Outils — vue longue

Obsidian plugin that runs queries over page frontmatter (YAML metadata) to generate dynamic tables, lists, and analytical views. Particularly valuable in llm-wiki-pattern implementations where LLMs consistently add structured metadata to wiki pages.

Core Functionality

YAML Frontmatter Queries:

• Extract and analyze metadata from wiki pages
• Filter pages by tags, dates, categories, confidence levels
• Generate dynamic content that updates automatically
• Create analytical views across the entire knowledge base

Dynamic Generation:

• Tables and lists update automatically as pages change
• No manual maintenance of summary content
• Always reflects current state of wiki

Metadata Patterns in LLM Wikis

Standard Frontmatter:

---
title: Page Title
category: concepts|entities|projects|sources
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: [tag1, tag2, tag3]
sources: [list of contributing sources]
confidence: high|medium|low
---

Extended Metadata:

• Source count tracking
• Creation and update timestamps
• Confidence assessments
• Category classifications
• Relationship mappings

Query Examples

Recent Updates:

• Pages updated in last 7 days
• Most frequently updated content
• Recent source integrations

Quality Analysis:

• Pages with low confidence ratings
• Content lacking source citations
• Orphan pages without inbound links

Content Overview:

• Pages by category with creation dates
• Tag frequency analysis
• Source contribution tracking

Use Cases in Wiki Management

Dashboard Creation:

• Overview of wiki health and activity
• Quick access to different content types
• Monitoring of maintenance needs

Quality Assurance:

• Identify content needing review or updates
• Find gaps in coverage or documentation
• Track source diversity and quality

Analytics and Insights:

• Understand knowledge accumulation patterns
• Identify most valuable content areas
• Track evolution of interests and focus

LLM Integration

Automated Metadata:

• LLM consistently adds structured frontmatter
• Tags generated based on content analysis
• Confidence levels assessed during creation
• Source tracking maintained automatically

Dashboard Queries:

• LLM can create Dataview queries for specific analytics
• Generate custom views for different purposes
• Update query logic as wiki evolves

Implementation Strategy

Gradual Adoption:

• Start with basic frontmatter (title, category, dates)
• Add tags and sources as patterns emerge
• Implement confidence ratings for quality tracking

Query Development:

• Begin with simple lists and tables
• Develop more complex analytical queries over time
• Create reusable query templates for common needs

Benefits for Wiki Scaling

Automated Organization:

• No manual maintenance of category pages
• Dynamic content reflects current state
• Reduces bookkeeping burden on both human and LLM

Insight Generation:

• Surface patterns not visible in individual pages
• Identify trends in knowledge accumulation
• Support strategic decisions about focus areas

Quality Management:

• Systematic identification of maintenance needs
• Data-driven approach to wiki health
• Objective assessment of content quality

See also

• llm-wiki-pattern - Framework that benefits from structured metadata analysis
• obsidian-integration - Platform supporting Dataview functionality
• wiki-maintenance-automation - Automated processes enhanced by metadata queries
• yaml-frontmatter - Structure that Dataview analyzes

Markdown-based slide deck format that enables generating presentations directly from llm-wiki-pattern content. Provides structured presentation capabilities as an output format for LLM query responses and knowledge synthesis.

Core Concept

Markdown to Slides:

• Write slide content in standard markdown format
• Special syntax for slide breaks and formatting
• Generate professional presentations from plain text
• Version control friendly (plain text files)

Obsidian Plugin:

• Native support within Obsidian environment
• Preview slides while editing content
• Seamless integration with wiki browsing workflow

Use Cases in LLM Wikis

Query Response Format:

• LLM can generate slide decks as answer format
• Particularly valuable for:
  • Topic overviews and summaries
  • Comparison analyses
  • Sequential explanations
  • Research presentations

Knowledge Presentation:

• Transform wiki content into presentation format
• Extract key insights from multiple pages
• Create structured narratives from accumulated knowledge
• Generate training materials and briefings

Synthesis Output:

• Present complex analyses in digestible format
• Structure multi-source comparisons visually
• Create educational content from research

Implementation Pattern

LLM Workflow:

1. Receive query requiring presentation format
2. Identify relevant wiki pages and content
3. Structure information for slide format
4. Generate Marp-formatted markdown
5. File as new wiki page if valuable for future reference

Example Output Structure:

