Update app.py

app.py

@@ -1,12 +1,16 @@
-# Load and run the model:
-vllm serve "Tann-dev/sex-chat-dirty-girlfriend"
-
-# Call the server using curl:
-curl -X POST "http://localhost:8000/v1/chat/completions" \ 
-	-H "Content-Type: application/json" \ 
-	--data '{
-		"model": "Tann-dev/sex-chat-dirty-girlfriend"
-		"messages": [
-			{"role": "user", "content": "Hello!"}
-		]
-	}'
+from vllm import LLM, SamplingParams
+
+# Initialize the LLM (use your correct model ID)
+llm = LLM(model="Tann-dev/sex-chat-dirty-girlfriend")
+
+# Set up sampling parameters (you can adjust these as needed)
+sampling_params = SamplingParams(temperature=0.7, max_tokens=50)
+
+# Define a prompt to generate text from
+prompt = "Hello, how can I help you?"
+
+# Generate text from the model
+output = llm.generate([prompt], sampling_params=sampling_params)
+
+# Print the output
+print(f"Generated text: {output[0].text}")