ZacharyZhang-NY
dc9cfb5a30
A memory used to have one state: present. A session could not be reloaded
without searching, nothing separated what a person said today from what the
store ingested a year ago, and two statements that disagree about a number
were both handed to the reader as if the store believed both.
Schema v10. Atoms gain session_id, importance, recall_count, last_recalled_at
and archived_at; two tables arrive beside them — consolidations (one watermark
per holder+scenario lane) and conflicts (a pair, the term they disagree on,
both values, and whether anyone has settled it). v_atoms_current now also
hides archived rows, and apply() drops the view before rebuilding it because
CREATE VIEW IF NOT EXISTS would keep the old body and ignore the archive.
Working memory is a read, not a store: `working <holder> <session>` returns
what that session recorded, in order, with no search involved. Consolidation
rolls a lane's new memories into one standing summary and moves the watermark
to the newest memory actually rolled up — not to the clock of the pass, which
made a second pass count the same memories twice. The archive rule is stated
in the command that runs it (recorded before N days, never returned by a
search, importance at or under a floor) rather than hidden in a decay formula
nobody measured; --dry-run names the victims first.
A conflict is recorded when a new memory repeats a label with a different
number in the same holder's same scenario. Retrieval drops the older side
while the conflict is open and both sides answer again once it is settled:
settling is not superseding, and a word-only disagreement is left alone
because a reworded sentence would fire on every paraphrase. Numbers are keyed
to both the memory's subject and the nearest preceding label, measured: the
two thermostat sentences share only their subject, so a nearest-word-only rule
found nothing.
Search now counts the memories it handed back, which is the only use estimate
the store has, and the archive rule reads it. The dense index applies the same
currency rules as the view, so an archived memory cannot stay findable through
one leg while the other hides it.
Two reads over HTTP (working, conflicts) and two tools over MCP
(working_set, memory_conflicts); curation stays with the operator because an
agent should not decide what its own past is worth. remember and supersede
carry a session id; importance does not cross MCP, because recall_count is
observed and importance is stated.
Gates: 366 passed; ruff clean; mypy 24 errors in 9 files, the recorded 9cb46c1
baseline, net 0; pyright 0 on the touched files; go build/vet/test and gofmt
clean; mcp_write_smoke PASS.
380 lines
17 KiB
Python
380 lines
17 KiB
Python
"""What each retrieval leg is actually worth, on the frozen suite, asked as its holder.
|
|
|
|
The product fuses three legs with reciprocal rank fusion: a sparse page, a dense vector leg, and a
|
|
picture leg that only speaks up when the words come back thin. Each one costs latency and a model
|
|
snapshot, and the suite is the only honest referee. This harness turns each leg on and off over the
|
|
same probes and prints recall, first-hit quality, latency, and per-modality recall in one table, so
|
|
a default like `dense_embeddings_enabled=False` is a measurement rather than a preference.
|
|
|
|
Run: python -m bench.leg_check [--probes 300]
|
|
Writes: bench/reports/LEGS.md, bench/reports/leg_check.json
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import json
|
|
import shutil
|
|
import statistics
|
|
import sys
|
|
import time
|
|
from pathlib import Path
|
|
from typing import Any
|
|
|
|
from bench.leg_report import write_markdown
|
|
from bench.metrics import aggregate, newest_gold_first, score_query
|
|
from bench.query_set import load_queries, scale_probes, source_times
|
|
from bench.report import git_commit
|
|
from bench.run import latency
|
|
from bench.scratch import copy_store
|
|
from bench.systems import machine_facts
|
|
|
|
DEFAULT_HOME = Path("bench/runs/dense_scale")
|
|
DEFAULT_SCRATCH = Path("bench/runs/leg_check")
|
|
DEFAULT_OBJECTS = Path("bench/runs/baseline/objects")
|
|
DEFAULT_CLIP_INDEX = Path("bench/runs/leg_check_index")
|
|
DEFAULT_CLIP_MODEL = Path("bench/models/chinese-clip-vit-base-patch16")
|
|
DEFAULT_EMBEDDING_MODEL = Path("bench/models/paraphrase-multilingual-MiniLM-L12-v2")
|
|
ENCODE_SAMPLE = 200
|
|
|
|
# The page the product asks for by default; measure() checks it against Settings, so "as shipped" cannot rot into a hypothesis.
