Feat: add gpustack model provider (#4469)

### What problem does this PR solve?

Add GPUStack as a new model provider.
[GPUStack](https://github.com/gpustack/gpustack) is an open-source GPU
cluster manager for running LLMs. Currently, locally deployed models in
GPUStack cannot integrate well with RAGFlow. GPUStack provides both
OpenAI compatible APIs (Models / Chat Completions / Embeddings /
Speech2Text / TTS) and other APIs like Rerank. We would like to use
GPUStack as a model provider in ragflow.

[GPUStack Docs](https://docs.gpustack.ai/latest/quickstart/)

Related issue: https://github.com/infiniflow/ragflow/issues/4064.

### Type of change

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



### Testing Instructions
1. Install GPUStack and deploy the `llama-3.2-1b-instruct` llm, `bge-m3`
text embedding model, `bge-reranker-v2-m3` rerank model,
`faster-whisper-medium` Speech-to-Text model, `cosyvoice-300m-sft` in
GPUStack.
2. Add provider in ragflow settings.
3. Testing in ragflow.

rag/llm/__init__.py

@@ -42,6 +42,7 @@ from .embedding_model import (
     VoyageEmbed,
     HuggingFaceEmbed,
     VolcEngineEmbed,
+    GPUStackEmbed,
 )
 from .chat_model import (
     GptTurbo,
@@ -80,6 +81,7 @@ from .chat_model import (
     AnthropicChat,
     GoogleChat,
     HuggingFaceChat,
+    GPUStackChat,
 )
 
 from .cv_model import (
@@ -116,6 +118,7 @@ from .rerank_model import (
     BaiduYiyanRerank,
     VoyageRerank,
     QWenRerank,
+    GPUStackRerank,
 )
 from .sequence2txt_model import (
     GPTSeq2txt,
@@ -123,6 +126,7 @@ from .sequence2txt_model import (
     AzureSeq2txt,
     XinferenceSeq2txt,
     TencentCloudSeq2txt,
+    GPUStackSeq2txt,
 )
 from .tts_model import (
     FishAudioTTS,
@@ -130,6 +134,7 @@ from .tts_model import (
     OpenAITTS,
     SparkTTS,
     XinferenceTTS,
+    GPUStackTTS,
 )
 
 EmbeddingModel = {
@@ -161,6 +166,7 @@ EmbeddingModel = {
     "Voyage AI": VoyageEmbed,
     "HuggingFace": HuggingFaceEmbed,
     "VolcEngine": VolcEngineEmbed,
+    "GPUStack": GPUStackEmbed,
 }
 
 CvModel = {
@@ -220,6 +226,7 @@ ChatModel = {
     "Anthropic": AnthropicChat,
     "Google Cloud": GoogleChat,
     "HuggingFace": HuggingFaceChat,
+    "GPUStack": GPUStackChat,
 }
 
 RerankModel = {
@@ -237,6 +244,7 @@ RerankModel = {
     "BaiduYiyan": BaiduYiyanRerank,
     "Voyage AI": VoyageRerank,
     "Tongyi-Qianwen": QWenRerank,
+    "GPUStack": GPUStackRerank,
 }
 
 Seq2txtModel = {
@@ -245,6 +253,7 @@ Seq2txtModel = {
     "Azure-OpenAI": AzureSeq2txt,
     "Xinference": XinferenceSeq2txt,
     "Tencent Cloud": TencentCloudSeq2txt,
+    "GPUStack": GPUStackSeq2txt,
 }
 
 TTSModel = {
@@ -253,4 +262,5 @@ TTSModel = {
     "OpenAI": OpenAITTS,
     "XunFei Spark": SparkTTS,
     "Xinference": XinferenceTTS,
+    "GPUStack": GPUStackTTS,
 }