Skip to main content

Natural AI Data Explorer — analyze datasets in plain language, locally and privately

Project description

Datialog — Natural AI Data Explorer

DOI PyPI License: CC BY-NC 4.0

Analyze datasets in plain language using AI. No code required. Your data never leaves your machine.

Installation

pip install datialog

Usage

# Launch (opens browser + system tray icon)
datialog

# Custom port
datialog --port 9090

# Terminal mode (no system tray)
datialog --no-tray

Or from Python:

import datialog
datialog.launch()

Features

  • Natural language — ask questions in Spanish or English
  • 100% local — data never leaves your machine with Ollama
  • Multi-backend — Ollama, Groq, OpenAI, Anthropic, LM Studio
  • Multiple formats — CSV, Excel, Stata, SAS, Parquet, JSON
  • Auto EDA — exploratory analysis with one click
  • Python console — integrated code console
  • Checkpoint & Undo — revert transformations
  • System tray — background mode with tray icon

Supported formats

Format Extension
CSV .csv
Excel .xlsx, .xls
Stata .dta
SAS .sas7bdat
Parquet .parquet
JSON .json

Requirements

  • Python 3.10+
  • For local models: Ollama
  • For cloud models: API key from Groq, OpenAI or Anthropic

Author

Ivan Pastor Sanzdatialog.app

Citation

@software{pastor_sanz_2026_datialog,
  author    = {Pastor Sanz, Iván},
  title     = {Datialog — Natural AI Data Explorer},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.20075103},
  url       = {https://doi.org/10.5281/zenodo.20075103}
}

License

CC BY-NC 4.0 — free for personal, academic and research use. Commercial use requires explicit permission from the author.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

datialog-1.3.0-py3-none-any.whl (29.8 kB view details)

Uploaded Python 3

File details

Details for the file datialog-1.3.0-py3-none-any.whl.

File metadata

  • Download URL: datialog-1.3.0-py3-none-any.whl
  • Upload date:
  • Size: 29.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for datialog-1.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 fd31bdf70878fff7869ecc67b39429fa44ee950743a8dee77157893095001257
MD5 bc798e7767e6dcb6b5c8f6be02d865da
BLAKE2b-256 1f1fe6b75d2dbd94458e66512f7023276eebdb799f59e12fdfdbcbcb3336c0e4

See more details on using hashes here.

Provenance

The following attestation bundles were made for datialog-1.3.0-py3-none-any.whl:

Publisher: build_and_publish.yml on datialog-app/datialogpy

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page