Rag on Neat Guy Codinghttps://neatguycoding.com/tags/rag/Recent content in Rag on Neat Guy CodingHugo -- gohugo.ioen© 2026 NeatGuyCodingMon, 18 May 2026 00:00:00 +0000Agentic RAG: When Retrieval Pipelines Grow a Planning-and-Tools Loophttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-agentic-rag-with-erika-cardenas-weaviate-podcast-109/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-agentic-rag-with-erika-cardenas-weaviate-podcast-109/Agentic RAG: When retrieval pipelines add LLM plan–act–observe loops, tool calling, and multi-step validation—separating verified docs from interview speculation for production teams.AI-Powered Search: When RAG, Agents, and Classic IR Get Rewiredhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-doug-turnbull-and-trey-grainger-on-ai-powered-search-weaviate-podcast-13/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-doug-turnbull-and-trey-grainger-on-ai-powered-search-weaviate-podcast-13/AI-Powered Search: When RAG, agents, and classic IR get rewired—retrieval quality vs. agent loops, long context vs. searchable history, leaderboard embeddings vs. domain corpora, with Doug Turnbull and Trey Grainger on what ships.Enterprise RAG and Agents: From Frankenstein Pipelines to an Optimizable Whole Systemhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-contextual-ai-with-amanpreet-singh-weaviate-podcast-114/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-contextual-ai-with-amanpreet-singh-weaviate-podcast-114/Enterprise RAG and agents: from stitched-together pipelines to an end-to-end optimizable system—RAG 2.0, active retrieval, preference learning (KTO/APO), and LMUnit-style evaluation, with evidence boundaries called out.Enterprise RAG and Agents: When Vector Databases Meet Four Decades of Analytics Softwarehttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-saurabh-mishra-and-bob-van-luijt-on-weaviate-and-sas-weaviate-podcast-12/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-saurabh-mishra-and-bob-van-luijt-on-weaviate-and-sas-weaviate-podcast-12/Enterprise RAG and agents when vector databases meet four decades of analytics software—engineering tensions in regulated industries, SAS RAM, Weaviate integration, and production boundaries.Enterprise RAG on Financial Research Corpora: Engineering Trade-offs in Vector Stores, Agents, and Evalhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-morningstar-intelligence-engine-with-aravind-kesiraju-weaviate-podcast-1/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-morningstar-intelligence-engine-with-aravind-kesiraju-weaviate-podcast-1/Enterprise RAG on financial research corpora: engineering trade-offs across vector stores, agents, and eval—ingestion throughput, retrieval granularity, entitlements, and agent latency.From RAG to Search Agents: Three Tensions in Retrieval, Synthetic Data, and Evaluationhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-search-agents-with-nandan-thakur-weaviate-podcast-137/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-search-agents-with-nandan-thakur-weaviate-podcast-137/From RAG to search agents: BEIR co-author Nandan Thakur on BrowseComp-Plus, synthetic data pipelines, GRPO economics, and why retrieval benchmarks, training cost, and harness design pull in different directions.REFRAG: Turning RAG Context from a Token String into a Compressible Representationhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-refrag-with-xiaoqiang-lin-weaviate-podcast-130/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-refrag-with-xiaoqiang-lin-weaviate-podcast-130/REFRAG compresses retrieved passages into chunk-level decoder positions, then uses RL to selectively expand high-entropy spans—mechanisms, training pipeline, and how to read TTFT and RAG benchmarks without over-generalizing paper numbers.Retrieval List Diversification: Geometric Post-Processing, Evaluation Gaps, and RAG Context Budgetshttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-pyversity-with-thomas-van-dongen-weaviate-podcast-132/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-pyversity-with-thomas-van-dongen-weaviate-podcast-132/Retrieval list diversification: geometric post-processing, evaluation gaps, and RAG context budgets—MMR, MSD, DPP, Cover, and SSD as NumPy reranking after any Python retrieval stack.Sufficient Context: RAG Should Measure Whether There's Enough to Answer, Not Just Whether Chunks Look Relevanthttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-sufficient-context-with-hailey-joren-weaviate-podcast-125/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-sufficient-context-with-hailey-joren-weaviate-podcast-125/Sufficient context asks whether retrieved chunks let a model answer the question—not just whether they look relevant. A Weaviate Podcast #125 walkthrough of Joren et al. (ICLR 2025) on RAG evaluation, abstention, and selective generation.Synthetic Data: Boundaries of Data Fabrication in RAG, Agents, and Evaluationhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-synthetic-data-with-david-berenstein-and-ben-burtenshaw-weaviate-podcast/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-synthetic-data-with-david-berenstein-and-ben-burtenshaw-weaviate-podcast/Synthetic data for RAG, agents, and offline evaluation—when to augment, how to trust the distribution, and pipelines from distilabel and Persona Hub to Hub SQL and quality filters.The Boundaries of Enterprise RAG: Managed Pipelines, Vector Stores, and Write-Back Retrievalhttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-vertex-ai-rag-engine-with-lewis-liu-and-bob-van-luijt-weaviate-podcast-1/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-vertex-ai-rag-engine-with-lewis-liu-and-bob-van-luijt-weaviate-podcast-1/The boundaries of enterprise RAG: managed pipelines, vector stores, and write-back retrieval—engineering lessons from Vertex AI RAG Engine × Weaviate on parsing leverage, multi-corpus routing, and generative feedback loops.When Queries Become Whole Blocks of Code: The Split Between RAG Evaluation and Search-Style Benchmarkshttps://neatguycoding.com/posts/2026-05-18-weaviate-podcast-rag-benchmarks-with-nandan-thakur-weaviate-podcast-124/Mon, 18 May 2026 00:00:00 +0000https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-rag-benchmarks-with-nandan-thakur-weaviate-podcast-124/Production RAG no longer matches short-query IR leaderboards—BEIR co-author Nandan Thakur on why search benchmarks and long-context, nugget-level RAG evaluation are diverging axes.