8 min read
DiskANN in Azure SQL Is GA: Do You Still Need a Separate Vector Store?
DiskANN vector indexes are now GA in Azure SQL and Fabric SQL. When embeddings belong next to your rows, and when Azure AI Search still wins.
RAG
91 articles
8 min read
Hybrid Search in PostgreSQL: What It Costs to Own the Fusion
Azure AI Search and Cosmos DB fuse keyword and vector results for you; pgvector doesn't. What owning RRF in PostgreSQL involves, and when it pays.
8 min read
Splitting an AI Journey's Latency Budget Across Its Steps
A journey-level latency budget only works when each step gets a cap, a timeout and a fallback; here is how to split one across a RAG request.
9 min read
RAG Citations People Can Check: Treat Them as Part of the Answer
Good retrieval is wasted if users cannot verify the answer, so design RAG citations to be checkable, validated in code and measured like relevance.
8 min read
Hybrid Search for RAG: Test What the BM25 Leg Rescues
Hybrid search is default RAG advice, but the BM25 leg has real costs; a three-way test on Azure AI Search shows which questions it rescues.
7 min read
Raising Groundedness Without Guesswork: Label the Failures First
Once retrieval is ruled out, ungrounded answers fall into a few repeatable patterns: label them, fix one at a time and track completeness too.
8 min read
Treat Retrieval Changes Like Schema Changes: A RAG Regression Gate
Make retrieval-first a team rule: an owned question set, a side-by-side index comparison on Azure AI Search, and a gate that fails on lost answers.
8 min read
Designing LLM Test Cases That Catch Hallucinations
Most eval sets only ask questions the documents can answer. Add unanswerable, false-premise and stale-context cases, each with an expected behaviour.
8 min read
Is Your Reranker Earning Its Place? Test It Before You Pay for It
The semantic ranker only reorders the top 50 results. A with-and-without test on a labelled set shows which RAG queries it rescues and which it just slows.
7 min read
Wrong RAG Answer? Rule Out Retrieval Before You Edit the Prompt
Most wrong RAG answers start with the passages, not the prompt. A labelled question set and a retrieval-only triage on Azure AI Search show which one to fix.
8 min read
Gating LLM Changes on Groundedness Flips, Not Fluency Averages
How I compare a baseline and a candidate prompt or model on frozen context, count groundedness regressions per row, and treat fluency as a tie-breaker.
8 min read
Fine-Tuning or RAG? Decide by the Failure You're Fixing
Fine-tuning and RAG fix different failures. How to tell which one you have on Microsoft Foundry in early 2026, what each costs, and when to combine them.
8 min read
Agentic Retrieval or a Hand-Built RAG Pipeline? How I Decide
Azure AI Search knowledge bases now plan queries for you, in preview. When to hand over the RAG pipeline, when to keep building it, and how to test both.
9 min read
Six Vector Stores for RAG and Where Each One Hurts
Azure AI Search, DocumentDB, Cosmos DB for NoSQL, pgvector, Pinecone and Redis each fail differently in RAG. Where each one hurts in January 2026.
9 min read
Seven RAG Failure Modes and the Pattern That Fixes Each
Diagnose why a RAG system fails before adding patterns: hybrid search, semantic reranking, grounding gates and citations on Azure AI Search, mapped to failures.
1 min read
Building a Custom GPT for Your Documentation with Azure OpenAI
This pattern works for any documentation. The key is good chunking, quality embeddings, and a well-crafted system prompt that keeps the bot focused on your…
1 min read
Building Production RAG Systems: Best Practices for 2026
Production RAG is iterative. Start simple, measure everything, and improve based on real user feedback.
1 min read
Vector Database Selection: Comparing Azure AI Search, Cosmos DB, and PostgreSQL
Azure AI Search, Cosmos DB with vector indexing, and Azure Database for PostgreSQL with pgvector each provide vector search capabilities with different…
1 min read
Azure AI Search: Implementing Hybrid Search for Better RAG Results
Pure vector search excels at semantic similarity but can miss exact keyword matches. Pure keyword search finds exact terms but misses conceptually similar…
1 min read
Prompt Engineering Patterns for Enterprise RAG Systems
Poorly designed prompts lead to hallucinations, ignored context, or responses that fail to meet business requirements. A systematic approach to prompt…
1 min read
GraphRAG: Combining Knowledge Graphs with Retrieval-Augmented Generation
GraphRAG excels when your questions involve multi-hop reasoning, relationship discovery, or when entity connections matter more than document similarity.
