https://bsbhadwal.com/posts/Recent content in Posts on Bharat Singhhttps://bsbhadwal.com/images/bharat-singh.jpghttps://bsbhadwal.com/images/bharat-singh.jpgHugoenTue, 13 Oct 2026 00:00:00 +0530https://bsbhadwal.com/posts/reciprocal-rank-fusion-vs-cross-encoders-reranking-funnel/Mon, 12 Oct 2026 00:00:00 +0530https://bsbhadwal.com/posts/reciprocal-rank-fusion-vs-cross-encoders-reranking-funnel/Designing high-throughput hybrid retrieval reranking funnels combining Reciprocal Rank Fusion (RRF) and Cross-Encoder neural scoring under sub-50ms SLAs.https://bsbhadwal.com/posts/deterministic-guardrails-stateful-multi-agent-loops/Wed, 16 Sep 2026 00:00:00 +0530https://bsbhadwal.com/posts/deterministic-guardrails-stateful-multi-agent-loops/Engineering deterministic state-machine guardrails in autonomous multi-agent loops to prevent trajectory drift, infinite loops, and token budget exhaustion.https://bsbhadwal.com/posts/context-caching-vs-semantic-caching-latency-physics/Wed, 19 Aug 2026 00:00:00 +0530https://bsbhadwal.com/posts/context-caching-vs-semantic-caching-latency-physics/Architectural comparison of LLM context caching and semantic caching. Analyzing TTFT, token economics, cache hit ratios, and multi-agent latency budgets.https://bsbhadwal.com/posts/colbert-late-interaction-at-scale-memory-bandwidth-physics/Wed, 22 Jul 2026 00:00:00 +0530https://bsbhadwal.com/posts/colbert-late-interaction-at-scale-memory-bandwidth-physics/Deep architectural analysis of ColBERT late interaction multi-vector retrieval, memory bandwidth physics, PLAID indexing, and sub-50ms latency SLAs.https://bsbhadwal.com/posts/evaluating-rag-without-ground-truth-llm-as-a-judge-pitfalls/Mon, 15 Jun 2026 00:00:00 +0530https://bsbhadwal.com/posts/evaluating-rag-without-ground-truth-llm-as-a-judge-pitfalls/Production analysis of evaluating enterprise RAG pipelines without human ground truth, mitigating LLM-as-a-judge bias, and building empirical synthetic test sets.https://bsbhadwal.com/posts/semantic-nanopublications-to-knowledge-graphs-rag-grounding/Wed, 20 May 2026 00:00:00 +0530https://bsbhadwal.com/posts/semantic-nanopublications-to-knowledge-graphs-rag-grounding/Applying 15 years of semantic web nanopublication principles and RDF graph triples to establish verifiable provenance and mitigate hallucination in enterprise RAG pipelines.https://bsbhadwal.com/posts/shrinking-billion-scale-vector-indexes-matryoshka-embeddings-binary-quantization/Sat, 18 Apr 2026 00:00:00 +0530https://bsbhadwal.com/posts/shrinking-billion-scale-vector-indexes-matryoshka-embeddings-binary-quantization/Techniques for shrinking billion-scale vector indexes using Matryoshka Representation Learning (MRL) and 1-bit binary quantization with Hamming distance rescoring.https://bsbhadwal.com/posts/the-retrieval-fallacy-why-more-tokens-dont-equal-better-context/Thu, 12 Mar 2026 00:00:00 +0530https://bsbhadwal.com/posts/the-retrieval-fallacy-why-more-tokens-dont-equal-better-context/Why 1M+ token context windows do not replace Information Retrieval. Examining needle-in-a-haystack decay, attention dilution, and cost economics.https://bsbhadwal.com/posts/late-chunking-in-retrieval-augmented-generation/Mon, 09 Feb 2026 00:00:00 +0530https://bsbhadwal.com/posts/late-chunking-in-retrieval-augmented-generation/Technical breakdown of Late Chunking in RAG architectures. Contrasting Jina AI token mean pooling and Voyage AI contextualized embeddings against naive chunking.https://bsbhadwal.com/posts/the-unit-economics-of-hosted-inference-vs-apis/Wed, 19 Nov 2025 00:00:00 +0530https://bsbhadwal.com/posts/the-unit-economics-of-hosted-inference-vs-apis/Financial and latency model analyzing the tipping point for migrating from third-party LLM APIs to self-hosted vLLM/TGI GPU clusters at enterprise scale.https://bsbhadwal.com/posts/why-workflow-dags-break-at-scale-pubsub-vs-prefect/Thu, 16 Oct 2025 00:00:00 +0530https://bsbhadwal.com/posts/why-workflow-dags-break-at-scale-pubsub-vs-prefect/Why static workflow DAG orchestrators collapse under multi-tenant RAG workloads at scale, and how event-driven Pub/Sub message buses solve tenant isolation.https://bsbhadwal.com/posts/architecting-dynamic-self-discovering-ai-agents-a-langgraph-and-grpc-reflection-prototype/Fri, 22 Aug 2025 00:00:00 +0530https://bsbhadwal.com/posts/architecting-dynamic-self-discovering-ai-agents-a-langgraph-and-grpc-reflection-prototype/Architecting self-discovering AI agents using gRPC Server Reflection and LangGraph for dynamic schema discovery without hardcoded API tools.https://bsbhadwal.com/posts/the-react-scaling-dilemma/Fri, 15 Aug 2025 00:00:00 +0530https://bsbhadwal.com/posts/the-react-scaling-dilemma/Comparative architectural analysis of how expanding tool quantities degrades ReAct agent reasoning accuracy, burns latency budgets, and necessitates hierarchical routing.https://bsbhadwal.com/posts/think-for-yourself-lessons-from-linus/Tue, 12 Aug 2025 00:00:00 +0530https://bsbhadwal.com/posts/think-for-yourself-lessons-from-linus/Analyzing Linus Torvalds rejection of trivial helper abstractions in the Linux kernel and its lessons for clean software and AI interface design.