Update app.py

app.py

@@ -292,7 +292,8 @@ def generate(text, history, rag_option, model_option,  temperature=0.5, max_new_
         #payload = tokenizer.apply_chat_template(prompt,tokenize=False)
         #result = client.text_generation(payload, do_sample=True,return_full_text=False, max_new_tokens=2048,top_p=0.9,temperature=0.6,)    
         #inference allg:
-        result= requests.post(API_URL, headers=HEADERS, json={"inputs": prompt})
+        response= requests.post(API_URL, headers=HEADERS, json={"inputs": prompt})
+        result = response.json()
         print("prompt:..................")
         print(prompt)
         print("result:..................")