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/tts_model.py

@@ -355,3 +355,35 @@ class OllamaTTS(Base):
         for chunk in response.iter_content():
             if chunk:
                 yield chunk
+
+class GPUStackTTS:
+    def __init__(self, key, model_name, **kwargs):
+        self.base_url = kwargs.get("base_url", None)
+        self.api_key = key
+        self.model_name = model_name
+        self.headers = {
+            "accept": "application/json",
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {self.api_key}"
+        }
+
+    def tts(self, text, voice="Chinese Female", stream=True):
+        payload = {
+            "model": self.model_name,
+            "input": text,
+            "voice": voice
+        }
+
+        response = requests.post(
+            f"{self.base_url}/v1-openai/audio/speech",
+            headers=self.headers,
+            json=payload,
+            stream=stream
+        )
+
+        if response.status_code != 200:
+            raise Exception(f"**Error**: {response.status_code}, {response.text}")
+
+        for chunk in response.iter_content(chunk_size=1024):
+            if chunk:
+                yield chunk