# llm_wiki | nash_su | Knowledge Base | Instagit

LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

GitHub Stars: 18.7k

Repository: https://github.com/nashsu/llm_wiki

---

## Articles

### [What Is the Purpose of the skills.rs File in the LLM Wiki Agent?](/nashsu/llm_wiki/what-is-the-purpose-of-the-skills.rs-file-in-the-llm-wiki-agent)

Discover the purpose of the skills.rs file in the LLM Wiki agent. Learn how it manages instruction bundles for the LLM runtime. Explore skill discovery, validation, and loading.

- Tags: internals
- Published: 2026-09-13

### [How the Tauri Backend Is Wired in LLM Wiki: React-to-Rust Communication Explained](/nashsu/llm_wiki/how-is-the-tauri-backend-wired-in-llm-wiki)

Discover how the Tauri backend integrates with the LLM Wiki React frontend. Learn about secure Rust communication, invoke calls, and event listeners for a seamless web UI.

- Tags: internals
- Published: 2026-09-13

### [Where to Find the Ingestion Pipeline Specification in LLM Wiki](/nashsu/llm_wiki/where-to-find-the-ingestion-pipeline-specification-in-llm-wiki)

Locate the ingestion pipeline specification in LLM Wiki across TypeScript modules and markdown files. Find detailed orchestration logic in src/lib/ingest.ts for easy access.

- Tags: documentation
- Published: 2026-09-13

### [Frontend Dependencies Used in LLM Wiki: A Complete Technical Breakdown](/nashsu/llm_wiki/what-are-the-frontend-dependencies-used-in-llm-wiki)

Explore the frontend dependencies of LLM Wiki including React, Vite, and Tailwind CSS. Get a complete technical breakdown of libraries used for markdown, graphs, and desktop integration.

- Tags: deep-dive
- Published: 2026-09-13

### [How LLM Wiki Handles Cascade Cleanup of Deleted Sources](/nashsu/llm_wiki/how-does-llm-wiki-handle-cascade-cleanup-of-deleted-sources)

Discover how LLM Wiki manages cascade cleanup of deleted sources. Learn about file removal, vector embedding purging, media deletion, and comprehensive index updates.

- Tags: internals
- Published: 2026-09-13

### [How the LLM-Wiki Source Folder Auto-Watch Feature Works: Implementation and Configuration](/nashsu/llm_wiki/how-does-the-source-folder-auto-watch-feature-work)

Discover how LLM-Wiki's source folder auto-watch uses Rust file watching and TypeScript rules to efficiently queue files for knowledge graph ingestion. Learn implementation and configuration.

- Tags: internals
- Published: 2026-09-13

### [How to Stream Agent Chat Using the LLM Wiki API: A Complete Implementation Guide](/nashsu/llm_wiki/how-to-stream-agent-chat-using-the-llm-wiki-api)

Learn to stream agent chat with the LLM Wiki API's streamChat function. This guide shows real-time token streaming using SSE for OpenAI and Anthropic responses.

- Tags: how-to-guide
- Published: 2026-09-13

### [How to Use the LLM Wiki API for Hybrid Search: A Complete Guide](/nashsu/llm_wiki/how-to-use-the-llm-wiki-api-for-hybrid-search)

Learn to use the LLM Wiki API for hybrid search. Combine BM25 keyword scoring and vector search via LanceDB with this complete guide. Access the local HTTP API today.

- Tags: how-to-guide
- Published: 2026-09-13

### [How to Access the Local HTTP API of LLM Wiki: A Developer's Integration Guide](/nashsu/llm_wiki/how-to-access-the-local-http-api-of-llm-wiki)

Learn how to access LLM Wiki's local HTTP API to integrate external tools and scripts with your wiki projects, pages, and knowledge graphs. Get started with our developer guide.