|
|
SHIPPED_TOP_K = 24
|
|
|
|
# The modality whose questions carry a question type; measured whole, because 15 probes of 150 cannot separate six categories.
|
|
MEMORY_MODALITY = "conversation"
|
|
|
|
# (label, atoms asked, dense leg, picture leg); the picture leg answers only on a thin page, which is the product's rule.
|
|
CONFIGS: list[dict[str, Any]] = [
|
|
{"label": "words only", "top_k": 10, "dense": False, "visual": False},
|
|
{"label": "words only (the configured 24)", "top_k": SHIPPED_TOP_K, "dense": False, "visual": False},
|
|
{"label": "words only, wider page", "top_k": 30, "dense": False, "visual": False},
|
|
{"label": "+ dense leg", "top_k": 10, "dense": True, "visual": False},
|
|
{"label": "+ dense leg, wider page", "top_k": 30, "dense": True, "visual": False},
|
|
{"label": "+ picture leg", "top_k": 10, "dense": False, "visual": True},
|
|
{"label": "+ picture leg, wider page", "top_k": 30, "dense": False, "visual": True},
|
|
]
|
|
|
|
|
|
def prepare(
|
|
home: Path,
|
|
scratch: Path,
|
|
objects: Path,
|
|
clip_index: Path,
|
|
*,
|
|
dense: bool,
|
|
visual: bool,
|
|
clip_model: Path,
|
|
embedding_model: Path,
|
|
) -> Path:
|
|
"""Build a scratch store that can run every leg: vectors, the picture index, and the bytes.
|
|
|
|
The picture index and the CLIP snapshot are 48 minutes of encoding, so they are carried in from
|
|
wherever they were built rather than rebuilt per row.
|
|
"""
|
|
copy_home, _ = copy_store(home, scratch)
|
|
if visual:
|
|
for name in ("clip_image_index.npy", "clip_image_index_atoms.json"):
|
|
source = clip_index / name
|
|
if not source.exists():
|
|
raise SystemExit(
|
|
f"{source}: the picture index has not been built; run `ely-eye index-visual` "
|
|
"with ELY_EYE_CLIP_MODEL_DIR set, or point --clip-index at its cache"
|
|
)
|
|
(copy_home / "cache").mkdir(parents=True, exist_ok=True)
|
|
shutil.copy2(source, copy_home / "cache" / name)
|
|
if not (clip_model / "onnx" / "model_fp16.onnx").exists():
|
|
raise SystemExit(f"{clip_model / 'onnx' / 'model_fp16.onnx'}: the CLIP snapshot is missing")
|
|
if not objects.is_dir():
|
|
raise SystemExit(f"{objects}: the picture leg needs the object store to check image bytes")
|
|
link = copy_home / "objects"
|
|
if not link.exists() and not link.is_symlink():
|
|
link.symlink_to(objects.resolve())
|
|
if dense and not (embedding_model / "config.json").exists():
|
|
raise SystemExit(f"{embedding_model}: the embedding snapshot is missing; the dense leg cannot run")
|
|
|
|
return copy_home
|
|
|
|
|
|
def _dense_vectors(store: Path) -> int:
|
|
"""Vectors the source store already carries, read without opening it for write."""
