Update app.py

app.py

@@ -110,19 +110,18 @@ def main(query: str, client: QdrantClient, collection_name: str, tokenizer: Mist
             ]
         )
     )
+    print(f'Tokenized text: {tokenized.text}')
     outputs = llm.generate(
         prompts=tokenized.text, 
         sampling_params=vllm.SamplingParams(
             temperature=0, 
             max_tokens=3000,
-            stop_token_ids=[tokenizer.instruct_tokenizer.tokenizer.eos_id],
-            detokenize=False
+            stop_token_ids=[tokenizer.instruct_tokenizer.tokenizer.eos_id]
         )
     )
-    print(f'TEXT: {outputs[0]}')
-    response = tokenizer.decode(outputs[0])
+    print(f'TEXT: {outputs}')
 
-    text = response[0].outputs[0].text
+    text = outputs[0].outputs[0].text
 
     tokenized_2 = tokenizer.encode_chat_completion(
         ChatCompletionRequest(