Add CLI option for maximum number of tokens being generated

evoprompt/models.py

@@ -72,7 +72,11 @@ class LLMModel(ABC):
         stop: str = None,
         history: list[dict[str, str]] | None = None,
         **kwargs: Any,
-    ) -> tuple[str, list[dict[str, str]], ModelUsage]:
+    ) -> tuple[str, ModelUsage]:
+        if chat is None:
+            chat = self.chat
+        max_tokens = kwargs.pop("max_tokens", self.options.max_tokens)
+
         # create prompt
         prompt = prompt_prefix + prompt + prompt_suffix + prompt_appendix
         messages = [self._get_user_message(prompt)]