#rag
Every summary, chronological. Filter by category, tag, or source from the rail.
Multiscale Indexing: Solving the Fixed Chunk Size Trap
Fixed chunk sizes are a form of lossy compression that creates a 20-40% recall gap. Instead of tuning chunk sizes, index data at multiple scales and use Reciprocal Rank Fusion (RRF) to merge results for significantly higher accuracy.
AI EngineerBuilding a Persistent Knowledge Layer for AI Agents
To move beyond 'first-day hire' AI agents, enterprises need a persistent, specialized knowledge layer that manages tribal knowledge and uses runtime coding agents to reduce token usage and improve accuracy.
The AI Engineering Skill Stack: From Foundations to Deployment
AI engineering is the practice of building functional systems around existing LLMs. Success requires a three-tier skill stack: technical foundations, AI-specific implementation (RAG/Agents), and production-grade deployment.
IBM TechnologyArchitecting AI Agents: Skills, MCP, RAG, and Memory
Effective AI agents require more than training data; they need a combination of procedural skills, external connectivity via MCP, static knowledge retrieval (RAG), and experiential learning (Memory) to solve complex tasks.
IBM TechnologySchemaRouter: Field-Aware Tool Routing for Agentic RAG
SchemaRouter improves agentic RAG efficiency by using field-aware routing, which maps user queries to specific tool schemas rather than relying on generic semantic similarity.
Adaptive Compression for Edge-based RAG
The article proposes a framework for optimizing Retrieval-Augmented Generation (RAG) on edge devices by dynamically compressing retrieved context based on runtime constraints, balancing model accuracy with hardware limitations.
Optimizing RAG Systems with Intent-Based Classification
Moving from generic semantic search to intent-aware retrieval significantly improves answer accuracy by classifying user questions before fetching data.
Building Production AI: The Data Science & AI Loop
Production-ready AI systems rely on a continuous feedback loop where robust data science pipelines (ETL, governance) feed AI models, and AI, in turn, generates synthetic data to improve those same pipelines.
IBM TechnologyTRACE: A Framework for Trustworthy RAG Systems
The TRACE framework addresses reliability in retrieval-augmented generation by implementing a multi-stage verification process to mitigate hallucinations and ensure factual grounding in conversational AI.
Moving Beyond Chunking: Structural Retrieval for Complex Documents
Standard RAG often fails on structured documents by destroying context through chunking. A better approach is to preserve the document's original tree structure and use an agent to navigate it, ensuring higher precision and better context retention.
IBM TechnologyGraphContainer: A Unified Platform for Graph RAG Evaluation
GraphContainer is a platform designed to standardize the comparison and debugging of Graph RAG pipelines, addressing the lack of unified tooling for evaluating graph-based retrieval methods.
Designing Robust RAG Systems for Complex and Contradictory Data
RAG systems often fail not due to hallucinations, but because they are built on messy, contradictory, or outdated data without proper architectural guardrails to handle ambiguity.
IBM TechnologyHG-RAG: Improving Knowledge Graph Retrieval with Hierarchical Guidance
HG-RAG enhances retrieval-augmented generation by using hierarchical structures within knowledge graphs to improve context relevance and reduce noise in LLM responses.
Building AI Knowledge Systems: Intrinsic, Extrinsic, and Learned
To build effective AI agents, developers must move beyond model-intrinsic knowledge by grounding agents in organizational data (extrinsic) and implementing automated feedback loops (learned) to continuously optimize performance.
Stop Blaming Your RAG Pipeline: 16 Production Techniques
Most RAG failures are pipeline issues, not model limitations. Improving retrieval precision through hybrid search, reranking, and rigorous evaluation is more effective than simply swapping models.
Optimizing RAG Retrieval with Hierarchical Search
Hierarchical RAG improves precision and reduces computational costs by replacing flat, corpus-wide similarity searches with a two-stage process: document-level filtering followed by targeted chunk retrieval.
DysLexLens: Analyzing Dyslexic AI User Experiences via LLMs
DysLexLens is an end-to-end framework that extracts, structures, and validates insights from noisy online forum data to understand how dyslexic learners interact with AI tools.
ToE: Hierarchical Claim Verification Against Adversarial Misinformation
Tree of Evidence (ToE) is a fact-checking framework that uses a reinforcement learning-driven agent to decompose claims into hierarchical argument trees, significantly improving verification accuracy against adversarially poisoned inputs.
DysLexLens: A Framework for Analyzing Dyslexic Learner AI Experiences
DysLexLens is an end-to-end, evidence-traceable framework that uses dictionary-driven filtering and knowledge graphs to analyze how dyslexic learners interact with AI tools via online forums.
Cross-Document AI for Predictive Financial Compliance
Moving from document-level validation to cross-document graph correlation and probabilistic risk modeling reduces false positives by 76% and enables proactive fraud detection.
AI EngineerBuilding AI-Native Search with Spanner
Google Cloud Spanner now integrates full-text, vector, and hybrid search directly into the database, eliminating the need for separate search engines, ETL pipelines, and data synchronization issues.
Google Cloud TechConfigurable Clinical Information Extraction with Agentic RAG
Agentic RAG systems for clinical data require modular configuration to balance precision and recall, as monolithic pipelines often fail to handle the high variability of medical documentation.
CONCORD: Asynchronous Sparse Aggregation for Device-Cloud RAG
CONCORD is a framework for device-cloud Retrieval-Augmented Generation that optimizes performance under document isolation by using asynchronous sparse aggregation to balance local privacy with cloud-scale retrieval.
Scaling RAG Pipelines to 10M+ Documents with High Accuracy
To minimize hallucinations at scale, implement a multi-stage RAG pipeline that combines hybrid indexing, reciprocal rank fusion, and a strict 'retrieve, constrain, verify, abstain' workflow that forces the model to cite evidence or admit ignorance.
Fixing RAG Hallucinations Through Better Retrieval Architecture
RAG failures are rarely LLM hallucinations; they are retrieval failures. To fix them, you must move beyond simple semantic search and implement robust document versioning, metadata filtering, and re-ranking.
Improving Financial Document Analysis with GraphRAG
Traditional vector-based RAG struggles with the non-linear, cross-referenced nature of financial documents. GraphRAG improves accuracy and reduces hallucinations by mapping entity relationships, ensuring multi-page data continuity.
Fixing RAG Pipelines by Optimizing Chunking, Not Models
Most RAG failures are caused by poor data retrieval, not model hallucinations. Improving chunking strategy and inspecting raw retrieved data is the most effective way to improve accuracy.
Building Stateful AI Agents with Gemini Enterprise
Google Cloud's Gemini Enterprise Agent Platform enables stateful AI agents through cloud-based sessions and automated memory banks, allowing developers to build contextual, RAG-enabled applications with minimal code.
Google Cloud TechBeyond RAG: Building Hybrid Knowledge Architectures
RAG is effective for static, unstructured retrieval but fails at reasoning, structured data, and long-term memory. Production systems require hybrid architectures that combine retrieval with knowledge graphs and persistent state.
RAG Evolves from Keyword Search to Agentic Reasoning
Information retrieval progressed from keyword matching (TF-IDF/BM25) to semantic vectors, hybrid systems, RAG for LLM augmentation, and agentic setups that autonomously plan retrieval, validate sources, and synthesize multi-step answers.
IBM TechnologyShowing 30 of 40