🪟 Context Windows - minezone · Scour

Part 4: Improving Retrieval Quality with Token-Aware Chunking and HyDE 💸Affordable LLMs

github.com·5d·DEV

My RAG Pipeline Was 84% Confident 💬Prompt Engineering

github.com·5d·DEV

Design predictable AI performance to scale selling through Microsoft Marketplace 💬Prompt Engineering

techcommunity.microsoft.com·1d

AgentSim: A Platform for Verifiable Agent-Trace Simulation 🔄Autonomous Agents

Foued-pro/Mnemos: local-first persistent memory for Claude Desktop, enabling private hybrid RAG search across past conversations without API calls 💾Retro Computing

github.com·5d·Hacker News

dog-qiuqiu/invincat: A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management. 💬AI Code Assistants

github.com·4d·Hacker News

When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models 🔍RAG

Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models 🔍RAG

When RAG Isn’t Enough: Moving from Retrieval to Relationship-Aware Systems in Enterprise AI: 🔍RAG

techcommunity.microsoft.com·6d

CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG 🔍RAG

PRAG End-to-End Privacy-Preserving Retrieval-Augmented Generation 🔍RAG

How Large Language Models Balance Internal Knowledge with User and Document Assertions 🔍RAG

ComplianceNLP: Knowledge-Graph-Augmented RAG for Multi-Framework Regulatory Gap Detection 🧩LLM Integration

Contexts are Never Long Enough: Structured Reasoning for Scalable Question Answering over Long Document Sets 🔧DSPy

AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models 🔍RAG

ragR: Retrieval-Augmented Generation and RAG Assessment in R 🔍RAG

From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors 📉Model Quantization

Lightweight and Production-Ready PDF Visual Element Parsing 🏔️Alpine.js

Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation 🔍RAG

Prism-Reranker: Beyond Relevance Scoring -- Jointly Producing Contributions and Evidence for Agentic Retrieval 🔍RAG

Log in to enable infinite scrolling