https://www.dhruvboghani.com/blog.htmlAI, LLM and data engineering https://www.dhruvboghani.com/blog/document-parsing-for-rag-pdfs-tables-and-scans.htmlhttps://www.dhruvboghani.com/blog/document-parsing-for-rag-pdfs-tables-and-scans.htmlFri, 30 Oct 2026 00:00:00 +0000How to parse documents for RAG: extracting clean text from PDFs, keeping tables intact, running OCR on scans, preserving structure and checking quality. https://www.dhruvboghani.com/blog/text-to-sql-with-llms-making-it-reliable.htmlhttps://www.dhruvboghani.com/blog/text-to-sql-with-llms-making-it-reliable.htmlThu, 29 Oct 2026 00:00:00 +0000How to make text-to-SQL with LLMs reliable: giving the model the right schema, safe read-only execution, validation, few-shot examples and evaluation. https://www.dhruvboghani.com/blog/rate-limiting-and-retries-for-llm-apis.htmlhttps://www.dhruvboghani.com/blog/rate-limiting-and-retries-for-llm-apis.htmlWed, 28 Oct 2026 00:00:00 +0000How to handle LLM API rate limits: request and token limits, exponential backoff with jitter, client-side throttling, queues, fallbacks and timeouts. https://www.dhruvboghani.com/blog/observability-for-llm-applications-tracing-cost-and-quality.htmlhttps://www.dhruvboghani.com/blog/observability-for-llm-applications-tracing-cost-and-quality.htmlTue, 27 Oct 2026 00:00:00 +0000How to monitor LLM applications in production: tracing each request, tracking tokens and cost, measuring latency, and evaluating answer quality over time. https://www.dhruvboghani.com/blog/idempotent-consumers-handling-duplicate-events-safely.htmlhttps://www.dhruvboghani.com/blog/idempotent-consumers-handling-duplicate-events-safely.htmlMon, 26 Oct 2026 00:00:00 +0000How to build idempotent consumers in event-driven systems: why duplicates happen, idempotency keys, processed-event tables, upserts and the outbox pattern. https://www.dhruvboghani.com/blog/hybrid-search-for-rag-combining-keyword-and-vector-search.htmlhttps://www.dhruvboghani.com/blog/hybrid-search-for-rag-combining-keyword-and-vector-search.htmlSun, 25 Oct 2026 00:00:00 +0000Why hybrid search improves RAG: combining BM25 keyword search with vector search, merging results with reciprocal rank fusion, and adding a reranker. https://www.dhruvboghani.com/blog/building-an-ai-copilot-inside-a-crm.htmlhttps://www.dhruvboghani.com/blog/building-an-ai-copilot-inside-a-crm.htmlSat, 24 Oct 2026 00:00:00 +0000How to build an AI copilot inside a CRM: useful features, grounding on CRM data, permission-aware retrieval, tool actions, review steps and measuring value. https://www.dhruvboghani.com/blog/real-time-dashboards-with-trino-and-apache-iceberg.htmlhttps://www.dhruvboghani.com/blog/real-time-dashboards-with-trino-and-apache-iceberg.htmlFri, 23 Oct 2026 00:00:00 +0000How to build near real-time dashboards on Trino and Apache Iceberg: streaming ingestion, commit intervals, table layout, compaction and fast queries. https://www.dhruvboghani.com/blog/semantic-caching-to-cut-llm-costs-and-latency.htmlhttps://www.dhruvboghani.com/blog/semantic-caching-to-cut-llm-costs-and-latency.htmlThu, 22 Oct 2026 00:00:00 +0000How semantic caching cuts LLM costs and latency: embedding-based lookups, similarity thresholds, cache keys, invalidation and when caching is unsafe. https://www.dhruvboghani.com/blog/guardrails-for-llm-applications-a-practical-guide.htmlhttps://www.dhruvboghani.com/blog/guardrails-for-llm-applications-a-practical-guide.htmlWed, 21 Oct 2026 00:00:00 +0000How to add guardrails to LLM applications: input checks, output validation, tool permissions, grounding and monitoring that keep AI features safe and reliable. https://www.dhruvboghani.com/blog/ai-agents-vs-chatbots-what-is-the-difference.htmlhttps://www.dhruvboghani.com/blog/ai-agents-vs-chatbots-what-is-the-difference.htmlTue, 20 Oct 2026 00:00:00 +0000AI agents vs chatbots explained: how they differ in goals, tools, memory and control, and how to decide which one your product actually needs. https://www.dhruvboghani.com/blog/data-quality-checks-in-streaming-pipelines.htmlhttps://www.dhruvboghani.com/blog/data-quality-checks-in-streaming-pipelines.htmlMon, 19 Oct 2026 00:00:00 +0000How to add data quality checks to streaming pipelines: schema, validity, freshness, volume and duplicates, plus dead-letter queues and alerts that matter. https://www.dhruvboghani.com/blog/schema-evolution-in-apache-iceberg.htmlhttps://www.dhruvboghani.com/blog/schema-evolution-in-apache-iceberg.htmlSun, 18 Oct 2026 00:00:00 +0000How Apache Iceberg handles schema evolution with column IDs: adding, renaming, dropping and widening columns without rewriting data or breaking