[KB] create @kbn/product-doc-artifact-builder package (elastic#193847)

## Summary

Related elastic#193473

Add initial implementation of the knowledge base artifact builder. This
PR only introduces the builder script, it doesn't do anything about
automation.

---------

Co-authored-by: kibanamachine <[email protected]>
Co-authored-by: Elastic Machine <[email protected]>
(cherry picked from commit 1ab1add)

# Conflicts:
#	.github/CODEOWNERS

package.json

@@ -1463,6 +1463,7 @@
     "@kbn/picomatcher": "link:packages/kbn-picomatcher",
     "@kbn/plugin-generator": "link:packages/kbn-plugin-generator",
     "@kbn/plugin-helpers": "link:packages/kbn-plugin-helpers",
+    "@kbn/product-doc-artifact-builder": "link:x-pack/packages/ai-infra/product-doc-artifact-builder",
     "@kbn/repo-file-maps": "link:packages/kbn-repo-file-maps",
     "@kbn/repo-linter": "link:packages/kbn-repo-linter",
     "@kbn/repo-path": "link:packages/kbn-repo-path",

scripts/build_product_doc_artifacts.js

@@ -0,0 +1,11 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the "Elastic License
+ * 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
+ * Public License v 1"; you may not use this file except in compliance with, at
+ * your election, the "Elastic License 2.0", the "GNU Affero General Public
+ * License v3.0 only", or the "Server Side Public License, v 1".
+ */
+
+require('../src/setup_node_env');
+require('@kbn/product-doc-artifact-builder').runScript();

src/dev/precommit_hook/casing_check_config.js

@@ -116,6 +116,7 @@ export const IGNORE_DIRECTORY_GLOBS = [
   'src/babel-*',
   'packages/*',
   'packages/core/*/*',
+  'x-pack/packages/ai-infra/*',
   'packages/kbn-pm/src/utils/__fixtures__/*',
   'packages/kbn-check-prod-native-modules-cli/integration_tests/__fixtures__/*/node_modules/*',
   'x-pack/dev-tools',

tsconfig.base.json

@@ -1366,6 +1366,8 @@
       "@kbn/presentation-publishing/*": ["packages/presentation/presentation_publishing/*"],
       "@kbn/presentation-util-plugin": ["src/plugins/presentation_util"],
       "@kbn/presentation-util-plugin/*": ["src/plugins/presentation_util/*"],
+      "@kbn/product-doc-artifact-builder": ["x-pack/packages/ai-infra/product-doc-artifact-builder"],
+      "@kbn/product-doc-artifact-builder/*": ["x-pack/packages/ai-infra/product-doc-artifact-builder/*"],
       "@kbn/profiling-data-access-plugin": ["x-pack/plugins/observability_solution/profiling_data_access"],
       "@kbn/profiling-data-access-plugin/*": ["x-pack/plugins/observability_solution/profiling_data_access/*"],
       "@kbn/profiling-plugin": ["x-pack/plugins/observability_solution/profiling"],
@@ -2084,4 +2086,4 @@
       "@kbn/ambient-storybook-types"
     ]
   }
-}
+}

x-pack/packages/ai-infra/product-doc-artifact-builder/README.md

@@ -0,0 +1,3 @@
+# @kbn/product-doc-artifact-builder
+
+Script to build the knowledge base artifacts

x-pack/packages/ai-infra/product-doc-artifact-builder/index.ts

@@ -0,0 +1,8 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+export { runScript } from './src/command';

x-pack/packages/ai-infra/product-doc-artifact-builder/jest.config.js

@@ -0,0 +1,12 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+module.exports = {
+  preset: '@kbn/test/jest_node',
+  rootDir: '../../../..',
+  roots: ['<rootDir>/x-pack/packages/ai-infra/product-doc-artifact-builder'],
+};

x-pack/packages/ai-infra/product-doc-artifact-builder/kibana.jsonc

@@ -0,0 +1,6 @@
+{
+  "type": "shared-common",
+  "id": "@kbn/product-doc-artifact-builder",
+  "owner": "@elastic/appex-ai-infra",
+  "devOnly": true
+}

x-pack/packages/ai-infra/product-doc-artifact-builder/package.json

@@ -0,0 +1,6 @@
+{
+  "name": "@kbn/product-doc-artifact-builder",
+  "private": true,
+  "version": "1.0.0",
+  "license": "Elastic License 2.0"
+}

x-pack/packages/ai-infra/product-doc-artifact-builder/src/artifact/artifact_name.ts

@@ -0,0 +1,16 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+export const getArtifactName = ({
+  productName,
+  productVersion,
+}: {
+  productName: string;
+  productVersion: string;
+}): string => {
+  return `kibana-kb-${productName}-${productVersion}.zip`.toLowerCase();
+};

x-pack/packages/ai-infra/product-doc-artifact-builder/src/artifact/manifest.ts

@@ -0,0 +1,26 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+export interface ArtifactManifest {
+  formatVersion: string;
+  productName: string;
+  productVersion: string;
+}
+
+export const getArtifactManifest = ({
+  productName,
+  stackVersion,
+}: {
+  productName: string;
+  stackVersion: string;
+}): ArtifactManifest => {
+  return {
+    formatVersion: '1.0.0',
+    productName,
+    productVersion: stackVersion,
+  };
+};

