Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

TabulaRAG

БесплатноНе проверен

Enables AI assistants to query tabular data (CSV/TSV) using natural language with cell-level citations, supporting multi-tenant workspaces, access control, and

GitHubEmbed

Описание

Enables AI assistants to query tabular data (CSV/TSV) using natural language with cell-level citations, supporting multi-tenant workspaces, access control, and semantic search.

README

TabulaRAG logo
TabulaRAG

A fast-ingesting tabular data MCP RAG tool backed with cell citations.
Upload a CSV or TSV, then query it in natural language. Results include cell-level citations so you can trace exactly where each answer came from. We also have multi-role access where admin users can add, delete, edit datasets as well as invite users to their enterprise/organization via invite codes.

Python 3.11 Node 20 TypeScript Strict License


Features

  • CSV/TSV ingestion — upload tabular files with automatic header detection, delimiter inference, and column type recognition (dates, money, measurements)
  • Semantic search — each row is embedded via sentence-transformers/all-MiniLM-L6-v2 and indexed in Qdrant for natural-language retrieval with cell-level citations
  • Structured queries — filter and aggregate data through the API with SQL over PostgreSQL JSON columns
  • Multi-tenant workspaces — enterprises with invite codes, roles (owner / admin / querier), and switchable active workspace
  • Folders & access control — public, protected, and private folders with user-group-based permissions
  • MCP server — exposes Streamable HTTP + SSE endpoints so AI assistants can use your tables as a retrieval tool
  • Auth — Google OAuth and email/password with verification codes and password reset (via Brevo SMTP)
  • Background indexing — threaded worker pool for non-blocking embedding and Qdrant upserts with progress tracking

Architecture

Layer Technology
Frontend React 19, TypeScript 5.9, Vite 7, React Router 7
Backend Python 3.11, FastAPI, SQLAlchemy 2.x, Uvicorn
Database PostgreSQL 16
Vector store Qdrant v1.13.4 (FastEmbed, 384-dim dense vectors)
Auth JWT, Google OAuth, bcrypt
MCP fastapi-mcp (Streamable HTTP + SSE)
Web server Nginx 1.27 (production frontend)
CI GitHub Actions (pytest, ESLint, Docker builds)

MCP integration

TabulaRAG exposes endpoints for AI assistant integration:

Type URL
OpenAPI http://localhost:8000/openapi.json
MCP (Streamable HTTP) http://localhost:8000/mcp

Authentication: use a personal MCP token (generated from the app's MCP section) in Authorization: Bearer <token>, or the server API_KEY for automation. Tokens are scoped per user and workspace.

If your MCP client runs outside the browser (e.g. Docker, desktop app), replace localhost with your machine's IP (ipconfig on Windows, ifconfig on Mac/Linux).


Local vs. Deployed

Feature Local (Docker Compose) Deployed
Database PostgreSQL in Docker External PostgreSQL
Vector store Qdrant in Docker External Qdrant

Prerequisites (Local)

Tool Version Notes
Docker Latest https://docs.docker.com/get-docker/
Docker Compose v2+ Bundled with Docker Desktop

Docker Compose v2 is required (docker compose, not docker-compose). It ships with Docker Desktop on Mac and Windows. Linux users may need to install it separately.

You do not need to install Python or Node locally — everything runs inside containers.


Quick start

cp .env.example .env      # create config (edit values as needed)
./scripts/dev-up.sh        # build and start all services

Once running:

Service URL
Frontend http://localhost:5173
Backend API http://localhost:8000
PostgreSQL localhost:5433
Qdrant http://localhost:6333

Health checks:

curl http://localhost:8000/health
curl http://localhost:8000/health/deps

Stop / logs:

./scripts/dev-down.sh
./scripts/dev-logs.sh              # all services
./scripts/dev-logs.sh backend      # single service

Environment variables

Copy .env.example to .env. The key variables:

Variable Required Description
POSTGRES_DB Yes Database name (default: tabularag)
POSTGRES_USER Yes Database user (default: tabularag)
POSTGRES_PASSWORD Yes Database password
DATABASE_URL Yes PostgreSQL connection string (set in docker-compose)
QDRANT_URL Yes Qdrant endpoint (set in docker-compose)
JWT_SECRET Yes Secret for signing JWT tokens
PUBLIC_API_BASE_URL Yes Backend URL used in email links (default: http://localhost:8000)
PUBLIC_UI_BASE_URL Yes Frontend URL used in email links (default: http://localhost:5173)
API_KEY No Optional static key for script/API access
GOOGLE_CLIENT_ID No Google OAuth client ID
GOOGLE_CLIENT_SECRET No Google OAuth client secret
SMTP_HOST No Brevo SMTP relay for verification/reset emails
SMTP_PORT No SMTP port (default: 587)
SMTP_USER No SMTP login
SMTP_PASSWORD No SMTP key
SMTP_FROM No Sender email address

SMTP is optional for local development. If SMTP_HOST is empty, verification and reset codes are written to the backend logs instead of being emailed. For any real deployment, configure SMTP so users receive emails.

The remaining variables in .env.example control embedding model tuning, Qdrant HNSW parameters, batch sizes, and indexing concurrency. The defaults work for local development.


License

MIT

from github.com/angelafeliciaa/TabulaRAG

Установка TabulaRAG

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/angelafeliciaa/TabulaRAG

FAQ

TabulaRAG MCP бесплатный?

Да, TabulaRAG MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для TabulaRAG?

Нет, TabulaRAG работает без API-ключей и переменных окружения.

TabulaRAG — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить TabulaRAG в Claude Desktop, Claude Code или Cursor?

Открой TabulaRAG на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare TabulaRAG with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai