[Feature Request]: New OpenAI model `gpt-4-0125-preview` is not available

Feature Description

I would like to use the latest model from OpenAI: gpt-4-0125-preview, published yesterday. You can see it announced in this blog post and listed on this page.

Reason

Currently, if you run the following script:

import os
from dotenv import load_dotenv
from llama_index import Document, ServiceContext, VectorStoreIndex
from llama_index.llms import OpenAI

MODEL = "gpt-4-0125-preview"

load_dotenv()
openai_api_key = os.getenv("OPENAI_API_KEY")
documents = [Document(text="my text")]
service_context = ServiceContext.from_defaults(llm=OpenAI(model=MODEL))
index = VectorStoreIndex.from_documents(documents, service_context=service_context)
query_engine = index.as_query_engine()
response = query_engine.query("What is this about ?")
print("response:", response)

You receive this error:

ValueError: Unknown model 'gpt-4-0125-preview'. Please provide a valid OpenAI model name in: gpt-4, gpt-4-32k, gpt-4-1106-preview, gpt-4-vision-preview, gpt-4-0613, gpt-4-32k-0613, gpt-4-0314, gpt-4-32k-0314, gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-3.5-turbo-1106, gpt-3.5-turbo-0613, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-0301, text-davinci-003, text-davinci-002, gpt-3.5-turbo-instruct, text-ada-001, text-babbage-001, text-curie-001, ada, babbage, curie, davinci, gpt-35-turbo-16k, gpt-35-turbo, gpt-35-turbo-1106, gpt-35-turbo-0613, gpt-35-turbo-16k-0613

Value of Feature

The new model include a fix allowing to use other language than english in json output.

The change to make seems to be quite simple, I tried it by updating the venv/Lib/site-packages/llama_index/llms/openai_utils.py file locally as such: Update this piece of code from:

GPT4_MODELS: Dict[str, int] = {
    # stable model names:
    #   resolves to gpt-4-0314 before 2023-06-27,
    #   resolves to gpt-4-0613 after
    "gpt-4": 8192,
    "gpt-4-32k": 32768,
    # 1106 model (Turbo, JSON mode)
    "gpt-4-1106-preview": 128000,
    # multimodal model
    "gpt-4-vision-preview": 128000,
    # 0613 models (function calling):
    #   https://openai.com/blog/function-calling-and-other-api-updates
    "gpt-4-0613": 8192,
    "gpt-4-32k-0613": 32768,
    # 0314 models
    "gpt-4-0314": 8192,
    "gpt-4-32k-0314": 32768,
}

GPT4_MODELS: Dict[str, int] = {
    # stable model names:
    #   resolves to gpt-4-0314 before 2023-06-27,
    #   resolves to gpt-4-0613 after
    "gpt-4": 8192,
    "gpt-4-32k": 32768,
    # 0125 model (Turbo, JSON mode)
    "gpt-4-0125-preview": 128000,
    # 1106 model (Turbo, JSON mode)
    "gpt-4-1106-preview": 128000,
    # multimodal model
    "gpt-4-vision-preview": 128000,
    # 0613 models (function calling):
    #   https://openai.com/blog/function-calling-and-other-api-updates
    "gpt-4-0613": 8192,
    "gpt-4-32k-0613": 32768,
    # 0314 models
    "gpt-4-0314": 8192,
    "gpt-4-32k-0314": 32768,
}

Note that they also introduce a gpt-4-turbo-preview model, which could be added the same way and would be great to have also.

I can take care of the PR if this is the right change and if needed. Thank you in advance.

run-llama / llama_index