Add support customization of the number of shards and replicas when creating an index for OpenSearch

[NotHolmes]

Checked

• I searched existing ideas and did not find a similar one
• I added a very descriptive title
• I've clearly described the feature request and motivation for it

Feature request

Add support for customizing the number of shards and replicas when creating an index in OpenSearch through LangChain with OpenSearchVectorSearch().create_index()

Motivation

Currently, LangChain doesn't let users set the number of shards or replicas when creating an OpenSearch index. Because of this, users have to use OpenSearchVectorSearch().client.indices.create() directly, which isn't fully compatible with LangChain and is inconvenient.

Proposal (If applicable)

we could potentially do something like this:

def _default_text_mapping(
    dim: int,
    number_of_shards: int = 1,
    number_of_replicas: int = 1,
    engine: str = "nmslib",
    space_type: str = "l2",
    ef_search: int = 512,
    ef_construction: int = 512,
    m: int = 16,
    vector_field: str = "vector_field",
) -> dict:
    """For Approximate k-NN Search, this is the default mapping to create index, with customizable shards and replicas."""
    return {
        "settings": {
            "index": {
                "number_of_shards": number_of_shards,
                "number_of_replicas": number_of_replicas,
                "knn": True,
                "knn.algo_param.ef_search": ef_search,
            }
        },
        "mappings": {
            "properties": {
                vector_field: {
                    "type": "knn_vector",
                    "dimension": dim,
                    "method": {
                        "name": "hnsw",
                        "space_type": space_type,
                        "engine": engine,
                        "parameters": {
                            "ef_construction": ef_construction,
                            "m": m,
                        },
                    },
                }
            }
        },
    }

and adjust every other function that uses this one accordingly.

[NotHolmes]

Closed. Moved to https://github.com/langchain-ai/langchain-community