|
|
import sqlite3
|
|
|
|
import sqlite_vec
|
|
from ely_eye import vector_index
|
|
|
|
if vector_index.TABLE != "vec_atoms":
|
|
raise SystemExit(f"the dense table is now {vector_index.TABLE}; update this harness's count")
|
|
if not store.is_file():
|
|
raise SystemExit(f"{store}: no product database")
|
|
with sqlite3.connect(f"file:{store}?mode=ro", uri=True) as connection:
|
|
connection.enable_load_extension(True)
|
|
sqlite_vec.load(connection)
|
|
connection.enable_load_extension(False)
|
|
if not connection.execute("SELECT 1 FROM sqlite_master WHERE name = 'vec_atoms'").fetchone():
|
|
return 0
|
|
return int(connection.execute("SELECT count(*) FROM vec_atoms").fetchone()[0])
|
|
|
|
|
|
def picture_facts(clip_index: Path) -> dict[str, Any]:
|
|
"""What the picture index really holds, read off the artifact instead of remembered in prose."""
|
|
import numpy as np
|
|
|
|
vectors_path = clip_index / "clip_image_index.npy"
|
|
atoms_path = clip_index / "clip_image_index_atoms.json"
|
|
vectors = np.load(vectors_path)
|
|
with atoms_path.open(encoding="utf-8") as handle:
|
|
try:
|
|
atoms = json.load(handle)
|
|
except json.JSONDecodeError as error:
|
|
raise ValueError(f"{atoms_path}: the picture index's atom list is unreadable ({error})") from error
|
|
if len(atoms) != int(vectors.shape[0]):
|
|
raise SystemExit(
|
|
f"{clip_index}: the picture index disagrees with itself — {len(atoms)} atom ids for "
|
|
f"{vectors.shape[0]} vectors"
|
|
)
|
|
return {
|
|
"path": str(clip_index),
|
|
"atoms": len(atoms),
|
|
"dim": int(vectors.shape[-1]),
|
|
"bytes": int(vectors_path.stat().st_size),
|
|
}
|
|
|
|
|
|
def encode_rate(clip_model: Path, objects: Path, count: int) -> dict[str, Any]:
|
|
"""Pictures per second the encoder manages, measured on a sample instead of remembered."""
|
|
import time
|
|
|
|
from ely_eye.clip_encoder import ClipEncoder
|
|
from PIL import Image
|
|
|
|
suffixes = {".png", ".jpg", ".jpeg"}
|
|
sample = sorted(p for p in objects.rglob("*") if p.suffix.lower() in suffixes)[:count]
|
|
if len(sample) < count:
|
|
raise SystemExit(f"{objects}: only {len(sample)} pictures to time the encoder on")
|
|
encoder = ClipEncoder(clip_model)
|
|
began = time.perf_counter()
|
|
rows = 0
|
|
for start in range(0, len(sample), 8):
|
|
batch = [Image.open(path).convert("RGB") for path in sample[start : start + 8]]
|
|
rows += len(encoder.encode_images(batch))
|
|
seconds = time.perf_counter() - began
|
|
if rows != len(sample):
|
|
raise SystemExit(f"the encoder returned {rows} vectors for {len(sample)} pictures")
|
|
return {"pictures": rows, "seconds": seconds, "per_second": rows / seconds}
|
|
|
|
|
|
def _schema(home: Path) -> int:
|
|
import sqlite3
|
|
|
|
with sqlite3.connect(home / "data" / "ely_eye.sqlite") as connection:
|
|
return int(connection.execute("PRAGMA user_version").fetchone()[0])
|
|
|
|
|
|
def rank_all(service: Any, ids: dict[str, str], probes: list[Any], top_k: int) -> tuple[list[list[str]], list[int], list[float]]:
|
|
"""Ask the product as each probe's own holder and collapse atoms to sources by first hit."""
