langchain/docs/extras/modules/data_connection/text_embedding/integrations/elasticsearch.ipynb

268 lines
5.9 KiB
Plaintext
Raw Normal View History

Add ElasticsearchEmbeddings class for generating embeddings using Elasticsearch models (#3401) 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 a [model deployed in an Elasticsearch cluster](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-model-ref.html#ml-nlp-model-ref-text-embedding). ### Main features: 1. The ElasticsearchEmbeddings class initializes with an Elasticsearch connection object and a model_id, providing an interface to interact with the Elasticsearch ML client through [infer_trained_model](https://elasticsearch-py.readthedocs.io/en/v8.7.0/api.html?highlight=trained%20model%20infer#elasticsearch.client.MlClient.infer_trained_model) . 2. The `embed_documents()` method generates embeddings for a list of documents, and the `embed_query()` method generates an embedding for a single query text. 3. The class supports custom input text field names in case the deployed model expects a different field name than the default `text_field`. 4. The implementation is compatible with any model deployed in Elasticsearch that generates embeddings as output. ### Benefits: 1. Simplifies the process of generating embeddings using Elasticsearch models. 2. Provides a clean and intuitive interface to interact with the Elasticsearch ML client. 3. Allows users to easily integrate Elasticsearch-generated embeddings. Related issue https://github.com/hwchase17/langchain/issues/3400 --------- Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
2023-05-23 21:50:33 +00:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "1eZl1oaVUNeC"
},
"source": [
"# Elasticsearch\n",
"Walkthrough of how to generate embeddings using a hosted embedding model in Elasticsearch\n",
"\n",
"The easiest way to instantiate the `ElasticsearchEmebddings` class it either\n",
"- using the `from_credentials` constructor if you are using Elastic Cloud\n",
"- or using the `from_es_connection` constructor with any Elasticsearch cluster"
],
"id": "72644940"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "6dJxqebov4eU"
},
"outputs": [],
"source": [
"!pip -q install elasticsearch langchain"
],
"id": "298759cb"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "RV7C3DUmv4aq"
},
"outputs": [],
"source": [
"import elasticsearch\n",
"from langchain.embeddings.elasticsearch import ElasticsearchEmbeddings"
],
"id": "76489aff"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "MrT3jplJvp09"
},
"outputs": [],
"source": [
"# Define the model ID\n",
"model_id = \"your_model_id\""
],
"id": "57bfdc82"
},
{
"cell_type": "markdown",
"metadata": {
"id": "j5F-nwLVS_Zu"
},
"source": [
"## Testing with `from_credentials`\n",
"This required an Elastic Cloud `cloud_id`"
],
"id": "0ffad1ec"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "svtdnC-dvpxR"
},
"outputs": [],
"source": [
"# Instantiate ElasticsearchEmbeddings using credentials\n",
"embeddings = ElasticsearchEmbeddings.from_credentials(\n",
" model_id,\n",
" es_cloud_id=\"your_cloud_id\",\n",
" es_user=\"your_user\",\n",
" es_password=\"your_password\",\n",
")"
],
"id": "fc2e9dcb"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "7DXZAK7Kvpth"
},
"outputs": [],
"source": [
"# Create embeddings for multiple documents\n",
"documents = [\n",
" \"This is an example document.\",\n",
" \"Another example document to generate embeddings for.\",\n",
"]\n",
"document_embeddings = embeddings.embed_documents(documents)"
],
"id": "8ee7f1fc"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "K8ra75W_vpqy"
},
"outputs": [],
"source": [
"# Print document embeddings\n",
"for i, embedding in enumerate(document_embeddings):\n",
" print(f\"Embedding for document {i+1}: {embedding}\")"
],
"id": "0b9d8471"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "V4Q5kQo9vpna"
},
"outputs": [],
"source": [
"# Create an embedding for a single query\n",
"query = \"This is a single query.\"\n",
"query_embedding = embeddings.embed_query(query)"
],
"id": "3989ab23"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "O0oQDzGKvpkz"
},
"outputs": [],
"source": [
"# Print query embedding\n",
"print(f\"Embedding for query: {query_embedding}\")"
],
"id": "0da6d2bf"
},
{
"cell_type": "markdown",
"metadata": {
"id": "rHN03yV6TJ5q"
},
"source": [
"## Testing with Existing Elasticsearch client connection\n",
"This can be used with any Elasticsearch deployment"
],
"id": "32700096"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GMQcJDwBTJFm"
},
"outputs": [],
"source": [
"# Create Elasticsearch connection\n",
"es_connection = Elasticsearch(\n",
" hosts=[\"https://es_cluster_url:port\"], basic_auth=(\"user\", \"password\")\n",
")"
],
"id": "0bc60465"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "WTYIU4u3TJO1"
},
"outputs": [],
"source": [
"# Instantiate ElasticsearchEmbeddings using es_connection\n",
"embeddings = ElasticsearchEmbeddings.from_es_connection(\n",
" model_id,\n",
" es_connection,\n",
")"
],
"id": "8085843b"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "4gdAUHwoTJO3"
},
"outputs": [],
"source": [
"# Create embeddings for multiple documents\n",
"documents = [\n",
" \"This is an example document.\",\n",
" \"Another example document to generate embeddings for.\",\n",
"]\n",
"document_embeddings = embeddings.embed_documents(documents)"
],
"id": "59a90bf3"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "RC_-tov6TJO3"
},
"outputs": [],
"source": [
"# Print document embeddings\n",
"for i, embedding in enumerate(document_embeddings):\n",
" print(f\"Embedding for document {i+1}: {embedding}\")"
],
"id": "54b18673"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "6GEnHBqETJO3"
},
"outputs": [],
"source": [
"# Create an embedding for a single query\n",
"query = \"This is a single query.\"\n",
"query_embedding = embeddings.embed_query(query)"
],
"id": "a4812d5e"
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "-kyUQAXDTJO4"
},
"outputs": [],
"source": [
"# Print query embedding\n",
"print(f\"Embedding for query: {query_embedding}\")"
],
"id": "c6c69916"
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}