readers. https://www.dhruvboghani.com/blog/change-data-capture-cdc-explained.htmlhttps://www.dhruvboghani.com/blog/change-data-capture-cdc-explained.htmlSat, 17 Oct 2026 00:00:00 +0000What change data capture is, how log-based CDC works, how it compares to batch extracts, and the pitfalls to plan for when streaming database changes. https://www.dhruvboghani.com/blog/embedding-models-how-to-choose-one.htmlhttps://www.dhruvboghani.com/blog/embedding-models-how-to-choose-one.htmlFri, 16 Oct 2026 00:00:00 +0000How to choose an embedding model for semantic search and RAG: quality on your data, dimensions, context length, language, cost, latency and hosting. https://www.dhruvboghani.com/blog/rag-evaluation-how-to-measure-answer-quality.htmlhttps://www.dhruvboghani.com/blog/rag-evaluation-how-to-measure-answer-quality.htmlThu, 15 Oct 2026 00:00:00 +0000How to evaluate a RAG system: build a test set, measure retrieval and answer quality separately, use LLM judges carefully and track it in CI. https://www.dhruvboghani.com/blog/multi-tenant-saas-architecture-patterns.htmlhttps://www.dhruvboghani.com/blog/multi-tenant-saas-architecture-patterns.htmlWed, 14 Oct 2026 00:00:00 +0000Multi-tenant SaaS patterns compared: shared schema, schema per tenant and database per tenant, plus isolation, security, scaling and noisy neighbours. https://www.dhruvboghani.com/blog/speech-to-text-latency-in-voice-bots.htmlhttps://www.dhruvboghani.com/blog/speech-to-text-latency-in-voice-bots.htmlTue, 13 Oct 2026 00:00:00 +0000Why voice bots feel slow and how to cut speech-to-text latency with streaming ASR, better endpointing, partial results and a tighter voice pipeline. https://www.dhruvboghani.com/blog/llm-function-calling-explained.htmlhttps://www.dhruvboghani.com/blog/llm-function-calling-explained.htmlMon, 12 Oct 2026 00:00:00 +0000How LLM function calling works: tool schemas, the request loop, argument validation, errors and security, with a practical example in Python. https://www.dhruvboghani.com/blog/lakehouse-vs-data-warehouse.htmlhttps://www.dhruvboghani.com/blog/lakehouse-vs-data-warehouse.htmlSun, 11 Oct 2026 00:00:00 +0000Lakehouse vs data warehouse compared: storage, table formats, cost, performance, governance and how to choose the right one for your data platform. https://www.dhruvboghani.com/blog/chunking-strategies-for-rag.htmlhttps://www.dhruvboghani.com/blog/chunking-strategies-for-rag.htmlSat, 10 Oct 2026 00:00:00 +0000How to chunk documents for RAG: fixed-size, recursive, structure-aware and semantic splitting, chunk size, overlap and metadata that matter. https://www.dhruvboghani.com/blog/prompt-engineering-for-structured-json-output.htmlhttps://www.dhruvboghani.com/blog/prompt-engineering-for-structured-json-output.htmlFri, 09 Oct 2026 00:00:00 +0000How to make an LLM return valid JSON using a schema, a response format, validation, and a retry when the shape is wrong. https://www.dhruvboghani.com/blog/apache-flink-stateful-stream-processing-basics.htmlhttps://www.dhruvboghani.com/blog/apache-flink-stateful-stream-processing-basics.htmlThu, 08 Oct 2026 00:00:00 +0000How Flink keeps state in a streaming job, including keyed state, checkpoints, watermarks, and what fails in production. https://www.dhruvboghani.com/blog/kafka-vs-redpanda-for-real-time-pipelines.htmlhttps://www.dhruvboghani.com/blog/kafka-vs-redpanda-for-real-time-pipelines.htmlWed, 07 Oct 2026 00:00:00 +0000How Kafka and Redpanda differ for streaming pipelines, covering the API, operations, storage, and when each one fits. https://www.dhruvboghani.com/blog/vector-database-comparison-pgvector-vs-pinecone.htmlhttps://www.dhruvboghani.com/blog/vector-database-comparison-pgvector-vs-pinecone.htmlTue, 06 Oct 2026 00:00:00 +0000A practical comparison of pgvector and Pinecone for AI and data engineers, focusing on architecture, performance, and use cases. https://www.dhruvboghani.com/blog/how-voice-ai-agents-work.htmlhttps://www.dhruvboghani.com/blog/how-voice-ai-agents-work.htmlMon, 05 Oct 2026 00:00:00 +0000The building blocks of a real-time voice AI agent, from telephony and speech-to-text to the LLM, text-to-speech and CRM updates. https://www.dhruvboghani.com/blog/iceberg-time-travel.htmlhttps://www.dhruvboghani.com/blog/iceberg-time-travel.htmlSun, 04 Oct 2026 00:00:00 +0000How Iceberg snapshots let you query past versions of a table with Trino, debug bad loads and roll back safely. https://www.dhruvboghani.com/blog/what-is-rag.htmlhttps://www.dhruvboghani.com/blog/what-is-rag.htmlSat, 03 Oct 2026 00:00:00 +0000Retrieval-Augmented Generation explained: how it works, when to use it, and the mistakes that make RAG systems give bad answers.