freekmurze4d ago
🔗 Building RAG in Laravel: Four Ingestion Bugs That Silently Wreck Retrieval
https://mujahidabbas.dev/blog/building-rag-laravel-pgvector/
#php #laravel #ai #rag #vectordatabase
Building RAG in Laravel: Four Ingestion Bugs That Silently Wreck Retrieval - Blog

Every Laravel RAG tutorial builds the same ingestion pipeline and never checks if it works. Four decisions — chunking, the pgvector index operator, embedding dimensions, the model lock — quietly wreck retrieval with no error. Here's each bug, and how the eval catches it.

Mujahid Abbas - Full Stack Developer
Meteora WebJun 12

🚨 NEWS: Vector Database per sviluppatori: Chroma, Pinecone e Weaviate – come scegliere

Ecco i punti chiave in breve:
💡 Hai un modello di embedding che produce vettori da 1536 dimensioni, una collezione di 100.000 documenti e un'applicazione RAG che deve rispondere in meno di due secondi. Il problema non è più generare...

🚀 LINK: https://meteoraweb.com/intelligenza-artificiale-software/vector-database-per-sviluppatori-chroma-pinecone-e-weaviate-come-scegliere

#sviluppatori #rAG #embedding #vectorDatabase #chroma

Meteora WebJun 12

🚨 NEWS: LangChain e LLM per Sviluppatori: la Pillar Guide per Costruire Applicazioni AI in Produzione

Ecco i punti chiave in breve:
💡 Il problema: state costruendo un prototipo che non reggerà mai il traffico realeAvete un LLM che risponde, una chiamata API che funziona in console e un entusiasmo che dura fino al primo caricamento l...

🚀 LINK: https://meteoraweb.com/intelligenza-artificiale-software/langchain-e-llm-per-sviluppatori-la-pillar-guide-per-costruire-applicazioni-ai-in-produzione

#lLM #langChain #rAG #vectorDatabase #embeddings

phanmemnhanhoaJun 11

"⚡ Bạn có biết các hệ thống AI tìm kiếm hình ảnh, âm thanh và văn bản như thế nào không?

Đọc bài viết này, bạn sẽ nắm rõ:
✅ Định nghĩa và tầm quan trọng của Vector nhúng (Embedding Vector)
✅ Điểm vượt trội của Vector Database so với SQL và NoSQL
✅ Ứng dụng thực tế trong hệ thống gợi ý (Recommendation System)
✅ Cách lựa chọn giải pháp Vector Database phù hợp cho dự án AI

📌 Khám phá ngay bài tổng hợp từ Nhân Hòa:
https://nhanhoa.com/tin-tuc/vector-database-la-gi.html

#machinelearning #vectordatabase #llm #nhanhoa"

CrAIg WallsJun 8

Semantic caching can use any vector store. If you’re already using a vector store such as Qdrant, you can use it to speed up semantically similar requests and reduce token usage without adding another database to your stack.

#SpringAI #Java #GenAI #SemanticCaching #VectorDatabase

https://medium.com/@thetalkingapp/spring-ai-recipe-semantic-caching-with-any-vector-store-8b5022be91cb

Zuri (he/him) ❌️👑 | 🕐 CETMay 30

How many times do you need to shuffle a card deck to make it truly random?

How much uranium does one need for a nuclear bomb?

How does autocomplete work?

The answer are #MarkovChains

How a feud in Russia led to modern prediction algorithms.

https://www.youtube.com/watch?v=KZeIEiBrT_w

https://piped.video/watch?v=KZeIEiBrT_w

https://inv.nadeko.net/watch?v=KZeIEiBrT_w

#Mathematics #science #computerScience #LLMs #AI #artificialIntelligence #vectorDatabase #RAG #WordEmbeddings #MachineLearning #DeepLearning #ManhattanProject #Veritasium #Yahoo

The Strange Math That Predicts (Almost) Anything

YouTube
Doug OrtizMay 6

What if your RAG system is 60% slower because you're feeding it too much context?

Here's the context window optimization trick that's revolutionizing retrieval-augmented generation performance.

If you're wrestling with RAG performance, drop a comment or send a connection request.

#RAG #AI #VectorDatabase #PostgreSQL #pgVector #dougortiz

anonchegApr 21

Title: P2: Choosing vector database [2024-07-29 Mon]
vectors
- Parallelization and Distributed Processing

Mantra for: My body wants joy to be fried. My mind wants
to succeed. My soul don't need anything.
😶 #dailyreport #rag #embeddings #encoder #vectordatabase

anonchegApr 21
Title: P2: P1: Choosing vector database [2024-07-29 Mon]
partition the vector space and facilitate efficient
nearest neighbor search.
- Compression and Quantization - Reducing the
dimensionality and precision of vector embeddings, sparce #dailyreport #rag #embeddings #encoder #vectordatabase
anonchegApr 21
Title: P1: P1: Choosing vector database [2024-07-29 Mon]
- Approximate Nearest Neighbor (ANN) indexing
- locality-sensitive hashing (LSH), product quantization
(PQ), or hierarchical navigable small world graphs (HNSW)
- Tree-based Indexing - k-d trees or ball trees to #dailyreport #rag #embeddings #encoder #vectordatabase