All Documents
3,528 documents available
Triggering Evals via GitHub Actions
Documents how to trigger eval runs remotely via `gh workflow run` with 14 configurable inputs and example commands for five benchmarks.
DFAH: Determinism-Faithfulness Assurance Harness
A harness for measuring whether LLM agents produce consistent, auditable behavior when given the same input multiple times.
Logging & Evals
Documents a trigger-based logging system, cost tracking, token analytics, and a separate evals dashboard for reviewing LLM interactions.
Responsible AI (RAI)
Documents where AI is used, model choices, guardrails, cost controls, and risk mitigations for an LLM-based system.
How Zapier 4x'd Their AI Feedback Collection (Vitor)
Summarizes a talk on how Zapier increased AI feedback collection 4x through UX changes and systematic analysis.
Demo Walkthrough
Walks through querying a pre-populated Qdrant RAG system for a Boeing 737 manual, including health checks, example queries, and evaluation commands.
MLOps Learning Path (GCP Focused - Solid, Comprehensive & Practical)
Outlines a four-stage MLOps learning path centered on GCP Vertex AI, with resources and hands-on exercises for each stage.
app/config.py
Outlines a six-phase learning roadmap to build an enterprise chatbot with OpenAI Responses API, RAG, tools, Chainlit UI, and FastAPI.
An Image is Worth 16X16 Words: Transformers for Image Recognition at Scale
Introduces the Vision Transformer (ViT) that applies a standard Transformer directly to image patches for classification, outperforming CNNs when pre-trained at scale.
MeReader: Intelligent Offline-First eBook Reader
Describes an offline-first eBook reader that uses a local AI assistant with progress-aware RAG to answer questions without spoilers.
📋 PROMPT POUR CURSOR AGENT - EMBEDDINGS & SYNTHÈSE
Guides a Cursor agent to build an embeddings section and comparative synthesis for a French-language educational search app.
CLI Commands
Documents 14 CLI commands for preparing, ingesting, maintaining, and testing a Warhammer 40k lore RAG pipeline.
Evaluation & Datasets
Explains evaluation metrics, benchmarks, and leaderboards for AI models across text, vision, and audio domains.
Product Requirements Document: Project-Memory (Context Management MCP Tool)
Specifies a Go-based MCP server that externalizes LLM context via summarization, vector embedding, and SQLite storage.
RFC-001: Continuity
Proposes replacing a multi-runtime memory system with a single Go binary that captures, categorizes, and retrieves session memories for Claude Code.
How to set up QMD for Claude
Walks through installing qmd, indexing projects, adding it as an MCP server, and configuring Claude to use it before reading files.
Frequently Asked Questions About *ktrain*
Answers 25 common questions about installing, training, evaluating, and deploying ktrain models, with code examples and workarounds.
Product Requirements Document: Multi-LLM Teams Chat Bot System
Specifies a Microsoft Teams integration where multiple LLM-powered bots join conversations, respond to messages, and react with emojis via OpenRouter.
Table of Contents - Raspodijeljene i nerelacijske baze podataka
Lists 12 lecture topics for a distributed and non-relational databases course, covering NoSQL, SQL, and cloud databases.
SynthMoCap Datasets
Documents three synthetic datasets (SynthBody, SynthFace, SynthHand) for non-commercial use, with download scripts and metadata schemas.
Google Cloud
Documents steps to set up a Google Cloud RAG engine and Vertex AI Search with Dialogflow CX, including trial credits and regional agent creation.
Using approximate nearest neighbor search in real-world applications
Explains approximate nearest neighbor search concepts, Faiss library internals, and how to integrate ANN with filtering in search and recommendation systems.
Evaluation commands
Defines a 6-phase implementation plan for adding SerpAPI tools, model selection, custom scorers, workflow enhancements, agent instruction improvements, and frontend integration to a governed RAG multi-agent system.
Interactive Flashcards TUI - Implementation Roadmap
Maps a five-phase build plan for a terminal flashcard app with AI, document support, and RAG features.