Brian Godsey

Dec 4, 2024 | pub.towardsai.net | Brian Godsey

Smarter Retrieval Systems Need MoreSemantic search has transformed the way we retrieve information. Using vector embeddings, we can represent the semantic meaning of text documents and search them by approximate concept, topic, or general idea instead of by exact words and phrases. This makes semantic search powerful — but it also has significant limitations.

Nov 22, 2024 | datastax.com | Brian Godsey

The mission of AI agents is to use independent reasoning and planning to follow instructions, make independent decisions, and to take actions, often without user involvement. Ideally, AI agents should be able to adapt to and to seek out new information, make adjustments in real-time, and follow through on their missions autonomously.

Nov 12, 2024 | datastax.com | Brian Godsey

These days, it seems like everyone is doing retrieval-augmented generation (RAG), and more and more are adding knowledge graphs to make graph RAG. But many of them get stuck in the R&D stage, struggling (at least a little bit) to pull their proofs of concept into production. Graph RAG, just like most AI technologies, is subject to a few tough-to-avoid rules:Powerful potential: Graph RAG can add significant enterprise value. Easy to start: Implementing simple graph RAG is straightforward.

Oct 31, 2024 | towardsdatascience.com | Brian Godsey

Overcoming the challenges of productionizing graph RAGWhen I read the recent article in VentureBeat about how Glean just secured over $260 million in its latest funding round, I had two immediate gut feelings. First, it was satisfying to see this very public example of graph RAG living up to its potential as a powerful, valuable technology that connects people with knowledge more efficiently than ever.

Oct 18, 2024 | thenewstack.io | Brian Godsey

These days, it seems like everyone is doing retrieval-augmented generation (RAG), and more and more are adding knowledge graphs to make graph RAG. But many of them get stuck in the R&D stage, struggling (at least a little bit) to pull their proofs of concept into production. Graph RAG, just like most AI technologies, is subject to a few tough-to-avoid rules:Powerful potential: Graph RAG can add significant enterprise value. Easy to start: Implementing simple graph RAG is straightforward.