Frontmatter
| id | 9710 |
| title | [SQLite VSS Migration] 100% Offline Markdown Tensor Chunking |
| state | Closed |
| labels | enhancementaiarchitecture |
| assignees | tobiu |
| createdAt | Apr 4, 2026, 11:05 PM |
| updatedAt | Apr 5, 2026, 12:27 AM |
| githubUrl | https://github.com/neomjs/neo/issues/9710 |
| author | tobiu |
| commentsCount | 1 |
| parentIssue | 9673 |
| subIssues | [] |
| subIssuesCompleted | 0 |
| subIssuesTotal | 0 |
| blockedBy | [] |
| blocking | [] |
| closedAt | Apr 5, 2026, 12:27 AM |
[SQLite VSS Migration] 100% Offline Markdown Tensor Chunking
Closedenhancementaiarchitecture
tobiu added parent issue #9673 on Apr 4, 2026, 11:05 PM
tobiu assigned to @tobiu on Apr 5, 2026, 12:27 AM

tobiu
Apr 5, 2026, 12:27 AM
SQLite VSS Migration complete. Resolved type-locking requirements, implemented abstraction of TextEmbeddingService (decoupling generative and embedding contexts), and verified robust pre-filtering of attributes leveraging sqlite-vec bounds.
tobiu closed this issue on Apr 5, 2026, 12:27 AM
Description
Phase 2 of the Memory Core overhaul. Evolve beyond containerized ChromaDB to a pure zero-dependency SQLite Vector DB driven by local
qwen3-embedding.Acceptance Criteria
qwen3-embedding.##blocks and JSON keys, rather than AST parsing).