minne

v1.0.3 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo Productivity & Wikis

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Updates Release Notes, Fix, and Performance across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	Search can filter results by type: knowledge entities, ingested content, or both. Search can filter results by type: knowledge entities, ingested content, or both. Source: llm_adapter@2026-06-12 Confidence: high	—
Feature	Low	Admin UI lets you select the local FastEmbed model; changes apply after restart and trigger re‑embedding when vector dimension changes. Admin UI lets you select the local FastEmbed model; changes apply after restart and trigger re‑embedding when vector dimension changes. Source: llm_adapter@2026-06-12 Confidence: high	—
Performance	Medium	Pooled FastEmbed workers and batched embedding generation improve ingestion and search speed. Pooled FastEmbed workers and batched embedding generation improve ingestion and search speed. Source: llm_adapter@2026-06-12 Confidence: high	—
Performance	Medium	Backend allocation and retrieval optimizations lower search and chat latency. Backend allocation and retrieval optimizations lower search and chat latency. Source: llm_adapter@2026-06-12 Confidence: high	—
Bugfix
Bugfix	High	API key revocation now correctly clears the stored key. API key revocation now correctly clears the stored key. Source: llm_adapter@2026-06-12 Confidence: high	—
Bugfix	Medium	Modal dialogs (scratchpad editor, admin prompts, entity creation) open and close more reliably. Modal dialogs (scratchpad editor, admin prompts, entity creation) open and close more reliably. Source: llm_adapter@2026-06-12 Confidence: high	—
Bugfix	Low	Improved knowledge‑entity relationship suggestions when creating entities manually. Improved knowledge‑entity relationship suggestions when creating entities manually. Source: llm_adapter@2026-06-12 Confidence: high	—

Full changelog

Release Notes

Search: filter results by type — knowledge entities, ingested content, or both
Admin: choose the local FastEmbed model from the admin UI; changes save immediately and apply after restart (re-embeds when the vector dimension changes)
Performance: pooled FastEmbed workers and batched embedding generation for faster ingestion and search
Performance: lower search and chat latency from backend allocation and retrieval optimizations
Fix: modal dialogs (scratchpad editor, admin prompts, entity creation) open and close more reliably
Fix: improved knowledge-entity relationship suggestions when creating entities manually
Fix: API key revocation now correctly clears the stored key