Azure AI Search Client Component Calling get_index function twice

[msetbar]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

We have the following code:

openai_api_key: str = "PLACEHOLDER FOR YOUR API KEY"
openai_api_version: str = "2023-05-15"
model: str = "text-embedding-ada-002"

azure_endpoint: str = "PLACEHOLDER FOR YOUR AZURE OPENAI ENDPOINT"
azure_openai_api_key: str = "PLACEHOLDER FOR YOUR AZURE OPENAI KEY"
azure_openai_api_version: str = "2023-05-15"
azure_deployment: str = "text-embedding-ada-002"

vector_store_address: str = "YOUR_AZURE_SEARCH_ENDPOINT"
vector_store_password: str = "YOUR_AZURE_SEARCH_ADMIN_KEY"

embeddings: AzureOpenAIEmbeddings = AzureOpenAIEmbeddings(
    azure_deployment=azure_deployment,
    openai_api_version=azure_openai_api_version,
    azure_endpoint=azure_endpoint,
    api_key=azure_openai_api_key,
)

vector_store: AzureSearch = AzureSearch(
    azure_search_endpoint=vector_store_address,
    azure_search_key=vector_store_password,
    index_name=index_name,
    embedding_function=embeddings.embed_query,
    # Configure max retries for the Azure client
    additional_search_client_options={"retry_total": 4},
)

docs = vector_store.similarity_search(
    query="What did the president say about Ketanji Brown Jackson",
    k=3,
    search_type="similarity",
)
print(docs[0].page_content)

In AzureSearch, get_index function is called twice which is not needed. One is called for intialization of client and the second time is called for the intialization of client_async. Please check this line: https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/vectorstores/azuresearch.py#L361

Error Message and Stack Trace (if applicable)

It is just adding up a latency to AzureSearch component since it is called get_index function twice.

Description

I am trying to use LangChain to integrate with Azure AI Search and noticed that get_index function is getting called twice when trying to intialize AzureSearch.

System Info

System Information

OS: Linux
OS Version: #1 SMP PREEMPT Thu Jun 30 08:18:26 UTC 2022
Python Version: 3.10.14 (main, Jul 2 2024, 22:06:13) [GCC 12.2.0]

Package Information

langchain_core: 0.3.31
langchain: 0.3.15
langchain_community: 0.3.15
langsmith: 0.3.2
langchain_text_splitters: 0.3.5

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.11.11
async-timeout: 4.0.3
dataclasses-json: 0.6.7
httpx: 0.27.2
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
orjson: 3.10.15
packaging: 24.1
pydantic: 2.10.4
pydantic-settings: 2.7.1
pytest: Installed. No version info available.
PyYAML: 6.0.1
requests: 2.32.3
requests-toolbelt: 1.0.0
rich: 13.9.4
SQLAlchemy: 2.0.36
tenacity: 9.0.0
typing-extensions: 4.12.2
zstandard: 0.23.0

[keenborder786]

@msetbar one is for client and one is for async_client

[hrishi-008]

Async should be instantiated if async_ is set to true in **kwargs