f9f92706f3
RAG pipeline now includes a cross-encoder rerank step between retrieval
and generation. The LLM re-sorts top-K results by relevance before
they become context. Falls back to original order if model output is
unparseable (~5% with 7B models). Also improved the generation prompt
to be domain-aware ("staffing database") and request specific citations.
Fixed 4 catalog manifests with bucket="data" (pre-federation leftover)
that poisoned the entire DataFusion query context on startup. The
"users", "lab_trials", "meta_runs", and "new_candidates" datasets
now correctly reference bucket="primary". This bug was surfaced by
the quality evaluation pipeline — wouldn't have been found by
structural tests alone.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
96 lines
2.1 KiB
JSON
96 lines
2.1 KiB
JSON
{
|
|
"id": "8192d934-fc90-46dd-b8bd-c443a4743b19",
|
|
"name": "demo_customers",
|
|
"schema_fingerprint": "7af9708f2366f790e0ae03db6f681f5a4d4b8af4d1527b091bedfee1be81d304",
|
|
"objects": [
|
|
{
|
|
"bucket": "primary",
|
|
"key": "datasets/demo_customers.parquet",
|
|
"size_bytes": 4519,
|
|
"created_at": "2026-04-17T01:00:48.361437263Z"
|
|
}
|
|
],
|
|
"created_at": "2026-04-17T01:00:48.361437860Z",
|
|
"updated_at": "2026-04-17T01:00:48.361681724Z",
|
|
"description": "",
|
|
"owner": "",
|
|
"sensitivity": "pii",
|
|
"columns": [
|
|
{
|
|
"name": "id",
|
|
"data_type": "Int32",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "name",
|
|
"data_type": "Utf8",
|
|
"sensitivity": "pii",
|
|
"description": "",
|
|
"is_pii": true
|
|
},
|
|
{
|
|
"name": "email",
|
|
"data_type": "Utf8",
|
|
"sensitivity": "pii",
|
|
"description": "",
|
|
"is_pii": true
|
|
},
|
|
{
|
|
"name": "city",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "tier",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "lifetime_spend",
|
|
"data_type": "Float64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "is_active",
|
|
"data_type": "Int32",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "signed_up_at",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "notes",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
}
|
|
],
|
|
"lineage": {
|
|
"source_system": "mysql",
|
|
"source_file": "dsn: mysql://lh:***@127.0.0.1:3306/lh_demo",
|
|
"ingest_job": "mysql-stream-1776387648361",
|
|
"ingest_timestamp": "2026-04-17T01:00:48.361437263Z",
|
|
"parent_datasets": []
|
|
},
|
|
"freshness": null,
|
|
"tags": [],
|
|
"row_count": 10,
|
|
"last_embedded_at": null,
|
|
"embedding_stale_since": null,
|
|
"embedding_refresh_policy": null
|
|
} |