In this video, viewers learn how to build knowledge graphs using generative AI and large language models (LLMs). The tutorial covers the entire process, starting with extracting entities and relationships from raw text, such as resumes, using LLMs. The extracted data is then ingested into a graph database, specifically Neo4j, and queried using the Cypher language. The tutorial also demonstrates how to fine-tune LLMs to convert natural language queries into Cypher queries for database interaction. Additionally, viewers learn how to create node embeddings and graph features for machine learning applications and how to build applications like chatbots using Langchain and Gradio. The video includes a hands-on example where a recruiting company processes resumes to extract entities such as person, education, skills, and positions, and their relationships. The extracted data is structured into a knowledge graph, queried, and used to build interactive applications. The tutorial emphasizes the importance of designing precise prompts to extract accurate information from LLMs and provides detailed instructions for each step of the process, including setting up the Google Cloud AI platform and using Vertex AI for text generation. The video concludes with a preview of the next steps, which involve converting the extracted data into Cypher insert statements for ingestion into the graph database.