From bd2ee70c63d21a6dab57d606dba91f2232558fe2 Mon Sep 17 00:00:00 2001 From: Stream Date: Mon, 26 Jan 2026 02:53:40 +0800 Subject: [PATCH] fix: remove output tokens constraint Signed-off-by: Stream --- api/core/llm_generator/llm_generator.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/api/core/llm_generator/llm_generator.py b/api/core/llm_generator/llm_generator.py index efa9e05727..8f9b6aa19f 100644 --- a/api/core/llm_generator/llm_generator.py +++ b/api/core/llm_generator/llm_generator.py @@ -555,7 +555,6 @@ class LLMGenerator: return {"questions": [], "error": f"Model schema not found for {model_name}"} completion_params = model_config.get("completion_params", {}) if model_config else {} - model_parameters = {**completion_params, "max_tokens": 256} try: response = invoke_llm_with_pydantic_model( provider=model_instance.provider, @@ -563,7 +562,7 @@ class LLMGenerator: model_instance=model_instance, prompt_messages=prompt_messages, output_model=SuggestedQuestionsOutput, - model_parameters=model_parameters, + model_parameters=completion_params, stream=False, tenant_id=tenant_id, )