example usage (langchain-ai#5182)

Adding example usage for elasticsearch knn embeddings [per](langchain-ai#3401 (comment)) https://github.com/hwchase17/langchain/blob/master/langchain/embeddings/elasticsearch.py
Undertone0809 · Jun 19, 2023 · 8dc2b9c · 8dc2b9c
1 parent 0a17dd6
commit 8dc2b9c
Showing 1 changed file with 33 additions and 46 deletions.
diff --git a/docs/modules/models/text_embedding/examples/elasticsearch.ipynb b/docs/modules/models/text_embedding/examples/elasticsearch.ipynb
@@ -17,118 +17,105 @@
     {
       "cell_type": "code",
       "source": [
-        "!pip install elasticsearch langchain"
+        "!pip -q install elasticsearch langchain"
       ],
       "metadata": {
-        "id": "OOiBBjc0Kd-6"
+        "id": "6dJxqebov4eU"
       },
       "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\")"
+        "import elasticsearch\n",
+        "from langchain.embeddings.elasticsearch import ElasticsearchEmbeddings"
       ],
       "metadata": {
-        "id": "Wr8unljAKdCh"
+        "id": "RV7C3DUmv4aq"
       },
       "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))"
+        "# Define the model ID\n",
+        "model_id = 'your_model_id'"
       ],
       "metadata": {
-        "id": "YIDsrBqTKs85"
+        "id": "MrT3jplJvp09"
       },
       "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'"
+        "# 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",
+        ")\n"
       ],
       "metadata": {
-        "id": "sfFhnFHOKvbM"
+        "id": "svtdnC-dvpxR"
       },
       "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",
+        "# 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_generator.embed_documents(documents)"
+        "    'This is an example document.', \n",
+        "    'Another example document to generate embeddings for.'\n",
+        "]\n",
+        "document_embeddings = embeddings.embed_documents(documents)\n"
       ],
       "metadata": {
-        "id": "lJg2iRDWKvV_"
+        "id": "7DXZAK7Kvpth"
       },
       "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}\")"
+        "# Print document embeddings\n",
+        "for i, embedding in enumerate(document_embeddings):\n",
+        "    print(f\"Embedding for document {i+1}: {embedding}\")\n"
       ],
       "metadata": {
-        "id": "R3sYQlh3KvTQ"
+        "id": "K8ra75W_vpqy"
       },
       "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)"
+        "# Create an embedding for a single query\n",
+        "query = 'This is a single query.'\n",
+        "query_embedding = embeddings.embed_query(query)\n"
       ],
       "metadata": {
-        "id": "n0un5Vc0KvQd"
+        "id": "V4Q5kQo9vpna"
       },
       "execution_count": null,
       "outputs": []
     },
     {
       "cell_type": "code",
       "source": [
-        "# Print the generated query embedding\n",
-        "print(f\"Embedding for query: {query_embedding}\")"
+        "# Print query embedding\n",
+        "print(f\"Embedding for query: {query_embedding}\")\n"
       ],
       "metadata": {
-        "id": "PANph6pmKvLD"
+        "id": "O0oQDzGKvpkz"
       },
       "execution_count": null,
       "outputs": []