Update app.py

app.py

@@ -292,15 +292,23 @@ 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:
-        response= requests.post(API_URL, headers=HEADERS, json={"inputs": prompt})
-        result = response.json()
-        print("result:------------------")
-        print(result[0]['generated_text'])
+        data = {
+            "inputs": prompt,
+            "options": {"max_new_tokens": 1024},
+        }
+        response= requests.post(API_URL, headers=HEADERS, data=json.dumps(data))
+        #result = response.json()
+        #print("result:------------------")
+        #print(result[0]['generated_text'])
+        if response.status_code == 200:
+            result = json.loads(response.text)["generated_text"]
+        else:
+            raise Exception(f"Request failed with status code {response.status_code}: {response.text}")
 
     except Exception as e:
         raise gr.Error(e)
 
-    return result[0]['generated_text'] 
+    return result #result[0]['generated_text'] 
     
     #Antwort als Stream ausgeben... 
     #for i in range(len(result)):