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

Locallens

LocalLens is an open-source Python application that indexes local files and lets users search them by meaning or exact terms, ask questions grounded in the indexed material, and use voice input and spoken answers. It offers a command-line interface and a separate self-hosted web app. The CLI stores vectors with embedded Qdrant Edge; the web app uses a Dockerized Qdrant server. Its documented stack includes MiniLM emb

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Locallens — 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 LocalLens when you want to search a local file collection or ask questions about its contents using an offline-first tool, and can install the relevant local dependencies.

Who it is for

  • People searching personal or work document collections stored locally.
  • Command-line users who want semantic and exact-match file retrieval without setting up the web app.
  • Users who prefer a visual interface for indexing folders, filtering searches, and asking questions.
  • Developers connecting local file search to an MCP-compatible AI client.

Documented uses

  • Index a folder of local files for later retrieval.
  • Find documents by topic or meaning, or search for exact terms using hybrid retrieval.
  • Ask natural-language questions and get answers grounded in indexed files.
  • Speak a question and hear an answer through the documented voice components.
  • Expose indexing and retrieval tools to an MCP client.
Before you choose

Requirements & limits

The project is publicly available on GitHub under the MIT license. The CLI requires Python 3.11 or later; the web app additionally lists Ollama, Docker with Docker Compose, and Node.js 18 or later.

  • The CLI and web app have distinct storage paths: embedded Qdrant Edge for the CLI and a Dockerized Qdrant server for the web app.
  • The README describes the application as offline-first, with no cloud APIs or telemetry.
  • Question answering uses Ollama and the qwen2.5:3b model; semantic embeddings use all-MiniLM-L6-v2 and keyword search uses BM25.
  • Voice interaction uses Moonshine for speech recognition and Piper for speech playback.
  • The README lists Python entry-point plugins for adding custom file-format extractors.

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

Index and search a folder from the CLI

Install LocalLens, index a local folder, then retrieve files with a natural-language search.

Before you start

  • Python 3.11 or later.
  • A local folder of files to index.

Steps

  1. Install the CLI with the command below.

    Documented command
    pip install locallens

  2. Run locallens doctor to verify the setup.

  3. Index a folder with locallens index ~/Documents, substituting the folder you want to search.

  4. Run a query such as locallens search "meeting notes from last week".

Expected outcome

The indexed folder can be searched from the command line using semantic and keyword retrieval.

Guide limitations

  • This recipe covers CLI indexing and search; question answering requires a separate locallens ask command and an Ollama setup.
  • The README identifies the CLI path as using embedded Qdrant Edge, so Docker is not required for this route.
Documentation 1 ↗
Source-based practical guide

Set up the LocalLens web app

Start the web interface and its documented local services for file indexing and search.

Before you start

  • Python 3.11 or later.
  • Ollama installed and running.
  • Docker and Docker Compose.
  • Node.js 18 or later.

Steps

  1. Clone the repository using the README's web-app instructions and enter the project directory.

  2. Run the command below to start Qdrant, pull the Ollama model, and install dependencies.

    Documented command
    make setup

  3. Run the command below to start the documented Qdrant, API, and frontend services.

    Documented command
    make dev

  4. Open http://localhost:5173 and use the Index, Search, or Ask pages.

Expected outcome

The README describes a local web interface for indexing folders, searching, and asking questions, with voice available in the Ask page.

Guide limitations

  • The documented web-app instructions identify local services and prerequisites; they do not establish that the web app is hosted for public use.
  • Voice and question answering rely on their documented local speech and Ollama components.
Documentation 1 ↗
Evidence and transparency

Sources & review

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