Support Xinference (#320)

### What problem does this PR solve?

Issue link:#299

### Type of change

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

rag/llm/__init__.py

@@ -21,6 +21,7 @@ from .cv_model import *
 EmbeddingModel = {
     "Ollama": OllamaEmbed,
     "OpenAI": OpenAIEmbed,
+    "Xinference": XinferenceEmbed,
     "Tongyi-Qianwen": HuEmbedding, #QWenEmbed,
     "ZHIPU-AI": ZhipuEmbed,
     "Moonshot": HuEmbedding
@@ -30,6 +31,7 @@ EmbeddingModel = {
 CvModel = {
     "OpenAI": GptV4,
     "Ollama": OllamaCV,
+    "Xinference": XinferenceCV,
     "Tongyi-Qianwen": QWenCV,
     "ZHIPU-AI": Zhipu4V,
     "Moonshot": LocalCV
@@ -41,6 +43,7 @@ ChatModel = {
     "ZHIPU-AI": ZhipuChat,
     "Tongyi-Qianwen": QWenChat,
     "Ollama": OllamaChat,
+    "Xinference": XinferenceChat,
     "Moonshot": MoonshotChat
 }