langchain/libs/partners/elasticsearch
Max Jakob ee7a7954b9
elasticsearch: add ElasticsearchRetriever (#18587)
Implement
[Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/)
interface for Elasticsearch.

I opted to only expose the `body`, which gives you full flexibility, and
none the other 68 arguments of the [search
method](https://elasticsearch-py.readthedocs.io/en/v8.12.1/api/elasticsearch.html#elasticsearch.Elasticsearch.search).

Added a user agent header for usage tracking in Elastic Cloud.

---------

Co-authored-by: Erick Friis <erick@langchain.dev>
2024-03-06 00:42:50 +00:00
..
langchain_elasticsearch elasticsearch: add ElasticsearchRetriever (#18587) 2024-03-06 00:42:50 +00:00
scripts
tests elasticsearch: add ElasticsearchRetriever (#18587) 2024-03-06 00:42:50 +00:00
.gitignore
LICENSE
Makefile
poetry.lock elasticsearch: add ElasticsearchRetriever (#18587) 2024-03-06 00:42:50 +00:00
pyproject.toml docs: Update elasticsearch README (#18497) 2024-03-05 15:49:16 -08:00
README.md docs: Update elasticsearch README (#18497) 2024-03-05 15:49:16 -08:00

langchain-elasticsearch

This package contains the LangChain integration with Elasticsearch.

Installation

pip install -U langchain-elasticsearch

Elasticsearch setup

Elastic Cloud

You need a running Elasticsearch deployment. The easiest way to start one is through Elastic Cloud. You can sign up for a free trial.

  1. Create a deployment
  2. Get your Cloud ID:
    1. In the Elastic Cloud console, click "Manage" next to your deployment
    2. Copy the Cloud ID and paste it into the es_cloud_id parameter below
  3. Create an API key:
    1. In the Elastic Cloud console, click "Open" next to your deployment
    2. In the left-hand side menu, go to "Stack Management", then to "API Keys"
    3. Click "Create API key"
    4. Enter a name for the API key and click "Create"
    5. Copy the API key and paste it into the es_api_key parameter below

Elastic Cloud

Alternatively, you can run Elasticsearch via Docker as described in the docs.

Usage

ElasticsearchStore

The ElasticsearchStore class exposes Elasticsearch as a vector store.

from langchain_elasticsearch import ElasticsearchStore

embeddings = ... # use a LangChain Embeddings class or ElasticsearchEmbeddings

vectorstore = ElasticsearchStore(
    es_cloud_id="your-cloud-id",
    es_api_key="your-api-key",
    index_name="your-index-name",
    embeddings=embeddings,
)

ElasticsearchEmbeddings

The ElasticsearchEmbeddings class provides an interface to generate embeddings using a model deployed in an Elasticsearch cluster.

from langchain_elasticsearch import ElasticsearchEmbeddings

embeddings = ElasticsearchEmbeddings.from_credentials(
    model_id="your-model-id",
    input_field="your-input-field",
    es_cloud_id="your-cloud-id",
    es_api_key="your-api-key",
)

ElasticsearchChatMessageHistory

The ElasticsearchChatMessageHistory class stores chat histories in Elasticsearch.

from langchain_elasticsearch import ElasticsearchChatMessageHistory

chat_history = ElasticsearchChatMessageHistory(
    index="your-index-name",
    session_id="your-session-id",
    es_cloud_id="your-cloud-id",
    es_api_key="your-api-key",
)