From 6c32821ad46bc10e75a98ae08d1e88e17b9becc0 Mon Sep 17 00:00:00 2001
From: Emerson Gomes <emerson.gomes@gmail.com>
Date: Sat, 27 Jul 2024 11:07:29 -0500
Subject: [PATCH] Allow removal of max_output_tokens by setting
 GEN_AI_MAX_OUTPUT_TOKENS=0 (#1958)

Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
---
 backend/danswer/llm/chat_llm.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/backend/danswer/llm/chat_llm.py b/backend/danswer/llm/chat_llm.py
index 632e09c51..6dc33df45 100644
--- 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,
             )