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

AI Localbase

AI Localbase is a self-hostable RAG application that indexes uploaded documents in Qdrant and uses retrieved passages to inform model-powered question answering through a web interface. It connects to Ollama or OpenAI-compatible chat and embedding APIs, stores chat history in SQLite, and includes an optional MCP server for external tools and agents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Localbase — 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 you want to run document search and retrieval-augmented chat in a local or self-hosted environment, or make that knowledge base available to external tools through MCP.

Who it is for

  • Individuals building a searchable knowledge base from local documents.
  • Small teams creating an internal document question-answering workspace.
  • Developers prototyping self-hosted RAG or connecting a knowledge source to external MCP tools.

Documented uses

  • Upload and index TXT, Markdown, text-based PDF, XLSX and CSV documents.
  • Ask questions and retrieve relevant document passages in model-assisted chat.
  • Manage knowledge bases and review their document lists.
  • Expose knowledge-base capabilities to external agents and tools through the optional MCP server.
  • Generate small RAG evaluation datasets from existing knowledge-base documents.
Before you choose

Requirements & limits

The project is open source under the MIT license. Its documented deployment uses Docker Compose; an Ollama or OpenAI-compatible endpoint must be configured for chat and embeddings.

  • The application uses Qdrant for vector search, SQLite for chat history and local JSON files for configuration and knowledge-base state.
  • Embedding model dimensions must match Qdrant's configured vector size.
  • MCP is disabled by default and uses HTTP JSON responses; it does not provide SSE long-lived connections.
  • The documented application design is single-instance because SQLite state and in-memory MCP jobs are not shared across backend replicas.
  • The README lists TXT, Markdown, text-based PDF, XLSX and CSV ingestion.

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 AI Localbase with Docker Compose

Start the web interface, backend and Qdrant, then reach the model settings.

Before you start

  • Docker Compose
  • The project repository, including its .env.example file
  • An Ollama or OpenAI-compatible chat and embedding model endpoint

Steps

  1. Copy .env.example to .env.

  2. Run docker compose up --build.

  3. Open http://localhost:4173 and configure the Chat and Embedding models in Settings.

Expected outcome

The Compose services start and the web interface is available for model configuration.

Guide limitations

  • QDRANT_VECTOR_SIZE must match the embedding model's dimensions; changing dimensions requires a new collection prefix or rebuilding the old collection.
  • For server deployments, set AUTH_PASSWORD or AUTH_SETUP_TOKEN to protect initial setup.
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
AI LocalbaseUpload and index TXT, Markdown, text-based PDF, XLSX and CSV documents.Docker, Self-hosted, WebThe project is open source under the MIT license. Its documented deployment uses Docker Compose; an Ollama or OpenAI-compatible endpoint must be configured for chat and embeddings.
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
14 October 2026
Original website title
veyliss/ai-localbase · Official homepage title · retained in its source language
How we review sourcesSuggest a correction