From cef1803af6d9420552db8d0b8d2bd40033e25c68 Mon Sep 17 00:00:00 2001
From: Storme-bit <tk.stomre@gmail.com>
Date: Fri, 17 Apr 2026 06:01:21 -0700
Subject: [PATCH] adding in entity extraction layer with semantic search
 enabled

---
 .../memory-service/src/entities/extraction.js | 40 ++++++++++++++-----
 1 file changed, 29 insertions(+), 11 deletions(-)

diff --git a/packages/memory-service/src/entities/extraction.js b/packages/memory-service/src/entities/extraction.js
index 0bdf851..52ca042 100644
--- a/packages/memory-service/src/entities/extraction.js
+++ b/packages/memory-service/src/entities/extraction.js
@@ -1,8 +1,10 @@
-const { getEnv } = require('@nexusai/shared');
+const {semantic} = require('../semantic')
+const { getEn, SERVICES, formatEpisodeText } = require('@nexusai/shared');
 const { upsertEntity } = require('./index');
 
 const EXTRACTION_URL = getEnv('EXTRACTION_URL', 'http://localhost:11434');
 const EXTRACTION_MODEL = getEnv('EXTRACTION_MODEL', 'qwen2.5:3b');
+const EMBEDDING_SERVICE_URL = getEnv('EMBEDDING_SERVICE_URL', SERVICES.EMBEDDING_URL);
 
 const ENTITY_TYPES = ['person', 'place', 'project', 'technology', 'concept', 'organization'];
 
@@ -38,12 +40,22 @@ function buildExtractionPrompt(userMessage, aiResponse) {
     ].join('\n');
 }
 
-async function extractAndStoreEntities(userMessage, aiResponse) {
-    console.log('[entities] Input:', { 
-        userMessage: userMessage?.slice(0, 100), 
-        aiResponse: aiResponse?.slice(0, 100) 
+async function embedEntity(entity) {
+    // Combine name, type and notes into a single descriptive string for embedding
+    const text = `${entity.name} (${entity.type}): ${entity.notes ?? entity.name}`;
+
+    const res = await fetch(`${EMBEDDING_SERVICE_URL}/embed`, {
+        method: 'POST',
+        headers: { 'Content-Type': 'application/json' },
+        body: JSON.stringify({ text }),
     });
 
+    if (!res.ok) throw new Error(`Embedding service error: ${res.status}`);
+    const data = await res.json();
+    return data.embedding;
+}
+
+async function extractAndStoreEntities(userMessage, aiResponse) {
     console.log('[entities] Extraction triggered')
     try {
         const res = await fetch(`${EXTRACTION_URL}/api/generate`, {
@@ -60,26 +72,32 @@ async function extractAndStoreEntities(userMessage, aiResponse) {
             }),
         });
 
-        console.log('[entities] Ollama responded:', res.status);
-
         if (!res.ok) throw new Error(`Ollama responded ${res.status}`);
 
         const data = await res.json();
-        console.log('[entities] Raw response:', data.response?.slice(0, 200));
         const raw = data.response?.trim() ?? '';
 
         // Strip markdown fences defensively — small models sometimes add them anyway
         const clean = raw.replace(/^```(?:json)?\n?/, '').replace(/\n?```$/, '').trim();
         const entities = JSON.parse(clean);
-        console.log('[entities] Parsed entities:', entities);
 
         if (!Array.isArray(entities)) throw new Error('Response was not a JSON array');
 
         let saved = 0;
         for (const { name, type, notes } of entities) {
-            // Skip anything malformed or with an unrecognised type
             if (!name || !type || !ENTITY_TYPES.includes(type)) continue;
-            upsertEntity(name, type, notes ?? null);
+
+            const entity = upsertEntity(name, type, notes ?? null);
+
+            // Embed and upsert to Qdrant fire-and-forget
+            embedEntity(entity)
+                .then(vector => semantic.upsertEntity(entity.id, vector, {
+                    name: entity.name,
+                    type: entity.type,
+                    notes: entity.notes,
+                }))
+                .catch(err => console.warn(`[entities] Failed to embed entity "${entity.name}":`, err.message));
+
             saved++;
         }