Image of an entity network with color-coded communities

Project GraphRAG

LLM-Derived Knowledge Graphs

Nouvelles et reportages

The image features three white icons on a gradient background transitioning from blue on the left to green on the right. The first icon, located on the left, depicts a hierarchical structure resembling a workflow with connected squares. The middle icon represents GraphRAG (interconnected nodes and lines). The third icon, on the right, shows a globe with a magnifying glass overlaying it, symbolizing global search.
Blog de recherche Microsoft

| Bryan Li, Ha Trinh, Darren Edge, et Jonathan Larson

Retrieval-augmented generation (RAG) helps AI systems provide more information to a large language model (LLM) when generating responses to user queries. A new method for conducting “global” queries can optimize the performance of global search in GraphRAG.

Three icons that represent (left to right) search, GraphRAG, and the globe.
Blog de recherche Microsoft

| Julian Whiting, Zachary Hills, Alonso Guevara Fernández, Ha Trinh, Adam Bradley, et Jonathan Larson

GraphRAG leverages semantic structuring of data to generate responses to complex user queries. A collaboration with Uncharted expands the frontiers of this technology, developing a new approach to processing local queries: DRIFT search.

GraphRAG image on blue to green gradient
Blog de recherche Microsoft

| Alonso Guevara Fernández, Katy Smith, Joshua Bradley, Darren Edge, Ha Trinh, Sarah Smith, Ben Cutler, Steven Truitt, et Jonathan Larson

GraphRAG uses LLM-generated knowledge graphs to substantially improve complex Q&A over retrieval-augmented generation (RAG). Discover automatic tuning of GraphRAG for new datasets, making it more accurate and relevant.

Dans l’actualité | Fierce Network

Grounding AI models is like giving them a map to navigate the world, but what happens when that map isn’t up to date or misses crucial details? That’s the problem hyperscalers and AI leaders are now trying to solve. As…

Dans l’actualité | The Stack

Redmond opens up to discuss its new tool, which can extract data from unstructured text using large language models. Microsoft’s GraphRAG is a new approach to Retrieval-Augmented Generation (RAG) that Redmond has described a «significant advance in enhancing the capability…

white icons on a blue and green gradient background
Blog de recherche Microsoft

| Darren Edge, Ha Trinh, et Dayenne Souza

Intelligence Toolkit was built to help fight human trafficking and is applicable to a broad range of societal challenges. Learn how Microsoft researchers worked with global experts to develop generative AI tools that could help tackle urgent issues at scale.

GraphRAG blog hero
Blog de recherche Microsoft

| Darren Edge, Ha Trinh, Steven Truitt, et Jonathan Larson

GraphRAG, a graph-based approach to retrieval-augmented generation (RAG) that significantly improves question-answering over private or previously unseen datasets, is now available on GitHub.

Research Focus: May 27, 2024
Blog de recherche Microsoft

How can generative AI tools represent less common identities and narratives; Can LLMs help players participate in game narratives; Using LLMs to improve geospatial demographic data; A Graph RAG Approach to Query-Focused Summarization; and more.

Project Ire - GraphRag background: Blue-green gradient
Blog de recherche Microsoft

| Jonathan Larson et Steven Truitt

Editor’s note, Apr. 2, 2024 – Figure 1 was updated to clarify the origin of each source. Perhaps the greatest challenge – and opportunity – of LLMs is extending their powerful capabilities to solve problems beyond the data on which…