nbtest improvements

notebooks/document-chunking/.nbtest.yml

@@ -0,0 +1,8 @@
+masks:
+- "'name': '[^']+'"
+- "'cluster_name': '[^']+'"
+- "'cluster_uuid': '[^']+'"
+- "'build_flavor': '[^']+'"
+- '[0-9]+\.[0-9]+\.[0-9]+'
+- "'build_hash': '[^']+'"
+- "'build_date': '[^']+'"

notebooks/document-chunking/Makefile

@@ -1,7 +1,10 @@
 NBTEST = ../../bin/nbtest
+NOTEBOOKS = \
+        with-index-pipelines.ipynb
 
-.PHONY: all
+.PHONY: all $(NOTEBOOKS)
 
-all:
-	$(NBTEST) \
-		with-index-pipelines.ipynb
+all: $(NOTEBOOKS)
+
+$(NOTEBOOKS):
+	$(NBTEST) $@

notebooks/document-chunking/_nbtest.teardown.with-index-pipelines.ipynb

@@ -0,0 +1,74 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1422b7bb-bc8c-42bb-b070-53fce3cf6144",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from elasticsearch import Elasticsearch\n",
+    "from getpass import getpass\n",
+    "\n",
+    "# https://www.elastic.co/search-labs/tutorials/install-elasticsearch/elastic-cloud#finding-your-cloud-id\n",
+    "ELASTIC_CLOUD_ID = getpass(\"Elastic Cloud ID: \")\n",
+    "\n",
+    "# https://www.elastic.co/search-labs/tutorials/install-elasticsearch/elastic-cloud#creating-an-api-key\n",
+    "ELASTIC_API_KEY = getpass(\"Elastic Api Key: \")\n",
+    "\n",
+    "# Create the client instance\n",
+    "client = Elasticsearch(\n",
+    "    # For local development\n",
+    "    # hosts=[\"http://localhost:9200\"] \n",
+    "    cloud_id=ELASTIC_CLOUD_ID,\n",
+    "    api_key=ELASTIC_API_KEY,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4a89367-d23a-4340-bc92-2dcabd18adcd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client.indices.delete(index=\"chunk_passages_example\")\n",
+    "client.ingest.delete_pipeline(id=\"chunk_text_to_passages\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4ac37f1b-6122-49fe-a3b8-e8f2025a0961",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "try:\n",
+    "    client.ml.delete_trained_model(model_id=\"sentence-transformers__all-minilm-l6-v2\", force=True)\n",
+    "except:\n",
+    "    pass"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/document-chunking/with-index-pipelines.ipynb

@@ -523,17 +523,6 @@
     "\n",
     "pretty_response(response)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b269da89",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "client.indices.delete(index=INDEX_NAME)\n",
-    "client.ingest.delete_pipeline(id=\"chunk_text_to_passages\")\n"
-   ]
   }
  ],
  "metadata": {
@@ -555,7 +544,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.3"
+   "version": "3.11.6"
   }
  },
  "nbformat": 4,

notebooks/search/.nbtest.yml

@@ -0,0 +1,11 @@
+masks:
+- "'name': '[^']+'"
+- "'build_flavor': '[^']+'"
+- '[0-9]+\.[0-9]+\.[0-9]+'
+- "'cluster_name': '[^']+'"
+- "'cluster_uuid': '[^']+'"
+- "'build_hash': '[^']+'"
+- "'build_date': '[^']+'"
+- "'_version': [0-9]+"
+- '^ID: .*$'
+- '^Score: [0-9]+\.[0-9][0-9]*$'

notebooks/search/Makefile

@@ -1,13 +1,16 @@
 NBTEST = ../../bin/nbtest
+NOTEBOOKS = \
+	00-quick-start.ipynb \
+	01-keyword-querying-filtering.ipynb \
+	02-hybrid-search.ipynb \
+	03-ELSER.ipynb \
+	04-multilingual.ipynb \
+	05-query-rules.ipynb \
+	06-synonyms-api.ipynb
 
-.PHONY: all
+.PHONY: all $(NOTEBOOKS)
 
-all:
-	$(NBTEST) \
-		00-quick-start.ipynb \
-		01-keyword-querying-filtering.ipynb \
-		02-hybrid-search.ipynb \
-		03-ELSER.ipynb \
-		04-multilingual.ipynb \
-		05-query-rules.ipynb \
-		06-synonyms-api.ipynb
+all: $(NOTEBOOKS)
+
+$(NOTEBOOKS):
+	$(NBTEST) $@

