Recall
Turn a question into prompt-ready memory with one GET. mode auto/standard/deep controls depth; weakEvidence tells you when to abstain.
GET /v1/brain/context is the primary read primitive. One call fuses document hits, entity facts, and timeline events into a single contextMd block ready to inject into a system prompt. The brain does not generate answers — your model does, using the returned memory.
Make the call
import { BrainClient } from "@unisonlabs/sdk";
const brain = new BrainClient({ token: process.env.UNISON_TOKEN });
const ctx = await brain.context({ q: "payment service architecture", k: 10 });
const memory = ctx.weakEvidence ? "" : ctx.contextMd;
// inject `memory` into your model's system promptfrom unisonlabs import UnisonBrain
client = UnisonBrain() # reads UNISON_TOKEN
ctx = client.context("payment service architecture")
memory = "" if ctx.weak_evidence else ctx.context_mdcurl 'https://brain.unisonlabs.ai/v1/brain/context?q=payment+service+architecture&mode=auto&k=10' \
-H "Authorization: Bearer $UNISON_TOKEN"Response shape
{
"query": "payment service architecture",
"mode": "auto",
"weakEvidence": false,
"topScore": 0.91,
"hits": [{ "path": "/workspace/...", "title": "…", "score": 0.91, "snippet": "…" }],
"entities": [{ "entity": { "slug": "payments-svc" }, "facts": [ … ] }],
"contextMd": "## Memory\n\n…"
}Choosing a mode
| Mode | When to use |
|---|---|
auto (default) | Most calls — server picks depth based on score distribution |
standard | Low-latency paths where you want consistent speed |
deep | Ambiguous or high-stakes queries needing exhaustive retrieval |
Pass mode=deep for queries where you'd rather wait than miss a hit.
weakEvidence — the abstention flag
weakEvidence: true means the best hit scored below 0.5. Treat it as "the brain does not know." Pass an empty memory block to the model rather than thin matches — memory layers that never abstain teach agents to fabricate provenance.
Key parameters
| Param | Default | Notes |
|---|---|---|
q | — | required |
k | 10 | 1–50 results |
mode | auto | auto / standard / deep |
pathPrefix | — | scope to a subtree, e.g. /workspace/teams/platform/ |
maxEntities | 3 | entities expanded with facts + timeline |
includeBodies | false | inline document bodies for single-shot pipelines |
See also: Context recall concept · API reference
.NET (HTTP) Quickstart
Call the Unison brain from C# using System.Net.Http.HttpClient and System.Text.Json — no NuGet packages required.
Ingest
Stream conversations and documents into the brain with POST /v1/brain/ingest. Entity extraction and fact extraction run async; sourceRef keeps retries idempotent.