querymind-cli 0.1.0

CLI AI Data Analyst — query CSV and Excel files in plain English

🧠 QueryMind

Ask questions about your data in plain English. No SQL. No code. Just a terminal.

QueryMind is a CLI data analyst that lets you load a CSV or Excel file and query it conversationally — right in your terminal.

>> top 5 regions by sales
>> which month had the highest profit?
>> average spend by payment method in ascending order
>> show sales in sheet Orders by customer segment

---

Install

pip install querymind-cli

Requirements:

• Python 3.10+
• Ollama (optional — enables LLM fallback for complex queries)

If you want LLM support, install Ollama and pull the model:

ollama pull phi

---

Quickstart

querymind

You'll be prompted to:

1. Enter a CSV or Excel file path
2. Select sheets (Excel only)
3. Map your metric and dimension columns
4. Start asking questions

---

What it can do

Query	What happens
top 5 products by revenue	Ranked bar chart in terminal
which region had lowest sales	Ascending comparison with insight
average profit by category	Mean aggregation per group
sales trend over time monthly	Monthly groupby on datetime column
show sales in sheet Orders by region	Sheet-scoped query
which manager had the most sales	Cross-sheet join (Orders + Users)
sales by region in ascending order	Explicit sort order

---

Supported file formats

Format	Extension
CSV	.csv, .tsv
Excel	.xlsx, .xls, .xlsm

Auto-detects: encoding (UTF-8 BOM, latin-1), delimiter (comma, semicolon, tab, pipe), packed integer dates (DDMMYYYY, YYYYMMDD).

---

How it works

Your query
    ↓
InputGuard       — blocks gibberish and sensitive input
    ↓
InterpreterAgent — rule-based intent extraction (fast, no LLM needed)
    ↓
LLMInterpreter   — Ollama fallback for complex queries (optional)
    ↓
JoinResolver     — auto-detects and performs cross-sheet joins
    ↓
Analyzer         — pandas groupby / aggregation
    ↓
InsightGenerator — formats result + ASCII bar chart

---

Beta

QueryMind is in active development. If something breaks or a query gives a wrong answer, please open an issue with:

• Your query
• The column names in your file (no need to share actual data)
• The output you got

This feedback directly shapes what gets fixed next.

---

License

MIT