🔍 Search Indexing - sidsq

Discussed on DEV

📇Vector Indexing Sease·

The AI side of the Vespa Search Engine

⚙️Database Internals elastic.co·

How we built a persistent agent memory layer on Elasticsearch with 0.89 recall and zero tenant leaks

Covered by 3 sources including DEV Community, lemmy.ml

Discussed on Hacker News and Lobsters

🎯Vector Search Hacker News·

Forked CozoDB to give agents cognitive primitives

Discussed on Hacker News

🧠Query Planners Databricks·

Accelerate search queries with full-text search indexes on Databricks

🧠Query Planners deepbluedynamics.com·

How Lume Works: The Retrieval Primitives

Discussed on Hacker News

📇Vector Indexing arxiv.org·

MonaVec: A Training-Free Embedded Vector Search Kernel for Edge and Offline AI Systems

Covers Easy way to do both: async <-> sync (crates.io dump loading and parsing example)

🎯Vector Search pedroalonso.net·

When Does a Knowledge Graph Beat Vector Search — and When Do You Actually Need Neo4j?

🎯Vector Search medium.com

Retrieval Is the Product: BM25, Embeddings, and the Hybrid Default

⚙️Database Internals ip2location.medium.com·

Enhance Elasticsearch Ingest Pipelines with the IP2Location Processor

🗂️Vector Indexes kevinjztan.medium.com·

Hybrid Search Won My Last Benchmark. At a Finer Grain, It Lost by 33%.

🎯Vector Search Blocks and Files·

Zilliz lays out vector database and lakebase differences

🚀Query Optimization medium.com

Elasticsearch Is Not Dead. It Is Just Not Built for What You Are Building Now.

🗳️Raft Consensus SiliconANGLE·

Elastic reportedly acquires site reliability engineering startup Deductive AI

Covers Source: Elastic agrees to buy CRV-backed DeductiveAI for up to $85M

🎯Vector Search medium.com

Late Interaction Embeddings: A Practical Next Step for Better Retrieval

🎯Vector Search The New Stack·

Your agent wants to search like a 2010 quant

Covers https://research.perplexity.ai/articles/rethinking-search-as-code-generation

🎯Vector Search sadiqueali.medium.com·

Laravel Vector Search: Semantic Search in Your App Without a PhD in Machine Learning

🐘PostgreSQL Internals medium.com

Jingra: A Reproducible Framework for Vector Search Benchmarking

Elasticsearch troubleshooting

# Vector Search and RAG: A Primer

The AI side of the Vespa Search Engine

How we built a persistent agent memory layer on Elasticsearch with 0.89 recall and zero tenant leaks

Forked CozoDB to give agents cognitive primitives

Accelerate search queries with full-text search indexes on Databricks

How Lume Works: The Retrieval Primitives

MonaVec: A Training-Free Embedded Vector Search Kernel for Edge and Offline AI Systems

When Does a Knowledge Graph Beat Vector Search — and When Do You Actually Need Neo4j?

Retrieval Is the Product: BM25, Embeddings, and the Hybrid Default

Enhance Elasticsearch Ingest Pipelines with the IP2Location Processor

Hybrid Search Won My Last Benchmark. At a Finer Grain, It Lost by 33%.

Zilliz lays out vector database and lakebase differences

Elasticsearch Is Not Dead. It Is Just Not Built for What You Are Building Now.

Elastic reportedly acquires site reliability engineering startup Deductive AI

Late Interaction Embeddings: A Practical Next Step for Better Retrieval

Your agent wants to search like a 2010 quant

Laravel Vector Search: Semantic Search in Your App Without a PhD in Machine Learning

Your agent can’t find the tool it needs