embeddings archivos

nomic-embed-text: Competitive Open Embeddings

Nomic released an open-source embeddings model rivaling OpenAI. When to use, comparison, and how to integrate in your RAG.

OpenAI released text-embedding-3 with higher quality and the variable-dimensions trick. How to leverage what’s new without rebuilding your RAG stack.

pgvector 0.5 added HNSW and changed the conversation. When PostgreSQL with pgvector is enough, how to index well, and where it starts to hurt.

Cohere Embed v3 added internal document-quality ranking and kept its multilingual focus. How it compares with OpenAI and when it fits better.

Vector databases have gone from experimental to backbone of LLM products. A pragmatic comparison of the three most-used options in 2023.

pgvector turns PostgreSQL into a competent vector database. When to choose it over Qdrant or Pinecone and how to configure it well.

Embeddings turn text into vectors with semantic meaning. How they’re generated, which models to choose, and what they’re really useful for.

Chroma is the simplest option to start with embeddings and semantic search. When it shines, when it falls short, and how to deploy it.