Update README.md

README.md

@@ -1,100 +1,352 @@
 ---
 license: apache-2.0
+
 language:
 - en
 
-base_model:
-- google/flan-t5-small
-
-library_name: transformers
+base_model: google/flan-t5-small
+base_model_relation: adapter
 
+library_name: peft
 pipeline_tag: text2text-generation
 
+datasets:
+- syed7741/aegis-industrial-ai-dataset
+
 tags:
+- peft
+- lora
+- flan-t5
 - rag
 - industrial-ai
 - generative-ai
 - semantic-search
-- sentence-transformers
-- fastapi
 - document-intelligence
 - robotics
 - predictive-maintenance
 - worker-safety
 - workflow-automation
+- fastapi
 - huggingface
 ---
 
 # AEGIS Industrial RAG Assistant
 
-**AEGIS Industrial RAG Assistant** is the Retrieval-Augmented Generation component of the AEGIS AI industrial intelligence platform.
+**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 project demonstrates how an industrial AI application can combine:
+The adapter was trained on top of:
 
-- Hugging Face datasets
-- semantic search
-- sentence-transformer embeddings
-- vector retrieval
-- local language models
-- FastAPI
-- React / TypeScript
-- source attribution
-- industrial knowledge retrieval
+```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.
 
 ---
 
-## Important Status
+# Model Status
+
+✅ **This repository now contains a genuinely trained LoRA adapter.**
 
-This repository currently documents the **AEGIS RAG model pipeline and model configuration**.
+It is no longer only a documentation repository.
 
-It is **not currently a separately fine-tuned language model checkpoint**.
+The trained adapter weights are stored in:
 
-The current prototype uses:
+```text
+adapter_model.safetensors
+```
+
+The LoRA configuration is stored in:
 
-### Language Model
+```text
+adapter_config.json
+```
 
-`google/flan-t5-small`
+The adapter was trained locally on CPU using the public AEGIS synthetic industrial dataset.
 
-### Embedding Model
+---
 
-`sentence-transformers/all-MiniLM-L6-v2`
+# Base Model
 
-### Knowledge Dataset
+```text
+google/flan-t5-small
+```
 
-`syed7741/aegis-industrial-ai-dataset`
+The original FLAN-T5-small parameters remain the base model.
 
-A future version of this repository is planned to contain a genuinely fine-tuned AEGIS model or adapter trained for industrial question answering.
+AEGIS fine-tuning was performed using parameter-efficient LoRA adaptation rather than full-model fine-tuning.
 
 ---
 
-# AEGIS AI
+# Training Dataset
+
+The adapter was trained using:
 
-AEGIS AI is an end-to-end industrial artificial intelligence platform designed as an AI engineering portfolio project.
+```text
+syed7741/aegis-industrial-ai-dataset
+```
 
-The platform explores:
+The dataset currently contains:
+
+```text
+64 synthetic industrial records
+```
+
+covering:
 
-- Retrieval-Augmented Generation
-- AI Agents
-- Industrial Document Intelligence
 - Worker Safety
 - Predictive Maintenance
 - Robot Monitoring
-- Computer Vision
+- Vision Inspection
 - AI Alerts
-- Factory Operations
 - Workflow Automation
-- Real-Time Monitoring
+- 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.
+
+Configuration:
+
+| 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 the 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
+```
+
+Then 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()
+```
+
+PEFT adapters are loaded together with their original base model.
+
+---
+
+# 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.
+```
 
 ---
 
-# RAG Architecture
+# AEGIS RAG Architecture
 
-The current pipeline is:
+The trained adapter is designed to work as part of the larger AEGIS Retrieval-Augmented Generation system.
 
 ```text
 User Question
       ↓
-React / TypeScript UI
+React / TypeScript
       ↓
 FastAPI
       ↓
@@ -102,14 +354,186 @@ AEGIS RAG Service
       ↓
 Sentence Transformer
       ↓
-384-Dimensional Query Embedding
-      ↓
-Local Vector Search
+Semantic Vector Search
       ↓
-Relevant Industrial Knowledge
+Retrieved Industrial Knowledge
       ↓
-FLAN-T5
+AEGIS LoRA Adapter
       ↓
-Grounded Answer
+Grounded Response
       ↓
-Source Attribution
+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 include:
+
+- 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
+- RAG
+- Document intelligence
+- Semantic search
+- Conversational AI
+- Multilingual AI
+- AI backend APIs
+- Workflow automation
+- Grounded generation
+- Source attribution
+
+---
+
+# Safety Notice
+
+The AEGIS training dataset currently 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