1 min read
Implementing Retrieval-Augmented Generation with Microsoft Fabric
Use Fabric notebooks to create interactive RAG applications that combine data exploration with AI-powered question answering over enterprise datasets.
1 min read
Implementing RAG with LangChain and Azure OpenAI
Experiment with chunk sizes, overlap, and retrieval strategies. Hybrid search combining semantic and keyword matching often provides the best results for…
1 min read
Azure AI Search: Implementing Hybrid Search with Vectors and Keywords
Hybrid search significantly improves retrieval quality for RAG applications by leveraging both semantic understanding and exact keyword matching.
1 min read
Retrieval-Augmented Generation: Chunking Strategies for Better Results
The best chunking strategy depends on your document types. Technical documentation benefits from header-aware chunking. Conversational content works well…
1 min read
Vector Database Selection: Choosing the Right Solution for RAG
The best vector database depends on your specific requirements. Azure AI Search excels for hybrid search with integrated semantic ranking. Pinecone offers…
1 min read
Hybrid Search: Combining Vector and Keyword Search in Azure AI Search
Vector search excels at semantic similarity but can miss exact matches. Keyword search finds precise terms but misses synonyms and context. Together, they…
1 min read
Embedding Models: Choosing Between OpenAI, Azure, and Open Source
The text-embedding-ada-002 and newer text-embedding-3 models provide high-quality embeddings with minimal setup.
1 min read
Vector Database Selection: Comparing Azure AI Search, Pinecone, and Qdrant
Best for organizations already invested in Azure with hybrid search requirements. Pros: Hybrid search, semantic ranking, enterprise security, managed…
1 min read
Implementing Hybrid Search in Azure AI Search
Keyword search excels at exact matches and rare terms. Vector search captures semantic similarity. Combining them leverages both strengths while mitigating…
1 min read
RAG Chunking Strategies: Finding the Optimal Approach
The simplest approach splits text at regular intervals with optional overlap. Semantic chunking respects content boundaries like paragraphs and sections.
1 min read
Building RAG Applications with Azure AI Search and GPT-4o
RAG works by first retrieving relevant documents from a search index, then passing those documents as context to an LLM for generation. This approach…
1 min read
Multimodal RAG: Combining Text, Images, and Tables for Enhanced Search
Multimodal RAG ensures users find relevant information regardless of how it's represented in the source documents.
1 min read
Evaluating RAG Systems: Metrics and Automated Testing with Azure AI
Fail builds when quality metrics drop below thresholds, catching regressions before they reach production.
1 min read
Azure AI Search Vector Optimization: Reducing Costs While Improving Recall
Vector search costs can spiral quickly at scale. After optimizing Azure AI Search deployments processing 50 million vectors, I've identified key patterns…
1 min read
Multimodal RAG: Retrieval Across Text, Images, and Documents
Multimodal RAG unlocks intelligence from documents containing text, tables, and images.
1 min read
Query Transformation Techniques: Improving RAG Recall
Query transformation is a high-leverage improvement for RAG systems.
1 min read
Reranking Strategies: Improving RAG Precision
Cross-encoder reranking typically improves RAG precision by 10-20%.
1 min read
Chunking Strategies for RAG: Finding the Right Granularity
Choose chunking strategy based on document structure and retrieval requirements.
1 min read
GraphRAG Implementation: Combining Graphs with Retrieval
GraphRAG excels at complex questions requiring synthesis across multiple documents.
1 min read
RAG Advanced Patterns: Beyond Basic Retrieval
Advanced RAG combines query expansion, hybrid retrieval, reranking, and context compression for better results.
1 min read
Multimodal RAG Advances: Images, Documents, and Beyond
Multimodal RAG unlocks knowledge trapped in visual formats. Start with document-heavy use cases where diagrams and charts carry critical information.
1 min read
Hybrid Search Improvements: Latest Techniques for Better Retrieval
Hybrid search continues to outperform pure vector or keyword approaches. Invest in tuning your fusion strategy for your specific domain.
7 min read
Multimodal RAG on Azure: Caption PDF Figures Before You Embed Them
Make diagrams and charts in PDFs retrievable with Document Intelligence 4.0 figure extraction, GPT-4o descriptions and Azure AI Search hybrid queries.
7 min read
Hybrid Search in PostgreSQL: pgvector, Full-Text and RRF in One Query
How to build hybrid search inside PostgreSQL with pgvector, full-text search and weighted reciprocal rank fusion, and when a dedicated search service is better.
