Update app.py

app.py

@@ -152,16 +152,16 @@ def main():
 
                     max_output_tokens = 2048 # Just a generic value
 
-                    os.environ['HFTOKEN'] = str(llm_key)
+                    os.environ['HF_TOKEN'] = str(llm_key)
                     Settings.llm = HuggingFaceInferenceAPI(
                         model_name=llm_name, 
-                        token=os.environ.get("HFTOKEN"),
+                        token=os.environ.get("HF_TOKEN"),
                         temperature=temperature,
                         max_tokens=max_output_tokens
                     )
                     Settings.tokenizer = AutoTokenizer.from_pretrained(
                         llm_name,
-                        token=os.environ.get("HFTOKEN"),
+                        token=os.environ.get("HF_TOKEN"),
                     )
                     Settings.num_output = max_output_tokens
                     Settings.embed_model = HuggingFaceInferenceAPIEmbedding(