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

InsightsLM: Fully Local & Private Version

InsightsLM is a self-hosted document research application that runs locally in Docker, allowing users to chat with PDFs, text files and audio, inspect citations, transcribe audio and generate audio summaries using local AI services.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

InsightsLM: Fully Local & Private Version — 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 document research and audio summaries need to run on a self-managed local stack, and you can configure Docker services and their supporting environment.

Who it is for

  • Individuals who want to research personal documents with locally run AI services.
  • Teams seeking a self-hosted tool for internal knowledge management.

Documented uses

  • Ask questions about uploaded documents and receive answers grounded in those sources.
  • Follow citations to verify where an answer appears in source material.
  • Transcribe audio files and generate audio summaries from source materials.
Before you choose

Requirements & limits

The repository is public and identifies the software as open source under the MIT license. Its documented use requires a local installation rather than a hosted service.

  • The frontend is React, Vite and TypeScript; n8n provides backend automation and Supabase runs locally for database and storage.
  • Ollama is used for local inference and embeddings, with Whisper ASR for transcription and Coqui TTS for speech generation.
  • Setup depends on the separate local-ai-packaged base repository and requires environment-variable and Docker Compose configuration.
  • The supplied Compose configuration is GPU-oriented for Coqui and Whisper and may need adjustment for Apple Silicon or CPU use.

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 the local InsightsLM service stack

Prepare the documented local package and start its Docker services.

Before you start

  • Python
  • Git or GitHub Desktop
  • Docker or Docker Desktop
  • Cole Medin’s local-ai-packaged repository
  • A code editor is recommended

Steps

  1. Clone the local-ai-packaged repository and, inside it, clone insights-lm-local-package.

  2. Copy the base repository’s .env.example to .env, populate its required secrets, and add the variables from the package’s .env.copy, including a webhook authentication key.

  3. Merge the package’s whisper-cache volume and insights-lm, coqui-tts and whisper-asr services into the base Docker Compose configuration; update the Ollama model to qwen3:8b-q4_K_M.

  4. Start Docker Desktop and run the base repository’s start script using the command appropriate for your system.

Expected outcome

The documented setup starts the local containers needed for the InsightsLM stack.

Guide limitations

  • The supplied Compose configuration sets Coqui and Whisper to use a GPU; the README directs Apple Silicon and CPU users to their respective documentation for adjustments.
  • The start-script command varies by system; the README gives an Nvidia GPU command as an example.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
theaiautomators/insights-lm-local-package · Official homepage title · retained in its source language
How we review sourcesSuggest a correction

Related options

InsightsLM — The repository describes this package as a fully local, self-hosted version of InsightsLM.

Explore project →