← 최신 프로덕트

Using DSPy to enrich a dataset of the Nobel laureate network

I've been working a fair bit with DSPy lately, and I did some work in combining the benefits of vector search and LLMs (via a DSPy pipeline) to disambiguate records with a high degree of accuracy to help enrich a dataset.

blog.kuzudb.com 방문외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Fast vector similarity using Rust and Python

    github.com

    High-performance vector similarity library in Rust with Python bindings: Spearman, Kendall, distance correlation, Jensen-Shannon, Hoeffding's D, and bootstrapped confidence intervals

    Hacker News141점

  2. Bridge-ds

    github.com

    Dataset handling for any modality a la Pandas

    Hacker News7점

  3. I wrote a VectorDB in Go, built for Hackers, not Hyperscalers

    github.com

    A Vector Store written in Go - Supports hybrid retrieval over BM25, Flat, HNSW, IVF, PQ and IVFPQ Index with Quantization, Metadata Filtering, Reranking, Reciprocal Rank Fusion, Soft Deletes, Index Rebuilds and much much more

    Hacker News8점

  4. Evaluating LLMs on creative writing via reader usage, not benchmarks

    narrator.sh

    I'd love to get some people to mess around with a little side project I built to teach myself DSPy!

    Hacker News36점

  5. I used an LLM to parse HN Who's Hiring comments to structured job data

    hnjobsai.vercel.app

    Discover the best AI jobs at frontier AI companies across machine learning, AI research, data science, AI training, and robotics.

    Hacker News16점