8 min read
Where Should Your Vectors Live on Azure? Search Index vs Database
Azure AI Search, Cosmos DB for NoSQL and PostgreSQL with pgvector can all hold embeddings now. Here is how I decide between a search index and your database.
7 min read
GraphRAG 1.x: When Global Search Justifies the Indexing Bill
How Microsoft's GraphRAG 1.x builds a knowledge graph, what local, global and DRIFT search do, and when its indexing cost is worth paying over vector RAG.
8 min read
RAG Beyond Top-K: Retrieval Upgrades Worth Making in January 2025
Which RAG retrieval upgrades Azure AI Search gives you as GA or preview in January 2025, which you build yourself, and the order I'd add them in.
8 min read
Five LLM Application Patterns, From Least to Most Autonomy
A practical ladder of LLM patterns on Azure in January 2025: structured outputs, grounded RAG, tool workflows, self-review and agents.
1 min read
Filtered Vector Search in Azure AI Search: Best Practices
Pre-filtering: Filter before vector search Post-filtering: Filter after vector search Azure AI Search uses pre-filtering with automatic optimization.
1 min read
Azure AI Search Updates: What's New in Summer 2024
Expanded Vector Dimensions Semantic Ranking Improvements Customer-Managed Keys for Vectors
1 min read
Memory and State Management in AI Agents
AI agents need memory to maintain context across interactions. Today I'm exploring how to implement effective memory systems.
1 min read
End-to-End RAG Evaluation: Complete System Assessment
Individual component metrics tell part of the story, but end-to-end evaluation measures how well your entire RAG pipeline performs as a system.
1 min read
Context Recall in RAG: Are You Finding All Relevant Documents?
While context precision measures noise in retrieved results, context recall measures completeness. Are you retrieving all the documents needed to fully…
1 min read
Context Precision in RAG: Evaluating Retrieval Quality
Context precision measures whether the retrieved documents are actually relevant to answering the question. High precision means less noise for the…
1 min read
Answer Relevancy in RAG: Does the Response Address the Question?
An answer can be factually correct and grounded in context but still fail to address what was actually asked. Answer relevancy measures how well the…
1 min read
Faithfulness Scoring in RAG: Detecting Hallucinations
Faithfulness is perhaps the most critical metric for RAG systems. An unfaithful answer that hallucinates information not in the source documents can be…
1 min read
Generation Metrics for RAG: Measuring Answer Quality
While retrieval metrics measure what documents are found, generation metrics evaluate the quality of the synthesized answer. This guide covers metrics…
1 min read
Retrieval Metrics for RAG: A Deep Dive
The retrieval component of RAG systems directly impacts generation quality. This guide provides a comprehensive overview of retrieval metrics and how to…
1 min read
RAGAS Framework: Automated RAG Evaluation
RAGAS (Retrieval Augmented Generation Assessment) is an open-source framework for evaluating RAG pipelines. This guide covers how to implement and use RAGAS…
1 min read
RAG Evaluation: Measuring Retrieval-Augmented Generation Quality
Retrieval-Augmented Generation (RAG) systems combine retrieval and generation components, each requiring specific evaluation strategies. This guide covers…
1 min read
Cohere on Azure: Enterprise Search and RAG Solutions
Cohere's models are now available on Azure AI, offering specialized capabilities for enterprise search and retrieval-augmented generation (RAG). This guide…
7 min read
Azure AI Search Index Projections: Keys, Deletes and Chunk Order
The edge cases of index projections in Azure AI Search: what the chunk index schema needs, how keys change on re-index, deletes, and keeping chunk order.
7 min read
Tuning Hybrid Search in Azure AI Search: What RRF Lets You Change
Which hybrid search knobs Azure AI Search exposes on the 2023-11-01 API, why I avoid client-side score weighting, and how to measure changes before shipping.
7 min read
Keeping Azure AI Search Vector Indexes Small Without Compression
Azure AI Search has no built-in vector compression yet. How to estimate vector index size, read the quota, and cut it with chunking and dimension choices.
7 min read
Azure AI Search Semantic Ranker: Configuration, Thresholds and Cost
How to design semantic configurations, use reranker scores as a RAG cut-off, and decide when Azure AI Search's semantic ranker is worth paying for.
7 min read
Integrated Vectorization in Azure AI Search: What It Does and Doesn't Do
What integrated vectorization in Azure AI Search actually removes from a RAG pipeline, what it leaves behind, and when I'd still embed in my own code.
