Semantic Search & Document Parsing

Acerca de

Empowers high-performance document processing by converting PDFs, DOCX, and PPTX files into searchable markdown via the LlamaParse API. This toolset leverages local multilingual embeddings to execute semantic searches, allowing users to find relevant content based on meaning rather than just exact text matches. With support for workspace management to cache embeddings and advanced filtering options like distance thresholds and context window adjustments, it provides a robust workflow for navigating dense technical documentation or massive research libraries with speed and precision.

Características Principales

• Local semantic keyword search using multilingual embeddings and cosine similarity
• Rust-based CLI utilities designed for high performance and reliability
• High-speed document conversion to markdown using the LlamaParse API
• Persistent workspace management for caching embeddings across large file sets
• 2 GitHub stars
• Configurable search parameters including top-k results and distance thresholds

Casos de Uso

• Managing and querying large-scale document collections with persistent embedding caches
• Searching through hundreds of research papers or technical manuals for specific concepts
• Converting large batches of proprietary document formats into markdown for LLM processing