OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Obsidianrag

Obsidianrag is a self-hosted retrieval-augmented question-answering application for Obsidian Markdown vaults. Its plugin manages the backend, indexing lifecycle, chat and source links; the backend uses SQLite FTS5 and embedded LanceDB for hybrid keyword and vector retrieval, while a configured model provider generates answers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Obsidianrag — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a chat workflow grounded in an Obsidian vault and are prepared to run the backend, configure a generation provider and explicitly build the index.

Who it is for

  • Obsidian users who want to ask questions across their Markdown notes.
  • People building a searchable personal knowledge base with keyword and vector retrieval.
  • Self-hosters who can run a backend and configure a compatible model provider.

Documented uses

  • Build or refresh a hybrid index of an Obsidian vault.
  • Ask questions and receive answers grounded in retrieved notes with numeric source citations.
  • Search indexed notes without generation, including a lexical-only search option.
Before you choose

Requirements & limits

  • The Obsidian plugin manages the backend and index lifecycle; the model provider is configured separately.
  • Supported generation options include Ollama, LM Studio and OpenAI-compatible servers.
  • The repository documents a backend installation via uv and plugin assets from a GitHub release; Docker is also identified as part of the project packaging.
  • API 3 clients and backends are incompatible with version 4.0.1, so plugin and backend versions matter.
  • The README says regular Markdown files are scanned without following links, and indexing must be triggered explicitly.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the backend and Obsidian plugin

Set up the documented backend and plugin assets in an Obsidian vault.

Before you start

  • An Obsidian vault
  • The uv tool installer
  • The ObsidianRAG 4.0.1 backend and plugin release assets

Steps

  1. Install the backend with the command below.

    Documented command
    uv tool install obsidianrag==4.0.1

  2. Get main.js, manifest.json and styles.css from the plugin-v4.0.1 GitHub release.

  3. Place the assets in /.obsidian/plugins/vault-rag/.

  4. Enable Vault RAG in Obsidian.

Expected outcome

The backend and plugin are installed for the vault; the README's first-run procedure continues with provider setup, backend startup and an explicit index build.

Guide limitations

  • This guide covers installation only, not model-provider configuration or a successful question-answering run.
  • The README states that the backend does not index automatically at startup.
Documentation 1 ↗
Source-based practical guide

Build an index and open the chat

Follow the documented first-run sequence to prepare the vault for question-answering.

Before you start

  • The backend and Obsidian plugin installed
  • A generation provider started with the configured model available
  • The backend executable set in Vault RAG settings

Steps

  1. Start the generation provider and make the configured model available.

  2. In Vault RAG settings, confirm the backend executable; the README gives obsidianrag or obsidianrag.exe as usual names.

  3. Start the backend.

  4. Select Build index, then open the chat view.

Expected outcome

The documented first-run flow builds the vault index and opens the plugin chat view.

Guide limitations

  • The README does not describe provider configuration steps in this sequence.
  • Index building is explicit and does not happen automatically at backend startup.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
ObsidianragBuild or refresh a hybrid index of an Obsidian vault.Docker, Self-hosted
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
Vasallo94/ObsidianRAG · Official homepage title · retained in its source language
How we review sourcesSuggest a correction