Tag

RAG

6 articles tagged with “RAG”

.d.ts A/B-testing ACR AI AI-Search API-gateway API-providers APM ASP.NET-Core Alertmanager Anthropic-API Arize AutoGen Azure-APIM Azure-OpenAI Bedrock Bundler CI Capitalize Claude CoT Copilot Cosmos-DB Cursor DORA DefinitelyTyped Docker-Hub Event-Grid FinOps GHCR GPT Gemini Gemma GitFlow GitHub Google-DeepMind Groq GroupChat HPA Helm ICL Istio JSON JSON-mode LLM LLM-monitoring LLM-security LangChain LangGraph LangSmith Linkerd MCP MTEB Mistral Model-Context-Protocol Node16 OIDC OTEL Omit OpenAI-API OpenTelemetry Outlines P99 PII PII-filtering PagerDuty Partial Phi Phoenix Pick Pinecone Qdrant RAG RAG-evaluation ReAct Record SDK SLI SLM SLO Semantic-Kernel Service-Bus TC39 TTFT Vertex-AI Windsurf a-star agents aggregation ai ai-gateway aks alerting algorithms api-design api-gateway api-versioning apim app-router app-service appsec architecture arm-templates aspnet-core aspnetcore assertion-functions asserts async audit authentication authorization automation azure azure-content-safety azure-front-door azure-functions azure-openai azure-policy azure-storage batch-API bdd benchmarks best-practices bfs bi-encoder bias-detection bicep binary-search branching bst cache-components caching cap-theorem capability-tagging cascading case-based-reasoning chain-of-thought charts chatbot checkpointing chunking ci-cd ci-optimization cicd class-decorator clean-architecture cloud cloud-security cloudevents code-review coding-agents comparison compilerOptions compliance compose concurrency concurrent-rendering conditional-types consistency consistent-hashing constrained-generation constraints consumer-driven container-registry containers content-moderation content-safety context context-compression context-window contract-testing conversational-agents cosmos-db cost-allocation cost-control cost-optimization cost-performance coverage cqrs cross-session csharp cve cypress dapper dashboards dast data-fetching databases dataloader ddd decision-framework declaration-files decorators dependency-injection dependency-scanning deployment-slots deployments deprecation design-patterns devops dfs dijkstra discriminated-unions distributed-tracing distributive docker documentation dotnet dotnet-9 drift-detection dynamic-discovery dynamic-programming e2e-testing ef-core ef-core-9 embeddings engineering environments episodic-memory error-budget evaluation event-driven event-grid event-hubs eventing examples experience-replay experimentalDecorators factuality fail-fast feature-flags federation few-shot fiber fine-tuning flaky-tests flex-consumption frontend function-calling gen-ai-semantic-conventions generics git github-actions goal-decomposition golden-signals gpt-4o grammar graph graphql grounding grpc guardrails hallucination-detection harmful-content hcl health-checks heap hooks hotchocolate http http2 http3 hybridcache iac idempotency identity image-scanning in-context-learning incident-response indexes infer inference infrastructure input-validation integration integration-testing introsort invariant isolation jailbreak jest joins jotai jsonb jwt k8s key-remapping key-vault kiota knapsack knowledge-base kubernetes language latency legacy-code linq load-balancing long-term-memory lost-in-the-middle lower-bound mTLS managed-identity mapped-types materialized-views memoization memory memory-consolidation merge message-queue messaging metadata metrics microservices microsoft minimal-apis mocking mocks model-routing moderation module-augmentation module-resolution modules mongodb monitoring msw multi-agent multi-stage-builds multi-tenant multimodal mvcc narrowing network-security nextjs-16 normalization nosql oauth oauth2 observability oidc on-call online-evals opa open-source openapi orchestration output-format output-validation owasp paas package-exports pact pactflow page-objects parsing partitioning paths pattern-matching performance personal-AI pgvector pinecone pipeline planning playwright plugins policy-as-code polly postgresql pricing production production-monitoring project-references prompt-design prompt-engineering prompt-injection protobuf pulumi python quality quality-gates quality-score quantization queues rag rate-limiting react react-19 react-compiler react-internals react-query react-server-components realtime reasoning recursion recursive-types red-black red-green-refactor red-teaming redis regression-testing release-management replanning resource-limits rest reusable-workflows rls rolling-updates runtime-safety saga-pattern sast sbom scale schema schema-design schema-validation sdlc secrets-management security security-testing self-consistency semantic-similarity serializable server-actions serverless service-bus service-mesh sharding shortest-path sidecar-proxy signalr snapshot-testing software-design sorting spies sql stability state-graph state-management streaming streams strict-mode stride string-types structured-output stubs summarisation supertest supply-chain system-design tail-call tanstack-query task-framing tdd template-literals templates terraform test-architecture test-doubles test-pyramid testcontainers testing testing-patterns testing-strategy threat-modeling token-bucket token-budget token-economics token-limit token-masking token-tracking tokens tokens-per-second tool-calling tool-registry tool-use topological-sort toxicity tracing trajectory transactions trees trie trunk-based tsconfig type-guards type-narrowing type-predicates type-safe-routes type-system type-transforms types typescript unit-testing usage-metrics user-feedback utility-types validation valkey values vault vector-db vector-search vector-store vendor-neutral version-control versioning visual-regression vitest vulnerabilities weaviate web-api web-security websockets window-functions wiremock working-memory workload-identity workspaces xunit yarp zero-shot zero-trust zod zustand

AI Engineering

Designing RAG Systems That Actually Scale

Intermediate

Chunking strategies, embedding pipelines, retrieval patterns, and when RAG breaks down in production systems.

14 Jan 202612 min

Read →

Databases

Vector Database Selection for Production RAG

Cosmos DB, AI Search, Qdrant, Pinecone — benchmarks, cost, and operational complexity for production vector search.

11 Feb 20269 min

Read →

AI Engineering

How to Build a Production-Ready AI System (Azure OpenAI + AI Search — Real Architecture)

Advanced

Azure OpenAI + AI Search + embeddings — real-world architecture for production AI systems, including legacy data, orchestration, hybrid retrieval, cost control, and failure modes.

18 Feb 202615 min

Read →

AI Engineering

When to Fine-Tune vs Few-Shot vs RAG

Intermediate

A decision framework for choosing between fine-tuning, few-shot prompting, and RAG for production LLM applications.

22 Jan 202610 min

Read →

AI Engineering

Building a Personal AI Knowledge Base

How to build a personal RAG system over your notes, bookmarks, and documents — using embeddings, vector search, and a conversational interface.

25 Jan 202611 min

Read →

AI Engineering

Embeddings: From Theory to Production Choice

Intermediate

Convert text, images, and code into dense vectors that capture semantic meaning — the foundational primitive of modern AI systems, and the choice that dominates RAG quality.

26 May 202611 min

Read →