Back to all features knowledge + extensibility

Node-based RAG Retrieval.

A Retrieval node you wire in like any other. It pulls relevant context from your own docs, codebase, or knowledge base straight into the chain at runtime — embed → search → top‑k → context.

Planning node type: Context · Retrieval
what it is

Retrieval is just another node.

No separate RAG pipeline bolted onto your app. You drop a Retrieval node on the canvas and wire it between two others — the same way you place an Investigate or a Plan.

An upstream node hands it a question. It embeds the query, searches your indexed corpus, keeps the top‑k chunks, and writes them to shared Context — where Plan, Create, and Review read grounded source instead of guessing. It runs, reports state, and meters its own spend like every other node on the graph.

in the chain wired
Investigatequestion
Retrieval top-k → Context
Creategrounded draft

corpus → embed → search → top-k → write run.context

how it works · live

Run the Retrieval node.

One loop, every time it fires: embed → search → top‑k → context. Press Run and watch the corpus light up with matches, the top‑k rank by similarity, and the result land in shared Context.

retrieval node · runtime idle
query How do retries and timeouts work on a node?
embed01

query → vector
1536-dim

search02

scan 24 chunks
cosine sim

top-k03

keep k = 3
drop the rest

context04

write
run.context

your corpus docs · code · kb

24 indexed chunks · idle

top-k by similarity k = 3
#1orchestration.md0.91
#2node-retry.ts0.84
#3timeouts.md0.79
Context run.context · empty

No data leaves your machine — embed, index and search all run locally.

why it matters

Grounded chains, not guesses.

Retrieval as a node means every workflow can be grounded in your own truth — with the same wiring, state, and accounting as the rest of the canvas.

composable

Wire it anywhere in the graph.

Put a Retrieval node before Plan to ground a strategy in your specs. Put one inside a Parallel branch so twenty agents each pull their own context. Feed its output through a Merge. It is a first-class node — branch it, gate it, retry it, cap its concurrency.

Investigate Retrieval Plan Create
local-first

Your corpus never leaves.

Index and search run on your machine, against a self-hosted vector store. Pair it with local embedding models for an air-gap-friendly RAG that never ships a byte of your source to a third party.

cited

Every chunk is traceable.

Retrieved context carries its source path and similarity score, so a Review node — or a human — can check exactly where an answer came from.

metered

Counts its own spend.

Embedding calls are metered per node and roll up into the run total in Analytics — retrieval cost is never a black box.

tunable

k, model, threshold.

Set top-k, the embedding model, and a minimum similarity threshold per node — different parts of a chain can retrieve differently.