Trending

The state of SIMD in Rust in 2025

Vectorizing for Fun and Performance

The Case Against PGVector

word2vec-style vector arithmetic on docs embeddings

VectorWare – from creators of `rust-GPU` and `rust-CUDA`

Binary Retrieval-Augmented Reward Mitigates Hallucinations

Production RAG: what I learned from processing 5M+ documents

Show HN: Pyversity – Fast Result Diversification for Retrieval and RAG

SWE-Grep and SWE-Grep-Mini: RL for Fast Multi-Turn Context Retrieval

Optimizing filtered vector queries from tens of seconds to single-digit milliseconds in PostgreSQL

I worked on RAG for a $25B+ company (What I learnt & Challenges)

Optimizing filtered vector queries from tens of seconds to single-digit milliseconds in PostgreSQL

[P] Flow Matching: A visual introduction

How I solved nutrition aligned to diet problem using vector database

Operations on Word Vectors - Debiasing solution

[D] Measuring how similar a vector's neighbourhood (of vectors) is

I built 50+ RAGs in 2 years. Here are the architectures that get products out the door!

[R] The Massive Legal Embedding Benchmark (MLEB) and Voyage/Cohere/Jina training on user data?

weaviate

Save item

weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database​.

qdrant

Save item

qdrant

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

milvus-io

Save item

milvus

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

google

Save item

highway

Performance-portable, length-agnostic SIMD with runtime dispatch

meilisearch

Save item

meilisearch

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

lancedb

Save item

lance

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, and PyTorch with more integrations coming..

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.

kuzudb

Save item

kuzu

Embedded property graph database built for speed. Vector search and full-text search built in. Implements Cypher.

chroma-core

Save item

chroma

Open-source search and retrieval database for AI applications.