- Tags: how-to-guide
- Published: 2026-09-13

### [LLM Wiki Agent SSE Events: Complete Event Stream Reference](/nashsu/llm_wiki/what-sse-events-does-the-llm-wiki-agent-emit)

Discover the eleven SSE events emitted by the LLM Wiki agent, covering session lifecycle, tool use, file changes, and message deltas. Explore the complete event stream reference for nashsu/llm_wiki.

- Tags: api-reference
- Published: 2026-09-13

### [How the LLM Wiki Agent Handles External Shell Command Requests](/nashsu/llm_wiki/how-does-the-llm-wiki-agent-handle-external-shell-command-requests)

Discover how the LLM Wiki agent executes external shell commands. Learn about its secure sandboxed Rust backend and structured JSON responses for efficient processing.

- Tags: how-to-guide
- Published: 2026-09-13

### [How to Integrate Custom Tools with the Rust Backend Chat Agent in LLM Wiki](/nashsu/llm_wiki/how-to-integrate-custom-tools-with-the-rust-backend-chat-agent)

Integrate custom tools with the Rust backend chat agent in LLM Wiki. Learn to implement the Tool trait, register your tool, and invoke it via Tauri commands for enhanced functionality.

- Tags: how-to-guide
- Published: 2026-09-13

### [Which LLM Models Are Compatible with LLM Wiki’s Vector Search?](/nashsu/llm_wiki/what-llm-models-are-compatible-with-llm-wikis-vector-search)

Discover which LLM models work with LLM Wiki's vector search. Explore compatibility with OpenAI, Azure, Google Vertex AI, Ollama, and more.

- Tags: compatibility
- Published: 2026-09-13

### [How Vector Search Is Configured and Used in LLM Wiki: A Complete LanceDB Implementation Guide](/nashsu/llm_wiki/how-is-vector-search-configured-and-used-in-llm-wiki)

Learn how to configure and use vector search in LLM Wiki with LanceDB. Implement embedding, retrieval, and hybrid search modes using a Rust backend and Tauri commands for efficient knowledge retrieval.

- Tags: how-to-guide
- Published: 2026-09-13

### [How the Multi-Phase Retrieval Pipeline Works in LLM Wiki: A 4-Stage Architecture](/nashsu/llm_wiki/how-does-the-multi-phase-retrieval-pipeline-in-llm-wiki-function)

Explore the 4-stage multi-phase retrieval pipeline in LLM Wiki. Discover how tokenized search, vector search, graph expansion, and context assembly maximize recall within LLM limits.

- Tags: architecture
- Published: 2026-09-13

### [How the Louvain Community Detection Algorithm Works in LLM Wiki: Graph-Based Knowledge Clustering](/nashsu/llm_wiki/how-does-the-louvain-community-detection-algorithm-work-in-llm-wiki)

Discover how the Louvain community detection algorithm clusters LLM Wiki pages by analyzing its link graph for interconnected knowledge.

- Tags: deep-dive
- Published: 2026-09-13

### [Understanding the 4-Signal Knowledge Graph Relevance Model in LLM Wiki](/nashsu/llm_wiki/what-are-the-signals-used-in-the-4-signal-knowledge-graph-relevance-model)

Explore the 4-signal knowledge graph relevance model used in LLM Wiki. Discover how title similarity, full-text overlap, wikilink similarity, and backlink strength determine contextual relevance.

- Tags: deep-dive
- Published: 2026-09-13

### [How LLM Wiki Implements Incremental Caching for Ingestion](/nashsu/llm_wiki/how-does-llm-wiki-implement-incremental-caching-for-ingestion)

Discover how LLM Wiki uses incremental caching with SHA-256 hashes to speed up ingestion, avoiding redundant LLM processing for unchanged files while updating image captions.

- Tags: internals
- Published: 2026-09-13

### [What Is the Two-Step Chain-of-Thought Ingest Process in LLM Wiki?](/nashsu/llm_wiki/what-is-the-two-step-chain-of-thought-ingest-process)

Understand the two-step chain-of-thought ingest process in LLM Wiki. This auto-ingest pipeline improves accuracy and traceability by separating document reasoning from content creation.

