reduce rerank batch size (#2801)

### What problem does this PR solve?

### Type of change


- [x] Performance Improvement

api/db/init_data.py

@@ -132,7 +132,7 @@ def init_llm_factory():
     TenantService.filter_update([1 == 1], {
         "parser_ids": "naive:General,qa:Q&A,resume:Resume,manual:Manual,table:Table,paper:Paper,book:Book,laws:Laws,presentation:Presentation,picture:Picture,one:One,audio:Audio,knowledge_graph:Knowledge Graph,email:Email"})
     ## insert openai two embedding models to the current openai user.
-    print("Start to insert 2 OpenAI embedding models...")
+    # print("Start to insert 2 OpenAI embedding models...")
     tenant_ids = set([row["tenant_id"] for row in TenantLLMService.get_openai_models()])
     for tid in tenant_ids:
         for row in TenantLLMService.query(llm_factory="OpenAI", tenant_id=tid):

rag/llm/rerank_model.py

@@ -142,7 +142,7 @@ class YoudaoRerank(DefaultRerank):
         token_count = 0
         for _, t in pairs:
             token_count += num_tokens_from_string(t)
-        batch_size = 32
+        batch_size = 8
         res = []
         for i in range(0, len(pairs), batch_size):
             scores = self._model.compute_score(pairs[i:i + batch_size], max_length=self._model.max_length)