Unable to create Vector Store: Error code: 404 - {'error': {'code': '404', 'message': 'Resource not found'}}

> Please provide us with the following information:
> ---------------------------------------------------------------

### This issue is for a: (mark with an `x`)
```
- [x] bug report -> please search issues before submitting
- [ ] feature request
- [ ] documentation issue or request
- [ ] regression (a behavior that used to work and stopped in a new release)
```

### Minimal steps to reproduce
>
1) clone the repository
2) cd to Retrieval_Augmented_Generation_(RAG)_samples
3) Update .env file with required values
4) Create an index in azure search service and provide the index name to index_name variable.
5) Deploy text-embedding-ada-002 at Azure Open AI service and use the deployment name and version number for parameters of AzureOpenAIEmbeddings as below:
aoai_embeddings = AzureOpenAIEmbeddings(
azure_deployment="text-embedding-ada-002",
openai_api_version="2", # e.g., "2023-12-01-preview"
)
6) Run sample_rag_langchain..ipynb notebook.

### Any log messages given by the failure
>

### Expected/desired behavior
>

### OS and Version?
> Windows 7, 8 or 10. Linux (which distribution). macOS (Yosemite? El Capitan? Sierra?)

### Versions
>

### Mention any other details that might be useful

aoai_embeddings = AzureOpenAIEmbeddings(
azure_deployment="text-embedding-ada-002", ==> the name of the model deployment in Azure Open AI service.
openai_api_version="2", # e.g., "2023-12-01-preview"
)

vector_store_address: str = os.getenv("AZURE_SEARCH_ENDPOINT") ==> which is https://************.search.windows.net
vector_store_password: str = os.getenv("AZURE_SEARCH_ADMIN_KEY")
> ---------------------------------------------------------------
> Thanks! We'll be in touch soon.

从 Retrieval_Augmented_Generation_(RAG)_samples/sample_rag_langchain..ipynb 开始，检查 .env 值、Azure Search 索引、Azure Search endpoint 和管理员密钥，以及 AzureOpenAIEmbeddings deployment 和 API 版本。重新创建 vector store，并将已配置的资源名称和 endpoint 与 Azure 资源进行比较；完成标准是 notebook 能够在不出现 404 错误的情况下创建 vector store。

由索引模型根据 Issue 内容生成。