Keysat
c7ce44d963
Workstream A–C substrate for the Ten31 agentic system: - A1: docs/crm-overview.md; CLAUDE.md conventions + guardrail #9 - A2: additive/reversible core migration (canonical_entities, entity_links, interaction_log, relationship_edges, soft-delete) + ledgered runner - B1/B3: chunking + deterministic entity resolution (backend/ingest) - B2: dense (bge-m3) + BM25 sparse ingest to Qdrant crm_chunks - C: CRM MCP server (reads, retrieval modes, logged writes) — no outbound tools - docs: redaction/re-hydration, Gmail enablement runbook - synthetic test data; .env.example; housekeeping (.gitignore, untrack crm.db, drop legacy files + start9/0.3.5) Verified end-to-end on synthetic data + live Sparks (hybrid > dense on entity queries). Real backfill runs on Ten31 infra; index holds synthetic data only. Branch snapshot also captures pre-existing working-tree changes. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
65 lines
2.2 KiB
Python
65 lines
2.2 KiB
Python
#!/usr/bin/env python3
|
|
"""Phase-0 Workstream B — backfill the CRM into Qdrant.
|
|
|
|
Chunk -> dense (bge-m3 via Spark Control) + sparse (BM25 client-side) -> upsert
|
|
to Qdrant `crm_chunks` with payload. Idempotent: deterministic point ids mean
|
|
re-running upserts in place. Reads the CRM by file path; never sends data to Claude.
|
|
|
|
python3 backend/ingest/backfill.py --db data/crm_dev.db --recreate
|
|
"""
|
|
import argparse
|
|
import sqlite3
|
|
|
|
import chunking
|
|
import config
|
|
import embed
|
|
import qdrant_io
|
|
import sparse
|
|
|
|
|
|
def run(db, recreate=False, batch=32):
|
|
conn = sqlite3.connect(db)
|
|
conn.row_factory = sqlite3.Row
|
|
chunks = chunking.build_chunks(conn)
|
|
conn.close()
|
|
print(f"Built {len(chunks)} chunks from {db}")
|
|
|
|
state = qdrant_io.create_collection(recreate=recreate)
|
|
qdrant_io.ensure_indexes()
|
|
print(f"Collection '{config.COLLECTION}': {state}")
|
|
|
|
total = 0
|
|
for i in range(0, len(chunks), batch):
|
|
group = chunks[i:i + batch]
|
|
dense = embed.dense_embed([c["text"] for c in group])
|
|
points = []
|
|
for c, dv in zip(group, dense):
|
|
sv = sparse.encode(c["text"])
|
|
points.append({
|
|
"id": c["point_id"],
|
|
"vector": {"dense": dv, "sparse": {"indices": sv["indices"], "values": sv["values"]}},
|
|
"payload": {
|
|
"lp_id": c["lp_id"], "lp_name": c["lp_name"], "person_id": c["person_id"],
|
|
"doc_type": c["doc_type"], "date_ts": c["date_ts"], "text": c["text"],
|
|
"source_model": c["source_model"], "source_id": c["source_id"], "chunk_key": c["chunk_key"],
|
|
},
|
|
})
|
|
qdrant_io.upsert(points)
|
|
total += len(points)
|
|
print(f" upserted {total}/{len(chunks)}")
|
|
|
|
print(f"Done. Qdrant '{config.COLLECTION}' now holds {qdrant_io.count()} points.")
|
|
|
|
|
|
def main():
|
|
ap = argparse.ArgumentParser()
|
|
ap.add_argument("--db", default=config.DEFAULT_DB)
|
|
ap.add_argument("--recreate", action="store_true", help="drop & recreate the collection first")
|
|
ap.add_argument("--batch", type=int, default=32)
|
|
args = ap.parse_args()
|
|
run(args.db, recreate=args.recreate, batch=args.batch)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|