🔎 Information Retrieval

Discussed on DEV

🔢Pgvector 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)

🔍Tantivy 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

🕸️Graph Databases pedroalonso.net·

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

📝NLP medium.com

Multi-Query RAG: Why Your RAG Pipeline Misses Relevant Documents — and How to Fix It

☸️Kubernetes chenshaowen.com·

Elasticsearch troubleshooting

🔍Tantivy medium.com

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

🔍RAG medium.com

Pure Vector Search Is Not Enough Anymore. Here Is What You Actually Need.

📁File Systems elastic.co·

Why your Elasticsearch cluster is hitting disk watermarks: 14 real-world causes explained

🔍Tantivy arxiv.org·

ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback

🔍Tantivy GitHub·

Show HN: A small, crazy fast hybrid search engine written in Rust

Covers 2 stories including Ollama

Discussed on Hacker News

🎨Chroma arxiv.org·

Non-negative Elastic Net Decoding for Information Retrieval

🔍RAG GitHub·

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly

Discussed on Hacker News

🏗️MLIR arxiv.org·

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

📝NLP GitHub·

Push vs. Pull Agent Memory?

Discussed on Hacker News and DEV

🔍Tantivy arxiv.org·

When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval

🔍Tantivy arxiv.org·

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking

🔗ActivityPub lemmy.ml·

Agent memory on Elasticsearch: hybrid retrieval and DLS

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

Jingra: A Reproducible Framework for Vector Search Benchmarking

The AI side of the Vespa Search Engine

# Vector Search and RAG: A Primer

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

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

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

Multi-Query RAG: Why Your RAG Pipeline Misses Relevant Documents — and How to Fix It

Elasticsearch troubleshooting

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

Pure Vector Search Is Not Enough Anymore. Here Is What You Actually Need.

Why your Elasticsearch cluster is hitting disk watermarks: 14 real-world causes explained

ADORE: Iterative Query Expansion with Retrieval-Grounded Relevance Feedback

Show HN: A small, crazy fast hybrid search engine written in Rust

Non-negative Elastic Net Decoding for Information Retrieval

Show HN: Pgsemantic – Point at your Postgres DB, get vector search instantly

SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

Push vs. Pull Agent Memory?

When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval

Entity Labels Are Not Entity Signals: A Framework for Observable Relevance in Document Re-Ranking

Agent memory on Elasticsearch: hybrid retrieval and DLS