🤖 Build AI-powered customer agents for multi-channel messaging, enhancing engagement and providing real-time support for enterprise applications.

A Python library to train task-specific LLMs without training data, for offline NLP and Text Classification tasks, such as Guardrail Models and Intent Classification 🤖🚀

This is an intelligent safety chatbot designed to assist users in matters of personal safety and emergency guidance. It acts as a digital safety companion that not only responds empathetically but also provides real-world help when needed. The system can identify user intent, offer safety tips, and locate the nearest safe places such as hospitals.

building a chinese dialogue system based on the newest version of rasa(基于最新版本rasa搭建的对话系统)

The Riatix NL-to-SQL Engine introduces an alternate approach to natural-language querying - one that focuses on schema-aware intent translation instead of direct SQL generation.

Intent classifier with Pytorch for short conversational utterances (e.g., booking, cancellations, product or account inquiries, support requests, and greetings) with training, evaluation, and inference for multi-class intent detection.

Bayesian Network & Hidden Markov Model implementation for customer intent classification and text denoising | CS5100 AI Project

An NLP-integrated Visual Novel Game that redefines the mystery solving genre with dynamic deduction. Go beyond static puzzles and branching narratives. This project focuses on creating a living investigation where player input, processed via Natural Language Processing (NLP), genuinely drives the narrative, beyond static gameplay.

AI-powered speech-to-text and text-to-speech platform with intelligent analysis using Deepgram. Features sentiment analysis, topic detection, intent recognition, and multiple voice personas.

Fit-for-purpose AI orchestration approach. Exploring how deterministic code, lightweight models, and selective escalation to LLMs can build faster, cheaper, and more reliable workflows. Not a product — just systems design patterns and prototypes.

A PyTorch-based NLP chatbot that uses entity extraction for pincode lookups and general queries in India.

Chat to your Database GenAI Chatbot

A machine learning system for classifying customer intents in Vietnamese conversations, designed for e-commerce customer service applications.

A conversational AI flight booking chatbot with ML-powered intent classification, transaction management, and natural language processing for Berry Airlines.

Classification of user intents in their requests to the university QA chatbot using the RuBERT, its modifications, and various techniques.

This project involves analyzing WhatsApp chat data to extract valuable insights. Using Python and various libraries like Pandas and Matplotlib, the project processes and visualizes chat statistics such as message frequency, most active participants, and sentiment analysis.

A clean, provider-agnostic message classification service using AI models. Built with modern Python practices, featuring robust configuration management and optimized performance through intelligent caching.

ElectroCare AI Assistant Chatbot – A multilingual customer-support chatbot built with Flask, NLP, and intent classification, supporting English, Italian, and Tigrigna.

MIntRec2.0 is the first large-scale dataset for multimodal intent recognition and out-of-scope detection in multi-party conversations (ICLR 2024)

An NLU project that uses LSTM models to classify a user's intent and extract key information (slots) from text in the MASSIVE dataset.