Projects

Browse Projects

Browse projects tagged with "NLP".

Tags

All Tags admin-dashboard anomaly-detection API-integration authentication automation AWS azure benchmarking big-data browser-automation churn-prediction CI-CD classification CLI clustering computer-vision CRUD customer-segmentation data-analysis data-pipeline dataclasses deep-learning deployment Docker docker email explainability fastapi feature-engineering finance fine-tuning flask game generative-ai guardrails GUI hugging-face huggingface hypothesis-testing image-classification IQR-capping jupyter label-encoding LLM log-analysis logistic-regression machine-learning min-max-scaling mlflow mlops MLOps model-registry neural-network NLP OOP pandas productivity prompt-engineering pyspark python RAG regression resampling REST-API retention-strategy scikit-learn scipy scope scripting semantic-search sentiment-analysis seq2seq serverless shap slack statistical-analysis tabular-data terminal terminal-ux text-classification text-generation time-series transfer-learning transformer unsupervised-learning vector-database visualisation web-app web-scraping xgboost zero-shot

Order

A–Z Newest Oldest

AI Portfolio Assistant

Web

I built a conversational AI assistant directly into my portfolio site. Recruiters and visitors can ask anything about my projects, skills, and background — and get grounded, cited answers in real time, powered by RAG (Retrieval-Augmented Generation) and Llama 3.3 70B via Groq.

LLM RAG NLP flask web-app machine-learning API-integration REST-API admin-dashboard CI-CD deployment

GitHub Live Details

AWS Lambda & Amazon Bedrock: Benchmarking TF-IDF, LSTM, and Zero-Shot LLM Sentiment Analysis

Ai-ml

A full ML pipeline benchmarking TF-IDF + Logistic Regression, a Keras LSTM, and Claude Haiku via Amazon Bedrock on 50,000 IMDb reviews. The winning model is deployed live as a serverless REST API on AWS Lambda with a Flask frontend.

NLP machine-learning deep-learning deployment flask REST-API data-analysis visualisation python web-app LLM sentiment-analysis serverless AWS Docker text-classification benchmarking

GitHub Live Details

CV Gap Analyser — Semantic Job Matching with HuggingFace and Pinecone

Ai-ml

Semantic CV vs job description analysis identifying missing skills and producingactionable gap recommendations. HuggingFace embeddings for match scoring, Pineconefor a searchable job library, ROUGE for ATS keyword alignment. Accepts jobdescriptions as text, PDF, or URL via trafilatura extraction.

NLP machine-learning LLM deployment REST-API docker CI-CD jupyter web-app huggingface vector-database semantic-search

GitHub Live Details

Email Subject Generator — T5 Transformer

Ai-ml

T5-small fine-tuned on the AESLC corpus (14k Enron email/subject pairs) to generate professional subject lines from an email body. Five suggestions returned at varying temperature levels — from beam-search conservative to top-p creative sampling.

deep-learning NLP text-generation transformer seq2seq fine-tuning azure deployment REST-API CI-CD jupyter web-app

GitHub Live Details

LLM Document Summarizer — LLMOps with Amazon Bedrock

Ai-ml

PDF document summarizer using Amazon Bedrock (Claude Haiku) with production LLMOps patterns: versioned YAML prompt templates, automated ROUGE evaluation, Bedrock Guardrails for PII redaction, and MLflow tracking of every inference call. Deployed on Azure App Service.

LLM AWS azure deployment web-app benchmarking jupyter REST-API docker CI-CD NLP prompt-engineering mlops guardrails

GitHub Live Details

Language Detector — Character N-gram Classification

Ai-ml

Detects the language of any text across 22 languages using character n-gram TF-IDF features. Returns the top 3 languages with confidence scores and a plain-English explanation of the character patterns driving the detection.

NLP classification machine-learning text-classification azure deployment REST-API docker CI-CD jupyter web-app benchmarking

GitHub Live Details

SMS Spam Classifier

Ai-ml

SMS spam detection comparing three approaches — Naive Bayes, SVM, and Amazon Bedrock (Claude Haiku zero-shot) — on the same test set. Every prediction comes with a plain-English explanation of the words that drove it. Class imbalance addressed explicitly. Deployed on Azure App Service.

classification machine-learning NLP text-classification flask azure deployment explainability resampling zero-shot jupyter scikit-learn benchmarking AWS

GitHub Live Details

Telco Customer Churn Predictor

Data

Churn prediction with plain-language risk explanations a retention team can act on. Logistic Regression wins (ROC-AUC 0.8362), benchmarked against Amazon Bedrock Claude Haiku 4.5 zero-shot — tied at 70%. Flask API on Azure.

machine-learning AWS azure flask jupyter deployment benchmarking data-analysis statistical-analysis feature-engineering visualisation web-app API-integration LLM REST-API data-pipeline label-encoding resampling python NLP xgboost logistic-regression shap explainability churn-prediction classification tabular-data model-registry zero-shot scikit-learn

GitHub Live Details ⏳ Loading Period

Browse Projects

AI Portfolio Assistant

AWS Lambda & Amazon Bedrock: Benchmarking TF-IDF, LSTM, and Zero-Shot LLM Sentiment Analysis

CV Gap Analyser — Semantic Job Matching with HuggingFace and Pinecone

Email Subject Generator — T5 Transformer

LLM Document Summarizer — LLMOps with Amazon Bedrock

Language Detector — Character N-gram Classification

SMS Spam Classifier

Telco Customer Churn Predictor

No projects found