#semantic-search — Public Fediverse posts

via @dotnet : Microsoft Agent Framework – Building Blocks for AI Part 3

https://ift.tt/CQUJ8zm
#MicrosoftAgentFramework #AIAgent #BuildingBlocksForAI #MEAI #MicrosoftExtensionsForAI #VectorData #RAG #SemanticSearch #AIinDotNet #AgentFramework #AIContextProvider …

I spent some time trying to make search behavior visible in one small Quarkus app.

Full-text is good at exact terms. Vector search helps when user language and catalog language drift apart. Hybrid is usually the one I’d trust first in a real product search.

This article walks through all three with Quarkus, PostgreSQL, Elasticsearch, Hibernate Search, and local embeddings.

https://www.the-main-thread.com/p/full-text-vector-hybrid-search-quarkus-java

#Java #Quarkus #PostgreSQL #Elasticsearch #SemanticSearch #HibernateSearch #VectorSearch

📚 Kilo Code Series #5: Codebase Indexing with Nomic & Qdrant!

Enable semantic AI search across your entire codebase.

📖 Read: https://devopstales.github.io/ai/kilo-code-series-05-indexing/?utm_source=twitter&utm_medium=social

#KiloCode #AI #Indexing #SemanticSearch

pg_semantic_cache: an open-source extension that enables semantic query result caching in #PostgreSQL. Traditional caching requires exact query matches; this extension uses vector embeddings to find and retrieve cached results for semantically similar queries.

✨ Give the project a try on GitHub (and don't forget to star the project while you're there): https://github.com/pgEdge/pg_semantic_cache

➡️ Read more: https://www.pgedge.com/blog/pg_semantic_cache-in-production-tags-eviction-monitoring-and-python-integration

#postgres #data #llm #semanticsearch #ai #aiengineering #opensourceai #opensource

via @dotnet : Vector Data in .NET – Building Blocks for AI Part 2

https://ift.tt/VtJUvye
#VectorData #NET #AI #BuildingBlocks #SemanticSearch #RAG #Embedding #Embeddings #VectorDatabase #Qdrant #Redis #CosmosDB #SQLServer #PostgreSQL #SQLite #InMemory #VectorSto…

Did you know? Our pgedge-vectorizer tool (on GitHub: https://github.com/pgEdge/pgedge-vectorizer) automatically chunks text content and generates vector embeddings with the help of background workers.

OpenAI, Voyage AI, and Ollama are supported as embedding providers, and a simple SQL interface allows you to enable vectorization on any table. (There’s even built-in views and functions for monitoring queue status.)

#github #opensource #semanticsearch #vector #vectordatabase #openai #ollama #voyageai

via @dotnet : .NET AI Essentials – The Core Building Blocks Explained

https://ift.tt/CjSQkpt
#NET #DotNet #CSharp #AI #ArtificialIntelligence #MEAI #MicrosoftExtensionsAI #LLM #SemanticSearch #VectorData #Embeddings #AgentFramework #ModelContextProtocol #MCP #Mi…

I'll be speaking at PHP Tek in May — two talks I've been building toward for a while.

**Kubernetes for PHP Developers**: The translation guide from Docker Compose to production K8s. No 40-hour course required.

**Semantic Search in Laravel**: Building search that understands meaning using pgvector and embeddings. Based on what I built for DailyMedToday.

Both talks from production experience, not theory.

Full details: https://eric.mann.blog/speaking-at-php-tek-2026/

#PHP #Kubernetes #Laravel #PHPTek #SemanticSearch

RAG-системы: что это такое, принципы работы, архитектура и ограничения

Retrieval-Augmented Generation (RAG) всё чаще упоминается в контексте LLM и всё чаще фигурирует в требованиях к разработчикам, но за этим термином обычно скрывается довольно размытое представление о том, как такие системы реально устроены. В этой статье я разбираю RAG как архитектурный подход: зачем он вообще появился, какие задачи решает, как выглядит базовый пайплайн от данных до ответа модели и где на практике чаще всего возникают проблемы.

https://habr.com/ru/articles/989000/

#rag #llm #retrieval #nlp #embeddings #semanticsearch #informationretrieval

How small shifts in phrasing reveal whether an agent understands intent or only echoes words. https://hackernoon.com/when-the-words-change-but-the-meaning-shouldnt-paraphrases-as-stress-loads #semanticsearch

Learn to build a local AI semantic search engine with Ollama and TypeScript. No cloud APIs needed—understand intent, not just keywords. Free and
priv https://hackernoon.com/local-ai-powered-search-engine-using-slm-embeddings #semanticsearch

FYI: Semantic Search: Understanding User Intent & Content #shorts: Semantic search moves beyond simple text matching. It's about understanding the relationship between user queries, content, and the domain it exists within, ensuring more relevant search results. #semanticsearch #SEO #contentstrategy #userintent https://www.youtube.com/shorts/kSRILR1R2p0

Searching for Meaning (1 of 2): The Technology Behind Semantic Search timdasey.substack.com/p/searching-fo… (useful explanations) #AI #SemanticSearch

Searching for Meaning (1 of 2)...

via #AIFoundry : Foundry IQ in Microsoft Agent Framework

https://ift.tt/7pPmwX4
#FoundryIQ #MicrosoftAgentFramework #AI #Python #RAG #KnowledgeBase #AzureAI #EnterpriseAI #MultiHopReasoning #SemanticSearch #AIIntegration #OpenSource #IntelligentRetrieval #DataManagement #Clou…