Skip to content

Updates the semantic text tutorial to use EIS #490

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Sep 25, 2025
Merged

Updates the semantic text tutorial to use EIS #490

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
b4525d9
Updates the semantic text tutorial for using EIS.
szabosteve Sep 24, 2025
7cd8921
Changes version number.
szabosteve Sep 24, 2025
f16a00a
Changes install command.
szabosteve Sep 25, 2025
9a92e58
Changes inference ID.
szabosteve Sep 25, 2025
cc598cd
Adds notebook to allowlist.
szabosteve Sep 25, 2025
dcfc6ae
Removes item from notebook exclude list.
szabosteve Sep 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion bin/find-notebooks-to-test.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ EXEMPT_NOTEBOOKS=(
"notebooks/esql/esql-getting-started.ipynb"
"notebooks/search/07-inference.ipynb"
"notebooks/search/08-learning-to-rank.ipynb"
"notebooks/search/09-semantic-text.ipynb"
"notebooks/search/10-semantic-reranking-retriever-cohere.ipynb"
"notebooks/search/11-semantic-reranking-hugging-face.ipynb"
"notebooks/search/12-semantic-reranking-elastic-rerank.ipynb"
Expand Down Expand Up @@ -57,7 +58,6 @@ EXEMPT_NOTEBOOKS__8_12=(

EXEMPT_NOTEBOOKS__8_14=(
# Add any notebooks that must be skipped on versions 8.14 or older here
"notebooks/search/09-semantic-text.ipynb",
# This notebook has the text_expansion deprecation notice for 8.15.
# Only running on 8.15 so includes the deprecation notice and newer so the local output is the same as CI
"notebooks/langchain/langchain-vector-store-using-elser.ipynb",
Expand Down
112 changes: 5 additions & 107 deletions notebooks/search/09-semantic-text.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@
"- An Elastic deployment:\n",
" - We'll be using [Elastic Cloud](https://www.elastic.co/guide/en/cloud/current/ec-getting-started.html) for this example (available with a [free trial](https://cloud.elastic.co/registration?onboarding_token=vectorsearch&utm_source=github&utm_content=elasticsearch-labs-notebook))\n",
"\n",
"- Elasticsearch 8.15 or above, or [Elasticsearch serverless](https://www.elastic.co/elasticsearch/serverless)"
"- Elasticsearch 9.1 or above, or [Elasticsearch serverless](https://www.elastic.co/elasticsearch/serverless)"
]
},
{
Expand Down Expand Up @@ -84,7 +84,7 @@
},
"outputs": [],
"source": [
"!pip install \"elasticsearch<9\""
"!pip install elasticsearch"
]
},
{
Expand Down Expand Up @@ -241,109 +241,6 @@
"Read [this page](https://www.elastic.co/guide/en/elasticsearch/client/python-api/current/connecting.html#connect-self-managed-new) to learn how to connect using API keys."
]
},
{
"cell_type": "markdown",
"id": "22fa643780acd44a",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"source": [
"## Create the Inference Endpoint\n",
"\n",
"Let's create the inference endpoint by using the [Create inference API](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html).\n",
"\n",
"For this example we'll use the [ELSER service](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-elser.html), but the inference API also supports [many other inference services](https://www.elastic.co/guide/en/elasticsearch/reference/current/put-inference-api.html#put-inference-api-desc)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8ee2188ea71324f5",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"source": [
"try:\n",
" client.inference.delete(inference_id=\"my-elser-endpoint\")\n",
"except exceptions.NotFoundError:\n",
" # Inference endpoint does not exist\n",
" pass\n",
"\n",
"try:\n",
" client.options(\n",
" request_timeout=60, max_retries=3, retry_on_timeout=True\n",
" ).inference.put(\n",
" task_type=\"sparse_embedding\",\n",
" inference_id=\"my-elser-endpoint\",\n",
" body={\n",
" \"service\": \"elser\",\n",
" \"service_settings\": {\"num_allocations\": 1, \"num_threads\": 1},\n",
" },\n",
" )\n",
" print(\"Inference endpoint created successfully\")\n",
"except exceptions.BadRequestError as e:\n",
" if e.error == \"resource_already_exists_exception\":\n",
" print(\"Inference endpoint created successfully\")\n",
" else:\n",
" raise e"
]
},
{
"cell_type": "markdown",
"id": "e94fd66761fd8087",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"source": [
"Once the endpoint is created, we must wait until the backing ELSER service is deployed.\n",
"This can take a few minutes to complete."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "adb33329ce20b2f1",
"metadata": {
"collapsed": false,
"jupyter": {
"outputs_hidden": false
}
},
"outputs": [],
"source": [
"inference_endpoint_info = client.inference.get(inference_id=\"my-elser-endpoint\")\n",
"model_id = inference_endpoint_info[\"endpoints\"][0][\"service_settings\"][\"model_id\"]\n",
"\n",
"while True:\n",
" status = client.ml.get_trained_models_stats(\n",
" model_id=model_id,\n",
" )\n",
"\n",
" deployment_stats = status[\"trained_model_stats\"][0].get(\"deployment_stats\")\n",
" if deployment_stats is None:\n",
" print(\"ELSER Model is currently being deployed.\")\n",
" time.sleep(5)\n",
" continue\n",
"\n",
" nodes = deployment_stats.get(\"nodes\")\n",
" if nodes is not None and len(nodes) > 0:\n",
" print(\"ELSER Model has been successfully deployed.\")\n",
" break\n",
" else:\n",
" print(\"ELSER Model is currently being deployed.\")\n",
" time.sleep(5)"
]
},
{
"cell_type": "markdown",
"id": "818f7a72a83b5776",
Expand All @@ -356,7 +253,8 @@
"source": [
"## Create the Index\n",
"\n",
"Now we need to create an index with a `semantic_text` field. Let's create one that enables us to perform semantic search on movie plots."
"Now we need to create an index with a `semantic_text` field. Let's create one that enables us to perform semantic search on movie plots.\n",
"We use the preconfigured `.elser-2-elastic` inference endpoint which uses the ELSER model via the [Elastic Inference Service](https://www.elastic.co/docs/explore-analyze/elastic-inference/eis)."
]
},
{
Expand All @@ -381,7 +279,7 @@
" \"plot\": {\"type\": \"text\", \"copy_to\": \"plot_semantic\"},\n",
" \"plot_semantic\": {\n",
" \"type\": \"semantic_text\",\n",
" \"inference_id\": \"my-elser-endpoint\",\n",
" \"inference_id\": \".elser-v2-elastic\",\n",
" },\n",
" }\n",
" },\n",
Expand Down