xai-rai 0.1.2

Unified multimodal explainability and responsible AI framework

(BETA) BitsXAI

Model Agnostic XAI + RAI Middleware Layer Python Package | Bitstek.io

Multi-Modal Explainable and Responsible AI Python Package - V1

A modular Python SDK for Explainable AI (XAI) and Responsible AI (RAI), combining model explainability, trust diagnostics, and multi-modal routing in a unified framework.

---

Description

Python SDK for modular Explainable & Responsible AI : model adapters, explainers, risk diagnostics, and multi-modal routing in one framework.

---

Developer

Developed and maintained by @8bitjawad

Overview

This project is designed to provide a structured framework for building, testing, and extending explainability and responsible AI workflows.

Instead of using isolated tools for explanations, fairness checks, and robustness analysis, the SDK unifies them under a layered architecture.

It provides:

• Explainability algorithms (SHAP, LIME, counterfactuals etc.)
• Responsible AI diagnostics (bias, drift, robustness)
• Pluggable model adapters for multiple modalities
• Routing/orchestration across components
• Visualization and reporting support

Supported modalities:

• Tabular models
• NLP
• Vision Models
• LLMs
• Text-to-Image (TTI) models

---

Why XAI/RAI Instead of Using Individual Libraries?

Libraries like SHAP or LIME solve explanation problems individually.

This project aims to provide:

• A unified SDK abstraction
• Explainability + Responsible AI in one system
• Multi-modal support via adapters
• Routing logic across models and modalities
• Extensible architecture for research and deployment
• LLM Explanations for ease of understanding

xai_rai combines explainability, responsible AI diagnostics, multi-modal orchestration, and unified result abstractions within a single extensible SDK.---

Architecture

xai_rai follows a layered, result-centric architecture:

Facade
↓
Pipeline
↓
Analyzers / Explainers
↓
Inference Engines / Adapters
↓
Unified Result Objects
↓
Charts / Reports / UI
---

Core Features

Explainability

• SHAP feature attribution
• LIME local explanations
• Counterfactual explanations
• Natural language narratives
• Multi-modal explanation pipelines

---

Responsible AI

• Fairness diagnostics
• Population Stability Index (PSI) drift detection
• Robustness checks
• Confidence/anomaly scoring

---

Usage

Installation

Base

pip install xai-rai

Text-to-Image

pip install xai-rai[tti]

Vision

pip install xai-rai[vision]

Full Installation

pip install xai-rai[full]

Example Usage

Quickstart — Text-to-Image XAI

````md id="jlwm8k" ```

from PIL import Image

from xai_rai import TextToImageExplainer

explainer = TextToImageExplainer(
    device="cpu",
    enable_caption_analysis=True,
)

image = Image.open("generated.png")

result = explainer.explain(
    image=image,
    prompt="a futuristic cyberpunk city",
)

print(result.summary())

Design Philosophy

The framework follows:

Modular Architecture

Each concern lives in its own layer.

---

Adapter Pattern

Models are accessed through standardized interfaces.

---

Separation of Concerns

Explainability and Responsible AI diagnostics are distinct modules.

---

Extensibility

New:

• modalities
• explainers
• diagnostics
• visualization layers

can be added without changing the whole system.

---

Roadmap

Current

• Tabular explainability
• NLP explainability
• Vision explainability
• LLM explainability
• Text-to-image explainability
• SHAP / LIME integration
• Counterfactual explanations
• Multi-modal result objects
• RAI diagnostics
• Trust / alignment analysis

---

Example Use Cases

xai_rai can support:

• Explainable healthcare models
• Explainable and Responsible AI for Businesses
• Responsible AI and toxicity screens

---

Public APIs

from xai_rai import (
    TabularExplainer,
    VisionExplainer,
    NLPExplainer,
    LLMExplainer,
    TextToImageExplainer,
)

Contribution

This project is currently in Beta and is being actively improved and worked on. If you wish to contribute, please follow the following guidelines: Keep modules modular and loosely coupled Follow the layered architecture Add type hints where possible Prefer result-centric APIs over raw dictionaries Include lightweight tests for new features Keep public APIs clean and stable

For major architectural changes or new modality integrations, open an issue/discussion first before implementing large changes.