GitHub - open-puffer: opensource and fastest vectorDB
opensource and fastest vectorDB. Contribute to harishsg993010/open-puffer development by creating an account on GitHub.
Local PDF knowledge base that indexes PDFs using embeddings from Ollama and vector search via PGlite with pgvector, stored locally in ~/Documents/.pdf-library.
Provides a CLI to add PDFs or URLs, tag documents, perform semantic or full-text search, list, inspect, tag, remove documents, and view stats. Uses chunked text extraction, 1024-dimension embeddings, HNSW indexing, and optional OpenCode tool integration for scripted access.