Doug Ortiz2d ago

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

sayzardApr 28

EyeingAI (@EyeingAI)

Actian이 AI Dev 26 행사에서 온프레미스 벡터 데이터베이스 'VectorAI DB'를 발표했습니다. 단일 컨테이너로 배포 가능하다고 강조해, 벡터 DB 구축과 운영을 단순화하려는 AI 개발자에게 중요한 제품 소식입니다.

https://x.com/EyeingAI/status/2049181777932013739

#vectordatabase #onpremise #aidev #database #actian

EyeingAI (@EyeingAI) on X

Actian launched VectorAI DB at AI Dev 26 today, April 28. CTO on the mainstage, on-premise vector database, one container. I kinda hate how much I want this. I've spent the last year wiring up etcd clusters.

X (formerly Twitter)
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
anonchegApr 21

Title: P0: Choosing vector database [2024-07-29 Mon]
Today I have been choosing vector database for my little
project of RAG for cheepest PC.

The best open-source solutions that I consider:
SQLite-VEC, Redis, Clickhouse, ElasticSearch. (•́ᴗ•̀✿)

I am thinking now how to organize wide and massive amount
of information about PC configuration and files.
¯_(ツ)_/¯

Main approaches to implement vector database: #dailyreport #rag #embeddings #encoder #vectordatabase

sayzardApr 15

Akshay (@akshay_pachaar)

에이전트 메모리를 3차원으로 설계해야 한다는 관점을 제시했다. 단일 벡터DB 중심 메모리의 한계를 지적하며, 의미 유사성 외에도 다른 차원의 지식을 저장해야 한다는 새로운 에이전트 메모리 아키텍처 아이디어를 설명한다.

https://x.com/akshay_pachaar/status/2044329897603244093

#agentmemory #vectordatabase #aiagents #memory #architecture

Akshay 🚀 (@akshay_pachaar) on X

Agent memory is three-dimensional. Most agent memory systems use a single store. Usually a vector database. It handles semantic similarity well, but it captures only one dimension of knowledge. Here's the gap. Store these three facts: → Alice is the tech lead on Project Atlas

X (formerly Twitter)
Chinstrap CommunityApr 1

Zilliz - Provides a managed vector database service.

Cossmology Profile: https://dub.sh/HxFCcoG

Key People: Charles Xie, James Luan

#VectorDatabase #OpenSource #OSS #COSS

Rost GlukhovMar 26
Text embeddings for RAG and search - Python, Ollama, OpenAI-compatible APIs:
https://www.glukhov.org/rag/embeddings/
#Embeddings #RAG #Python #Ollama #LLM #SelfHosting #VectorDatabase
Text embeddings for RAG and search - Python, Ollama, OpenAI-compatible APIs

Learn what text embeddings are, how they power RAG and semantic search, and how to call embedding APIs from Python using Ollama or an OpenAI-compatible server (for example llama.cpp). Includes persistence, retrieval, and links to chunking, vector stores, and reranking on this site.

Rost Glukhov | Personal site and technical blog
Linux Professional InstituteMar 23

Databases for #AI: Should you use a vector #database? 🤔

This article compares #opensource projects competing to handle modern #AI workloads, including #machinelearning and #LLMs. Discover which databases best meet today’s AI challenges: https://lpi.org/636x

(Disclaimer: This post contains an AI-generated image.)

#AndyOram #AI #vectordatabase #machinelearning #LLMs #SQL #opensource #hybridsearch #generativeAI #MariaDB #MongoDB #Milvus #Qdrant #Weaviate #Vespa #ChromaDB #LanceDB