Enable ElasticsearchStore to retrieve with the pure BM25 algorithm without vector search

[g-votte]

This PR is migrated from the main repo of LangChain, since the libs/elasticsearch has been moved during the review process. The original PR is: langchain-ai/langchain#19314

Description

This pull request proposes the implementation of the BM25RetrievalStrategy for ElasticsearchStore. This retrieval strategy enables searches purely based on BM25 without involving vector search.

Usage Example of Introduced Feature

By specifying the BM25RetrievalStrategy as a constructor argument for ElasticsearchStore, users can perform searches using pure BM25 without vector search. Note that in the example below, the embedding option is not specified, indicating that the search is conducted without using embeddings.

from langchain_elasticsearch.vectorstores import ElasticsearchStore

store = ElasticsearchStore(
    es_url="http://localhost:9200",
    index_name="test_index",
    strategy=ElasticsearchStore.BM25RetrievalStrategy(),
)

store.add_texts(
    [
        "foo",
        "foo bar",
        "foo bar baz",
        "bar",
        "bar baz",
        "baz"
    ],
)

results = store.similarity_search(query="foo", k=10)
print(results)

The example above outputs:

[Document(page_content='foo'), Document(page_content='foo bar'), Document(page_content='foo bar baz')]

Details

For more details, please refer to the original PR: langchain-ai/langchain#19314

[g-votte]

I have migrated the changes from the original PR. Although @joemcelroy and @maxjakob have kindly approved the original one, I welcome any additional comments you might have.

The documentation has been excluded from this PR because, in my understanding, the docs will continue to be managed in LangChain's main repository. Consequently, once this PR is merged, I intend to submit a new PR specifically for the documentation in the main repository.

PTAL.
@joemcelroy @miguelgrinberg @maxjakob @baskaryan @efriis

[maxjakob]

Thanks again for your contribution @g-votte!

The documentation has been excluded from this PR because, in my understanding, the docs will continue to be managed in LangChain's main repository. Consequently, once this PR is merged, I intend to submit a new PR specifically for the documentation in the main repository.

That is correct, the docs still live in the main repo. It would be great if you could create another PR with the documentation change.