rootandClaude Opus 4.6
8ca4ba5717
- Fixed Unicode crash in chunker (ligatures like fi causing byte boundary panic) - Chunker now works with char indices, not byte indices - 8 PDFs ingested: hybrid_ai_data_lake (133p), spark_vs_flink_iceberg (124p), code_sorting (70p), hybrid_indexing (69p), rust_in_tech_stack (49p), etc. - 477 chunks embedded via supervisor (43/sec) - HNSW index built in 0.44s - Search results <200ms, finding correct conversations by meaning - Tested: "S3 architecture", "CRM WordPress", "Rust vs Python" — all correct Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
72 lines
1.6 KiB
JSON
72 lines
1.6 KiB
JSON
{
|
|
"id": "0ae8f29b-bf70-4c9d-8b64-6ea7cb7f76a1",
|
|
"name": "rust_in_tech_stack",
|
|
"schema_fingerprint": "314ee8ede68287240d7cec1403d252787c8ceb4ee2afa72cffcb0853ac3ac889",
|
|
"objects": [
|
|
{
|
|
"bucket": "data",
|
|
"key": "datasets/rust_in_tech_stack.parquet",
|
|
"size_bytes": 99623,
|
|
"created_at": "2026-03-28T03:32:50.769271381Z"
|
|
}
|
|
],
|
|
"created_at": "2026-03-28T03:32:50.769272195Z",
|
|
"updated_at": "2026-03-28T03:32:50.769710478Z",
|
|
"description": "",
|
|
"owner": "",
|
|
"sensitivity": null,
|
|
"columns": [
|
|
{
|
|
"name": "source_file",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "conversation_title",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "turn_number",
|
|
"data_type": "Int32",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "role",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "content",
|
|
"data_type": "Utf8",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
},
|
|
{
|
|
"name": "page_number",
|
|
"data_type": "Int32",
|
|
"sensitivity": null,
|
|
"description": "",
|
|
"is_pii": false
|
|
}
|
|
],
|
|
"lineage": {
|
|
"source_system": "pdf",
|
|
"source_file": "Rust in Tech Stack.pdf",
|
|
"ingest_job": "ingest-1774668770769",
|
|
"ingest_timestamp": "2026-03-28T03:32:50.769271381Z",
|
|
"parent_datasets": []
|
|
},
|
|
"freshness": null,
|
|
"tags": [],
|
|
"row_count": 49
|
|
} |