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

Lars

Lars is an open-source Python application that runs language models locally and answers questions about uploaded documents using retrieval-augmented generation, with citations and an in-window document reader.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Lars — 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 Lars when you want a local document-question-answering workflow and value inspecting cited source material in an integrated reader.

Who it is for

  • People who want to ask questions about their own documents using a locally run language model.
  • Researchers or document reviewers who want to inspect cited passages alongside generated answers.
  • Self-hosters who can install and run a Python application and its model dependencies.

Documented uses

  • Ask conversational questions grounded in uploaded files.
  • Inspect source documents, page references, highlighted text or extracted images associated with responses.
  • Continue earlier conversations and ask follow-up questions.
  • Work with listed document types including PDFs, office files, spreadsheets, presentations, images and HTML.
Before you choose

Requirements & limits

The documented first-run process starts a local browser interface and downloads a language model; the first query downloads an embedding model. The project is open source under AGPL-3.0.

  • The application is documented for Python 3.11.
  • Initial use downloads a Phi-3 Mini language model, and the first query downloads an embedding model from Hugging Face Hub.
  • Nvidia CUDA acceleration is listed as supported; GPU use is optional.
  • The project lists both local text extraction and Azure OCR options for scanned documents and improved extraction.
  • Citations are not guaranteed on every answer, according to the README.

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

Start Lars for a first local document-chat session

Launch the application and open its local browser interface.

Before you start

  • Python 3.11 is identified in the installation guidance.
  • Internet access is needed on first run to download the language model and, on the first query, the embedding model.

Steps

  1. After installing, open a terminal in the project directory and enter the web_app folder.

  2. Run the command below (use the command below on Linux or macOS).

    Documented command
    python app.py
    Documented command
    python3 app.py

  3. Open http://localhost:5000/ in a browser.

  4. On first run, allow the model download to complete; the embedding model downloads on the first query.

Expected outcome

The Lars interface opens locally in a browser, with its model and embedding downloads initiated as described by the project.

Guide limitations

  • The initial model download may take time depending on internet connection speed.
  • The README describes citations as generally present in some combination, not guaranteed for every response.
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
LarsAsk conversational questions grounded in uploaded files.Desktop, Self-hostedThe documented first-run process starts a local browser interface and downloads a language model; the first query downloads an embedding model. The project is open source under AGPL-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
15 October 2026
Original website title
abgulati/LARS · Official homepage title · retained in its source language
How we review sourcesSuggest a correction