Skip to main content

✔ Power BI Automation Using Open AI API

Problem Statement:

  • Power BI documentation is essential for maintaining the accuracy and integrity of data models, ensuring compliance with regulations, and improving collaboration and efficiency across teams.
  • It is a time-consuming task that requires more human intervention and is highly error prone.
  • Our model aims to automate this process using OpenAI's NLP capabilities.

Purpose:

  • The purpose of our Power BI model documentation automation is to provide a Time-saving and Accurate solution for fetching pbix details. Below are the purpose that our model is fulfilling:
    • Automating the Power BI model documenter using one of the most efficient GPT-3 architecture i.e. text-davinci-002.
    • Fetched the Measures, Source Information, and Model Relationships attributes from the Power BI report.
    • Wrote back the Measures and Modification Descriptions and displayed on hovering the respective properties in updated pbit files.
    • Presented the output into three directories, namely EXCEL, JSON and Updated PBIT.

Input/Output Deliverables:

- Input: 
    - Single File
    - Multiple Files
    - A Folder

- Output:
    - Excel Directory
    - JSON Directory
    - Updated PBIT Directory

Features:

  • Implemented following features in our model:
    1. Features in JSON Deliverables:

      • DataModelSchema Generation: Generated the datamodelschema file for the respective pbit file and stored it in JSON format.
    2. Features in EXCEL Deliverables:

      • Measure Sheet:
        • Measure Name
        • Measure Expression
        • Measure Data Type
        • Measure Description
      • Source Information Sheet:
        • Table No
        • Table Name
        • Table Mode
        • Table Type
        • Table Source
        • Original Table Name
        • Table Query
        • Modification
        • Modification Description
      • Relationships Sheet:
        • From Table
        • From Column
        • To Table
        • To Column
        • State
        • Direction
        • Cardinality
    3. Features in UPDATED PBIT Deliverables:

      • Dynamic Hover Description: Made the Measures and Modifications Description to hover on each respective properties.

Prerequisites:

  • In order to use this script, one need to ensure to met the following requirements:
    • A Power BI Desktop installation (version - 2.115.663.0 64-bit).
    • A valid API secret key for OpenAI's NLP capabilities.
    • Python 3.7 or later installed on your machine.
    • Access to the Power BI models that you want to document.


✔ Package Description

PyPbitExtractor

- Created a python package for the given python script and published it on https://pypi.org/

Package Usage

- from PyPbitExtractor import Extractor
    - This command will install all the uninstalled required libraries used in script.
- Extractor.api()
    - This command will prompt user for Open API Secret Key.
- Extractor.main()
    - This will prompt user for input of file selection and thereafter the repective file/folder.

Package Installation

pip install PyPbitExtractor

Metadata

Release files for PyPbitExtractor 1.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for PyPbitExtractor 1.2.0
File Size Uploaded Provenance
pypbitextractor-1.2.0.tar.gz 9.8 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for PyPbitExtractor 1.2.0
File Interpreter ABI Platform
pypbitextractor-1.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 19.0 kB

Release files / pypbitextractor-1.2.0.tar.gz

Download URL pypbitextractor-1.2.0.tar.gz
Size 9.8 kB
Tags Source
SHA-256 checksum
How to use checksums
4e64ff1f87e751bfe8a878c3ff654b7695720daf49a279505c664d20ad49d900
BLAKE2b-256 checksum
How to use checksums
b1d0c88cc4964a2730b7a87b251cfbef74f03cf968aa5751ec3ea98993df2b04
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.2

Release files / pypbitextractor-1.2.0-py3-none-any.whl

Download URL pypbitextractor-1.2.0-py3-none-any.whl
Size 9.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f52da12c2d31f521e309c6d6371836026981688b8f2ccc8f2159caa86dda43e0
BLAKE2b-256 checksum
How to use checksums
bb94c91c75eb327660e84bd85f3f9765de99384e963e08a9c06564bda0c6acf1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.2

Security for PyPbitExtractor 1.2.0

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.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page