From be5f830878eecd7f7b16eec15b01070ef8cf3041 Mon Sep 17 00:00:00 2001
From: Kevin Hu <kevinhu.sh@gmail.com>
Date: Wed, 15 Jan 2025 14:36:27 +0800
Subject: [PATCH] Truncate text for zhipu embedding. (#4490)

### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/llm/embedding_model.py | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/rag/llm/embedding_model.py b/rag/llm/embedding_model.py
index df57f5d9f..1babf1152 100644
--- a/rag/llm/embedding_model.py
+++ b/rag/llm/embedding_model.py
@@ -217,6 +217,14 @@ class ZhipuEmbed(Base):
     def encode(self, texts: list):
         arr = []
         tks_num = 0
+        MAX_LEN = -1
+        if self.model_name.lower() == "embedding-2":
+            MAX_LEN = 512
+        if self.model_name.lower() == "embedding-3":
+            MAX_LEN = 3072
+        if MAX_LEN > 0:
+            texts = [truncate(t, MAX_LEN) for t in texts]
+
         for txt in texts:
             res = self.client.embeddings.create(input=txt,
                                                 model=self.model_name)