Chipper provides a web interface and CLI for building RAG pipelines that split documents, generate embeddings via Hugging Face, and retrieve relevant context to enhance LLM responses. It supports query workflows with web scraping capabilities and can act as a proxy between Ollama clients like Enchanted or Open WebUI and an Ollama backend. Built on Haystack, it integrates with ElasticSearch for retrieval and runs as a fully containerized Docker service.