RAGWire v1.0.0

RAGWire v1.0.0 — Initial Release

Production-grade RAG toolkit for document ingestion and retrieval with hybrid search support.

Features

• Document Loading — PDF, DOCX, XLSX, PPTX and more via MarkItDown
• LLM Metadata Extraction — extracts company name, document type, and fiscal period using your LLM
• Smart Text Splitting — markdown-aware and recursive chunking strategies
• Multiple Embedding Providers — Ollama, OpenAI, HuggingFace, Google, FastEmbed
• Qdrant Vector Store — dense, sparse, and hybrid search
• Advanced Retrieval — similarity, MMR, and hybrid search
• SHA256 Deduplication — at both file and chunk level

Installation

pip install ragwire

# With Ollama support (local, no API key)
pip install "ragwire[ollama]"

# With all providers
pip install "ragwire[all]"