In today’s rapidly evolving digital landscape, the complexity of distributed systems and microservices architectures has reached unprecedented levels. As organizations strive to maintain visibility into their increasingly intricate tech stacks, observability has emerged as a critical discipline. At the forefront of this field stands OpenTelemetry, an open-source observability framework that has gained significant traction in … continue reading
Imagine searching for a crucial piece of information in a traditional search engine, only to be overwhelmed with thousands of irrelevant results. This limitation is especially problematic in critical industries like nuclear power, where precision and reliability are paramount. Enter sentence embeddings—a powerful, yet often overlooked technology that is set to transform how we access … continue reading
The AI company Galileo has just announced its latest Hallucination Index, which is a framework that evaluates 22 leading generative AI models. Models are tested using a metric called context adherence, which measures “closed-domain hallucinations: cases where your model said things that were not provided in the context.” The best performing model overall for RAG, … continue reading
GraphRAG is an open source research project out of Microsoft for creating knowledge graphs from datasets that can be used in retrieval-augmented generation (RAG). RAG is an approach in which data is fed into an LLM to give more accurate responses. For instance, a company might use RAG to be able to use its own … continue reading
The vector database Qdrant has developed a new vector-based hybrid search capability, BM42, which provides accurate and efficient retrieval for RAG applications. The name is a reference to BM25, which is a text based search that has been used as the standard in search engines for the last 40 years. According to Qdrant, the introduction … continue reading
Elastic has just released a new tool called Playground that will enable users to experiment with retrieval-augmented generation (RAG) more easily. RAG is a practice in which local data is added to an LLM, such as private company data or data that is more up-to-date than the LLMs training set. This allows it to give … continue reading
DataStax is making a number of improvements to its development platform that will allow developers to more easily implement retrieval augmented generation (RAG) in their generative AI applications. “The Generative AI stack is a big and complex ball of technology that many are working to get their arms around. We’re focused on helping developers stay … continue reading
One of the challenges with generative AI models has been that they tend to hallucinate responses. In other words, they will present an answer that is factually incorrect, but will be confident in doing so, sometimes even doubling down when you point out that what they’re saying is wrong. “[Large language models] can be inconsistent … continue reading
