FEAT: RESTful API

[jiayini1119]

Resolves #18

python -m plexar.deploy.cmdline supervisor -a localhost:9999 --log-level debug

python -m plexar.deploy.cmdline worker --supervisor-address localhost:9999 -a localhost:10000 --log-level debug

In [1]: from plexar.client import RESTfulClient
In [2]: client = RESTfulClient("http://0.0.0.0:8000")
In [3]: client.launch_model(model_name="baichuan", quantization="q4_0")
Out[3]: '0e1c880e-1b07-11ee-b9de-a1e57d13cecc'
In [4]: client.generate(model_uid='0e1c880e-1b07-11ee-b9de-a1e57d13cecc', prompt="Once upon a time, there was a very old computer.")

In [5]: client.launch_model(model_name="wizardlm-v1.0", quantization="q4_0")
Out[5]: '21d09084-1b07-11ee-b9de-a1e57d13cecc'
In [6]: client.chat(model_uid="21d09084-1b07-11ee-b9de-a1e57d13cecc", prompt="What can I eat in the capital of France?", system_prompt="you are a helpful AI assistant", chat_history=[{"role": "user", "conte
   ...: nt": "Hello!"}, {"role": "assistant", "content": "Hi what can I help you?"}, {"role": "user", "content": "What is the capital of France?"},{"role": "assistant", "content": "The capital of France is 
   ...: Paris."}])