qmd-reindex

Rebuild BM25 full-text and vector indexes for Mnemonic semantic search.

20|4|Updated Jan 24, 2026

Search Tags:#indexing #embeddings #search #mnemonic #qmd

Ready to run

npx skills add https://github.com/zircote/mnemonic --skill qmd-reindex

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: qmd-reindex
Source: https://github.com/zircote/mnemonic/tree/main/skills/qmd-reindex
Command: npx skills add https://github.com/zircote/mnemonic --skill qmd-reindex

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill ensures that your Mnemonic memories are accurately searchable by rebuilding the search index after changes.

Core Features & Use Cases

Search Indexing: Rebuilds BM25 full-text and vector embeddings for semantic search.
Data Synchronization: Keeps your search capabilities up-to-date with your memory store.
Use Case: After adding new client meeting notes or importing a batch of research papers into Mnemonic, run this Skill to make sure you can find them instantly using semantic search.

Quick Start

Run qmd update and qmd embed to re-index mnemonic memories for qmd semantic search.

Frequently Asked Questions about qmd-reindex

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I rebuild the semantic search index for Mnemonic memories after importing new data?▼

To rebuild the semantic search index for Mnemonic memories, run the qmd update and qmd embed commands. This regenerates BM25 full-text and vector embeddings to synchronize your search capabilities with newly captured or bulk-imported data.

Why does semantic search fail to find my recently added Mnemonic memories?▼

Semantic search fails to find recently added Mnemonic memories because the search index is outdated. You must re-index the memory store by running qmd update and qmd embed to regenerate the full-text and vector embeddings for accurate discoverability.

When do I need to re-index Mnemonic memories for semantic search?▼

You need to re-index Mnemonic memories for semantic search after adding new information, such as client meeting notes, or completing bulk imports of research papers. Re-indexing ensures your full-text and vector indexes reflect the latest stored data for accurate retrieval.

Does qmd re-indexing update both full-text and vector embeddings?▼

Yes, qmd re-indexing updates both BM25 full-text and vector embeddings. By running the update and embed scripts, you ensure your Mnemonic memory store maintains comprehensive search accuracy and data synchronization for semantic queries.