DEV Community

#embeddings

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Embedding Drift: Detect, Monitor & Swap Models Safely

Embedding Drift: Detect, Monitor & Swap Models Safely

Comments
4 min read
Our task categorizer routed 46% of tasks. A $0.04/MTok decision model routes 97%.

Our task categorizer routed 46% of tasks. A $0.04/MTok decision model routes 97%.

Comments
3 min read
AI Engineering for JavaScript Developers: What You Actually Need to Learn

AI Engineering for JavaScript Developers: What You Actually Need to Learn

1
Comments
13 min read
Semantic Caching Cuts Token Costs for Repeat LLM Prompts

Semantic Caching Cuts Token Costs for Repeat LLM Prompts

Comments
5 min read
Python Semantic Cache: Cut Free-Tier LLM Token Costs

Python Semantic Cache: Cut Free-Tier LLM Token Costs

Comments
6 min read
Your Semantic Cache Answers the Question Next Door

Your Semantic Cache Answers the Question Next Door

7
Comments 1
15 min read
Embeddings explained for people who write code

Embeddings explained for people who write code

Comments 6
4 min read
Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM

Qwen3 Embedding on Cloud TPU: Production Long-Context Retrieval with vLLM

Comments
4 min read
Building a RAG Retrieval Service: pgvector, Embedding Migrations, and Provenance Tracking

Building a RAG Retrieval Service: pgvector, Embedding Migrations, and Provenance Tracking

Comments
3 min read
jina-embeddings-v4 as an OpenAI-Compatible Embeddings Server

jina-embeddings-v4 as an OpenAI-Compatible Embeddings Server

6
Comments 1
4 min read
Embeddings: Meaning as Numbers

Embeddings: Meaning as Numbers

1
Comments
10 min read
Embedding Drift Monitoring — Practical AI Engineering Guide

Embedding Drift Monitoring — Practical AI Engineering Guide

1
Comments
4 min read
Hybrid Retrieval v2: Qwen Embeddings, BM25, and RRF with a FastEmbed Reranker

Hybrid Retrieval v2: Qwen Embeddings, BM25, and RRF with a FastEmbed Reranker

Comments
10 min read
Un chatbot RAG multilingüe sobre tus PDFs con FAISS y reranking (coste de búsqueda: 0 €)

Un chatbot RAG multilingüe sobre tus PDFs con FAISS y reranking (coste de búsqueda: 0 €)

Comments
2 min read
Why I Chose PDF RAG Chunking and Metadata for Catalog Semantic Search

Why I Chose PDF RAG Chunking and Metadata for Catalog Semantic Search

Comments
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.