Update app.py

app.py

@@ -3,7 +3,10 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 
 # ✅ Set up Hugging Face client with token from environment
-client = InferenceClient(model="deepseek-ai/DeepSeek-R1-0528", token=os.getenv("HF_TOKEN"))
+client = InferenceClient(
+        provider="auto",
+        api_key=os.environ["HF_TOKEN"],
+    )
 
 # 🧠 Function to generate software architecture
 def generate_software_spec(name, description, architecture, components, deployment, platform, extra):
@@ -51,14 +54,15 @@ def generate_software_spec(name, description, architecture, components, deployme
 
     print(prompt)
     # Generate response from Hugging Face Inference Client
-    response = client.text_generation(
-        prompt,
-        max_new_tokens=2048,
-        temperature=0.7,
-        top_p=0.9,
-        repetition_penalty=1.1,
-        do_sample=True,
+    response = client.chat_completion(
+        messages=[
+            {"role": "system", "content": "You are a helpful software architecture assistant."},
+            {"role": "user", "content": prompt}
+        ],
+        model="deepseek-ai/DeepSeek-R1-0528",
+        max_tokens=2048,
     )
+    print(response)
     return response.choices[0].message["content"] if response and response.choices else "Error: No response received."
 
 # 🎨 Gradio UI