Skip to content

[pull] main from elastic:main #59

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 1 commit into from
Apr 16, 2025
Merged

[pull] main from elastic:main #59

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
93 changes: 5 additions & 88 deletions notebooks/search/12-semantic-reranking-elastic-rerank.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,7 @@
"\n",
"In this notebook you'll learn how to implement semantic reranking in Elasticsearch using the built-in [Elastic Rerank model](https://www.elastic.co/guide/en/machine-learning/master/ml-nlp-rerank.html). You'll also learn about the `retriever` abstraction, a simpler syntax for crafting queries and combining different search operations.\n",
"\n",
"You will:\n",
"\n",
"- Create an inference endpoint to manage your `rerank` task. This will download and deploy the Elastic Rerank model.\n",
"- Query your data using the `text_similarity_rerank` retriever, leveraging the Elastic Rerank model."
"You will query your data using the `text_similarity_rerank` retriever, and the Elastic Rerank model to boost the relevance of your search results."
]
},
{
Expand Down Expand Up @@ -234,87 +231,6 @@
"time.sleep(3)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "DRIABkGAgV_Q"
},
"source": [
"## Create inference endpoint\n",
"\n",
"Next we'll create an inference endpoint for the `rerank` task to deploy and manage our model and, if necessary, spin up the necessary ML resources behind the scenes."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "DiKsd3YygV_Q",
"outputId": "c3c46c6b-b502-4167-c98c-d2e2e0a4613c"
},
"outputs": [],
"source": [
"try:\n",
" client.inference.delete(inference_id=\"my-elastic-reranker\")\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=\"rerank\",\n",
" inference_id=\"my-elastic-reranker\",\n",
" inference_config={\n",
" \"service\": \"elasticsearch\",\n",
" \"service_settings\": {\n",
" \"model_id\": \".rerank-v1\",\n",
" \"num_threads\": 1,\n",
" \"adaptive_allocations\": {\n",
" \"enabled\": True,\n",
" \"min_number_of_allocations\": 1,\n",
" \"max_number_of_allocations\": 4,\n",
" },\n",
" },\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",
"metadata": {},
"source": [
"Run the following command to confirm your inference endpoint is deployed."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"client.inference.get().body"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"⚠️ When you deploy your model, you might need to sync your ML saved objects in the Kibana (or Serverless) UI.\n",
"Go to **Trained Models** and select **Synchronize saved objects**."
]
},
{
"cell_type": "markdown",
"metadata": {
Expand Down Expand Up @@ -465,7 +381,7 @@
"source": [
"## Semantic reranker\n",
"\n",
"In the following `retriever` syntax, we wrap our standard `match` query retriever in a `text_similarity_reranker`. This allows us to leverage the NLP model we deployed to Elasticsearch to rerank the results based on the phrase \"flesh-eating bad guy\"."
"In the following `retriever` syntax, we wrap our standard `match` query retriever in a `text_similarity_reranker`. This allows us to leverage the [Elastic rerank model](https://www.elastic.co/guide/en/machine-learning/current/ml-nlp-rerank.html) to rerank the results based on the phrase \"flesh-eating bad guy\"."
]
},
{
Expand Down Expand Up @@ -523,7 +439,6 @@
" }\n",
" },\n",
" \"field\": \"plot\",\n",
" \"inference_id\": \"my-elastic-reranker\",\n",
" \"inference_text\": \"flesh-eating bad guy\",\n",
" }\n",
" },\n",
Expand All @@ -543,7 +458,9 @@
"source": [
"Success! \"The Silence of the Lambs\" is our top result. Semantic reranking helped us find the most relevant result by parsing a natural language query, overcoming the limitations of lexical search that relies on keyword matching.\n",
"\n",
"Semantic reranking enables semantic search in a few steps, without the need for generating and storing embeddings. This a great tool for testing and building hybrid search systems in Elasticsearch."
"Semantic reranking enables semantic search in a few steps, without the need for generating and storing embeddings. This a great tool for testing and building hybrid search systems in Elasticsearch.\n",
"\n",
"*Note* Starting with Elasticsearch version `8.18`, The `inference_id` field is optional. If not specified, it defaults to `.rerank-v1-elasticsearch`. If you are using an earlier version or prefer to manage your own endpoint, you can set up a custom `rerank` inference endpoint using the [create inference API](https://www.elastic.co/docs/api/doc/elasticsearch/operation/operation-inference-put)."
]
},
{
Expand Down
Loading