langchain/docs/modules/models/text_embedding/examples/elasticsearch.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "!pip install elasticsearch langchain"
      ],
      "metadata": {
        "id": "OOiBBjc0Kd-6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "%env ES_CLOUDID=<cloud id from cloud.elastic.co>\n",
        "%env ES_USER=<user>\n",
        "%env ES_PASS=<password>\n",
        "\n",
        "es_cloudid = os.environ.get(\"ES_CLOUDID\")\n",
        "es_user = os.environ.get(\"ES_USER\")\n",
        "es_pass = os.environ.get(\"ES_PASS\")"
      ],
      "metadata": {
        "id": "Wr8unljAKdCh"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Connect to Elasticsearch\n",
        "es_connection = Elasticsearch(cloud_id=es_cloudid, basic_auth=(es_user, es_pass))"
      ],
      "metadata": {
        "id": "YIDsrBqTKs85"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Define the model ID and input field name (if different from default)\n",
        "model_id = \"your_model_id\"\n",
        "input_field = \"your_input_field\"  # Optional, only if different from 'text_field'"
      ],
      "metadata": {
        "id": "sfFhnFHOKvbM"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Initialize the ElasticsearchEmbeddings instance\n",
        "embeddings_generator = ElasticsearchEmbeddings(es_connection, model_id, input_field)"
      ],
      "metadata": {
        "id": "V-pCgqLCKvYs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Generate embeddings for a list of documents\n",
        "documents = [\n",
        "  \"This is an example document.\",\n",
        "  \"Another example document to generate embeddings for.\",\n",
        "  ]\n",
        "document_embeddings = embeddings_generator.embed_documents(documents)"
      ],
      "metadata": {
        "id": "lJg2iRDWKvV_"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Print the generated document embeddings\n",
        "for i, doc_embedding in enumerate(document_embeddings):\n",
        "  print(f\"Embedding for document {i + 1}: {doc_embedding}\")"
      ],
      "metadata": {
        "id": "R3sYQlh3KvTQ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Generate an embedding for a single query text\n",
        "query_text = \"What is the meaning of life?\"\n",
        "query_embedding = embeddings_generator.embed_query(query_text)"
      ],
      "metadata": {
        "id": "n0un5Vc0KvQd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Print the generated query embedding\n",
        "print(f\"Embedding for query: {query_embedding}\")"
      ],
      "metadata": {
        "id": "PANph6pmKvLD"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}