Learn how a hypothetical distributed systems and AI specialist uses vector search to fine tune a retailer's trucking routes.

Check out this new way to provide the huge population of JavaScript developers access to the most powerful vector database in the world, through a simple API.

DataStax had to move fast to add this foundational AI-enablement feature. Here’s how ChatGPT, Copilot and other AI tools helped us build the code.

As you research vector search options, you’ll need to consider the following hard problems and the different approaches to solving them.

An examination of three methods to stop LLMs from hallucinating: Retrieval-augmented generation (RAG), reasoning, and iterative querying.

Amazon Neptune, the managed graph database service by AWS, makes analytics faster and more agile while introducing a vision aiming to simplify graph databases.

we look at how suboptimal embedding models, inefficient chunking strategies and a lack of metadata filtering can make it hard to get relevant responses from you

In this article, we will explore another well-known vector store called ChromaDB. Chroma DB is a vector store that is open-source.

Learn about a simple method for combining vector stores, lexical search and prompt engineering to perform accurate RAG on commodity hardware.

Harness the power of word vectors and similarity searches to help discover data correlations with enterprise data to assist with a marketing campaign.

Prepare for complexities of deploying vector search in production with insights on indexing, metadata filtering, query language, and vector lifecycle management

A deep dive into 5 early adopters of vector search- Pinterest, Spotify, eBay, Airbnb and Doordash- who have integrated AI into their applications.

Learn the value of Retrieval Augmented Generation (RAG) in AI, revolutionizing customer interactions & enhancing dialogue systems with advanced NLP capabilities

A dive into multi-modal embedding and frame search, two advanced video search techniques

There are three main ways to incorporate domain knowledge in an LLM: prompt engineering, fine tuning, and retrieval augmentation.

We show how content-centric knowledge graphs – a vector-store allowing links between chunks – are an easy to use and efficient approach to improve RAG results.

Build a Graph-RAG agent using Neo4j and Milvus to combine graph and vector search, delivering accurate, context-rich answers to complex queries.

Rerankers are ML models that take a set of search results and reorder them to improve relevance. We tested 6 of them.

Learn how vector search helped build a powerful way to identify recurring payments in the financial sector.

Transform your search in 5 minutes! Implement AI-powered hybrid search with OpenSearch and cloud tools for faster, more relevant results.