Knowledge Graphs for RAG

Aperçu

Knowledge graphs are instrumental in structuring complex data relationships, enabling intelligent search functionality, and developing robust AI applications capable of reasoning over various data types. They can integrate data from both structured and unstructured sources, including databases and documents, providing a flexible and intuitive way to model intricate, real-world scenarios.

Unlike tables or simple lists, knowledge graphs capture the meaning and context behind the data, revealing insights and connections that are hard to discover with conventional databases.

This rich, structured context is perfect for enhancing the output of large language models (LLMs), allowing for more relevant contextual construction than semantic search alone. This course, offered by Coursera, will guide you through leveraging knowledge graphs within retrieval augmented generation (RAG) applications.

You'll learn to:

• Understand the basics of how knowledge graphs store data, using nodes to represent entities and edges to represent relationships between nodes.
• Utilize 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, enabling vector similarity search for finding relevant texts.
• Construct a knowledge graph of text documents from scratch, using publicly available financial and investment documents as a demo use case.
• Explore advanced techniques for connecting multiple knowledge graphs and employing complex queries for comprehensive data retrieval.
• Write advanced Cypher queries to fetch relevant information from the graph and format it for inclusion in your LLM prompts.

Upon completing the course, you'll be well-equipped to use knowledge graphs to extract deeper insights from your data and enhance the performance of LLMs with structured, relevant context.

University:

Provider:

Coursera
Categories:

Data Integration Courses, Knowledge Graphs Courses, Neo4j Courses, Cypher Query Language Courses

Matières