Fix: Reduce excessive IO operations by loading LLM factory configurations (#6047)

…ions

### What problem does this PR solve?

This PR fixes an issue where the application was repeatedly reading the
llm_factories.json file from disk in multiple places, which could lead
to "Too many open files" errors under high load conditions. The fix
centralizes the file reading operation in the settings.py module and
stores the data in a global variable that can be accessed by other
modules.

### Type of change

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

rag/prompts.py

@@ -16,14 +16,13 @@
 import datetime
 import json
 import logging
-import os
 import re
 from collections import defaultdict
 import json_repair
+from api import settings
 from api.db import LLMType
 from api.db.services.document_service import DocumentService
 from api.db.services.llm_service import TenantLLMService, LLMBundle
-from api.utils.file_utils import get_project_base_directory
 from rag.settings import TAG_FLD
 from rag.utils import num_tokens_from_string, encoder
 
@@ -46,9 +45,9 @@ def chunks_format(reference):
 
 def llm_id2llm_type(llm_id):
     llm_id, _ = TenantLLMService.split_model_name_and_factory(llm_id)
-    fnm = os.path.join(get_project_base_directory(), "conf")
-    llm_factories = json.load(open(os.path.join(fnm, "llm_factories.json"), "r"))
-    for llm_factory in llm_factories["factory_llm_infos"]:
+
+    llm_factories = settings.FACTORY_LLM_INFOS  
+    for llm_factory in llm_factories:
         for llm in llm_factory["llm"]:
             if llm_id == llm["llm_name"]:
                 return llm["model_type"].strip(",")[-1]