Recently Added
3,528 documents
AI 102
Maps Azure AI services, Vision, Language, OpenAI, Document Intelligence, with links, code snippets, and provisioning details for a Portuguese-language workshop.
Notes
Collects RAG optimization techniques, a MicroSaaS business plan, and a LangChain development strategy into a single personal reference note.
FlexFlow Serve: Low-Latency, High-Performance LLM Serving
Introduces FlexFlow Serve, an open-source compiler and distributed system for low-latency, high-performance LLM serving with speculative inference.
OCI Retrieval-Augmented Generations (RAG) with Generative AI Agents Service
Walks through setting up OCI Generative AI Agents with Object Storage, OpenSearch, or Autonomous Database 23AI for RAG chatbots.
softrag
Provides a local-first RAG library using SQLite with sqlite-vec for document, embedding, and cache storage in a single.db file.
RAG-LLaMA3 AI Project
Describes a RAG pipeline using LLaMA3 to answer questions about DNALinux bioinformatics tools, with code to build your own.
Agentic RAG In This Project
Documents the agentic RAG pipeline, covering retrieval, entity extraction, tool planning, execution, and response synthesis with trace output.
Albert RAG API
Documents a French government RAG API that extends OpenAI-compatible chat endpoints with source-augmented queries.
RAG: RETRIEVAL AUGMENTED GENERATION
Explains the RAG pattern (Retrieval Augmented Generation) with diagrams, analogies, and a step-by-step breakdown of chunking, embeddings, and vector databases.
Retrieval Augmented Generation
Implements a local Retrieval-Augmented Generation system using LangChain, Ollama, and Hugging Face models to augment LLM responses with context from a vector store.
Book Source Code TODOs
Lists 50+ unstarted tasks across AI, cloud, DevOps, and documentation for a book's companion source code repository.
Indexer l'information avec des modèles de langage (RAG)
Explains how vector embeddings and approximate nearest neighbour search enable information retrieval (RAG) without relying on generative text.
FlashRAG
Explains FlashRAG's SKR method, retrieval algorithms (DPR, E5, BGE, ANCE), and multi-stage pipeline (recall, coarse ranking, fine ranking, reranking) for RAG systems.
Subgoals
Tracks unfinished features, bugs, and deployment plans for a Russian language learning app built with Svelte and Wiktionary data.
Overview
Introduces a collaborative smart shopping list project that learns purchase intervals and prioritises items due for restocking.
ember-validations 2.0 Goals
Outlines four major goals for a v2.0 rewrite of an Ember validation library, focusing on performance, error handling, Ember Data compatibility, and code quality.
Autonomous Performance Tuning via the Algorithm Engineering Cycle
Turns an autonomous agent into a performance engineer that iteratively optimizes code via falsifiable hypotheses, benchmarking, and git-backed experiments.
Describe features of Natural Language Processing (NLP) workloads on Azure (15-20%)
Lists NLP workload scenarios and Azure services for the AI-900 exam, with examples and service capabilities.
API documentation
Documents HTTP API endpoints for programmatic access to an archivy knowledge base, including authentication, search, folders, notes, and bookmarks.
2024
Collects Python, Pandas, Matplotlib, and Conda tips from a personal learning journal spanning 2023, 2024.
Awesome VuePress V1 
Curates official and community resources, plugins, themes, and projects for VuePress V1.
Knowledge about Unit Testing
Classifies unit test inputs into Normal, Boundary, and Abnormal categories, then explains Test Doubles (Dummies, Fakes, Stubs, Mocks) with PHP examples.
Penny Feature TODO
Catalogs 30+ potential features and enhancements for an AI assistant, organized by category with quick-win prioritization.
NXTG-Forge Orchestrator — Product Specification
Specifies a Rust-based orchestration engine that coordinates multiple AI coding tools under a unified plan, state, and governance layer.