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

Nosia

Nosia is a self-hosted AI platform that combines retrieval-augmented generation over private data with MCP connections to external tools, services and data sources. It includes a web interface, an OpenAI-compatible API, semantic search backed by pgvector, and support for custom LLM-driven and Ruby-based chat skills.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Nosia — 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 Nosia when you want a Docker-based, self-hosted service that combines document retrieval with MCP tool connections, or when an existing AI client needs an OpenAI-compatible endpoint.

Who it is for

  • Teams that want AI responses grounded in their own documents.
  • Developers connecting existing OpenAI-compatible clients to a self-hosted AI service.
  • Builders integrating models with external tools and data sources through MCP.

Documented uses

  • Retrieve relevant information from PDFs, text files, websites or Q&A pairs to augment AI responses.
  • Connect models to external services and tools using MCP.
  • Provide an OpenAI-compatible API endpoint for existing AI applications.
  • Extend chat with custom LLM-driven or Ruby-based skills.
Before you choose

Requirements & limits

The documented quickstart supports macOS, Debian, Ubuntu and 64-bit Windows 10/11. Windows requires Docker Desktop; the installer may need sudo/root access to install Docker on macOS or Linux. The default local address uses a self-signed SSL certificate.

  • The default completion model is ai/granite-4.0-h-tiny; the default embedding model is ai/granite-embedding-multilingual.
  • The README describes model changes through the LLM_MODEL and embedding-related environment variables.
  • Supported document inputs include PDFs, text files, websites and Q&A pairs.
  • The documented stack includes Docker Compose, Ruby and pgvector-backed semantic search.
  • The repository is public and specifies an MIT license.

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 and start Nosia with Docker Compose

Set up the documented local Nosia installation and open its web interface.

Before you start

  • macOS, Debian, Ubuntu, or 64-bit Windows 10/11
  • Internet connection
  • sudo/root access if Docker installation is needed on macOS or Linux
  • Docker Desktop installed and running on Windows

Steps

  1. Run the Nosia installation script for your operating system: the shell script on macOS/Linux or the PowerShell installer on Windows.

  2. From the installation configuration, start the services with the command below.

    Documented command
    docker compose up -d

  3. Open https://nosia.localhost to access the web interface.

Expected outcome

The local Nosia web interface is available at the documented address; the API endpoint is `https://nosia.localhost/v1`.

Guide limitations

  • The default installation uses a self-signed SSL certificate and produces a browser security warning.
  • On Windows, you may need to map nosia.localhost to 127.0.0.1 in the hosts file.
  • Production SSL configuration is covered by the repository's deployment guide.
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
NosiaRetrieve relevant information from PDFs, text files, websites or Q&A pairs to augment AI responses.Docker, Self-hostedThe documented quickstart supports macOS, Debian, Ubuntu and 64-bit Windows 10/11. Windows requires Docker Desktop; the installer may need sudo/root access to install Docker on macOS or Linux. The default local address uses a self-signed SSL certificate.
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
12 October 2026
Original website title
dilolabs/nosia · Official homepage title · retained in its source language
How we review sourcesSuggest a correction