The Update to GraphRAG: Improving AI Search Engines’ Ability to Provide Specific and Comprehensive Answers
The Difference Between RAG and GraphRAG
RAG (Retrieval Augmented Generation) combines a large language model (LLM) with a search index (or database) to generate responses to search queries. The search index grounds the language model with fresh and relevant data, reducing the possibility of AI search engines providing outdated or hallucinated answers.
GraphRAG Uses a Two-Step Process
Step 1: Indexing Engine
The indexing engine segments the search index into thematic communities formed around related topics. These communities are connected by entities (e.g., people, places, or concepts) and the relationships between them, forming a hierarchical knowledge graph. The LLM then creates a summary for each community, referred to as a Community Report.
Step 2: Query Step
In the second step, GraphRAG uses the knowledge graph it created to provide context to the LLM so that it can more accurately answer a question.
Update to GraphRAG
Microsoft explains that Retrieval Augmented Generation (RAG) struggles to retrieve information that’s based on a topic because it’s only looking at semantic relationships. GraphRAG outperforms RAG by first transforming all documents in its search index into a knowledge graph that hierarchically organizes topics and subtopics (themes) into increasingly specific layers.
Dynamic Community Selection
The original version of GraphRAG was inefficient because it processed all community reports, including irrelevant lower-level summaries, regardless of their relevance to the search query. Microsoft describes this as a “static” approach since it lacks dynamic filtering. The updated GraphRAG introduces “dynamic community selection,” which evaluates the relevance of each community report. Irrelevant reports and their sub-communities are removed, improving efficiency and precision by focusing only on relevant information.
Takeaways: Results of Updated GraphRAG
Microsoft tested the new version of GraphRAG and concluded that it resulted in a 77% reduction in computational costs, specifically the token cost when processed by the LLM. The improved GraphRAG is able to use a smaller LLM, further reducing costs without compromising the quality of the results.
Conclusion
Dynamic community selection in GraphRAG improves search results quality by generating responses that are more specific, relevant, and supported by source material. The updated GraphRAG is a significant improvement over the original, providing faster and more accurate results.
Frequently Asked Questions
Q: What is the main difference between RAG and GraphRAG?
A: RAG combines a large language model with a search index to generate responses, while GraphRAG uses a knowledge graph created from a search index to generate summaries referred to as community reports.
Q: How does GraphRAG improve search results quality?
A: GraphRAG uses dynamic community selection to evaluate the relevance of each community report and remove irrelevant reports and their sub-communities, improving efficiency and precision by focusing only on relevant information.
Q: What are the benefits of the updated GraphRAG?
A: The updated GraphRAG reduces computational costs by 77%, uses a smaller LLM, and provides faster and more accurate results by generating responses that are more specific, relevant, and supported by source material.
Q: What is the significance of dynamic community selection in GraphRAG?
A: Dynamic community selection in GraphRAG improves search results quality by generating responses that are more specific, relevant, and supported by source material.
