Loading...
Loading...
Loading...
3,528 documents available
本节的目的是用单词向量的具体例子，来说明随机投影保留结构的想法！
+ [Learning and practice of high performance computing](https://github.com/cjmcv/hpc)
> This repository contains a ready-to-use Low-Level Design (LLD) for the Intelligent Document Query Platform. It is organized so you can drop each file into a GitHub repo and iterate from there.
A local application that scans TV episodes of The Simpsons, transcribes them, creates searchable embeddings, and provides a web interface for semantic search and video clip creation.
Hiring managers waste significant time and effort manually searching for the right SHL assessments using inefficient keyword-based systems. The current process requires:
**Version:** 1.0.0-MVP
- Combines custom data with LLMs
You are an AI engineer designed to help users use Jina AI Search Foundation API's for their specific use case.
Sistema RAG (Retrieval Augmented Generation) para crear presupuestos de obra. La base de conocimiento se alimenta con documentos PDF, TXT, CSV, DOCX, XLSX y BC3/FIEBDC-3. El sistema responde con informacion precisa sobre precios, materiales y normas del sector construccion en Espana. Cuando no encuentra informacion en la BD, genera estimaciones de precio de mercado desglosadas y justificadas con aviso claro al usuario.
**Functions performing identical computations can be embedded identically across 30+ instruction set architectures by lifting binaries to architecture-neutral intermediate representations, then training transformer-based models with contrastive objectives on paired cross-compilation data.** The approach leverages your existing C→multi-ISA compilation pipeline as the primary supervision signal, treating functions compiled from the same source as positive pairs. State-of-the-art systems like Trex,
**embedx** is a FastEmbed-powered embedding service with a drop-in Ollama-compatible HTTP API. It uses Go for HTTP and Python subprocess with pipe communication for FastEmbed.
It gives my brain a pleasant thrum to learn new mathematics which mimics the algebra I learned in middle school. Basically this means that the system has operations with properties that match those of regular numbers as much as possible. Two pretty important onces are addition and multiplication with the properties of ditrbutivity and associativity. Roughly this corresponds to the mathematical notion of a Ring.
In complex systems, we often observe complex global behavior emerge from a collection of agents interacting with each other in their environment, with each individual agent acting only on locally available information, without knowing the full picture. Such systems have inspired development of artificial intelligence algorithms in areas such as swarm optimization and cellular automata. Motivated by the emergence of collective behavior from complex cellular systems, we build systems that feed eac
Status: Draft v0.7.0 (language-agnostic)
This file provides guidance to WARP (warp.dev) when working with code in this repository.
In our previous session, we explored basic graph matching using spatial coordinates and the Hungarian Algorithm. While this approach provides a foundation for matching keypoints between images, it only considers geometric distances. In this session, we'll enhance our matching by incorporating topological features using node2vec and commute times embeddings.
> **Purpose**: This document captures the complete project history and achievements for resume/portfolio purposes.
This file provides guidance to WARP (warp.dev) when working with code in this repository.
- We start by creating character-level bigram models.
**Release Date:** January 2026
Build a "chat with your video" search backend for the CMU Database Course YouTube playlist. The system extracts transcripts, generates text embeddings, and stores everything in LanceDB for semantic search. Video frames are extracted on-demand at query time using Lance's blob API.
This section will assess your understanding of general Word2Vec and Training Optimization concept.
This file provides comprehensive context for AI assistants (Qwen Code, Claude Code) working with code in this repository.
A comprehensive benchmarking suite designed to systematically compare the performance characteristics of leading vector databases (Qdrant, Weaviate, pgvector, Milvus, Pinecone) across various dimensions to provide actionable insights for AI application developers.
