rag | Iqraa.tech

Cut RAG Costs on Bedrock with Query-Aware Compression

AWS ML blog post on reducing RAG costs on Amazon Bedrock with query-aware compression

TL;DR 30 sec3 min coredeep dive optional Query-aware compression cuts RAG costs on Amazon Bedrock by 33 percent in AWS’s own benchmark: one extra small-model call strips retrieved context down to the spans that answer the actual query before the expensive model ever sees it. Tokens reaching the primary model dropped to 12 percent of… Continue reading →

RAG Techniques: the Advanced Collection, Mapped

Nir Diamant RAG Techniques repository on GitHub with numbered technique entries and Colab notebook links

TL;DR 30 sec6 min coredeep dive optional RAG techniques, as collected by Nir Diamant’s RAG_Techniques repository, fall into three working groups: how you cut documents, how you retrieve, and how you make the pipeline correct itself, and each group has a notebook you can run today. More than 30 techniques, each a runnable notebook, most… Continue reading →

LLM Zoomcamp: the Free 10-Week LLM Course

LLM Zoomcamp repository on GitHub showing the free 10 week course banner and module links for RAG, agents, and vector search

TL;DR 30 sec7 min coredeep dive optional LLM Zoomcamp is DataTalksClub’s free 10-week course on building production-ready LLM applications, running from agentic RAG and vector search through evaluation, monitoring, and a capstone, with no GPU and no ML background required. Seven modules plus a data-ingestion workshop and a capstone, taught through pre-recorded video and graded… Continue reading →

Gen AI Intensive: The Kaggle x Google 5-Day Course

Gen AI Intensive is the free Kaggle × Google 5-day course that 140,000 developers took in its first cohort. It covers large language models, embeddings, vector stores, agents, domain-specific models, and MLOps in five daily blocks of whitepaper plus podcast plus hands-on codelab. You leave with a working RAG pipeline, a LangGraph café ordering agent,… Continue reading →

06 - AWS RAG Optimization: Writing for Retrieval Accuracy

RAG optimization begins before a user submits a query, at the source documents that feed retrieval-augmented generation. Document and context engineering is the discipline of writing for two readers: the human who skims the page and the embedding model that chunks it. RAG Optimization: What You’ll Learn RAG optimization is the practice of writing and… Continue reading →

07 - AWS Vector Database for RAG: OpenSearch to pgvector

Vector database selection on AWS for RAG: compare OpenSearch, pgvector, MemoryDB, Neptune Analytics, DocumentDB, S3 Vectors, Bedrock Knowledge Bases, and Kendra in 2026.

Continue reading →

08 - AWS Healthcare RAG: Clinical Accuracy Architecture

Healthcare RAG on AWS using Amazon Bedrock, OpenSearch, and Neptune. Patient data augmentation, re-admission prediction, and talent management solutions grounded in HIPAA-eligible infrastructure.

Continue reading →