A developer built a RAG pipeline for SmartQueue, a Go-based distributed task queue for IT support tickets, using BM25 search instead of vector search to ground LLM responses in internal knowledge. The…
A Cloudera engineer describes how vector search in Elasticsearch enables semantic search and RAG pipelines by finding documents based on meaning rather than exact keywords. The post explains that vect…
Researchers propose a self-evolving framework for legal case retrieval that uses an LLM-based agent to iteratively create and refine rewriting rules for BM25, outperforming non-evolutionary baselines …
A developer identifies five common retrieval failures in RAG systems that cause incorrect answers, including chunk boundary issues, semantic ambiguity, ranking failures, stale data, and low-confidence…
Researchers introduced DR-DCI, a retriever-steered Direct Corpus Interaction framework that dynamically expands a local workspace for agentic search over large corpora. On Browsecomp-Plus, DR-DCI achi…
Hermes Agent introduces a 5-layer hybrid routing plugin that enables unlimited skills with near-zero latency. The system uses BM25 and trigger phrase matching for O(1) lookup, supports bilingual Chine…
A developer built a search engine over 50k saved tweets using hybrid retrieval and reranking, then added a single endpoint to turn it into an answer engine. By wiring Gemma 4 MoE to the retrieval pipe…
A developer argues that pure vector search is insufficient for production RAG systems, as it fails on exact-match queries like product codes or legal citations. Hybrid search, combining BM25 sparse re…
A developer built a Code-RAG benchmark on Apache Kafka 4.0.0 to study how retrieval pipeline choices affect model rankings. Comparing 16 embedding models, 5 chunking strategies, and 3 retrieval modes …
A developer built neuro-skill, a hybrid skill router that runs entirely on a local machine without API calls or GPUs, achieving 95% Hit@1 accuracy on core domains. The system fuses five signals via Re…
Agentic RAG systems that learn from past interactions are vulnerable to memory poisoning attacks, where attackers plant false memories that the system treats as ground truth. Researchers at the Univer…
A developer built a RAG (Retrieval-Augmented Generation) system to let their team chat with internal documentation, replacing a wiki search that failed to answer common questions. After experimenting …
Researchers from a study on arXiv introduce HieraRAG, a hierarchical framework for determining optimal granularity in RAG benchmark construction, using 5,872 synthetic QA pairs from FineWeb-10BT acros…
A developer built a Quantified-Self RAG (Retrieval-Augmented Generation) system that ingests a decade of personal medical records from messy PDF scans using Unstructured.io, Sentence-Transformers, and…
A developer built a production-grade RAG pipeline that achieves 95.6% retrieval accuracy and 99/100 answer quality by fusing BM25, TF-IDF, and dense vectors with weighted Reciprocal Rank Fusion, addre…
AgentMemory launched a persistent memory runtime for coding agents that captures every session, tool call, and prompt through 12 auto-hooks, enabling millisecond recall via triple-stream retrieval com…
A developer built Vektr, a custom RAG engine implementing HNSW graphs from scratch, achieving recall@10 of 0.984 — meaning 98.4% of queries returned all 10 true nearest neighbors in the top results. T…
A developer found that retrieval systems retrieving sensitive memories mislabeled as ordinary context produce false-certainty errors, where agents confidently act on sensitive content without verifica…
A company's internal omni-search system, built using Retrieval Augmented Generation (RAG), gave an on-call engineer the wrong runbook instructions for enabling a feature flag in production. The system…
A developer built a production-grade Medical Retrieval-Augmented Generation (RAG) system that cures LLM hallucinations by grounding clinical AI responses in peer-reviewed evidence from the PubMed API.…