From 83c673e093e763a8e4b6801b3e74ec6cdf93f661 Mon Sep 17 00:00:00 2001
From: Morler <478444+morler@users.noreply.github.com>
Date: Tue, 20 Aug 2024 09:44:15 +0800
Subject: [PATCH] Updated Model Information for Tongyi-Qianwen and ZHIPU-AI
 (#2003)

### What problem does this PR solve?

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [X] Bug Fix (non-breaking change which fixes an issue)
---
 conf/llm_factories.json | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/conf/llm_factories.json b/conf/llm_factories.json
index be1065c8e..44ebda550 100644
--- a/conf/llm_factories.json
+++ b/conf/llm_factories.json
@@ -104,6 +104,12 @@
                     "max_tokens": 2048,
                     "model_type": "embedding"
                 },
+                {
+                    "llm_name": "text-embedding-v3",
+                    "tags": "TEXT EMBEDDING,2K",
+                    "max_tokens": 2048,
+                    "model_type": "embedding"
+                },
                 {
                     "llm_name": "paraformer-realtime-8k-v1",
                     "tags": "SPEECH2TEXT",
@@ -131,13 +137,37 @@
             "status": "1",
             "llm": [
                 {
-                    "llm_name": "glm-3-turbo",
+                    "llm_name": "glm-4",
                     "tags": "LLM,CHAT,",
                     "max_tokens": 128000,
                     "model_type": "chat"
                 },
                 {
-                    "llm_name": "glm-4",
+                    "llm_name": "glm-4-airx",
+                    "tags": "LLM,CHAT,",
+                    "max_tokens": 8000,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "glm-4-air",
+                    "tags": "LLM,CHAT,",
+                    "max_tokens": 128000,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "glm-4-flash",
+                    "tags": "LLM,CHAT,",
+                    "max_tokens": 128000,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "glm-4-long",
+                    "tags": "LLM,CHAT,",
+                    "max_tokens": 1000000,
+                    "model_type": "chat"
+                },
+                {
+                    "llm_name": "glm-3-turbo",
                     "tags": "LLM,CHAT,",
                     "max_tokens": 128000,
                     "model_type": "chat"
@@ -153,6 +183,12 @@
                     "tags": "TEXT EMBEDDING",
                     "max_tokens": 512,
                     "model_type": "embedding"
+                },
+                {
+                    "llm_name": "embedding-3",
+                    "tags": "TEXT EMBEDDING",
+                    "max_tokens": 512,
+                    "model_type": "embedding"
                 }
             ]
         },