From a9abf9df48c08d031cc43dce043710351ac42626 Mon Sep 17 00:00:00 2001
From: Tuan Le <30828528+tuankg1028@users.noreply.github.com>
Date: Wed, 16 Jul 2025 10:41:06 +0700
Subject: [PATCH] Adds new Voyage embedding models (#8845)

### What problem does this PR solve?
This PR enhances the application's capabilities by adding support for
four new Voyage embedding models (voyage-3-large, voyage-3.5,
voyage-3.5-lite, and voyage-code-3) to the `llm_factories.json`
configuration file. These models expand the available options for text
embedding tasks, enabling improved processing of text data with a
maximum token limit of 32,000. This addition addresses the need for more
diverse and specialized embedding models to support various use cases
without altering existing functionality.

### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---
 conf/llm_factories.json | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/conf/llm_factories.json b/conf/llm_factories.json
index 461520f59..9b40e42ec 100644
--- a/conf/llm_factories.json
+++ b/conf/llm_factories.json
@@ -3244,6 +3244,30 @@
             "tags": "TEXT EMBEDDING, TEXT RE-RANK",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "voyage-3-large",
+                    "tags": "TEXT EMBEDDING,32000",
+                    "max_tokens": 32000,
+                    "model_type": "embedding"
+                },
+                {
+                    "llm_name": "voyage-3.5",
+                    "tags": "TEXT EMBEDDING,32000",
+                    "max_tokens": 32000,
+                    "model_type": "embedding"
+                },
+                {
+                    "llm_name": "voyage-3.5-lite",
+                    "tags": "TEXT EMBEDDING,32000",
+                    "max_tokens": 32000,
+                    "model_type": "embedding"
+                },
+                {
+                    "llm_name": "voyage-code-3",
+                    "tags": "TEXT EMBEDDING,32000",
+                    "max_tokens": 32000,
+                    "model_type": "embedding"
+                },
                 {
                     "llm_name": "voyage-multimodal-3",
                     "tags": "TEXT EMBEDDING,Chat,IMAGE2TEXT,32000",