Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779)

### What problem does this PR solve?

Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.

### Type of change

- [x] Refactoring
- [x] Performance Improvement

rag/llm/__init__.py

@@ -52,6 +52,8 @@ class SupportedLiteLLMProvider(StrEnum):
     JiekouAI = "Jiekou.AI"
     ZHIPU_AI = "ZHIPU-AI"
     MiniMax = "MiniMax"
+    DeerAPI = "DeerAPI"
+    GPUStack = "GPUStack"
 
 
 FACTORY_DEFAULT_BASE_URL = {
@@ -75,6 +77,7 @@ FACTORY_DEFAULT_BASE_URL = {
     SupportedLiteLLMProvider.JiekouAI: "https://api.jiekou.ai/openai",
     SupportedLiteLLMProvider.ZHIPU_AI: "https://open.bigmodel.cn/api/paas/v4",
     SupportedLiteLLMProvider.MiniMax: "https://api.minimaxi.com/v1",
+    SupportedLiteLLMProvider.DeerAPI: "https://api.deerapi.com/v1",
 }
 
 
@@ -108,6 +111,8 @@ LITELLM_PROVIDER_PREFIX = {
     SupportedLiteLLMProvider.JiekouAI: "openai/",
     SupportedLiteLLMProvider.ZHIPU_AI: "openai/",
     SupportedLiteLLMProvider.MiniMax: "openai/",
+    SupportedLiteLLMProvider.DeerAPI: "openai/",
+    SupportedLiteLLMProvider.GPUStack: "openai/",
 }
 
 ChatModel = globals().get("ChatModel", {})