WORKING VERSION

app.py

@@ -82,9 +82,21 @@ def generate(
     # Use LLaMa to create chat completion
     chat_completion = llm.create_chat_completion(conversation, stream=True)
 
+    outputs = []
     # Yield the chat completions
     for completion in chat_completion:
-        yield ("assistant", completion["choices"][0]["message"]["content"])
+        if "content" in completion["choices"][0]["delta"]:
+            outputs.append(completion["choices"][0]['delta']['content'])
+            yield "".join(outputs)
+
+    # t = Thread(target=model.generate, kwargs=generate_kwargs)
+    # t.start()
+
+    # outputs = []
+    # for text in streamer:
+    #     outputs.append(text)
+    #     yield "".join(outputs)
+
 
 chat_interface = gr.ChatInterface(
     fn=generate,