nexusAI/docs/services/memory-service.md

Memory Service

Package: @nexusai/memory-service
Location: packages/memory-service
Deployed on: Mini PC 1 (192.168.0.81)
Port: 3002

Purpose

Responsible for all reading and writing of long-term memory. Acts as the sole interface to both SQLite and Qdrant — no other service accesses these stores directly. On episode creation, automatically triggers entity and relationship extraction and embeds results into Qdrant.

Dependencies

• express — HTTP API
• better-sqlite3 — SQLite driver
• @qdrant/js-client-rest — Qdrant vector store client
• dotenv — environment variable loading
• @nexusai/shared — shared utilities and constants

Environment Variables

Variable	Required	Default	Description
PORT	No	3002	Port to listen on
SQLITE_PATH	Yes	—	Path to SQLite database file
QDRANT_URL	No	http://localhost:6333	Qdrant instance URL
EMBEDDING_SERVICE_URL	No	http://localhost:3003	Embedding service URL
EXTRACTION_URL	No	http://localhost:11434	Ollama URL for entity extraction
EXTRACTION_MODEL	No	qwen2.5:3b	Ollama model used for entity extraction

Internal Structure

src/
├── db/
│   ├── index.js       # SQLite connection + initialization + migrations
│   ├── schema.js      # Table definitions, indexes, FTS5, triggers
│   ├── projects.js    # Project CRUD functions
│   └── summaries.js   # Summary CRUD functions
├── episodic/
│   └── index.js       # Session + episode CRUD, FTS search, embedding write path
├── semantic/
│   └── index.js       # Qdrant collection management, upsert, search, delete
├── entities/
│   ├── index.js       # Entity + relationship CRUD (upsert, mention tracking)
│   └── extraction.js  # Automatic entity + relationship extraction via qwen2.5:3b
├── graph/
│   └── index.js       # Knowledge graph traversal (neighborhood queries, recursive CTE)
└── index.js           # Express app + all route definitions

SQLite Schema

Eight core tables:

• sessions — top-level conversation containers. Fields: external_id, name, project_id, metadata
• episodes — individual exchanges (user message + AI response) tied to a session
• entities — named things the system learns about (people, places, concepts, etc.). Fields include mention_count, confidence, source, last_seen_at
• relationships — directional labeled links between entities (from_id, to_id, label). Fields include mention_count, notes
• entity_episodes — join table linking entities to the episodes where they were extracted. Used for provenance and orphan cleanup
• summaries — condensed episode groups for efficient context retrieval
• projects — named groupings of sessions with name, description, colour, icon, isolated, notes, system_prompt

Migrations

Schema changes that cannot use CREATE TABLE IF NOT EXISTS are applied as idempotent migrations in db/index.js at startup:

try { db.exec(`ALTER TABLE sessions ADD COLUMN name TEXT`); } catch {}
try { db.exec(`ALTER TABLE sessions ADD COLUMN project_id INTEGER REFERENCES projects(id)`); } catch {}
try { db.exec(`CREATE INDEX IF NOT EXISTS idx_sessions_project ON sessions(project_id)`); } catch {}
try { db.exec(`ALTER TABLE projects ADD COLUMN isolated INTEGER NOT NULL DEFAULT 0`); } catch {}
try { db.exec(`ALTER TABLE projects ADD COLUMN notes TEXT`); } catch {}
try { db.exec(`ALTER TABLE projects ADD COLUMN system_prompt TEXT`); } catch {}
// Knowledge graph columns:
try { db.exec(`ALTER TABLE entities ADD COLUMN mention_count INTEGER NOT NULL DEFAULT 1`) } catch {}
try { db.exec(`ALTER TABLE entities ADD COLUMN confidence REAL NOT NULL DEFAULT 1.0`) } catch {}
try { db.exec(`ALTER TABLE entities ADD COLUMN source TEXT NOT NULL DEFAULT 'extraction'`) } catch {}
try { db.exec(`ALTER TABLE entities ADD COLUMN last_seen_at INTEGER`) } catch {}
try { db.exec(`ALTER TABLE relationships ADD COLUMN mention_count INTEGER NOT NULL DEFAULT 1`) } catch {}
try { db.exec(`ALTER TABLE relationships ADD COLUMN notes TEXT`) } catch {}

entity_episodes is defined in schema.js itself (not a migration) since it is a new table.

New migrations are always appended — never modify the schema file for existing tables since ALTER TABLE cannot use IF NOT EXISTS.

FTS5 Full-Text Search

An episodes_fts virtual table enables keyword search across all episodes. Three triggers (episodes_fts_insert, episodes_fts_update, episodes_fts_delete) keep the FTS index automatically in sync with the episodes table.

