README.md

---
license: apache-2.0

language:
- en

base_model: google/flan-t5-small
base_model_relation: adapter

library_name: peft
pipeline_tag: text-generation

datasets:
- syed7741/aegis-industrial-ai-dataset

tags:
- peft
- lora
- flan-t5
- rag
- industrial-ai
- generative-ai
- semantic-search
- document-intelligence
- robotics
- predictive-maintenance
- worker-safety
- workflow-automation
- fastapi
- huggingface
---

# AEGIS Industrial RAG Assistant

**AEGIS Industrial RAG Assistant** is a LoRA/PEFT adapter fine-tuned on the AEGIS Industrial AI Dataset for industrial question answering and Retrieval-Augmented Generation experiments.

The adapter was trained on top of:

```text
google/flan-t5-small
```

using:

```text
LoRA / PEFT
```

The project is part of **AEGIS AI**, an end-to-end industrial artificial intelligence platform combining RAG, document intelligence, semantic search, AI agents, computer vision, predictive maintenance, robotics monitoring, and workflow automation.

---

# Model Status

✅ **This repository contains a genuinely trained LoRA adapter.**

The trained adapter weights are stored in:

```text
adapter_model.safetensors
```

The LoRA configuration is stored in:

```text
adapter_config.json
```

The adapter was trained locally on CPU using the public AEGIS synthetic industrial dataset.

---

# Base Model

```text
google/flan-t5-small
```

The original FLAN-T5-small parameters remain the base model.

AEGIS fine-tuning was performed using parameter-efficient LoRA adaptation rather than full-model fine-tuning.

---

# Training Dataset

The adapter was trained using:

```text
syed7741/aegis-industrial-ai-dataset
```

The dataset currently contains:

```text
64 synthetic industrial records
```

covering:

- Worker Safety
- Predictive Maintenance
- Robot Monitoring
- Vision Inspection
- AI Alerts
- Workflow Automation
- Document Assistant
- Factory Status

Industries represented include:

- Manufacturing
- Oil & Gas
- Warehousing / Logistics
- Robotics

---

# Training Data Preparation

The original 64 industrial records were split before prompt expansion to reduce leakage between the training and evaluation sets.

Training split:

```text
54 records
```

Evaluation split:

```text
10 records
```

Each source record was transformed into multiple instruction/question-answer formats.

Final training examples:

```text
162
```

Final evaluation examples:

```text
30
```

---

# Fine-Tuning Method

The model was trained using **LoRA — Low-Rank Adaptation** through Hugging Face PEFT.

| Parameter | Value |
|---|---:|
| Base model | google/flan-t5-small |
| Method | LoRA / PEFT |
| Task | SEQ_2_SEQ_LM |
| LoRA rank | 4 |
| LoRA alpha | 16 |
| LoRA dropout | 0.05 |
| Target modules | q, v |
| Learning rate | 3e-4 |
| Batch size | 1 |
| Gradient accumulation | 4 |
| Epochs | 2 |
| Device | CPU |

---

# Trainable Parameters

The LoRA configuration trained:

```text
172,032 parameters
```

out of approximately:

```text
77.1 million total parameters
```

Trainable percentage:

```text
0.223%
```

This demonstrates parameter-efficient adaptation without retraining the complete FLAN-T5-small model.

---

# Training Results

## Epoch 1

```text
Training Loss:   1.6501
Evaluation Loss: 1.1663
```

## Epoch 2

```text
Training Loss:   1.1880
Evaluation Loss: 0.7744
```

Both training and evaluation loss decreased during the two training epochs.

---

# Fine-Tuned Test Result

Test question:

```text
What should I do before maintaining CONV-02?
```

Fine-tuned adapter response:

```text
isolate all energy sources, apply lockout/tagout, verify zero-energy state, and record the responsible technician.
```

This example demonstrates that the trained adapter learned the expected industrial safety response from the AEGIS training examples.