- Tags: deep-dive
- Published: 2026-09-13

### [Understanding the Three-Layer Architecture of LLM Wiki: Raw Sources, Wiki, and Schema](/nashsu/llm_wiki/what-is-the-three-layer-architecture-of-llm-wiki)

Explore the LLM Wiki three-layer architecture. Learn how raw sources wiki pages and schema create a traceable knowledge base.

- Tags: architecture
- Published: 2026-09-13

### [How to Set Up the LLM Wiki Project Locally: Complete Installation Guide](/nashsu/llm_wiki/how-to-set-up-llm-wiki-project-locally)

Set up the LLM Wiki project locally with our complete installation guide. Clone the repo, install dependencies, and run the Tauri app in minutes. Get started now.

- Tags: how-to-guide
- Published: 2026-09-13

### [What is Reciprocal Rank Fusion (RRF) and How It Powers LLM Wiki Search](/nashsu/llm_wiki/what-is-reciprocal-rank-fusion-rrf-and-how-is-it-used-in-llm-wiki-s-search)

Discover Reciprocal Rank Fusion RRF a powerful ranking technique that unifies LLM Wiki search results from filenames phrases and relevance for superior accuracy and efficiency.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Implements Budget Control and Context Window Splitting for Retrieval](/nashsu/llm_wiki/how-does-llm-wiki-implement-budget-control-and-context-window-splitting-for-retrieval)

Discover how LLM Wiki manages retrieval with budget control and context window splitting. Learn about character-level budgeting and hierarchical chunking for efficient context management.

- Tags: internals
- Published: 2026-09-12

### [How Graph Expansion Improves Search Results in LLM Wiki](/nashsu/llm_wiki/how-does-graph-expansion-improve-search-results-in-llm-wiki)

Discover how graph expansion elevates search results in LLM Wiki by connecting semantically related pages beyond keyword matches. Improve your LLM Wiki search experience today.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Implements Vector Semantic Search with LanceDB: A Technical Deep Dive](/nashsu/llm_wiki/how-is-vector-semantic-search-implemented-in-llm-wiki-using-lancedb)

Discover how LLM Wiki implements vector semantic search using LanceDB in its Rust backend. Learn about local vector stores, upsert semantics, and cosine similarity for relevant wiki retrieval.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Performs Tokenized Search Across Wiki and Source Directories](/nashsu/llm_wiki/how-does-llm-wiki-perform-tokenized-search-across-wiki-and-source-directories)

Discover how LLM Wiki executes tokenized search across wiki and source directories. Learn about its TypeScript frontend, Rust backend, and ranked result scoring for efficient data retrieval.

- Tags: deep-dive
- Published: 2026-09-12

### [The Four Phases of the Multi-Phase Retrieval Pipeline in LLM Wiki](/nashsu/llm_wiki/what-are-the-four-phases-of-the-multi-phase-retrieval-pipeline-in-llm-wiki)

Discover the four phases of LLM Wiki's multi-phase retrieval pipeline: Tokenized Search, Graph Expansion, Budget Control, and Context Assembly for efficient context delivery.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Renders the Graph View Using Sigma.js and Graphology](/nashsu/llm_wiki/how-does-llm-wiki-render-the-graph-view-using-sigma-js-and-graphology)

Discover how LLM Wiki renders its knowledge graph with Sigma.js and Graphology. Learn about the Graphology data model, ForceAtlas2 algorithm, and WebGL-accelerated canvas display.

- Tags: how-to-guide
- Published: 2026-09-12

### [How Four Relevance Signals Are Weighted in LLM Wiki's Graph Engine](/nashsu/llm_wiki/how-are-the-four-relevance-signals-weighted-in-llm-wiki-s-graph-engine)

Discover how LLM Wiki's graph engine weights four relevance signals: source overlap, direct links, common neighbors, and type affinity. Understand the calculation for final relevance scores.