x-pack/packages/ai-infra/product-doc-artifact-builder/src/artifact/mappings.ts

@@ -0,0 +1,39 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+import type { MappingTypeMapping } from '@elastic/elasticsearch/lib/api/types';
+
+export const getArtifactMappings = (inferenceEndpoint: string): MappingTypeMapping => {
+  return {
+    dynamic: 'strict',
+    properties: {
+      content_title: { type: 'text' },
+      content_body: {
+        type: 'semantic_text',
+        inference_id: inferenceEndpoint,
+      },
+      product_name: { type: 'keyword' },
+      root_type: { type: 'keyword' },
+      slug: { type: 'keyword' },
+      url: { type: 'keyword' },
+      version: { type: 'version' },
+      ai_subtitle: {
+        type: 'semantic_text',
+        inference_id: inferenceEndpoint,
+      },
+      ai_summary: {
+        type: 'semantic_text',
+        inference_id: inferenceEndpoint,
+      },
+      ai_questions_answered: {
+        type: 'semantic_text',
+        inference_id: inferenceEndpoint,
+      },
+      ai_tags: { type: 'keyword' },
+    },
+  };
+};

x-pack/packages/ai-infra/product-doc-artifact-builder/src/artifact/product_name.ts

@@ -0,0 +1,11 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+/**
+ * The allowed product names, as found in the source's cluster
+ */
+export const sourceProductNames = ['Kibana', 'Elasticsearch', 'Security', 'Observability'];

x-pack/packages/ai-infra/product-doc-artifact-builder/src/build_artifacts.ts

@@ -0,0 +1,161 @@
+/*
+ * Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
+ * or more contributor license agreements. Licensed under the Elastic License
+ * 2.0; you may not use this file except in compliance with the Elastic License
+ * 2.0.
+ */
+
+import Path from 'path';
+import { Client } from '@elastic/elasticsearch';
+import { ToolingLog } from '@kbn/tooling-log';
+import {
+  // checkConnectivity,
+  createTargetIndex,
+  extractDocumentation,
+  indexDocuments,
+  installElser,
+  createChunkFiles,
+  createArtifact,
+  cleanupFolders,
+  deleteIndex,
+} from './tasks';
+import type { TaskConfig } from './types';
+
+const getSourceClient = (config: TaskConfig) => {
+  return new Client({
+    compression: true,
+    nodes: [config.sourceClusterUrl],
+    sniffOnStart: false,
+    auth: {
+      username: config.sourceClusterUsername,
+      password: config.sourceClusterPassword,
+    },
+  });
+};
+
+const getEmbeddingClient = (config: TaskConfig) => {
+  return new Client({
+    compression: true,
+    nodes: [config.embeddingClusterUrl],
+    auth: {
+      username: config.embeddingClusterUsername,
+      password: config.embeddingClusterPassword,
+    },
+    // generating embeddings takes time
+    requestTimeout: 10 * 60 * 1000,
+  });
+};
+
+export const buildArtifacts = async (config: TaskConfig) => {
+  const log = new ToolingLog({
+    level: 'info',
+    writeTo: process.stdout,
+  });
+
+  log.info(
+    `Starting building artifacts for version=[${
+      config.stackVersion
+    }] and products=[${config.productNames.join(',')}]`
+  );
+
+  const sourceClient = getSourceClient(config);
+  const embeddingClient = getEmbeddingClient(config);
+
+  // log.info('Checking connectivity against clusters');
+  // await checkConnectivity({ sourceClient, embeddingClient });
+
+  await cleanupFolders({ folders: [config.buildFolder] });
+
+  log.info('Ensuring ELSER is installed on the embedding cluster');
+  await installElser({ client: embeddingClient });
+
+  for (const productName of config.productNames) {
+    await buildArtifact({
+      productName,
+      stackVersion: config.stackVersion,
+      buildFolder: config.buildFolder,
+      targetFolder: config.targetFolder,
+      sourceClient,
+      embeddingClient,
+      log,
+    });
+  }
+
+  await cleanupFolders({ folders: [config.buildFolder] });
+};
+
+const buildArtifact = async ({
+  productName,
+  stackVersion,
+  buildFolder,
+  targetFolder,
+  embeddingClient,
+  sourceClient,
+  log,
+}: {
+  productName: string;
+  stackVersion: string;
+  buildFolder: string;
+  targetFolder: string;
+  sourceClient: Client;
+  embeddingClient: Client;
+  log: ToolingLog;
+}) => {
+  log.info(`Starting building artifact for product [${productName}] and version [${stackVersion}]`);
+
+  const targetIndex = getTargetIndexName({ productName, stackVersion });
+
+  const documents = await extractDocumentation({
+    client: sourceClient,
+    index: 'search-docs-1',
+    log,
+    productName,
+    stackVersion,
+  });
+
+  await createTargetIndex({
+    client: embeddingClient,
+    indexName: targetIndex,
+  });
+
+  await indexDocuments({
+    client: embeddingClient,
+    index: targetIndex,
+    documents,
+    log,
+  });
+
+  await createChunkFiles({
+    index: targetIndex,
+    client: embeddingClient,
+    productName,
+    destFolder: Path.join(buildFolder, productName),
+    log,
+  });
+
+  await createArtifact({
+    buildFolder: Path.join(buildFolder, productName),
+    targetFolder,
+    productName,
+    stackVersion,
+    log,
+  });
+
+  await deleteIndex({
+    indexName: targetIndex,
+    client: embeddingClient,
+    log,
+  });
+
+  log.info(`Finished building artifact for product [${productName}] and version [${stackVersion}]`);
+};
+
+const getTargetIndexName = ({
+  productName,
+  stackVersion,
+}: {
+  productName: string;
+  stackVersion: string;
+}) => {
+  return `kb-artifact-builder-${productName}-${stackVersion}`.toLowerCase();
+};