---

# Using the Adapter

Install the required libraries:

```bash
pip install transformers peft torch sentencepiece
```

Load the AEGIS adapter:

```python
from transformers import (
    AutoModelForSeq2SeqLM,
    AutoTokenizer,
)

from peft import (
    PeftConfig,
    PeftModel,
)


ADAPTER_ID = (
    "syed7741/"
    "aegis-industrial-rag-assistant"
)


config = PeftConfig.from_pretrained(
    ADAPTER_ID
)


base_model = (
    AutoModelForSeq2SeqLM
    .from_pretrained(
        config.base_model_name_or_path
    )
)


tokenizer = (
    AutoTokenizer
    .from_pretrained(
        ADAPTER_ID
    )
)


model = PeftModel.from_pretrained(
    base_model,
    ADAPTER_ID,
)


model.eval()
```

---

# Example Inference

```python
prompt = """
industrial qa:
Context: Before maintenance on CONV-02,
isolate all energy sources, apply lockout/tagout,
verify zero-energy state, and record the responsible
technician.

Question:
What should I do before maintaining CONV-02?
""".strip()


inputs = tokenizer(
    prompt,
    return_tensors="pt",
)


output = model.generate(
    **inputs,
    max_new_tokens=96,
    num_beams=4,
    do_sample=False,
)


answer = tokenizer.decode(
    output[0],
    skip_special_tokens=True,
)


print(answer)
```

Expected response:

```text
isolate all energy sources, apply lockout/tagout, verify zero-energy state, and record the responsible technician.
```

---

# AEGIS RAG Architecture

The trained adapter is designed to work as part of the larger AEGIS Retrieval-Augmented Generation system.

```text
User Question
      ↓
React / TypeScript
      ↓
FastAPI
      ↓
AEGIS RAG Service
      ↓
Sentence Transformer
      ↓
Semantic Vector Search
      ↓
Retrieved Industrial Knowledge
      ↓
AEGIS LoRA Adapter
      ↓
Grounded Response
      ↓
Source Attribution
```

---

# Embedding Model

The AEGIS RAG pipeline currently uses:

```text
sentence-transformers/all-MiniLM-L6-v2
```

Embedding dimensions:

```text
384
```

The embedding model performs semantic retrieval over the industrial knowledge base before relevant context is supplied to the language model.

---

# Technology Stack

## AI / Machine Learning

- Hugging Face
- Transformers
- PEFT
- LoRA
- FLAN-T5
- Sentence Transformers
- Retrieval-Augmented Generation
- Semantic Search
- Vector Embeddings

## Backend

- Python
- FastAPI
- REST APIs
- PostgreSQL

## Frontend

- React
- TypeScript
- Material UI

## AI Platform Components

- RAG
- AI Agents
- Document Intelligence
- Computer Vision
- Predictive Maintenance
- Robot Monitoring
- Worker Safety
- Workflow Automation

---

# Current AEGIS Capabilities

Implemented:

- ✅ Public Hugging Face industrial dataset
- ✅ Dataset loader
- ✅ Document construction
- ✅ Text chunking
- ✅ Sentence-transformer embeddings
- ✅ Vector indexing
- ✅ Semantic retrieval
- ✅ Local language model
- ✅ FastAPI RAG endpoint
- ✅ React / TypeScript integration
- ✅ Retrieved-source attribution
- ✅ LoRA/PEFT fine-tuning
- ✅ Trained adapter checkpoint
- ✅ Hugging Face model repository
- ✅ CPU-based training pipeline
- ✅ No paid LLM API required

---

# Development Roadmap

Planned improvements:

- Larger industrial training dataset
- Arabic + English training data
- Arabic industrial terminology
- Multilingual question answering
- RAG evaluation suite
- Base-model vs fine-tuned-model benchmarking
- Hybrid semantic + keyword retrieval
- Reranking
- AI agents
- Conversation memory
- Document ingestion
- Computer vision integration
- Workflow automation
- Cloud deployment

---

# Enterprise AI Engineering

AEGIS demonstrates concepts applicable to enterprise AI systems including:

- LLM application development
- Parameter-efficient fine-tuning
- Retrieval-Augmented Generation
- Document intelligence
- Semantic search
- Conversational AI
- Multilingual AI
- AI backend APIs
- Workflow automation
- Grounded generation
- Source attribution

---

# Safety Notice

The AEGIS training dataset contains **synthetic industrial records** created for:

- AI engineering experimentation
- learning
- prototyping
- research
- portfolio demonstration

The model must not be treated as an authoritative source for industrial safety or operational decisions.

Its outputs must not replace:

- approved operating procedures
- manufacturer documentation
- workplace safety requirements
- engineering review
- regulatory requirements
- qualified professional judgment

---

# Related Work

## Dataset

```text
syed7741/aegis-industrial-ai-dataset
```

## Model / Adapter

```text
syed7741/aegis-industrial-rag-assistant
```

## GitHub

```text
github.com/syedasim7741/AEGIS-AI
```

---

# Author

**Sayyad Asim**

AI Engineering • RAG • AI Agents • LLM Fine-Tuning • Document Intelligence • Computer Vision • Robotics • Industrial AI