document-search

Self-hostable RAG backend for document knowledge: hybrid search, cited answers, and agentic deep reading. Java · Spring Boot · Spring AI · Elasticsearch.

CLI keyword search across websites, documents, and local folders. Crawls multi-level sites, renders JavaScript SPAs with a headless browser, and extracts text from PDF, DOCX and 100+ formats via Apache Tika — reporting exact page and line numbers. Fuzzy matching, JSON output, Docker image.

Distributed document search using TF-IDF algorithm.

TXT/PDF 본인의 커리어 문서를 자동 분석하고 문서 내용과 위치를 찾아주는 오픈소스 플랫폼

Apache Solr Document Search and Indexing Analysis with OCR

Mini desktop search engine with Binary Search Tree

RAG powered multimodal Q&A application.

📚 RAG-powered document Q&A system using Java, LangChain4j, and PostgreSQL pgvector — upload documents and query them with natural language using AI

This component of the TOP Framework provides adapters for connecting to document source systems.

HyperClarity is a Spring Boot RAG platform for document ingestion, semantic search, and LLM-powered answers.

🔍 High-performance 3-Gram Bloom Filter indexer & SIMD substring scanner for sub-millisecond full-text search across documents, code, PDFs, and OCR content.

Local document search and grounded Q&A with Spring AI, Angular, PostgreSQL/pgvector and Ollama.

Desktop document search app that indexes TXT, PDF, and DOCX files with a JavaFX interface and AVL tree; academic project.