Decisify
Decisify is a Python package that leverages generative AI to explain decisions made by optimization models.
Introduction
Mathematical optimization is a critical tool in operations research, enabling businesses to make data-driven decisions that maximize efficiency and minimize costs. However, the complexity of these models often makes it difficult for stakeholders to understand and trust the decisions being made.
Decisify addresses this challenge by using generative AI to provide clear, understandable explanations for the decisions produced by optimization models. By enhancing transparency and trust, Decisify aims to drive greater adoption of optimization techniques across diverse industries.
Features
- Explain optimization model decisions using generative AI
- Improve transparency and trust in operations research
- Facilitate the adoption of optimization techniques in various industries
Installation
You can install Decisify using pip:
pip install decisify
Usage
Here's a simple example of how to use Decisify:
import decisify
# Your optimization model code here
(1) Just define the Pydantic Models for (a) Input (b) Output
(2) Concrete implementation of optimization model
(3) A method to read, the solution
Now, you are read to use decisify, its simple from this point onwards
# Generate explanations for the model's decisions
trnsprt_model = TransportationModel()
solution = trnsprt_model.get_solution(input_data)
print(solution.model_dump_json())
interrogator = GurobiInterrogator(trnsprt_model, input_data)
answer = interrogator.answer("What is the optimal solution for the transportation problem?")
print(answer)
answer = interrogator.answer("How many factories and how many distribution centers are there?")
print(answer)
#Now, lets assume the user wants to change the supply at warehouse W1 to 20
answer = interrogator.what_if("the courier company just doubled the transportation costs, how does this affect the total cost?")
print(answer)
answer = interrogator.what_if("The demand at customer C1 has increased by 100 times, how does this affect the total cost?")
print(answer)
Contributing
We welcome contributions to Decisify! Please see our contributing guidelines for more information.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contact
For any questions or suggestions, please contact us at support@decisify.ai.
Metadata
Release files for decisify 0.1.0
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 | Actions |
|---|---|---|---|---|
| decisify-0.1.0.tar.gz | 14.2 kB | Without provenance | Details for decisify-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| decisify-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for decisify-0.1.0-py3-none-any.whl |
Total release size: 21.2 kB
Release files / decisify-0.1.0.tar.gz
| Download URL | decisify-0.1.0.tar.gz |
|---|---|
| Size | 14.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f38d44def0540f0be4b89349578725f9db30746f355177d6e12699e04d12e67a
|
|
BLAKE2b-256 checksum How to use checksums |
2cbbb5a7310852e92d1c2141bae1dc7c162696740a7259c909d315ca2567fb6d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.12.3
|
Release files / decisify-0.1.0-py3-none-any.whl
| Download URL | decisify-0.1.0-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
61ee7d2a7b0fb6a75efa94d1211a46dd9d89738139726b7139ff6519c1c7aa41
|
|
BLAKE2b-256 checksum How to use checksums |
9b9d72ef5610a3c1f87e72bd4a2bfcce08bedfa9558c100b491d22eb84629a20
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/5.1.1 CPython/3.12.3
|
Security for decisify 0.1.0
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.