rootandClaude Opus 4.6
3f19ad5d93
- process_knowledge.py: routes PDF content through devop.live /api/run - Uses extract mode: LLM extracts facts/entities/relationships, verifier checks - 543 extractions (279 facts, 264 entities) from 8 conversations - 60 verified entries from gemma2 cross-checking - All stored as queryable Parquet (processed_extractions, processed_validated) - Streaming SSE parsing for LLM Team responses - This proves the architecture: Lakehouse storage + devop.live processing Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
58 lines
1.3 KiB
JSON
58 lines
1.3 KiB
JSON
{
|
|
"id": "3ead1a7a-810b-49d1-add8-752bab52dfae",
|
|
"name": "processed_validated",
|
|
"schema_fingerprint": "8078de214059a2a4582203b32c1172fcc311c2d3c762a3b075c07268308f1841",
|
|
"objects": [
|
|
{
|
|
"bucket": "data",
|
|
"key": "datasets/processed_validated.parquet",
|
|
"size_bytes": 15271,
|
|
"created_at": "2026-03-28T05:16:57.439472748Z"
|
|
}
|
|
],
|
|
"created_at": "2026-03-28T05:16:57.439473552Z",
|
|
"updated_at": "2026-03-28T05:16:57.439749766Z",
|
|
"description": "",
|
|
"owner": "",
|
|
"sensitivity": null,
|
|
"columns": [
|
|
{
|
|
"name": "conversation",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "page",
|
|
"data_type": "Int64",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "type",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "content",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
}
|
|
],
|
|
"lineage": {
|
|
"source_system": "csv",
|
|
"source_file": "processed_validated.csv",
|
|
"ingest_job": "ingest-1774675017439",
|
|
"ingest_timestamp": "2026-03-28T05:16:57.439472748Z",
|
|
"parent_datasets": []
|
|
},
|
|
"freshness": null,
|
|
"tags": [],
|
|
"row_count": 60
|
|
} |