Integrate VectorStore from Elasticsearch client

docs/docs/examples/vector_stores/Elasticsearch_demo.ipynb

@@ -26,9 +26,7 @@
    "id": "b5331b6b",
    "metadata": {},
    "source": [
-    "## Basic Example\n",
-    "\n",
-    "In this basic example, we take the a Paul Graham essay, split it into chunks, embed it using an open-source embedding model, load it into Elasticsearch, and then query it."
+    "## Basic Example\n"
    ]
   },
   {
@@ -37,6 +35,8 @@
    "id": "f3aaf790",
    "metadata": {},
    "source": [
+    "In this basic example, we take the a Paul Graham essay, split it into chunks, embed it using an open-source embedding model, load it into Elasticsearch, and then query it. For an example using different retrieval strategies see [Elasticsearch Vector Store](https://docs.llamaindex.ai/en/stable/examples/vector_stores/ElasticsearchIndexDemo/).\n",
+    "\n",
     "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
    ]
   },
@@ -47,20 +47,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install llama-index-embeddings-huggingface\n",
-    "%pip install llama-index-vector-stores-elasticsearch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b3df0b97",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# !pip install llama-index elasticsearch --quiet\n",
-    "# !pip install sentence-transformers\n",
-    "# !pip install pydantic==1.10.11"
+    "%pip install -qU llama-index-vector-stores-elasticsearch llama-index-embeddings-huggingface llama-index"
    ]
   },
   {
@@ -73,8 +60,7 @@
     "# import\n",
     "from llama_index.core import VectorStoreIndex, SimpleDirectoryReader\n",
     "from llama_index.vector_stores.elasticsearch import ElasticsearchStore\n",
-    "from llama_index.core import StorageContext\n",
-    "from IPython.display import Markdown, display"
+    "from llama_index.core import StorageContext"
    ]
   },
   {
@@ -105,10 +91,18 @@
    "execution_count": null,
    "id": "06874a37",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2024-05-13 15:10:43 URL:https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt [75042/75042] -> \"data/paul_graham/paul_graham_essay.txt\" [1]\n"
+     ]
+    }
+   ],
    "source": [
     "!mkdir -p 'data/paul_graham/'\n",
-    "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'"
+    "!wget -nv 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'"
    ]
   },
   {
@@ -132,38 +126,41 @@
    "execution_count": null,
    "id": "667f3cb3-ce18-48d5-b9aa-bfc1a1f0f0f6",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/markdown": [
-       "<b>The author worked on writing and programming outside of school. They wrote short stories and tried writing programs on an IBM 1401 computer. They also built a microcomputer kit and started programming on it, writing simple games and a word processor.</b>"
-      ],
-      "text/plain": [
-       "<IPython.core.display.Markdown object>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# load documents\n",
     "documents = SimpleDirectoryReader(\"./data/paul_graham/\").load_data()\n",
     "\n",
+    "# define index\n",
     "vector_store = ElasticsearchStore(\n",
-    "    index_name=\"paul_graham_essay\", es_url=\"http://localhost:9200\"\n",
+    "    es_url=\"http://localhost:9200\",  # see Elasticsearch Vector Store for more authentication options\n",
+    "    index_name=\"paul_graham_essay\",\n",
     ")\n",
     "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
-    "\n",
     "index = VectorStoreIndex.from_documents(\n",
-    "    documents,\n",
-    "    storage_context=storage_context,\n",
-    ")\n",
-    "\n",
+    "    documents, storage_context=storage_context\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4d3658bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The author worked on writing and programming outside of school. They wrote short stories and tried writing programs on an IBM 1401 computer. They also built a microcomputer kit and started programming on it, writing simple games and a word processor.\n"
+     ]
+    }
+   ],
+   "source": [
     "# Query Data\n",
     "query_engine = index.as_query_engine()\n",
     "response = query_engine.query(\"What did the author do growing up?\")\n",
-    "display(Markdown(f\"<b>{response}</b>\"))"
+    "print(response)"
    ]
   }
  ],

llama-index-integrations/vector_stores/llama-index-vector-stores-elasticsearch/llama_index/vector_stores/elasticsearch/__init__.py

@@ -1,3 +1,16 @@
 from llama_index.vector_stores.elasticsearch.base import ElasticsearchStore
 
-__all__ = ["ElasticsearchStore"]
+from elasticsearch.helpers.vectorstore import (
+    AsyncBM25Strategy,
+    AsyncSparseVectorStrategy,
+    AsyncDenseVectorStrategy,
+    AsyncRetrievalStrategy,
+)
+
+__all__ = [
+    "AsyncBM25Strategy",
+    "AsyncDenseVectorStrategy",
+    "AsyncRetrievalStrategy",
+    "AsyncSparseVectorStrategy",
+    "ElasticsearchStore",
+]