---
marp: true
theme: default
---

# Topic Overview
Summary of key concepts

---

# Key Points
- Point 1 with wiki-link
- Point 2 with evidence
- Point 3 with implications

---

# Conclusions
Synthesis and next steps

Benefits for Knowledge Work

Structured Thinking:

• Forces clear organization of complex information
• Highlights key points and relationships
• Creates logical flow through related concepts

Reusable Assets:

• Presentations become permanent wiki artifacts
• Can be updated as knowledge evolves
• Serve as entry points for complex topics

Communication Tool:

• Share insights with others in accessible format
• Present research findings professionally
• Create educational materials from accumulated knowledge

Integration with Wiki Pattern

Output Diversity:

• One of several possible query response formats
• Alongside markdown pages, comparison tables, charts
• Chosen based on information structure and use case

Wiki Storage:

• Generated slide decks stored in wiki layer
• Cross-referenced with source pages
• Maintained and updated like other wiki content

Version Evolution:

• Presentations can be updated as knowledge evolves
• Track changes through git version control
• Reflect new insights and contradictory information

Technical Requirements

Obsidian Setup:

• Install Marp plugin for slide preview
• Configure theme and styling preferences
• Set up export options (PDF, HTML, etc.)

LLM Configuration:

• Include Marp syntax in schema documentation
• Train on slide structure best practices
• Configure when to choose slide format over alternatives

See also

• llm-wiki-pattern - Overall framework supporting diverse output formats
• query-workflow - Process that may generate slide presentations
• obsidian-integration - Platform supporting Marp plugin
• knowledge-compilation - Process of transforming content into structured formats

Local search engine for markdown files designed specifically for llm-wiki-pattern implementations. Provides hybrid BM25/vector search with LLM re-ranking, all running on-device. Essential tool for scaling wiki navigation beyond simple index-based browsing.

Core Capabilities

Hybrid Search Architecture:

• BM25 for keyword-based relevance scoring
• Vector embeddings for semantic similarity
• LLM re-ranking for improved result quality
• Combines best of lexical and semantic search

Local Operation:

• Runs entirely on-device, no external services required
• Privacy-preserving - content never leaves local machine
• Fast response times for interactive exploration
• No API costs or rate limits

Integration Options

CLI Interface:

• LLM can shell out to qmd for search operations
• Scriptable for automated wiki maintenance tasks
• Batch processing capabilities for large-scale analysis

MCP Server:

• Native tool integration for LLM agents
• Structured query and response format
• Seamless integration with agent workflows

Use Cases in LLM Wikis

Query Workflow Enhancement:

• Replace simple index.md scanning with sophisticated search
• Find relevant pages across large wiki collections
• Support complex multi-term and semantic queries

Lint Workflow Support:

• Find orphan pages and missing cross-references
• Identify contradictions between related pages
• Discover content gaps and redundancies

Exploration and Discovery:

• Surface unexpected connections between concepts
• Find related content across different categories
• Support research and synthesis workflows

Scaling Considerations

When to Implement:

• Essential when wiki grows beyond ~100 pages
• Index.md becomes unwieldy for navigation
• Complex queries require semantic understanding

Performance Characteristics:

• Handles thousands of markdown files efficiently
• Real-time search for interactive exploration
• Batch analysis for maintenance tasks

Alternative Approaches

While qmd is recommended by andrej-karpathy, the llm-wiki-pattern is tool-agnostic. Simple alternatives include:

Naive Search Scripts:

• Basic grep-based search over markdown files
• LLM can help implement custom search logic
• Sufficient for smaller wikis or specific domains

Existing Tools:

• Standard text search utilities (ripgrep, ag)
• Markdown-specific search tools
• Platform-native search (macOS Spotlight, Windows Search)

Implementation Strategy

Incremental Adoption:

• Start with index.md for small wikis
• Add basic search when navigation becomes cumbersome
• Implement qmd or similar when semantic search becomes valuable

LLM Integration:

• Configure search tool in schema layer
• Train LLM on search syntax and capabilities
• Integrate search into standard workflows

See also

• llm-wiki-pattern - Overall framework requiring search at scale
• obsidian-integration - Primary interface that benefits from enhanced search
• query-workflow - Process enhanced by sophisticated search capabilities
• lint-workflow - Maintenance tasks supported by search tools