feat(model): Add support for Azure openAI

[likenamehaojie]

Support Azure OpenAI Proxy

• Add API_AZURE_DEPLOYMENT environment variables to adapt to Azure openAI
• Add variables to adapter to Azure OpenAI

Description

Added support for Azure openAI and added API_AZURE_DEPLOYMENT environment variables to adapt to Azure openAI

How Has This Been Tested?

The test translation has been completed

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

[likenamehaojie]

LLM_MODEL=proxyllm
PROXY_API_KEY=xxxx
PROXY_API_BASE=https://xxxxxx.openai.azure.com/
PROXY_API_TYPE=azure
PROXY_SERVER_URL=xxxx
PROXY_API_VERSION=2023-05-15
PROXYLLM_BACKEND=gpt-35-turbo
API_AZURE_DEPLOYMENT=xxxx[deployment_name]

[csunny]

@likenamehaojie Thanks for your PR, We will make a test and merge it.

[fangyinc]

@likenamehaojie Thank you for your contribution. But there is still a small problem, please use the following command to format the python code: make fmt.

Of course, we recommend that you install pre-commit hooks with following command: pre-commit install.

[likenamehaojie]

I have adjusted the code format @fangyinc

[fangyinc]

OpeanAI LLM proxyllm can't work, error log：

2024-01-31 16:02:06 212eb64a67ea dbgpt.model.cluster.worker.default_worker[1] ERROR Model inference error, detail: Traceback (most recent call last):
  File "/app/dbgpt/model/cluster/worker/default_worker.py", line 246, in async_generate_stream
    async for output in generate_stream_func(
  File "/app/dbgpt/model/proxy/llms/chatgpt.py", line 41, in chatgpt_generate_stream
    async for r in client.generate_stream(request):
  File "/app/dbgpt/model/proxy/llms/chatgpt.py", line 188, in generate_stream
    async for r in self.generate_stream_v1(messages, payload):
  File "/app/dbgpt/model/proxy/llms/chatgpt.py", line 216, in generate_stream_v1
    chat_completion = await self.client.chat.completions.create(
  File "/app/dbgpt/model/proxy/llms/chatgpt.py", line 121, in client
    self._api_type, self._client = _build_openai_client(
  File "/app/dbgpt/model/utils/chatgpt_utils.py", line 152, in _build_openai_client
    return api_type, AsyncOpenAI(
TypeError: AsyncOpenAI.__init__() got an unexpected keyword argument 'api_azure_deployment'

2024-01-31 16:02:06 212eb64a67ea dbgpt.agent.agents.llm.llm_client[1] ERROR Call LLMClient error, Model server error!code=1, error msg is **LLMServer Generate Error, Please CheckErrorInfo.**: AsyncOpenAI.__init__() got an unexpected keyword argument 'api_azure_deployment', detail: Traceback (most recent call last):
  File "/app/dbgpt/agent/agents/llm/llm_client.py", line 184, in _completions_create
    parsed_output = self._output_parser.parse_model_nostream_resp(
  File "/app/dbgpt/core/interface/output_parser.py", line 109, in parse_model_nostream_resp
    raise ValueError(
ValueError: Model server error!code=1, error msg is **LLMServer Generate Error, Please CheckErrorInfo.**: AsyncOpenAI.__init__() got an unexpected keyword argument 'api_azure_deployment'

2024-01-31 16:02:06 212eb64a67ea dbgpt.agent.agents.base_agent[1] ERROR model:proxyllm generate Failed!LLM Chat Generrate Error!(Model server error!code=1, error msg is **LLMServer Generate Error, Please CheckErrorInfo.**: AsyncOpenAI.__init__() got an unexpected keyword argument 'api_azure_deployment')

[likenamehaojie]

@fangyinc 最新版本的OPENAI是不是对这个方法做了修改？

[likenamehaojie]

API_AZURE_DEPLOYMENT @fangyinc need add this environment variables,use main branch to test

[fangyinc]

API_AZURE_DEPLOYMENT @fangyinc need add this environment variables,use main branch to test

openai.AsyncOpenAI does not support the azure_deployment parameter and needs to be excluded from openai_params.

[likenamehaojie]

PROXY_API_TYPE=azure .is add this ? @fangyinc

[likenamehaojie]

This image shows that this parameter(azure_deployment) is present in the current version(main branch) @fangyinc

[fangyinc]

This image shows that this parameter(azure_deployment) is present in the current version(main branch) @fangyinc

Aha, what I mean is not that Azure openAI cannot work, but that OpenAI cannot work~

[likenamehaojie]

This image shows that this parameter(azure_deployment) is present in the current version(main branch) @fangyinc

Aha, what I mean is not that Azure openAI cannot work, but that OpenAI cannot work~

OK,I will fix this bug!

[likenamehaojie]

@fangyinc already fixed

[csunny]

Thanks for your PR, LGTM

[fangyinc]

Nice, LGTM.

[cxiaowen]

LLM_MODEL=proxyllm PROXY_API_KEY=xxxx PROXY_API_BASE=https://xxxxxx.openai.azure.com/ PROXY_API_TYPE=azure PROXY_SERVER_URL=xxxx PROXY_API_VERSION=2023-05-15 PROXYLLM_BACKEND=gpt-35-turbo API_AZURE_DEPLOYMENT=xxxx[deployment_name]

这个是怎么配置进DB-GPT的，也是这种azure模型，但是不知道怎么配置进DB-GPT