Hacker News with Generative AI: Vector Search

Vector Search at 10k QPS in PostgreSQL (vectorchord.ai)
VectorChord is a PostgreSQL extension designed for scalable, high-performance, and disk-efficient vector similarity search, and serves as the successor to pgvecto.rs. In our previous blog post, we showed that with just $250 per month, VectorChord achieved 131 QPS with 0.95 precision on 100 million vectors—demonstrating impressive cost-effective performance for large-scale vector search.
Vector Search with DuckDB (huggingface.co)
Datasets on the Hugging Face Hub rely on parquet files. We can interact with these files using DuckDB as a fast in-memory database system. One of DuckDB’s features is vector similarity search which can be used with or without an index.
Supercharge vector search with ColBERT rerank in PostgreSQL (vectorchord.ai)
Traditional vector search methods typically employ sentence embeddings to locate similar content. However, generating sentence embeddings through pooling token embeddings can potentially sacrifice fine-grained details present at the token level. ColBERT overcomes this by representing text as token-level multi-vectors rather than a single, aggregated vector. This approach, leveraging contextual late interaction at the token level, allows ColBERT to retain more nuanced information and improve search accuracy compared to methods relying solely on sentence embeddings.
An experiment of adding recommendation engine to your app using pgvector search (silk.us)
The reason I am excited about the latest genAI and vector search developments is that you can “plug in” these new technologies into your existing applications and their data, without having to re-platform or re-engineer your entire stack first. You can keep your existing application code and database design exactly as it is and then just add new genAI & vector search features where it makes sense.
VectorChord: Store 400k Vectors for $1 in PostgreSQL (pgvecto.rs)
We’re pleased to announce our new vector search extension for PostgreSQL, providing a highly cost-effective way to manage large vectors. Using VectorChord, you can achieve a QPS of 131 with 0.95 precision on 100 million 768-dimensional vectors for the top 10 queries. This setup costs only $250 monthly and can be hosted on a single machine.
Go library for in-process vector search and embeddings with llama.cpp (github.com/kelindar)
This library was created to provide an easy and efficient solution for embedding and vector search, making it perfect for small to medium-scale projects that still need some serious semantic power.
Hybrid Search with PostgreSQL and Pgvector (jkatz05.com)
A key metric when evaluating vector similarity search algorithms is “recall” - which measures the relevancy of the returned search results.
Sqlite-vec: Work-in-progress vector search SQLite extension that runs anywhere (github.com/asg017)
Vectorlite: Fast Vector Search for SQLite (github.com/1yefuwang1)
Show HN: txtai: open-source, production-focused vector search and RAG (neuml.github.io)
Txtai – A Strong Alternative to ChromaDB and LangChain for Vector Search and RAG (medium.com)
Drug Discovery with Vector Search (github.com/fzliu)