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

Opendocuments

Opendocuments is a self-hosted RAG application that indexes documents from connected repositories, files and web sources, then answers natural-language questions using hybrid vector and keyword retrieval with source citations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Opendocuments — 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 Opendocuments when you need self-hosted, cited question-answering over documents gathered from multiple sources, or want a TypeScript-based RAG application you can configure and extend.

Who it is for

  • Teams consolidating engineering, product, policy or operational documents into a searchable knowledge base.
  • Developers who want to run document search on infrastructure they manage and configure local or cloud language models.
  • AI coding-assistant users seeking access to an internal knowledge base through the documented MCP server.

Documented uses

  • Index documents from connected repositories, storage sources, local files or web pages.
  • Ask questions about an indexed corpus and inspect cited source documents.
  • Expose a knowledge base to MCP-compatible clients.
  • Extend ingestion or model support with TypeScript plugins.
Before you choose

Requirements & limits

The project is open source under the MIT license and is documented for self-hosting. Its quick start requires Node.js 20 or later; model setup can use Ollama or cloud providers.

  • The service is self-hosted, so deployment and data storage are managed on the operator's infrastructure.
  • The documented default stores metadata in SQLite and vectors in LanceDB.
  • Cloud model use requires provider configuration and API credentials; local-model setup uses Ollama.
  • The documented source connectors include GitHub, Notion, Google Drive, Confluence, S3, Swagger/OpenAPI, local files and web pages.

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

Set up a local Opendocuments instance and index files

Start the local service, index a directory of supported documents and submit a question.

Before you start

  • Node.js 20 or later
  • Install the Opendocuments CLI with npm
  • A configured model provider; initialization supports Ollama or cloud providers
  • A directory of documents to index

Steps

  1. Install the CLI with the command below.

    Documented command
    npm install -g opendocuments

  2. Run opendocuments init and configure a model provider.

  3. Run opendocuments start, then open http://localhost:3000.

  4. Index a directory with opendocuments index ./docs.

  5. Submit a question with opendocuments ask "What's our deployment process?".

Expected outcome

A running local Web UI and an indexed document directory that can be queried through the CLI.

Guide limitations

  • A model and indexed corpus must be ready before questions can be answered.
  • A normal start does not download a model; the initialization wizard may offer to pull missing Ollama models.
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
OpendocumentsIndex documents from connected repositories, storage sources, local files or web pages.Self-hostedThe project is open source under the MIT license and is documented for self-hosting. Its quick start requires Node.js 20 or later; model setup can use Ollama or cloud providers.
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
joungminsung/OpenDocuments · Official homepage title · retained in its source language
How we review sourcesSuggest a correction