Allow removal of max_output_tokens by setting GEN_AI_MAX_OUTPUT_TOKENS=0 (#1958)

Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
2025-03-29 11:12:02 +01:00 · 2024-07-27 11:07:29 -05:00 · 2024-07-27 11:07:29 -05:00 · 6c32821ad4
commit 6c32821ad4
parent d839595330
1 changed files with 1 additions and 1 deletions
--- a/backend/danswer/llm/chat_llm.py
+++ b/backend/danswer/llm/chat_llm.py
@ -266,7 +266,7 @@ class DefaultMultiLLM(LLM):
                stream=stream,
                # model params
                temperature=self._temperature,
-                max_tokens=self._max_output_tokens,
+                max_tokens=self._max_output_tokens if self._max_output_tokens > 0 else None,
                timeout=self._timeout,
                **self._model_kwargs,
            )