From 3a3ca8e6a9a077b6b13039b7ce00f20e4d8d659d Mon Sep 17 00:00:00 2001
From: Yeuoly <45712896+Yeuoly@users.noreply.github.com>
Date: Thu, 7 Mar 2024 15:35:56 +0800
Subject: [PATCH] fix: max tokens can only up to 2048 (#2734)

---
 api/core/model_runtime/model_providers/xinference/llm/llm.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/api/core/model_runtime/model_providers/xinference/llm/llm.py b/api/core/model_runtime/model_providers/xinference/llm/llm.py
index ffb4a0328c..602d0b749f 100644
--- a/api/core/model_runtime/model_providers/xinference/llm/llm.py
+++ b/api/core/model_runtime/model_providers/xinference/llm/llm.py
@@ -308,6 +308,7 @@ class XinferenceAILargeLanguageModel(LargeLanguageModel):
                 type=ParameterType.INT,
                 use_template='max_tokens',
                 min=1,
+                max=credentials.get('context_length', 2048),
                 default=512,
                 label=I18nObject(
                     zh_Hans='最大生成长度',