 
-# Function to generate text based on user input
-def generate_response(user_input):
-    # Encode the input prompt
-    inputs = tokenizer.encode(user_input, return_tensors="pt")
-
-    # Generate a response from the model
-    with torch.no_grad():  # Disable gradient calculation for inference
-        outputs = model.generate(inputs, max_length=100, num_return_sequences=1, no_repeat_ngram_size=2, top_p=0.9, top_k=50)
-    
-    # Decode the generated response
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    return response
-
-# Create Gradio interface for text input and output
-iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", 
-                     title="DistilGPT-2 Chatbot", 
-                     description="A lightweight conversational chatbot using DistilGPT-2.")
-
-# Launch the Gradio app
-iface.launch()
+@app.get("/")
+def greet_json():
+    return {"Hello": "World!"}