A collection of bookmarks filtered by the tag "Vector Search".
Filter by:
Showing 1-16 of 16 bookmarks tagged with "Vector Search"
All Stories
This curated guide brings together 16 vetted Vector Search resources, including 15 with structured technical analysis and 1 with practitioner field notes. Primary focus areas include AI Infrastructure Analysis, AI Model Release, CLI Search Tool, Cloud Infrastructure / Vector Database, Cloud Storage Service. Primary sources include github.com, aws.amazon.com, blog.cloudflare.com, chroma-explorer.com, clickhouse.com.
William’s notes from the collection, quoted in his own words.
A discussion on this: https://news.ycombinator.com/item?id=46081053 At the embedding size, this is an 11 billion parameter data set.
| Resource | Category & Format | Key Takeaway & Notes |
|---|---|---|
| Hacker News vector search dataset using ClickHouseclickhouse.com | Dataset / Vector Search Example / Parquet dataset + SQL DDL/DML examples (code snippet) / free online via ClickHouse documentation and S3 bucket | A discussion on this: https://news.ycombinator.com/item?id=46081053 At the embedding size, this is an 11 billion parameter data set. |
| GitHub - zvec-ai/zvec-grep: Local-first search across your workspace, built for humans and AI agents.github.com | Developer CLI Tool / open-source CLI tool with documentation / open source, free to install via npm | Unifies three search paradigms (ripgrep, BM25, vector) behind one command with hybrid ranking |
| datachain-ai/datachain: The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azuregithub.com | Python Library / open-source library with documentation / open source, pip install datachain | Turns unstructured files into typed, versioned datasets with sub-second filter, join, and group_by over millions of records |
| Contextual embedding beyond the gold passageperplexity.ai | AI Model Release / technical blog post / free online; model preview on Hugging Face | Novel training method distills token-level relevance from a context compression teacher into chunk-level scores, replacing single gold-chunk supervision |
| GitHub - Dicklesworthstone/frankensearch: Two-tier hybrid search for Rust: sub-millisecond initial results via potion-128M, quality-refined rankings in 150ms via MiniLM-L6-v2. Combines lexical (Tantivy BM25) and semantic (vector cosine) search with Reciprocal Rank Fusion. Progressive iterator API, f16 SIMD vector index, feature-gated compilation.github.com | Rust Library / open source software / open source | Two-tier hybrid architecture combining lexical (Tantivy BM25) and semantic (vector cosine) search |
| GitHub - jackccrawford/Clawmark: Continuity for AI agents — semantic search across sessionsgithub.com | Rust CLI Tool / command-line tool / open source on GitHub | Provides semantic search over agent memory using locally stored SQLite signals. |
| tobi/qmd: mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all localgithub.com | CLI Search Tool / command-line application with optional MCP server / open source on GitHub, installable via npm or bun | Combines fast BM25, embeddings‑based semantic retrieval, and optional LLM reranking |
| Trey Graingertreygrainger.com | Research Paper / research paper with presentation / free online (Arxiv, GitHub, Apache JIRA) | Uses inverted and complementary uninverted indexes to represent nodes as terms and edges as intersecting postings lists |
| Chroma Explorer - Modern ChromaDB Desktop Clientchroma-explorer.com | Desktop Application / native desktop application (macOS) / downloadable client (free trial, commercial licensing optional) | Connect to local, remote, or Chroma Cloud instances with secure API key storage |
| GitHub - joelhooks/pdf-library: Local PDF knowledge base with vector search using PGlite + pgvectorgithub.com | Developer Tool / Open Source Software / open source | Local-first architecture using PGlite and pgvector for vector search without external API costs. |
| Vectorize: a vector database for shipping AI-powered applications to production, fastblog.cloudflare.com | Cloud Infrastructure / Vector Database / blog post / product announcement / open beta, free to use with Cloudflare Workers | Vectorize is in open beta and available to any Cloudflare Workers developer |
| GitHub - nmslib/hnswlib: Header-only C++/python library for fast approximate nearest neighborsgithub.com | Open Source Library / source code repository on GitHub with documentation and examples / open source, free to use under the Apache‑2.0 license | Header‑only C++ core (C++11) with official Python bindings; other languages via community wrappers |
| Compression is all you need: 2x, 4x, 8x and 16x cheaper vector databasesanyamsinghal.notion.site | Technical Blog Post / long-form technical article / free online | Float16 storage alone gives 2x savings with minimal effort, yet is not the default in most vector databases |
| Introducing Amazon S3 Vectors: First cloud storage with native vector support at scale (preview) | Amazon Web Servicesaws.amazon.com | Cloud Storage Service / Product announcement blog post / Preview availability on AWS | Up to 90% cost reduction for uploading, storing, and querying vectors compared to conventional approaches |
| #123- AWS just quietly rewrote the vector database marketsiddharthsshah.substack.com | AI Infrastructure Analysis / Newsletter article / long-form analysis / Free online via Substack | S3 Vectors stores millions of vectors with sub-second semantic search at under $10 for 1M vectors vs $90/mo on Pinecone |
A collection of bookmarks filtered by the tag "Vector Search".
Showing 1-16 of 16 bookmarks tagged with "Vector Search"
All Stories
Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context. - dzhng/jevgrep
