feat(model): Support siliconflow models

[fangyinc]

Description

Closes #2156

How Has This Been Tested?

1. Using siliconflow proxyllm in DB-GPT webserver

# .env
LLM_MODEL=silicon_flow_proxyllm
SILICON_FLOW_MODEL_VERSION=Qwen/Qwen2.5-Coder-32B-Instruct
SILICON_FLOW_API_BASE=https://api.siliconflow.cn/v1
SILICON_FLOW_API_KEY={your-siliconflow-api-key}

2. Using SiliconFlowLLMClient
   Create python file test_proxyllm.py

import asyncio

from dbgpt.core import ModelRequest
from dbgpt.model.proxy import SiliconFlowLLMClient

client = SiliconFlowLLMClient(model_alias="Qwen/Qwen2.5-Coder-32B-Instruct")
print(
    asyncio.run(
        client.generate(
            ModelRequest._build("Qwen/Qwen2.5-Coder-32B-Instruct", "Hi!")
        )
    )
)

Run test_proxyllm.py

SILICON_FLOW_API_KEY={your-siliconflow-api-key} python test_proxyllm.py

The output like this:

ModelOutput(text='Hello! How can I assist you today?', error_code=0, incremental=False, model_context=None, finish_reason=None, usage={'completion_tokens': 9, 'prompt_tokens': 31, 'total_tokens': 40}, metrics=None)

How Has This Been Tested?

Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration

Snapshots:

Include snapshots for easier review.

Checklist:

• My code follows the style guidelines of this project
• I have already rebased the commits and make the commit message conform to the project standard.
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• Any dependent changes have been merged and published in downstream modules

[fangyinc]

Use siliconflow embedding model by DB-GPT SDK:

import os
from dbgpt.rag.embedding import OpenAPIEmbeddings

openai_embeddings = OpenAPIEmbeddings(
    api_url="https://api.siliconflow.cn/v1/embeddings",
    api_key=os.getenv("SILICON_FLOW_API_KEY"),
    model_name="BAAI/bge-large-zh-v1.5",
)

texts = ["Hello, world!", "How are you?"]
openai_embeddings.embed_documents(texts)

[csunny]

It's cool, and using the Jupyter Notebook makes it easy for code testing.

r+

[Aries-ckt]

r+