Hacker News with Generative AI: Retrieval

voyage-3.5 and voyage-3.5-lite: improved quality for a new retrieval frontier (voyageai.com)
Today, we’re excited to introduce voyage-3.5 and voyage-3.5-lite, which maintain the same sizes as their predecessors—voyage-3 and voyage-3-lite—but offer improved quality for a new retrieval frontier.
Show HN: HelixDB – Native graph and vector types for RAG and retrieval (github.com/HelixDB)
HelixDB is a powerful, graph-vector database built in Rust for millisecond query latency and ease of use.
AGI requires better retrieval, not just better LLMs. Here's why (medium.com)
Artificial General Intelligence is about developing AI that can learn new information on the fly, just like a human being you might hire and train. Despite Large Language Models scoring in the top 10% across nearly every STEM subject, we still haven’t reached AGI. Why? Because we need better contextualized models that can connect to knowledge bases and seamlessly retrieve information as effortlessly as human memory.
Retrieval powered by object storage: AMA (ycombinator.com)
Chroma now has a fully-distributed and serverless version backed by object-storage (also Apache 2.0).
OpenRecall (github.com/openrecall)