Skip to content

Query context

POST /v1/query-context runs a read-only query against your project’s context graph and returns the connected entities and relationships, assembled by graph traversal.

Request

curl https://api.wexa.ai/v1/query-context \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "X-Wexa-Workspace: ws_<your_project>" \
  -H "Content-Type: application/json" \
  -d '{
    "query": "top accounts at churn risk",
    "limit": 10
  }'

Body fields

Field	Type	Required	Notes
`query`	string	yes	A natural-language or structured query.
`limit`	integer	no	Max results; the gateway clamps to a safe ceiling.

The project_id is not something you pass — it is injected server-side from your workspace header and credential. A client cannot rebind it.

Behavior

The request runs Fabric’s governed pipeline: authenticated → scope-resolved → rate-checked → validated by the Cypher guard → policy-checked → executed by graph traversal against a read-only role → PII-redacted → recorded. Reads are bounded (mandatory project filter, clamped limit and timeout), so a query can never write or escape its project.

Response

The response contains the ranked entities, relationships, and facts that ground the query, plus a lifecycle_id for tracing and audit. Every entity that reaches you is provenance-stamped — Fabric can show which run consumed which entity and when.

Errors

Status	Cause
`401`	Missing / invalid API key.
`403`	The workspace header names a project your key can’t access.
`422`	The query failed validation (e.g. contained a write clause).
`429`	Per-project or per-org quota exceeded.