powerbihelper
AI-powered Power BI report generator. Chat with Ollama or Claude to build reports, test visuals, and analyze data.
Install
pip install powerbihelper
Quick Start
powerbihelper # opens browser chat UI
Configure your LLM (Ollama or Claude) in the sidebar, then chat:
- "Build a monthly sales dashboard with 4 KPI cards and trend charts"
- "Create an airline reliability report with PIREP analysis by ATA chapter"
- "Validate the report project at ./MyProject"
Features
- Browser Chat UI — talk to Ollama/Claude to build Power BI reports
- PBIP Project Generator — create complete projects from scratch (no Desktop needed)
- PBIR/TMDL Library — read, write, validate report and model files
- Visual Testing — headless Playwright-based testing with regression detection
- DAX Execution — query live Power BI Desktop models
- MCP Server — integrate with Claude Code (13 tools)
- Data Quality — null rates, duplicates, referential integrity checks
- Model Documentation — auto-generate data dictionary and measure catalog
CLI Commands
powerbihelper # browser chat UI (default)
powerbihelper ui # same as above
powerbihelper agent # terminal chat with Ollama
powerbihelper generate "prompt" # one-shot report generation
powerbihelper serve # MCP server for Claude Code
powerbihelper dax "EVALUATE X" # run DAX query
powerbihelper pbir read ./proj # parse PBIP project
powerbihelper pbir validate . # validate structure
powerbihelper tmdl ./model.tmdl # parse TMDL file
powerbihelper test --visual x.js # headless visual testing
powerbihelper cdp status # check Desktop CDP bridge
Use with Claude Code
Add to ~/.claude/settings.json:
{
"mcpServers": {
"powerbihelper": {
"command": "powerbihelper",
"args": ["serve"]
}
}
}
Use with Ollama
ollama pull gemma4
powerbihelper agent --model gemma4
Optional Extras
pip install powerbihelper[mcp] # Claude Code MCP server
pip install powerbihelper[testing] # Playwright visual testing
pip install powerbihelper[all] # everything
License
MIT
Metadata
Release files for powerbihelper 0.2.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| powerbihelper-0.2.0.tar.gz | 85.5 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| powerbihelper-0.2.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 162.2 kB
Release files / powerbihelper-0.2.0.tar.gz
| Download URL | powerbihelper-0.2.0.tar.gz |
|---|---|
| Size | 85.5 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
013c27601a9177f00dedad11c0cc6bad3a2c8a0d0312b36c77b86d3726c37c97
|
|
BLAKE2b-256 checksum How to use checksums |
e94ef8526c981a85445bd564780aaa4c9ba1441fbd8df91d1e364405df2186fe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Release files / powerbihelper-0.2.0-py3-none-any.whl
| Download URL | powerbihelper-0.2.0-py3-none-any.whl |
|---|---|
| Size | 76.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
16747795f5356cd22980c2e93ec795ea32f158603260c339480804424df28eab
|
|
BLAKE2b-256 checksum How to use checksums |
ebce77e4b37404cb8741067c3cd9b673c0f5e376eabbe4920fde303e32bfe0ff
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Security for powerbihelper 0.2.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.