one more langchain notebook added to nbtest

elastic · Jan 25, 2024 · 6dad915 · 6dad915
1 parent 9190da9
commit 6dad915
Show file tree

Hide file tree

Showing 4 changed files with 232 additions and 36 deletions.
diff --git a/notebooks/langchain/Makefile b/notebooks/langchain/Makefile
@@ -1,6 +1,7 @@
 NBTEST = ../../bin/nbtest
 NOTEBOOKS = \
-	langchain-using-own-model.ipynb
+	langchain-using-own-model.ipynb \
+	langchain-vector-store-using-elser.ipynb
 
 .PHONY: all $(NOTEBOOKS)
 

diff --git a/notebooks/langchain/_nbtest.setup.langchain-vector-store-using-elser.ipynb b/notebooks/langchain/_nbtest.setup.langchain-vector-store-using-elser.ipynb
@@ -0,0 +1,124 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "62ab8486-e088-424b-80d4-1e9a6a181051",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -qU elasticsearch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "088845c2-ec80-4a66-995d-6f8092fe5058",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# get the Elasticsearch client\n",
+    "from elasticsearch import Elasticsearch, exceptions\n",
+    "from getpass import getpass\n",
+    "import time\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": "26d7a2ad-4ace-4122-8d07-7b300014dca8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# delete model if already downloaded and deployed\n",
+    "try:\n",
+    "  client.ml.delete_trained_model(model_id=\".elser_model_2\", force=True)\n",
+    "  print(\"Model deleted successfully, We will proceed with creating one\")\n",
+    "except exceptions.NotFoundError:\n",
+    "  print(\"Model doesn't exist, but We will proceed with creating one\")\n",
+    "\n",
+    "# Creates the ELSER model configuration. Automatically downloads the model if it doesn't exist. \n",
+    "client.ml.put_trained_model(\n",
+    "    model_id=\".elser_model_2\",\n",
+    "    input={\n",
+    "      \"field_names\": [\"text_field\"]\n",
+    "    }\n",
+    "  )\n",
+    "\n",
+    "while True:\n",
+    "    status = client.ml.get_trained_models(\n",
+    "        model_id=\".elser_model_2\",\n",
+    "        include=\"definition_status\"\n",
+    "    )\n",
+    "    \n",
+    "    if (status[\"trained_model_configs\"][0][\"fully_defined\"]):\n",
+    "        break\n",
+    "    time.sleep(5)\n",
+    "\n",
+    "# Start trained model deployment if not already deployed\n",
+    "client.ml.start_trained_model_deployment(\n",
+    "  model_id=\".elser_model_2\",\n",
+    "  number_of_allocations=1,\n",
+    "  wait_for=\"starting\"\n",
+    ")\n",
+    "\n",
+    "while True:\n",
+    "  status = client.ml.get_trained_models_stats(\n",
+    "    model_id=\".elser_model_2\",\n",
+    "  )\n",
+    "  if (status[\"trained_model_stats\"][0][\"deployment_stats\"][\"state\"] == \"started\"):\n",
+    "    print(\"ELSER Model has been successfully deployed.\")\n",
+    "    break\n",
+    "  else:\n",
+    "    print(\"ELSER Model is currently being deployed.\")\n",
+    "  time.sleep(5)\n",
+    "\n",
+    "time.sleep(5)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75fb9815-56d2-45c7-8467-e92b2f8aee7c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client.indices.delete(index=\"workplace_index\", ignore_unavailable=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a8141b0-5ae5-44d4-aa84-32368a55d276",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}
diff --git a/notebooks/langchain/_nbtest.teardown.langchain-vector-store-using-elser.ipynb b/notebooks/langchain/_nbtest.teardown.langchain-vector-store-using-elser.ipynb
@@ -0,0 +1,64 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8bed2c83-87a7-40ca-bc5e-b9088c7e38a0",
+   "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=\"workplace_index\", ignore_unavailable=True)\n",
+    "\n",
+    "# delete the pipeline\n",
+    "try:\n",
+    "    client.ingest.delete_pipeline(id=\".elser_model_2_sparse_embedding\")\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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6dbce06c-fea9-457b-87c4-0a0e5cfcc1b7",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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
+}