Рет қаралды 9,066
Enroll now: bit.ly/3PaCeAK
Knowledge graphs enhance AI application development by connecting structured and unstructured data sources for a comprehensive view of complex, real-world scenarios. They go beyond traditional databases as they connect data from both structured and unstructured sources, providing an intuitive way to model complex, real-world scenarios.
Today, we’re introducing Knowledge Graphs for RAG, a new short course built in collaboration with Neo4j, where you’ll learn how to leverage knowledge graphs within retrieval augmented generation (RAG) applications.
Upon completing this course, you will:
Understand the basics of how knowledge graphs store data by using nodes to represent entities and edges to represent relationships between nodes.
Use Neo4j's query language, Cypher, to retrieve information from a fun graph of movie and actor data.
Add a vector index to a knowledge graph to represent unstructured text data and find relevant texts using vector similarity search.
Build a knowledge graph of text documents from scratch, using publicly available financial and investment documents as the demo use case
Explore techniques for connecting multiple knowledge graphs and using complex queries for comprehensive data retrieval.
Write advanced Cypher queries to retrieve relevant information from the graph and format it for inclusion in your prompt to a large language model (LLM)
Start enhancing the performance of LLMs with knowledge graphs.
Learn more: bit.ly/3PaCeAK