Jeff Vestal

Add support for generating embeddings in Elasticsearch

1

Elastic supports generating embeddings using [embedding models running in the stack](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-model-ref.html#ml-nlp-model-ref-text-embedding). Add a the ability to generate embeddings with Elasticsearch in langchain similar to other embedding modules.

Add ElasticsearchEmbeddings class for generating embeddings using Elasticsearch models

2

This PR introduces a new module, `elasticsearch_embeddings.py`, which provides a wrapper around Elasticsearch embedding models. The new ElasticsearchEmbeddings class allows users to generate embeddings for documents and query texts using...

### Feature request Extend `langchain/embeddings/elasticsearch.py` to support kNN indexing and searching. The high-level objectives will be: 1. Allow for the [creation of an index with the correct mapping](https://www.elastic.co/guide/en/elasticsearch/reference/current/dense-vector.html#index-vectors-knn-search) to store...

This PR adds a new method `from_es_connection` to the `ElasticsearchEmbeddings` class allowing users to use Elasticsearch clusters outside of Elastic Cloud. Users can create an Elasticsearch Client object and pass...

in the `ElasticKnnSearch` class added 2 arguments that were not exposed properly `knn_search` added: - `vector_query_field: Optional[str] = 'vector'` -- vector_query_field: Field name to use in knn search if not...

Allow query field to be passed in ElasticKnnSearch.knnSearch

1

### System Info The [_default_knn_query](https://github.com/jeffvestal/langchain/blob/10f34bf62e2d53f0b1a7b15ba21c2328b64862cd/langchain/vectorstores/elastic_vector_search.py#L402) takes `field` arg to specify the field to use when performing knn and hybrid search. both [knn_search](https://github.com/jeffvestal/langchain/blob/10f34bf62e2d53f0b1a7b15ba21c2328b64862cd/langchain/vectorstores/elastic_vector_search.py#L475) and [hybrid_search](https://github.com/jeffvestal/langchain/blob/10f34bf62e2d53f0b1a7b15ba21c2328b64862cd/langchain/vectorstores/elastic_vector_search.py#L537) need to allow that to be...

### Feature request Make `embedding` an [optional arg](https://github.com/jeffvestal/langchain/blob/10f34bf62e2d53f0b1a7b15ba21c2328b64862cd/langchain/vectorstores/elastic_vector_search.py#L332) when creating `ElasticKnnSearch` class ### Motivation If a user is only going to run knn/hybrid search AND use the `query_vector_builder` having an...

in ElasticKnnSearch added back create_index, add_texts, from_texts

1

Fixes https://github.com/hwchase17/langchain/issues/7117 Adding back `create_index` , `add_texts`, `from_texts` to ElasticKnnSearch Quick Test from langchain.vectorstores.elastic_vector_search import ElasticKnnSearch from langchain.embeddings import ElasticsearchEmbeddings ## Initialize ElasticsearchEmbeddings model_id = "sentence-transformers__all-distilroberta-v1" dims = 768 es_cloud_id...

## Feature Request As a Python user, I would like to simplify the code required to load an inference model from Hugging Face (or private source) into Elasticsearch. ## Use...