From 78b4906f7af27a43336995dac4a4238cc787c176 Mon Sep 17 00:00:00 2001
From: buua436 <sz_buua@foxmail.com>
Date: Wed, 17 Jun 2026 14:18:02 +0800
Subject: [PATCH] fix: tighten embedding truncation threshold (#16123)

### What problem does this PR solve?
Use a 95% max_length threshold before truncating embedding inputs, which
reduces the chance of provider-side invalid-parameter errors on
near-limit chunks.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---
 api/db/services/llm_service.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/api/db/services/llm_service.py b/api/db/services/llm_service.py
index 02852fa137..f651729806 100644
--- a/api/db/services/llm_service.py
+++ b/api/db/services/llm_service.py
@@ -137,7 +137,7 @@ class LLMBundle(LLM4Tenant):
                 safe_texts.append("None")
                 continue
             token_size = num_tokens_from_string(text)
-            if token_size > self.max_length:
+            if token_size > self.max_length * 0.95:
                 target_len = int(self.max_length * 0.95)
                 safe_texts.append(text[:target_len])
             else: