[Security Assistant] Migrate semantic_text to use highlighter instead…

… of inner_hits (elastic#204962)

## Summary

Switch to use elastic/elasticsearch#118064 when
retrieving Knowledge base Index entry docs

Followed testing instructions from
elastic#198020

Results:
<img width="1498" alt="Zrzut ekranu 2024-12-19 o 16 32 28"
src="https://github.com/user-attachments/assets/a16bf729-ac30-4ea7-9b11-6e9ecca842dc"
/>

<img width="1495" alt="Zrzut ekranu 2024-12-19 o 16 32 38"
src="https://github.com/user-attachments/assets/016c08c3-9865-4461-86a5-638e9559b202"
/>

<img width="1502" alt="Zrzut ekranu 2024-12-19 o 16 32 43"
src="https://github.com/user-attachments/assets/37a14a2d-191d-420c-940d-1de649e082fd"
/>

<img width="1491" alt="Zrzut ekranu 2024-12-19 o 16 32 47"
src="https://github.com/user-attachments/assets/e2be1e95-6fc8-4149-b1ff-2e8b8a9a0a8d"
/>

<img width="1494" alt="Zrzut ekranu 2024-12-19 o 16 32 50"
src="https://github.com/user-attachments/assets/38b17f44-e349-46ab-8069-80d1a3fd42ae"
/>

(cherry picked from commit 5539000)

x-pack/solutions/security/plugins/elastic_assistant/server/ai_assistant_data_clients/knowledge_base/helpers.test.tsx

@@ -159,7 +159,6 @@ describe('getStructuredToolForIndexEntry', () => {
       indexEntry: mockIndexEntry,
       esClient: mockEsClient,
       logger: mockLogger,
-      elserId: 'elser123',
     });
 
     expect(tool).toBeInstanceOf(DynamicStructuredTool);
@@ -181,15 +180,8 @@ describe('getStructuredToolForIndexEntry', () => {
               field1: 'value1',
               field2: 2,
             },
-            inner_hits: {
-              'test.test': {
-                hits: {
-                  hits: [
-                    { _source: { text: 'Inner text 1' } },
-                    { _source: { text: 'Inner text 2' } },
-                  ],
-                },
-              },
+            highlight: {
+              test: ['Inner text 1', 'Inner text 2'],
             },
           },
         ],
@@ -202,7 +194,6 @@ describe('getStructuredToolForIndexEntry', () => {
       indexEntry: mockIndexEntry,
       esClient: mockEsClient,
       logger: mockLogger,
-      elserId: 'elser123',
     });
 
     const input = { query: 'testQuery', field1: 'value1', field2: 2 };
@@ -220,7 +211,6 @@ describe('getStructuredToolForIndexEntry', () => {
       indexEntry: mockIndexEntry,
       esClient: mockEsClient,
       logger: mockLogger,
-      elserId: 'elser123',
     });
 
     const input = { query: 'testQuery', field1: 'value1', field2: 2 };

x-pack/solutions/security/plugins/elastic_assistant/server/ai_assistant_data_clients/knowledge_base/helpers.ts

@@ -6,7 +6,6 @@
  */
 
 import { z } from '@kbn/zod';
-import { get } from 'lodash';
 import { DynamicStructuredTool } from '@langchain/core/tools';
 import { errors } from '@elastic/elasticsearch';
 import { QueryDslQueryContainer, SearchRequest } from '@elastic/elasticsearch/lib/api/types';
@@ -140,12 +139,10 @@ export const getStructuredToolForIndexEntry = ({
   indexEntry,
   esClient,
   logger,
-  elserId,
 }: {
   indexEntry: IndexEntry;
   esClient: ElasticsearchClient;
   logger: Logger;
-  elserId: string;
 }): DynamicStructuredTool => {
   const inputSchema = indexEntry.inputSchema?.reduce((prev, input) => {
     const fieldType =
@@ -182,28 +179,27 @@ export const getStructuredToolForIndexEntry = ({
       const params: SearchRequest = {
         index: indexEntry.index,
         size: 10,
-        retriever: {
-          standard: {
-            query: {
-              nested: {
-                path: `${indexEntry.field}.inference.chunks`,
-                query: {
-                  sparse_vector: {
-                    inference_id: elserId,
-                    field: `${indexEntry.field}.inference.chunks.embeddings`,
-                    query: input.query,
-                  },
-                },
-                inner_hits: {
-                  size: 2,
-                  name: `${indexEntry.name}.${indexEntry.field}`,
-                  _source: [`${indexEntry.field}.inference.chunks.text`],
+        query: {
+          bool: {
+            must: [
+              {
+                semantic: {
+                  field: indexEntry.field,
+                  query: input.query,
                 },
               },
-            },
+            ],
             filter,
           },
         },
+        highlight: {
+          fields: {
+            [indexEntry.field]: {
+              type: 'semantic',
+              number_of_fragments: 2,
+            },
+          },
+        },
       };
 
       try {
@@ -217,18 +213,8 @@ export const getStructuredToolForIndexEntry = ({
             }, {});
           }
 
-          // We want to send relevant inner hits (chunks) to the LLM as a context
-          const innerHitPath = `${indexEntry.name}.${indexEntry.field}`;
-          if (hit.inner_hits?.[innerHitPath]) {
-            return {
-              text: hit.inner_hits[innerHitPath].hits.hits
-                .map((innerHit) => innerHit._source.text)
-                .join('\n --- \n'),
-            };
-          }
-
           return {
-            text: get(hit._source, `${indexEntry.field}.inference.chunks[0].text`),
+            text: hit.highlight?.[indexEntry.field].join('\n --- \n'),
           };
         });
 

x-pack/solutions/security/plugins/elastic_assistant/server/ai_assistant_data_clients/knowledge_base/index.ts

@@ -652,7 +652,6 @@ export class AIAssistantKnowledgeBaseDataClient extends AIAssistantDataClient {
     }
 
     try {
-      const elserId = ASSISTANT_ELSER_INFERENCE_ID;
       const userFilter = getKBUserFilter(user);
       const results = await this.findDocuments<EsIndexEntry>({
         // Note: This is a magic number to set some upward bound as to not blow the context with too
@@ -682,7 +681,6 @@ export class AIAssistantKnowledgeBaseDataClient extends AIAssistantDataClient {
                 indexEntry,
                 esClient,
                 logger: this.options.logger,
-                elserId,
               });
             })
         );