Open-source AI orchestration framework for building production-grade RAG pipelines and agents — the LEGO blocks under a custom answer engine.

Pick this when

You want a self-hostable, provider-swappable RAG core (OpenAI for demo, Ollama for production) rather than a hosted RAG service.

What makes it different

Tiny real footprint: ~107MB installed with embedded Qdrant in Session 22's measured comparison — while RAGflow demanded 16GB RAM + 50GB disk

Provider-agnostic by design — the same pipeline ran OpenAI and Ollama adapters

Pairs with an embedded vector store, so single-tenant RAG needs no database service at all

What it does

Orchestrates the full RAG cycle: ingestion, chunking, embedding, retrieval, grounded generation

Ships modular pipeline components you compose instead of writing retrieval plumbing

Backs the Session 22 evidence gate: <=6 retrieved chunks, citations before generation, refuse-on-empty

What it does not do

Common wrong expectations

Doesn't include a UI — Talent Lens needed its own Next.js front end and FastAPI service around it

Doesn't pick your model or vector store — those are adapter decisions you still own

Isn't a hosted service — you run it, which is the point

Where it sits in a stack

The orchestration layer of a self-hosted enterprise RAG: Haystack + embedded Qdrant under FastAPI, any LLM behind an adapter.

Shelf

Dev libraries & frameworks

Our status · watch

Strong candidate for any future 'ask my knowledge base' feature over the course KB; no current build uses it.

For your projects

The Session 22 evidence-gate spec (citations-first, refuse-on-empty, untrusted-document labeling) is a ready acceptance bar if the KB site ever grows a Q&A feature.

Freshness

current

Related tools

complementsQdrantcomplementsOllamacompetes withLangChain / LangGraph

qdrant: Session 22's chosen pairing — embedded Qdrant as the vector store

ollama: The production-grade local-LLM provider in the enterprise build

LangChain / LangGraph: Overlapping orchestration territory; Haystack was the course's RAG-specific pick

Every moment the course touched it (1)

SessionCoverageMomentWhat happened
Session 22: Automate Admin Tasks — Advanced RAG (Enterprise 'Internal Perplexity' Built Live)demonstratedChosen RAG core — ~107MB with embedded Qdrant; he also wants it inside his Hermes agent

← All tools by category