Update app.py

app.py

@@ -49,20 +49,19 @@ HF_API_KEY = os.getenv("HF_API_KEY")
 if HF_API_KEY is None:
     raise ValueError("HF_API_KEY environment variable is not set.")
 
-# 🤖 Use HuggingFace Inference API (cloud) for LLM
-HF_MODEL = "deepseek-ai/deepseek-llm-7b-instruct"  # change if desired
-client = InferenceClient(token=HF_API_KEY)
+HF_MODEL = "deepseek-ai/deepseek-llm-7b-instruct"  # or any other hosted model
+
+# 🤖 Create InferenceClient bound to model
+client = InferenceClient(model=HF_MODEL, token=HF_API_KEY)
 
 # 🔷 Wrap HF client into LangChain LLM interface
 class HuggingFaceInferenceLLM(LLM):
     """LLM that queries HuggingFace Inference API."""
 
-    model: str = HF_MODEL
     client: InferenceClient = client
 
     def _call(self, prompt, stop=None, run_manager=None, **kwargs):
         response = self.client.text_generation(
-            self.model,
             prompt,
             max_new_tokens=512,
             temperature=0.7,
@@ -104,4 +103,4 @@ with gr.Blocks() as demo:
     msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False)
     clear.click(lambda: None, None, chatbot, queue=False)
 
-demo.launch(debug=True, share=True)  # share=True gives you a public link
+demo.launch(debug=True)  # remove share=True if running in HF Spaces