Everything you need to build a working RAG system on your own hardware:
inference, retrieval, and the frameworks that connect them.

WHAT YOU GET

Everything in Vector Search Pack, plus four RAG and agent frameworks:

• LlamaIndex - the most direct path from documents to a queryable index
• LangChain - composable chains and tool calling when your pipeline branches
• Haystack - pipeline-first design with real evaluation tooling
• CrewAI - multi-agent orchestration for work that splits into roles

Plus an end-to-end architecture guide showing how the pieces fit: chunking,
embedding, indexing, retrieval, reranking and generation - and where each
framework earns its place.

WHY THIS SET

Most RAG projects fail on retrieval quality, not on the model. Having the
evaluation-first option (Haystack) alongside the fastest path (LlamaIndex)
means you can ship something working and then actually measure it.

ALL OPEN SOURCE, ALL PERMISSIVE

MIT and Apache-2.0 throughout. Full attribution with pinned commits included.

REQUIREMENTS

Docker Engine 24+ with Compose v2. Python 3.11+ for the framework components.

Instant delivery after payment. One-time purchase, free updates.