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

Dot

Dot is an open-source desktop application for chatting with documents and files using local language models and retrieval-augmented generation. It also offers a separate general-purpose chat mode. The project describes an Electron implementation using FAISS for local vector stores and LangChain, llama.cpp and Hugging Face components for conversation chains.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Dot — 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 Dot when you want document-grounded questions over a local file collection, or switch to its general chat mode for unrelated inquiries.

Who it is for

  • People who want to ask questions across a collection of documents on a desktop.
  • Developers interested in a JavaScript and Electron open-source document-chat application.

Documented uses

  • Load multiple documents and ask questions about their contents.
  • Use a separate chat mode for questions unrelated to loaded documents.
  • Explore an implementation combining local vector stores with language-model conversation chains.
Before you choose

Requirements & limits

The README directs users to download the application for Apple Silicon or Windows. The repository is public and licensed under GPL-3.0.

  • The app is described as fully local and uses FAISS for local vector stores.
  • The README identifies Phi-3.5 as the default model.
  • Document chat and general-purpose chat are separate modes.
  • The listed download platforms are Apple Silicon and Windows.

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 project dependencies for development

Prepare the repository by installing its documented Node.js dependencies.

Before you start

  • The Dot repository
  • Node.js and npm

Steps

  1. Clone the Dot repository.

  2. Run the command below in the project repository; the README suggests the command below if issues occur at this stage.

    Documented command
    npm install
    Documented command
    npm install --force

  3. Change to the aadotllm directory and run the command below again.

    Documented command
    npm install

Expected outcome

Dependencies are installed in both locations named by the README.

Guide limitations

  • The instructions cover dependency installation only; they do not document running or packaging the application.
  • The README describes --force as an option if the first installation stage has issues.
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
DotLoad multiple documents and ask questions about their contents.Desktop, macOS, Self-hosted, WindowsThe README directs users to download the application for Apple Silicon or Windows. The repository is public and licensed under GPL-3.0.
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
alexpinel/Dot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction