◄ Back to all products
DIGITAL DOWNLOAD
RAG Pipeline Starter
$9.99The complete retrieval-augmented generation pipeline, from raw documents to grounded LLM answers. Ingest PDFs, Markdown, or plain text; chunk intelligently; embed; store in a vector DB; retrieve relevant context; and generate accurate, cited responses. Modular design means you can swap any component — vector store, embedder, or LLM.
What’s Included
- Document ingestion pipeline supporting PDF, Markdown, .txt, and HTML
- Configurable text chunking (fixed size, sentence-aware, or semantic)
- Embedding generation with local cache and batch processing
- Vector store adapters: in-memory, FAISS, Chroma, and Qdrant
- Retrieval with top-k cosine similarity and metadata filtering
- Context injection into LLM prompt with source citation template
- CLI interface for indexing and querying; importable as a module
- Example dataset, README, integration guide, and MIT License
Apple Pay
Google Pay
🔒 Secure checkout via Stripe · Instant digital download · Python 3.10+ · MIT License