Jennifer Reif26 articles

Table of Contents Why RAG?Large Language Models (LLMs)Vector embeddingsVectors applied to wordsVectors applied to dataSimilarity searchWrapping up!Resources Retrieval Augmented Generation (RAG) may sound complex, but it accurately represents the process of the system. RAG is a method that enhances the …

Table of Contents Getting startedIssue #1: APIs, SDKs, and rapid changeIssue #2: ConfigIssue #3: JSON formatIssue #4: Loading data to Pinecone1. Metadata keysAlternative embeddings – Book descriptionsWrapping up!Resources As someone who is pretty familiar with relational and graph databases, I …

Table of Contents Why embedding models should matchDifferences in similarity searchAdvice for starting a blogWrapping up! This is episode 39 of the Breaktime Tech Talks podcast. I’m at a conference this week presenting on a variety of different topics, but …

Table of Contents Vector database architectureJSON formattingPinecone configurationConfiguring multiple vector storesWhy and how to participate in open sourceWrapping up! In this episode, I continue my journey with vector databases, integrating Pinecone, Neo4J , and Spring AI. While making some progress, …

Table of Contents Devnexus conference shout-outVector database explorationIssues getting up and runningOverall experienceMicrosoft LazyGraphRAGWrapping up! This is episode 37 of the Breaktime Tech Talks. You are listening to the Breaktime Tech Talks podcast, a bite-sized tech podcast for busy developers, …

Table of Contents Spring save() methodPatch YearCustom CypherProjectionsProjection as MovieMovie entity as projectionWrapping Up!Resources After working on a new online Spring Data Neo4j course, I learned a couple more things about updating an entity. The course required a different set …

Table of Contents NODES is a free, virtual conference run by Neo4j for developers, data scientists, and other technical roles who want to learn more about graph databases and how they can be used to solve complex problems. Join us …

Putting together a conference schedule for NODES 2024 (one of my favorite events of the year) is a massive undertaking, but my colleague and I used technologies and tools at our disposal to make this process a little more efficient and greatly reduce opportunities for mistakes.

For an upcoming event, I was asked to give a demo of how to run Neo4j on Kubernetes. I had very little experience with Kubernetes, so I decided to document my journey for later reference.

Technical events are a great way to learn new things, connect with people, and share knowledge with others.