Back to directory

SpruceUp

A standalone Python system that keeps a vector database automatically and incrementally synced with a set of source files, watching for changes and re-embedding only what changed.

SpruceUp

SpruceUp is a library, installed into an existing Python project, that automates keeping a vector database up to date with a set of source files. A developer writes a small entry-point file that defines sources such as local files or a Google Drive folder, a target vector store such as PgVector, Pinecone, or Weaviate, an embedder such as OpenAI, Cohere, Gemini, or Voyage AI, and a transform function that turns each changed file into a list of chunks to embed.

Running SpruceUp scans the configured sources, syncs any files not yet recorded in its manifest, and then enters a watch loop that picks up further changes incrementally, so re-indexing does not require reprocessing the entire source set on every run. The transform function is asynchronous, and file properties passed to it include the decoded text or raw bytes of each file depending on its format.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.