notebooks/search/_nbtest.setup.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e180af3a-3a2c-4186-a577-7051ec6460b1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -qU elasticsearch sentence-transformers"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63d22ea2-ecca-41bb-b08f-de8ad49cda41",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get the Elasticsearch client\n",
+    "from elasticsearch import Elasticsearch\n",
+    "from getpass import getpass\n",
+    "\n",
+    "ELASTIC_CLOUD_ID = getpass(\"Elastic Cloud ID: \")\n",
+    "ELASTIC_API_KEY = getpass(\"Elastic Api Key: \")\n",
+    "\n",
+    "client = Elasticsearch(cloud_id=ELASTIC_CLOUD_ID, api_key=ELASTIC_API_KEY,)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b367acaa-90e6-43d0-b9ae-cf42a0e2c0f1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "from urllib.request import urlopen\n",
+    "from sentence_transformers import SentenceTransformer\n",
+    "\n",
+    "if NBTEST[\"notebook\"] in ['01-keyword-querying-filtering.ipynb', '02-hybrid-search.ipynb', '06-synonyms-api.ipynb']:\n",
+    "    # these tests need book_index to exist ahead of time\n",
+    "    client.indices.delete(index=\"book_index\", ignore_unavailable=True)\n",
+    "    \n",
+    "    mappings = {\n",
+    "        \"properties\": {\n",
+    "            \"title_vector\": {\n",
+    "                \"type\": \"dense_vector\",\n",
+    "                \"dims\": 384,\n",
+    "                \"index\": \"true\",\n",
+    "                \"similarity\": \"cosine\"\n",
+    "            }\n",
+    "        }\n",
+    "    }\n",
+    "    client.indices.create(index='book_index', mappings=mappings)\n",
+    "\n",
+    "    url = \"https://raw.githubusercontent.com/elastic/elasticsearch-labs/main/notebooks/search/data.json\"\n",
+    "    response = urlopen(url)\n",
+    "    books = json.loads(response.read())\n",
+    "\n",
+    "    model = SentenceTransformer('all-MiniLM-L6-v2')\n",
+    "    operations = []\n",
+    "    for book in books:\n",
+    "        operations.append({\"index\": {\"_index\": \"book_index\"}})\n",
+    "        # Transforming the title into an embedding using the model\n",
+    "        book[\"title_vector\"] = model.encode(book[\"title\"]).tolist()\n",
+    "        operations.append(book)\n",
+    "    client.bulk(index=\"book_index\", operations=operations, refresh=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/search/_nbtest.teardown.03-ELSER.ipynb

@@ -0,0 +1,56 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bf006aa-91cf-4c3a-b685-1f8ca5892a33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from elasticsearch import Elasticsearch\n",
+    "from getpass import getpass\n",
+    "\n",
+    "ELASTIC_CLOUD_ID = getpass(\"Elastic Cloud ID: \")\n",
+    "ELASTIC_API_KEY = getpass(\"Elastic Api Key: \")\n",
+    "\n",
+    "client = Elasticsearch(cloud_id=ELASTIC_CLOUD_ID, api_key=ELASTIC_API_KEY,)\n",
+    "\n",
+    "# delete the notebook's index\n",
+    "client.indices.delete(index=\"elser-example-movies\", ignore_unavailable=True)\n",
+    "\n",
+    "# delete the pipeline\n",
+    "try:\n",
+    "    client.ingest.delete_pipeline(id=\"elser-ingest-pipeline\")\n",
+    "except:\n",
+    "    pass\n",
+    "\n",
+    "# delete the model\n",
+    "try:\n",
+    "    client.ml.delete_trained_model(model_id=\".elser_model_2\", force=True)\n",
+    "except:\n",
+    "    pass"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/search/_nbtest.teardown.ipynb

@@ -0,0 +1,73 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bcf0f81-aec8-4f49-918c-3163917885ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "indexes = {\n",
+    "    \"00-quick-start.ipynb\": \"book_index\",\n",
+    "    \"01-keyword-querying-filtering.ipynb\": \"book_index\",\n",
+    "    \"02-hybrid-search.ipynb\": \"book_index\",\n",
+    "    # 03-ELSER.ipynb has its own teardown notebook\n",
+    "    \"04-multilingual.ipynb\": \"articles\",\n",
+    "    \"05-query-rules.ipynb\": \"products_index\",\n",
+    "    \"06-synonyms-api.ipynb\": \"book_index\",\n",
+    "}\n",
+    "INDEX_NAME = indexes.get(NBTEST[\"notebook\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fcd17ce3-ece3-4268-b37b-bbf47c2437c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get the Elasticsearch client\n",
+    "from elasticsearch import Elasticsearch\n",
+    "from getpass import getpass\n",
+    "\n",
+    "ELASTIC_CLOUD_ID = getpass(\"Elastic Cloud ID: \")\n",
+    "ELASTIC_API_KEY = getpass(\"Elastic Api Key: \")\n",
+    "\n",
+    "client = Elasticsearch(cloud_id=ELASTIC_CLOUD_ID, api_key=ELASTIC_API_KEY,)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "abf51067-61f8-4cf3-b950-464805ea0e8d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# delete the notebook's index\n",
+    "if INDEX_NAME:\n",
+    "    client.indices.delete(index=INDEX_NAME, ignore_unavailable=True)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}