#lucene — Public Fediverse posts

Deep Research without Deep Pockets.

I pulled apart the premium “Deep Research” tools to see what they actually do, then built the same workflow locally without needing a huge model or huge spend.

The trick: make the pipeline do the hard work (search + reduce + evidence), so the LLM mostly just writes.

Part 5 of the DocSummarizer series: https://www.mostlylucid.net/blog/doomsummarizer-deep-research

What’s your best technique for reducing “model made it up” without just throwing a bigger model at it?
#rag #llm #deepresearch #ai #llm #lucene

@Lilith

#solr und #lucene gibt es schon im wesentlichen seit 2004.

@Lilith

#solr und #lucene gibt es schon im wesentlichen seit 2004.

@Lilith

#solr und #lucene gibt es schon im wesentlichen seit 2004.

@Lilith

#solr und #lucene gibt es schon im wesentlichen seit 2004.

@Lilith

#solr und #lucene gibt es schon im wesentlichen seit 2004.

Devoxx Poland is just a couple of days away!
Join my talk Wednesday at the Data & AI track to learn about the #OpenSearch project, and how it can provide you search, analytics, observability and vector database capabilities, all #opensource @linuxfoundation
👉 https://devoxx.pl/talk-details/?id=8605

#data #ai #developers #search #analytics #vectordb #observability #lucene #devoxx #devoxxpl #DevoxxPoland

#OpenSearch 3.0 is out! 🍾 🥳
After 3 years of 2.x, it's time for the next leap, which brings major upgrades to performance, data management, #vectorDB functionality, and much more.
📈 Upgrade to Apache #Lucene 10 and #JDK 21+
📈 Pull-based ingestion for streaming data, with support for Apache #Kafka and Amazon #Kinesis
📈 Power agentic #AI with native #MCP support
📈 Investigate logs with expanded PPL query tools, backed by Apache #Calcite

Check out @OpenSearchProject blog:
https://opensearch.org/blog/unveiling-opensearch-3-0/