Neo4j

Everyone loves text embedding models, and for good reason: They excel at encoding unstructured text, making it easier to discover semantically similar content. It’s no surprise that they form the backbone of most RAG applications, especially with the current emphasis on encoding and retrieving relevant information from documents and other textual resources. However, there are clear examples of questions one might ask where the text embedding approach to RAG applications falls short and delivers incorrect

While most people focus on retrieval-augmented generation (RAG) over unstructured text, such as company documents or documentation, I am pretty bullish on retrieval systems over structured information, particularly knowledge graphs. There has been a lot of excitement about GraphRAG, specifically Microsoft’s implementation. However, in their implementation, the input data is unstructured text in the form of documents, which is transformed into a knowledge graph using a large language model (LLM). In this blog post, we will show

I am always intrigued by new approaches to implementing Retrieval-Augmented Generation (RAG) over graphs, often called GraphRAG. However, it seems that everyone has a different implementation in mind when they hear the term GraphRAG. In this blog post, we will dive deep into the “From Local to Global GraphRAG” article and implementation by Microsoft researchers. We will cover the knowledge graph construction and summarization part and leave the retrievers for the next blog post. The