SQLite Configuration

• journal_mode = WAL — non-blocking reads during writes
• foreign_keys = ON — enforces referential integrity and cascade deletes
• PRAGMAs set via db.pragma(), not db.exec()

Dynamic Updates

Both updateSession and updateProject build their SET clause dynamically from only the fields passed — prevents partial updates from overwriting fields that weren't touched.

updateProject allowlist:

const allowed = ['name', 'description', 'colour', 'icon', 'isolated', 'notes', 'system_prompt'];

Qdrant / Semantic Layer

Three Qdrant collections are initialized on service startup via semantic.initCollections():

Collection	Purpose
episodes	Embeddings for individual conversation exchanges
entities	Embeddings for named entities
summaries	Embeddings for condensed episode summaries

All collections use 768-dimension vectors with Cosine similarity, matching nomic-embed-text via Ollama. Vector size and distance metric are defined in @nexusai/shared — not hardcoded here.

initCollections() iterates Object.values(COLLECTIONS) and creates any collection that doesn't already exist at startup — all three collections are guaranteed to exist before any requests are handled.

Each collection exposes upsert, search (with optional Qdrant filter), and delete operations. The wait: true flag is used on all writes.

Embedding Write Path

When a new episode is created:

1. Episode saved to SQLite synchronously — response returned immediately
2. User message + AI response combined: User: ...\nAssistant: ...
3. Text sent to embedding service (POST /embed)
4. Vector upserted into episodes Qdrant collection with payload { sessionId, createdAt }

This step is fire-and-forget — if embedding fails, the episode is still saved and searchable via FTS. The error is logged but not surfaced.

The Qdrant payload stores sessionId (the internal integer ID). See memory-isolation.md for how project-level filtering works.

Entity Layer

Entities and relationships use upsert semantics with composite unique constraints to prevent duplicates:

• UNIQUE(name, type) on entities — conflict increments mention_count and updates last_seen_at
• UNIQUE(from_id, to_id, label) on relationships — conflict increments mention_count and preserves existing notes
• ON DELETE CASCADE on relationship foreign keys

After each episode is saved, extraction.js automatically extracts named entities and relationships from the conversation using qwen2.5:3b on Ollama — fire-and-forget. Each saved entity is also linked to the episode via the entity_episodes join table.

For full details on the extraction pipeline and JSON format, see entity-extraction.md.
For the knowledge graph traversal layer, see knowledge-graph.md.

Knowledge Graph Layer

src/graph/index.js provides SQLite-based graph traversal over the entities and relationships tables. Two functions are exposed via HTTP:

• getNeighborhood(entityId, depth) — recursive CTE traversal, bidirectional, returns { nodes, edges }
• getEntityNeighbors(entityIds[]) — bulk 1-hop traversal for orchestration context assembly

For design rationale, traversal queries, and integration with orchestration, see knowledge-graph.md.

Summaries Layer

Session summaries are generated by orchestration-service/src/services/summarization.js after each episode write and stored here via POST /summaries. The memory service is responsible only for CRUD — generation logic lives in orchestration.

For full details on trigger conditions, prompt format, cumulative updates, and ChatML token stripping, see summarization.md.

Delete Behaviour (SQLite + Qdrant consistency)

SQLite cascades handle relational cleanup, but Qdrant is a separate store and must be cleaned explicitly. Each delete path that removes embedded rows also removes the corresponding vectors:

Delete	SQLite effect	Qdrant cleanup
DELETE /episodes/:id	Row removed	semantic.deleteEpisode(id) — vector by point ID
DELETE /sessions/by-external/:id	Session + episodes cascade-deleted	semantic.deleteEpisodesBySession(id) — payload-filter delete on sessionId
DELETE /entities/:id	Row removed, relationships cascade	semantic.deleteEntity(id) — vector by point ID

All three Qdrant deletes are fire-and-forget with error logging, matching the fire-and-forget write path — a Qdrant failure logs but does not fail the delete.

The session path uses a payload-filter delete (matching on the sessionId field in the vector payload) rather than enumerating episode point IDs. This matters because the SQLite cascade has already removed the episode rows by the time cleanup runs, so there are no IDs left to enumerate — the filter deletes by payload regardless. It also cleans up any pre-existing orphans for that session as a side effect.

Not cleaned on session delete: entity vectors. Entities are shared across sessions and projects (UNIQUE(name, type) is global), so deleting one session must not remove entities that other sessions still reference. Entity vector lifecycle is tied to explicit entity deletion and the (planned) memory consolidation / orphan-cleanup pass.

Historical orphans: vectors orphaned by session deletes before this cleanup existed are not removed retroactively. A one-time sweep (scroll the episodes collection, delete points whose sessionId no longer exists in SQLite) clears them.

Project Delete Behaviour

Deleting a project runs as a transaction — it first nulls out project_id on all assigned sessions, then deletes the project. This avoids a foreign key constraint failure since sessions.project_id has no ON DELETE rule:

const doDelete = db.transaction(() => {
  db.prepare(`UPDATE sessions SET project_id = NULL WHERE project_id = ?`).run(id);
  db.prepare(`DELETE FROM projects WHERE id = ?`).run(id);
});

For all HTTP endpoints, see api-routes.md.