- Tags: deep-dive
- Published: 2026-09-12

### [Understanding the Knowledge Graph Relevance Model in LLM Wiki](/nashsu/llm_wiki/what-is-the-knowledge-graph-relevance-model-in-llm-wiki)

Discover the knowledge graph relevance model in LLM Wiki. Learn how it calculates semantic and structural relevance using edge weights and embedding similarity for precise document retrieval.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Preserves Directory Structures During Folder Imports](/nashsu/llm_wiki/how-does-llm-wiki-preserve-directory-structures-during-folder-imports)

Discover how LLM Wiki maintains directory structures during folder imports by recreating your exact file hierarchy within the project for seamless organization.

- Tags: internals
- Published: 2026-09-12

### [How the Persistent Ingest Queue in LLM Wiki Handles Restarts and Retries](/nashsu/llm_wiki/how-does-the-persistent-ingest-queue-in-llm-wiki-handle-restarts-and-retries)

Discover how the LLM Wiki persistent ingest queue handles restarts and retries. Learn how it serializes task state to localStorage for robust recovery.

- Tags: internals
- Published: 2026-09-12

### [What Structured Analysis Does the LLM Produce in the First Ingest Step?](/nashsu/llm_wiki/what-structured-analysis-does-the-llm-produce-in-the-first-step-of-ingest)

Discover the six-section structured analysis LLMs produce in their first ingest step: entities, concepts, arguments, connections, contradictions, and recommendations. Preserve source data verbatim.

- Tags: internals
- Published: 2026-09-12

### [How LLM Wiki Uses Hashing for Efficient Ingest and Deduplication](/nashsu/llm_wiki/how-does-llm-wiki-use-hashing-for-efficient-ingest-and-deduplication)

Discover how LLM Wiki uses FNV-1a and SHA-256 hashing for efficient ingest and deduplication, eliminating redundant processing and caching LLM calls.

- Tags: internals
- Published: 2026-09-12

### [How LLM Wiki Implements Cascade-Deletion Rules for Wiki Pages](/nashsu/llm_wiki/how-does-llm-wiki-implement-cascade-deletion-rules-for-wiki-pages)

Discover how LLM Wiki implements cascade-deletion rules to automatically remove orphaned pages and clean vector-store entries when source files are deleted. Learn about the three-step matching process.

- Tags: how-to-guide
- Published: 2026-09-12

### [9 Types of Wiki Pages Generated by LLM Wiki: Complete Structure Guide](/nashsu/llm_wiki/what-are-the-different-types-of-wiki-pages-generated-by-llm-wiki)

Discover the nine wiki page types LLM Wiki generates, including entities, concepts, and synthesis reports. Explore their structure and learn how they organize your knowledge base.

- Tags: documentation
- Published: 2026-09-12

### [How LLM Wiki Handles Immutable Source Documents in the raw/sources Directory](/nashsu/llm_wiki/how-does-llm-wiki-handle-immutable-source-documents-in-the-raw-sources-directory)

Discover how LLM Wiki safeguards immutable source documents in raw/sources. Learn about its three-layer architecture that copies, extracts, and references files without altering originals.

- Tags: how-to-guide
- Published: 2026-09-12

### [Understanding the File-System Architecture of LLM Wiki: A Deep Dive into the Knowledge Base Structure](/nashsu/llm_wiki/what-is-the-file-system-architecture-of-llm-wiki)

Explore the LLM Wiki file-system architecture. Discover its three-layer data persistence model (Raw Wiki Schema) and monorepo structure, separating React frontend from Rust backend.

- Tags: deep-dive
- Published: 2026-09-12

### [How LLM Wiki Builds a Persistent Obsidian-Compatible Vault](/nashsu/llm_wiki/how-does-llm-wiki-build-a-persistent-obsidian-compatible-vault)

Discover how LLM Wiki creates an Obsidian-compatible vault. Learn to build persistent, self-contained markdown vaults that survive application restarts.

- Tags: how-to-guide
- Published: 2026-09-12