diff --git a/server/sources/ollama_handler.py b/server/sources/ollama_handler.py index b52694e..2ff130a 100644 --- a/server/sources/ollama_handler.py +++ b/server/sources/ollama_handler.py @@ -22,7 +22,7 @@ class OllamaLLM(GeneratorLLM): stream = ollama.chat( model=self.model, messages=history, - stream=False, + stream=True, ) for chunk in stream: