The Stardog Blog
Get the latest in your inbox
Popular Reads
The Stardog Voicebox Vision
Enable anyone to ask any question of any data and get accurate, timely, and hallucination-free answers—immediately. Check out the details.
Voicebox in the Sweet Spot
Stardog Voicebox is an hallucination-free, fast, accurate AI Data Assistant that has a special sweet spot: needle-in-a-haystack and path question answering for diverse enterprise data.
Data-Driven Quality: Change the Game with Knowledge Graphs & Generative AI
Accelerate supply chain visibility using the power of using Stardog’s Generative AI powered by a knowledge graph with Databricks. Manufacturing organizations can conduct quality event forensics to quickly identify problems and improve customer outcomes.
Latest Posts
Introducing BARQ: Stardog is 9x Faster for Graph OLAP!
BARQ is our new columnar OLAP graph query engine that’s up to 9x faster.
SKATHE is a Private GPU Cloud
Our private GPU cloud facility, SKATHE, for full stack control of Voicebox in regulated industries.
Solving Four LLM Design Problems
How Semantic Parsing (SP) addresses all four major LLM design problems.
Why generative AI projects fail in highly regulated industries — and how yours can succeed
How Financial Services can safely leverage GenAI to improve business.
The Agentic Present: Unleashing Creativity with Automation
How we use LLM agents inside Voicebox to unleash human creativity and agency through the power of automation
Safety RAG: Improving AI Safety by Extending AI's Data Reach
Safety RAG (SRAG) is how we get to 100% hallucination-free answers.
Altman's Marauders & Satya's Krewe: the Big Picture in GenAI in early 2024
Radical versus Pragmatic AI: Stardog is in the pragmatic faction, focused on better GenAI outcomes for the enterprise
Always Knowing What to Say Next
LLMs are machines for telling people (and other machines) what to say do next. Making them a part of ongoing streams of conversation is the key to using AI successfully.
Using RAG for Question Answering in Regulated Industries is a Bad Idea
The current rage for RAG in LLMs and GenAI is a very dumb idea for regulated enterprises. DO NOT DO THIS.
The Unconscious Patient Problem: A Look at the Importance of Entity Resolution in Healthcare and Life Sciences
The Databricks DI Platform, built on lakehouse architecture, coupled with Stardog as a semantic layer, provides a robust and scalable alternative to tedious and brittle traditional approaches to matching patient records.
How AI Uses Stardog
In our previous post we answered the question how Stardog uses AI by explaining our use of Hybrid AI with LLM to build, manage, and query knowledge graphs with ordinary language. The question today goes the other way around; how does AI use Stardog, that is, how does enterprise generative AI use an enterprise knowledge graph?
Designing LLM Applications with Knowledge Graphs and LangChain
Voicebox, our LLM-powered knowledge engineer, accelerates time to value by making it easier to build and query knowledge graphs, but we haven’t yet said much about how it works. In this blog I will explain the high-level design of Voicebox, including how we use LangChain.