fix the max token of Tongyi-Qianwen text-embedding-v3 model to 8k (#2118)

### 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._

fix the max token of Tongyi-Qianwen text-embedding-v3 model to 8k

close #2117

### Type of change

- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):

conf/llm_factories.json

@@ -106,8 +106,8 @@
                 },
                 {
                     "llm_name": "text-embedding-v3",
-                    "tags": "TEXT EMBEDDING,2K",
-                    "max_tokens": 2048,
+                    "tags": "TEXT EMBEDDING,8K",
+                    "max_tokens": 8192,
                     "model_type": "embedding"
                 },
                 {