Embeddings
10 pieces on Embeddings, including 2 step-by-step guides.
Guides
Run an LLM Locally to Interact with Your Documents: Complete Ollama & Open WebUI Guide
Build a completely offline, zero-leakage local document intelligence system using Ollama, Open WebUI, and nomic-embed-text with custom chunking and system prompt engineering.
Building Context-Aware Search in Python with LLM Embeddings and Metadata
A complete guide to constructing a semantic engine using SentenceTransformers and pre-filtering metadata to return context-rich results.
News & Analysis
740M EmbeddingGemma 2 Maps Text, Image, Video and Audio
Google DeepMind's Apache 2.0 EmbeddingGemma 2 maps text, code, images, video and audio into one 768-dimension space, scaling from 270M to 740M parameters.
Perplexity's 9B Contextual Embedder Beats voyage-context-4 by 14.4 Points
Perplexity releases pplx-embed-v2-context-9b-preview, an open-weights 9B RAG embedder that scores 45.5% Answer Recall@10 and cuts storage 8× vs float32.
Perplexity's Ivy, Tulip and ROSE Serve pplx-embed Without a Separate Engine
Perplexity reuses its LLM prefill/decode kernels for embedding inference, with 512 tokens saturating a sub-1B model on Hopper and Blackwell hardware.
Sentence Transformers v6.0 Adds ColBERT Training in 14.5 Hours on One GPU
Sentence Transformers v6.0 adds MultiVectorEncoder with full ColBERT-style training. A single RTX 3090 run beats every zero-shot retriever by 0.06 NDCG@10.
ME-POIs: Google's 53.7M-Parameter Model Adds Visit Rhythms to Place Embeddings
Google Research's ME-POIs boosts text-based place embeddings with human movement data, hitting +81.9% F1 on visit intent and beating Gemini on price-level classification.
ColBERT Late Interaction Lands in Sentence Transformers v6.0
Sentence Transformers v6.0 adds MultiVectorEncoder, bringing ColBERT-style late interaction retrieval—42× larger indexes, 26-point MLDR gains—into one pip install.
OlmoEarth Studio Now Exports Custom Embedding Vectors as COGs
Allen Institute for AI adds COG embedding exports to OlmoEarth Studio, enabling similarity search, few-shot segmentation, and change detection with three encoder sizes.
Why Vector Databases are Essential for Enterprise AI
A deep dive into embeddings, semantic search, and why standard SQL databases aren't enough for LLM context retrieval.