Update app.py

app.py

@@ -27,25 +27,26 @@ prompt_template="""<|begin_of_text|>Dibawah ini adalah percakapan antara dokter
 """
 
 def output_inference(tanya, history):
+    temp = ""
     prompt = prompt_template.format(ask=tanya)
     
     output = llm(
-      prompt,
-      stop=["<|end_of_text|>"],
-      max_tokens=512,
-      temperature=0.3,
-      top_p=0.95,
-      top_k=40,
-      min_p=0.05,
-      typical_p=1.0,
-      stream=False,
+    prompt,
+    stop=["<|end_of_text|>"],
+    max_tokens=512,
+    temperature=0.3,
+    top_p=0.95,
+    top_k=40,
+    min_p=0.05,
+    typical_p=1.0,
+    stream=True,
+    )    
+    for out in output:
+      stream = copy.deepcopy(out)
+      temp += stream["choices"][0]["text"]
+      yield temp
     
-    )
-    inference = output['choices'][0]['text']
-    
-    for i in range(len(inference)):
-        yield inference[: i+1]
-    # return output['choices'][0]['text']
+    history = ["init", prompt]
 
 
 gr.ChatInterface(