Skip to content

QUICKSTART-USER.adoc

Latest commit

 

History

History
154 lines (114 loc) · 4.35 KB

QUICKSTART-USER.adoc

File metadata and controls

154 lines (114 loc) · 4.35 KB
Raw

statistikles — Quick Start for Users

Table of Contents

What is statistikles?

Statistikles is a neurosymbolic statistical analysis assistant. An LLM routes your natural-language question to the correct statistical function; Julia performs all mathematical computation. Every number in a response is computed by a verified Julia function — never by neural inference.

Prerequisites

Before you begin, ensure you have:

Platform Additional Requirements

Linux

None beyond Julia and just

macOS

None beyond Julia and just

Windows

A POSIX shell (Git Bash or WSL) — the Justfile recipes use bash

Install

Option 1: Native Julia

# Clone and set up
git clone https://github.com/hyperpolymath/statistikles.git
cd statistikles
just setup

just setup resolves and installs the Julia package dependencies (Pkg.instantiate()) into the project environment. Nothing is installed outside the cloned directory and your Julia depot (~/.julia).

If you prefer not to use just, the equivalent raw command is:

julia --project=. -e 'using Pkg; Pkg.instantiate()'

Option 2: Container

No local Julia install required — just Podman or Docker:

git clone https://github.com/hyperpolymath/statistikles.git
cd statistikles
podman build -t statistikles:latest -f Containerfile .
podman run --rm -it statistikles:latest

(docker works identically in place of podman.) This builds the official docker.io/library/julia:1.10 base image with the project instantiated and precompiled, then runs it as a non-root user. Expected output matches "First Run" below.

First Run

just run

Expected output — a startup banner:

  ┌─────────────────────────────────────────────────────────────┐
  │  Statistikles v0.1.0                                        │
  │  Neurosymbolic Statistical Analysis Assistant              │
  │                                                             │
  │  DESIGN: LLM = natural language router/interpreter          │
  │          Julia = verified symbolic computation              │
  │                                                             │
  │  Every number is computed, never hallucinated.              │
  └─────────────────────────────────────────────────────────────┘

followed by either:

  • Connected to LM Studio (…​) and an interactive chat session, if an LM Studio server is running at http://localhost:1234/v1; or

  • Cannot connect to LM Studio at http://localhost:1234/v1 and an offline demo (Running offline demo instead…​) that computes descriptive statistics, a t-test, an ANOVA, a correlation, and more — no LLM needed.

To run the offline examples directly:

julia --project=. -e 'using Statistikles; run_examples()'

Self-Diagnostic

If something isn’t working:

just doctor

This checks required tools and common setup issues.

To attempt automatic repair:

just heal

Get Help

Uninstall

Statistikles installs nothing outside the cloned directory and the Julia package depot, so removal is:

rm -rf statistikles          # delete the clone
julia -e 'using Pkg; Pkg.gc()'   # optional: garbage-collect unused packages

Next Steps

  • Read the README for full feature overview

  • Read the EXPLAINME for architecture and design decisions

  • Try just tour for a guided walkthrough