Recently Added
3,528 documents
AoC Puzzle Description and Input Data
Configures HTTP requests to fetch Advent of Code puzzle descriptions and input data from the official website.
Vietnamese RAG Implementation Plan
Defines a plan for building a Vietnamese RAG system with token-aware chunking, embedding, and FastAPI endpoints.
General Usage
Documents Active Directory's range retrieval for LDAP attributes with many values, providing a helper class to page or fetch all values.
WARP.md
Guides WARP terminal AI on commands, architecture, and models for a legal document summarization tool using RAG and transformers.
Technical Documentation - NanoScope
Documents the architecture, RAG pipeline, fine-tuning process, and performance metrics of a Chrome extension for AI-powered bookmark management and text manipulation.
CLAUDE.md
Guides Claude Code to understand a SvelteKit portfolio site deployed to Cloudflare Pages with development commands and architecture.
Contextual Retrieval
Exposes two Go functions that prepend a short LLM-generated context to each document chunk before retrieval, improving search accuracy.
Basic Parameter Retrieval
Documents three functions for creating a TOML parameter dictionary and retrieving values, with name maps, tagging, and struct integration.
MagicChecklists Build Process
Documents a React build pipeline inside a WordPress plugin, covering dev, production, and distribution workflows.
Building Reliable RAG System with Semantic Double-Pass Merging and Hybrid Search
Describes a RAG system using semantic double-pass merging, hybrid BM42 search, and ColBERT reranking for improved retrieval accuracy.
COSMIC Command Line Interface
Documents every command, option, and workflow for the COSMIC CLI tool used to chunk documents with configurable pipeline stages.
π οΈ Complete Setup Guide
Walks through setting up an Intelligent Multi-Stage RAG Chatbot with Snowflake Cortex from scratch, covering permissions, document processing, search services, and local environment.
Greppy - Product Requirements Document
Defines requirements for a local semantic code search tool that returns results in under 10ms via a single Rust binary.
AI Agent Development Notes
Documents an AI agent's architecture, bugs, and design decisions for a RAG + plugin system built with Express and TypeScript.
Remove the default Simple handler
Explains four ways to query Sleeper tables: direct Java client, lambda via SQS, websockets, and Athena SQL, with JSON query examples.
Getting historical raw context information
Documents the HTTP REST API for querying historical raw context information from the STH component, including pagination, date filtering, and CSV export.
AIM AIE 6 Certification Challenge: AI-Driven Blog Chat Component
Proposes an AI chat assistant for a technical blog, covering problem definition, data collection, chunking, embedding fine-tuning, and evaluation results.
Markdown VDB β Technology Decisions
Justifies each Rust crate choice for a markdown vector database, linking requirements to specific libraries.
README
Indexes 20+ KDB.AI sample notebooks covering vector database use cases from quickstarts to multimodal RAG and time-series search.
SPEC: MCP Mode Skill Generation
Replaces MCP mode's raw document dump with an LLM-generated SKILL.md file containing actionable instructions and code patterns.
RAG Content Chunker Skill
Splits text or Markdown into token-counted chunks with deterministic IDs for RAG pipelines, supporting three chunking strategies.
BRD β Legal Document Generation Agent
Defines business requirements for a legal document generation agent using RAG to assemble pre-approved clauses with zero hallucination.
extend_retrieval
Explains how to customise Terrier's retrieval pipeline, weighting models, matching strategies, and query expansion, plus code snippets for index access.
Information Retrieval
Curates a collection of foundational and neural IR resources, including papers, courses, and tutorials, with brief annotations.