Skip to content

Chapters

This textbook is organized into 14 chapters covering 200 concepts in Conversational AI.

Chapter Overview

  1. Foundations of Artificial Intelligence and Natural Language Processing - This chapter introduces core AI concepts, timelines, and foundational NLP principles including text processing, string matching, and regular expressions.

  2. Search Technologies and Indexing Techniques - This chapter covers fundamental search approaches including keyword search, search indexing, inverted indexes, full-text search, and Boolean search operators.

  3. Semantic Search and Quality Metrics - This chapter explores advanced search techniques including synonym expansion, ontologies, taxonomies, semantic search, TF-IDF, Page Rank, and introduces search quality metrics like precision, recall, F-measures, and confusion matrices.

  4. Large Language Models and Tokenization - This chapter introduces large language models, transformer architecture, attention mechanisms, and various tokenization techniques including byte pair encoding.

  5. Embeddings and Vector Databases - This chapter covers word embeddings, embedding vectors, vector space models, embedding models (Word2Vec, GloVe, FastText), sentence embeddings, vector databases, and approximate nearest neighbor search algorithms.

  6. Building Chatbots and Intent Recognition - This chapter introduces chatbots, conversational agents, dialog systems, intent recognition and modeling, entity extraction, and FAQ systems.

  7. Chatbot Frameworks and User Interfaces - This chapter explores chatbot frameworks (Rasa, Dialogflow, LangChain, LlamaIndex), JavaScript libraries, user interface design, chat interfaces, and session management.

  8. User Feedback and Continuous Improvement - This chapter covers user feedback mechanisms, feedback buttons, the AI flywheel, continuous improvement cycles, user context, personalization, and chat history management.

  9. The Retrieval Augmented Generation Pattern - This chapter introduces the RAG pattern, external and internal knowledge sources, document corpus management, retrieval steps, augmentation, generation, context windows, prompt engineering, and RAG limitations including hallucination.

  10. Knowledge Graphs and GraphRAG - This chapter covers knowledge graphs, graph databases, nodes, edges, triples, RDF, graph query languages (OpenCypher, Cypher), Neo4j, GraphRAG patterns, and corporate nervous systems.

  11. NLP Pipelines and Text Processing - This chapter explores NLP pipelines, text preprocessing, normalization, stemming, lemmatization, part-of-speech tagging, dependency parsing, and coreference resolution.

  12. Database Queries and Parameter Extraction - This chapter covers database queries, SQL, query parameters, parameter extraction, query templates, parameterized queries, natural language to SQL conversion, and slot filling techniques.

  13. Security, Privacy, and User Management - This chapter addresses security, authentication, authorization, role-based access control (RBAC), data privacy, PII, GDPR compliance, data retention, logging systems, and log analysis.

  14. Evaluation, Optimization, and Career Development - This chapter covers chatbot evaluation metrics, KPIs, dashboards, acceptance rates, user satisfaction, response accuracy, A/B testing, performance tuning, optimization strategies, team projects, capstone projects, and chatbot career paths.

How to Use This Textbook

Progress through the chapters sequentially, as each chapter builds on concepts from previous chapters. The textbook follows a pedagogical progression from foundational AI concepts through search technologies, language models, embeddings, chatbot development, advanced patterns like RAG and GraphRAG, and finally security and evaluation topics. Dependencies between concepts are carefully respected to ensure a smooth learning experience.

Note: Each chapter includes a list of concepts covered. Make sure to complete prerequisites before moving to advanced chapters.