7 min read
Azure AI Search After Ignite 2023: What's GA and What's Still Preview
A January 2024 stock-take of Azure AI Search for RAG: which features are GA, which are preview, and which SDK and REST versions to build on.
6 min read
Self-Correcting RAG: Grade Retrieval Before You Answer
How to add retrieval grading, query rewriting, and groundedness checks to RAG on Azure OpenAI and Azure AI Search without tripling latency or cost.
6 min read
Structure-Aware Chunking for RAG: Headings, Tables and Breadcrumbs
Chunk documents along their headings, keep tables whole and prefix every chunk with its section path, using Document Intelligence markdown output and Python.
7 min read
A RAG Maturity Model: Diagnosing Where Your System Falls Short
A five-level RAG maturity model for Azure AI Search and Azure OpenAI, covering what each level fixes, what it costs, and when to stop climbing.
1 min read
Assistants Retrieval Tool: Building Knowledge Assistants
For many teams, the Assistants API's Retrieval tool removes the most tedious parts of building a knowledge assistant — you upload documents and the…
1 min read
Assistants API: File Handling and Knowledge Retrieval
I prefer the Assistants API's file-based retrieval when I need a fast, low-friction knowledge assistant — upload a set of documents and let the assistant…
2 min read
Building RAG Applications with Azure Cognitive Search and OpenAI
RAG with Azure Cognitive Search and Azure OpenAI is the production architecture I recommend most often for enterprise knowledge retrieval — not because it's…
1 min read
Multi-Index RAG: Querying Across Multiple Knowledge Sources
Implementing multi-index RAG systems to query and combine information from multiple knowledge sources.
1 min read
Recursive Retrieval for Complex RAG Queries
Implementing recursive retrieval strategies for handling complex, multi-step queries in RAG systems.
1 min read
Auto-Merge Retrieval for RAG Systems
Implementing auto-merge retrieval to automatically combine related chunks for comprehensive context.
1 min read
Sentence Window Retrieval for RAG Applications
Implementing sentence window retrieval to balance precision and context in RAG systems.
1 min read
Parent-Child Retrieval for RAG Systems
Implementing parent-child document retrieval to improve context and accuracy in RAG applications.
1 min read
Document Chunking Strategies for RAG Systems
Comprehensive guide to document chunking strategies for optimal retrieval in RAG applications.
1 min read
RAG Improvements: Advanced Retrieval Techniques
Advanced techniques for improving Retrieval-Augmented Generation systems for better accuracy and relevance.
1 min read
Vector Store Integrations: Choosing and Using Vector Databases
This concludes our August 2023 series on LLM optimization and vector stores.
1 min read
Hybrid Retrieval Patterns for RAG Applications
Hybrid retrieval improves RAG quality by combining the strengths of different search approaches. Tomorrow, I will cover Azure Dev Box and development…
2 min read
Copilot for Docs: Chat With Your Documentation
Copilot for Docs is one of the most concrete RAG applications Microsoft shipped publicly in this period—a conversational interface over documentation that…
1 min read
Implementing RAG with Azure Cognitive Search
RAG is the bridge between general-purpose LLMs and your specific enterprise data. Get it right, and you unlock tremendous value.
1 min read
Semantic Kernel Memory: Building AI with Long-Term Context
1. Organize into collections : Separate by topic/domain 2. Use meaningful IDs : Enable updates and deletions 3. Set appropriate relevance thresholds : Too…
1 min read
Re-ranking Search Results for Better RAG Performance
Cross encoders directly score query document pairs: Use an LLM to judge relevance: Using Cohere's specialized rerank API: 1. Retrieve more, re rank fewer :…
1 min read
Hybrid Search: Combining Vector and Keyword Search
A robust way to combine rankings: Adjust weights based on query characteristics: 1. Start balanced : 50/50 is often a good default 2. Tune on your data :…
1 min read
Document Chunking Strategies for RAG Systems
Simple but effective for uniform content: Respect sentence boundaries: Natural document structure: Use embeddings to find natural break points: Hierarchical…
1 min read
RAG Architecture Patterns: Building Production-Ready Systems
The basic pattern for straightforward use cases: Transform queries for better retrieval: Generate a hypothetical answer first, then use it for retrieval:…
7 min read
RAG on Azure OpenAI: Grounding GPT-3 Answers in Your Own Documents
What retrieval augmented generation is, why it beats fine-tuning for company knowledge, and a minimal loop on Azure OpenAI completions in January 2023.