Feat: add VLLM (#5380)

### What problem does this PR solve?

Read to add VLMM.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

rag/llm/__init__.py

@@ -160,6 +160,7 @@ EmbeddingModel = {
     "NVIDIA": NvidiaEmbed,
     "LM-Studio": LmStudioEmbed,
     "OpenAI-API-Compatible": OpenAI_APIEmbed,
+    "VLLM": OpenAI_APIEmbed,
     "Cohere": CoHereEmbed,
     "TogetherAI": TogetherAIEmbed,
     "PerfXCloud": PerfXCloudEmbed,
@@ -188,6 +189,7 @@ CvModel = {
     "LM-Studio": LmStudioCV,
     "StepFun": StepFunCV,
     "OpenAI-API-Compatible": OpenAI_APICV,
+    "VLLM": OpenAI_APICV,
     "TogetherAI": TogetherAICV,
     "01.AI": YiCV,
     "Tencent Hunyuan": HunyuanCV,
@@ -215,6 +217,7 @@ ChatModel = {
     "NVIDIA": NvidiaChat,
     "LM-Studio": LmStudioChat,
     "OpenAI-API-Compatible": OpenAI_APIChat,
+    "VLLM": OpenAI_APIChat,
     "Cohere": CoHereChat,
     "LeptonAI": LeptonAIChat,
     "TogetherAI": TogetherAIChat,
@@ -244,6 +247,7 @@ RerankModel = {
     "NVIDIA": NvidiaRerank,
     "LM-Studio": LmStudioRerank,
     "OpenAI-API-Compatible": OpenAI_APIRerank,
+    "VLLM": OpenAI_APIRerank,
     "Cohere": CoHereRerank,
     "TogetherAI": TogetherAIRerank,
     "SILICONFLOW": SILICONFLOWRerank,