All Documents
3,528 documents available
Software Requirements Specification (SRS)
Defines functional and non-functional requirements for a RAG-based corporate knowledge assistant with citation and hallucination guardrails.
Hallucination Guard - System Documentation & Literature Review
Documents a hallucination detection system with literature review, architecture, and methodology for LLM output verification.
Vesper — Implementation Plan
Breaks a journal app build into 5 sequential phases with checkboxes, exit criteria, and file references for each task.
Multilingual Agentic RAG (venv, Qdrant, NiceGUI, Gemini-001)
Defines a multilingual agentic RAG pipeline using Gemini embeddings, Tesseract OCR, Qdrant, and NiceGUI with CPU-first defaults.
plan
Maps a full-stack AI learning platform with Next.js 15, PostgreSQL, Gemini API, and RAG across 8 implementation phases.
Quick Start Guide
Walks through installing dependencies, creating Supabase tables, and configuring API keys for a multi-agent AI assistant.
Schema-Driven Document Extraction Service (Gently Take-Home)
Defines a full-stack document extraction service where document types are runtime data, not code, enabling zero-code addition of new schemas.
Partie 2 : Pipeline RAG
Guides a student through forking, cloning, Dockerizing, and running a RAG chatbot with Streamlit, ChromaDB, and Google Gemini.
Infinite-Context Chat Storage Specification
Specifies a graph-database-backed chat storage system that uses vector embeddings and adaptive indexing to give LLMs unlimited context without token waste.
Implementation Plan: Ethnobotany Vectorized Database
Lays out an 11-week plan to build a semantic search engine for ethnobotany literature using RAG, vector embeddings, and multi-LLM chat.
Contextinator v2.0 - Complete Usage Guide
Documents a Rust-powered CLI and Python library for fast filesystem operations plus an optional RAG pipeline for semantic code search with ChromaDB and OpenAI embeddings.
四、随机化 SVD
Teaches randomized SVD through three concrete applications: word vector projection, video background removal, and topic modeling.
The Simpsons Episode Database - Technical Plan
Plans a full-stack app that transcribes Simpsons episodes, creates searchable embeddings, and provides a web interface for semantic search and clip creation.
Intelligent Document Query Platform — GitHub-ready Low-Level Design (LLD)
Provides a copy-ready low-level design for a serverless document query platform with vector search and LLM integration.
Technical Book Rack RAG — Implementation Plan
Plans a 10-phase fork of a PDF RAG system into a technical-book RAG with concept-aware chunking and book metadata.
Building an AI Travel Assistant with Micronaut and LangChain4j
Builds a Micronaut travel advisor that embeds user queries, runs vector similarity search in Oracle AI Database, and returns semantically matched destinations via a chat endpoint.
HPC (High Performance Computing) bookmarks
Curates 200+ links to HPC resources: CFD codes, spectral methods, GPU solvers, multigrid libraries, and Fortran compiler projects.
End-of-term exam
Lists NLP and Python topics for an oral exam, with logistics for online Teams sessions.
GhostWriter Complete Setup Guide
Walks through setting up a full-stack app with a Go backend, React frontend, and iOS client, including Docker, database, and push notifications.
PRD — NoiseCancel v2: Multi-Platform Feed Intelligence
Plans a multi-platform social feed scraper with semantic dedup, AI digest, and Flutter archive view.
DinAI - RAG AI Chatbot Project Plan
Plans a four-phase RAG chatbot project, starting with a sequential web scraper for savollar.islom.uz and PostgreSQL/pgvector storage.
Contextify - Implementasyon Planı
Defines a multi-phase plan for a local AI agent memory system with Go MCP server, PostgreSQL+pgvector, Ollama embeddings, and a web UI.
deep-cuts — Media Intelligence Pipeline
Defines a pipeline that ingests YouTube shows and podcasts, transcribes them, runs LLM analysis, stores results with semantic search, and generates infographic cards per episode.
LokulMem — Product Requirements Document
Defines the full specification for a browser-native, zero-server memory library that gives LLMs persistent, inspectable user knowledge with decay and contradiction handling.