All Documents
3,528 documents available
plan
Plans a five-milestone RAG implementation for an Android gallery app using EmbeddingGemma, LiteRT, and DJL for on-device search.
NYCGO Project - Claude Code Guide
Orients developers to a two-repo data pipeline and admin UI for NYC governance organizations, with sprint history, commands, and safety protocols.
Frequently asked questions
Answers six common questions about submitting single-cell sequencing data to the Human Cell Atlas project.
PyRFA - API
Documents the PyRFA Python library for consuming and providing Reuters market data via OMM/RSSL, covering configuration, session management, and multiple data domains.
Project Agent Document (Client-Alignment First)
Aligns client and team on project scope, success criteria, data quality issues, and a phased roadmap before building a cost forecasting model.
AGENTS.md
Guides AI coding assistants on project structure, commands, and architecture for a Julia CommonMark library.
🚀 Retrieve — Implementation Plan
Defines an 11-phase implementation plan for a full-stack RAG application with document ingestion, vector search, and LLM answer generation.
Ganitha Saviya National Program - AI-Driven Data Pipeline
Documents a four-model AI pipeline that ingests seminar data, forecasts resources, assesses volunteer risk, maps school demand, and generates an interactive dashboard.
PRD: ProteinClassify — Transformer-Based Protein Analysis Platform
Defines a full-stack bioinformatics dashboard that classifies protein sequences into 321 families using ESM-2 embeddings, predicts 3D structures, and generates AI explanations.
DataWharf - Upcoming fixes, changes and enhancements
Lists planned fixes, features, and enhancements for the DataWharf application across 15 development areas.
Marriott Library Metadata Dictionary
Documents 18 metadata fields used by the Marriott Library digital collections, with Dublin Core mappings, Solr field names, and usage guidelines.
Design Rationale for dicom-parser-rs
Explains the minimalist, streaming, callback-based design of a DICOM parsing library in Rust, focusing on parsing binary byte streams only.
Software Requirements Specification (SRS)
Defines complete functional and non-functional requirements for a vehicle advertising platform with admin dashboard, vehicle app, and backend API.
Document DB (MCP Server) Requirements Specification
Specifies a local vector server for Japanese documents using OpenAI embeddings and sqlite-vec, exposed as MCP tools for insert/find/delete.
Socrates Development Plan
Lays out a four-phase build plan for an AI tutor with text, voice, diagrams, and vision features.
arXiv Knowledge Base — Specification
Defines a complete arXiv paper ingestion pipeline with hierarchical chunking, entity extraction, vector search, REST API, and Claude MCP integration.
Building a RAG Pipeline from Scratch
Teaches how to build a modular RAG pipeline from scratch with chunking, embeddings, vector storage, retrieval, and generation.
BigLake Iceberg Pipeline — Demo Scenarios
Walks through seven demo scenarios for a BigLake Iceberg pipeline, from dirty CSV ingestion to vector search on gold-layer tables.
SMART-CAM (Smart AI Camera) — Full Documentation
Documents an edge AI surveillance pipeline that detects people, extracts ReID embeddings, and tracks identities locally on a Raspberry Pi with optional Hailo NPU acceleration.
scope
Defines a Python tool that downloads YouTube transcripts and comments, then runs a 3-stage AI pipeline to produce topic summaries and atomic insights with hybrid search.
Legal MCP — Concept & Idea
Describes an AI-powered semantic search platform for German and EU law, using MCP to ground LLM answers in real legal texts.
Pulse — Life Cofounder | Build Log
Documents a full-stack monorepo that ingests LinkedIn and GitHub data, generates embeddings in-browser, and provides a RAG chat with an AI cofounder.
ReachInbox Email Aggregator - Development Plan
Breaks a full-stack email aggregator into 6 sequential phases with mandatory, core, and stretch tiers for an interview project.
Technical Requirements Document (TRD)
Specifies requirements for an AI platform that deduplicates and ranks pull requests and issues for open-source maintainers.