Sam Rolfe
f9dc574172
Satisfies docs/phase-4-corpus.md. content/ stays the single source of truth:
one pass over it writes both indexes, so the static pages and the retrieval
corpus cannot drift.
- corpus/: stdlib-only pipeline. validate -> chunk -> enrich -> embed -> upsert.
Chunking is block-based, so a boundary cannot fall inside a fenced block, a
table or front-matter (verified structurally, not by inspection).
- Deterministic ids: sha256(source_path + chunk_index + content_hash), rendered
as a UUID. Re-running updates points; re-chunking deletes the old ones by
source filter, so duplicates and orphans are both impossible.
- Incremental by content hash against a SQLite manifest. A provider, dimension
or chunker change is refused instead of mixed: it needs a rebuild.
- Payloads per section 4.2 plus provenance, validated before any vector is
written; a missing field fails the run and names the document and chunk.
- SQLite FTS5 over chunks (the keyword half of hybrid retrieval, decision D10)
with area/confidence filters and a `terms` column so front-matter tech and
tags are findable.
- Freshness audit: stale documents, due soon, index drift, contract drift;
optional Apprise alert; exit code for Prefect.
- Embeddings behind one interface: omniroute (OpenAI-compatible, retries, key
from the environment only) and local-hashing (offline placeholder). The
provider decision is still Sam's; the pipeline does not depend on it.
- deploy/qdrant.yml: mem_limit = memswap_limit = 400m, loopback only.
- docs/phase-4-notes.md: operator manual, DoD evidence, measured memory.
- 76 unit tests, no container and no network.
Measured, Qdrant 1.20.0 under a 400 m cap at 1024 dimensions: 500 / 5,000 /
20,000 chunks settle at 128 / 138 / 151 MiB, peaking at 149 / 305 / 292 MiB
during ingest. Qdrant's default settings are OOM-killed between 5,000 and
20,000, so the collection is created with HNSW and payloads on disk; recorded in
reference/stack.md with the ceiling and the escalation order.
Note: the `make corpus*` targets were swept into the Phase 3 deploy commit
24590cc by concurrent work in this tree; the Makefile content is correct, and
this commit contains the pipeline they call.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
101 lines
4.0 KiB
Python
101 lines
4.0 KiB
Python
"""Payload rules: every field present, enums enforced, missing field fails the run."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import unittest
|
|
|
|
from corpus import chunker, loader, payloads
|
|
from corpus.config import Config
|
|
from corpus.pipeline import chunk_id
|
|
from corpus.tests import support
|
|
|
|
|
|
def first_payload():
|
|
cfg = Config.from_env(root=support.REPO_ROOT, provider="local-hashing", dim=32)
|
|
doc = loader.load_documents(cfg)[0]
|
|
chunk = chunker.chunk_document(doc.body)[0]
|
|
payload = payloads.build_payload(doc, chunk, cfg)
|
|
payload["id"] = chunk_id(doc.path, chunk.index, doc.digest)
|
|
return cfg, doc, payload
|
|
|
|
|
|
class BuildTest(unittest.TestCase):
|
|
def test_payload_has_every_required_field(self):
|
|
cfg, doc, payload = first_payload()
|
|
payloads.validate_payload(payload)
|
|
for field in payloads.REQUIRED_FIELDS:
|
|
self.assertIn(field, payload)
|
|
self.assertEqual(payload["area"], doc.area)
|
|
self.assertEqual(payload["confidence"], doc.confidence)
|
|
self.assertEqual(payload["last_verified"], doc.last_verified)
|
|
self.assertEqual(payload["embedding_model"], cfg.model)
|
|
self.assertEqual(payload["embedding_dim"], cfg.dim)
|
|
|
|
def test_every_real_document_produces_valid_payloads(self):
|
|
cfg = Config.from_env(root=support.REPO_ROOT, provider="local-hashing", dim=32)
|
|
for doc in loader.load_documents(cfg):
|
|
for chunk in chunker.chunk_document(doc.body):
|
|
payload = payloads.build_payload(doc, chunk, cfg)
|
|
payload["id"] = chunk_id(doc.path, chunk.index, doc.digest)
|
|
payloads.validate_payload(payload, where=doc.path)
|
|
|
|
def test_source_type_is_doc_by_default(self):
|
|
_cfg, doc, payload = first_payload()
|
|
self.assertEqual(payload["source_type"], "doc")
|
|
|
|
def test_source_type_from_tags(self):
|
|
doc = loader.Document(
|
|
path="content/ai/adr-x.md", source_id="adr-x", area="ai", level=3, title="ADR",
|
|
claim="c", confidence="delivered", period="2024", tech=[], metrics=[], artefacts=[],
|
|
public=True, last_verified="2026-01-01", tags=["adr"], body="", digest="0" * 64,
|
|
url="/ai/a/adr-x/",
|
|
)
|
|
self.assertEqual(payloads.source_type_for(doc), "adr")
|
|
|
|
|
|
class ValidationTest(unittest.TestCase):
|
|
def test_missing_field_raises(self):
|
|
_cfg, _doc, payload = first_payload()
|
|
for field in ("area", "level", "source_type", "confidence", "period", "artefacts", "last_verified", "text"):
|
|
broken = dict(payload)
|
|
del broken[field]
|
|
with self.assertRaises(payloads.PayloadError, msg=f"missing {field} passed validation"):
|
|
payloads.validate_payload(broken)
|
|
|
|
def test_missing_provenance_field_raises(self):
|
|
_cfg, _doc, payload = first_payload()
|
|
for field in payloads.PROVENANCE_FIELDS:
|
|
broken = dict(payload)
|
|
del broken[field]
|
|
with self.assertRaises(payloads.PayloadError, msg=f"missing {field} passed validation"):
|
|
payloads.validate_payload(broken)
|
|
|
|
def test_bad_enums_raise(self):
|
|
_cfg, _doc, payload = first_payload()
|
|
for field, value in (
|
|
("area", "sales"),
|
|
("level", 4),
|
|
("source_type", "blog"),
|
|
("confidence", "vibes"),
|
|
):
|
|
broken = dict(payload)
|
|
broken[field] = value
|
|
with self.assertRaises(payloads.PayloadError, msg=f"{field}={value!r} passed validation"):
|
|
payloads.validate_payload(broken)
|
|
|
|
def test_empty_text_raises(self):
|
|
_cfg, _doc, payload = first_payload()
|
|
payload["text"] = " "
|
|
with self.assertRaises(payloads.PayloadError):
|
|
payloads.validate_payload(payload)
|
|
|
|
def test_bad_date_raises(self):
|
|
_cfg, _doc, payload = first_payload()
|
|
payload["last_verified"] = "last october"
|
|
with self.assertRaises(payloads.PayloadError):
|
|
payloads.validate_payload(payload)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|