|
|
from ely_eye.schemas import SearchFilters
|
|
|
|
rankings: list[list[str]] = []
|
|
distinct: list[int] = []
|
|
timings: list[float] = []
|
|
for index, query in enumerate(probes):
|
|
began = time.perf_counter()
|
|
hits = service.search(query.text, top_k=top_k, filters=SearchFilters(as_holder=query.holder)).hits
|
|
timings.append(time.perf_counter() - began)
|
|
sources: list[str] = []
|
|
for hit in hits:
|
|
source = ids[hit.atom.source_id]
|
|
if source not in sources:
|
|
sources.append(source)
|
|
distinct.append(len(sources))
|
|
rankings.append(sources)
|
|
if (index + 1) % 100 == 0:
|
|
print(f" {index + 1}/{len(probes)}", flush=True)
|
|
return rankings, distinct, timings
|
|
|
|
|
|
def _groups(
|
|
answerable: list[Any], scores: list[Any], rankings: list[list[str]], times: dict[str, str]
|
|
) -> dict[str, Any]:
|
|
"""recall@10 by modality and by the question type the set recorded, plus who came back first."""
|
|
by_modality: dict[str, list[float]] = {}
|
|
by_category: dict[str, list[float]] = {}
|
|
newest: dict[str, list[bool]] = {}
|
|
every_newest: list[bool] = []
|
|
for query, score, ranking in zip(answerable, scores, rankings, strict=True):
|
|
by_modality.setdefault(query.modality, []).append(score.recall_at_10)
|
|
by_category.setdefault(query.category or "unlabelled", []).append(score.recall_at_10)
|
|
flag = newest_gold_first(ranking, set(query.gold), times)
|
|
if flag is not None:
|
|
newest.setdefault(query.category or "unlabelled", []).append(flag)
|
|
every_newest.append(flag)
|
|
return {
|
|
"by_modality": {name: sum(rows) / len(rows) for name, rows in sorted(by_modality.items())},
|
|
"modality_counts": {name: len(rows) for name, rows in sorted(by_modality.items())},
|
|
"by_category": {name: sum(rows) / len(rows) for name, rows in sorted(by_category.items())},
|
|
"category_counts": {name: len(rows) for name, rows in sorted(by_category.items())},
|
|
"newest_gold_first": sum(every_newest) / len(every_newest) if every_newest else None,
|
|
"newest_gold_first_by_category": {name: sum(rows) / len(rows) for name, rows in sorted(newest.items())},
|
|
"newest_gold_first_counts": {name: len(rows) for name, rows in sorted(newest.items())},
|
|
}
|
|
|
|
|
|
def measure(home: Path, scratch: Path, objects: Path, clip_index: Path, probes: int, models: dict[str, Path]) -> dict[str, Any]:
|
|
"""Score every configuration on the same probes, one warm service per configuration."""
|
|
from ely_eye.config import Settings
|
|
from ely_eye.db import Database
|
|
from ely_eye.retrieval import RetrievalService
|
|
|
|
shipped = Settings().retrieval_top_k
|
|
if shipped != SHIPPED_TOP_K:
|
|
raise SystemExit(
|
|
f"the product asks for {shipped} atoms per search but this harness pins "
|
|
f"SHIPPED_TOP_K={SHIPPED_TOP_K}; update the rows before trusting the 'as shipped' label"
|
|
)
|
|
|
|
chosen = scale_probes(load_queries(), probes)
|
|
answerable = [query for query in chosen if query.gold]
|
|
if not answerable:
|
|
raise SystemExit("the frozen suite carries no answerable query; nothing to score")
|
|
print(f"{len(answerable)} answerable probes", flush=True)
|
|
times = source_times()
|
|
memory = [query for query in load_queries() if query.modality == MEMORY_MODALITY and query.gold]
|
|
if not memory:
|
|
raise SystemExit(f"the frozen suite carries no answerable {MEMORY_MODALITY} query; the memory tables would be empty")
|
|
print(f"{len(memory)} answerable {MEMORY_MODALITY} queries, measured whole beside the probes", flush=True)
|
|
|
|
vectors = _dense_vectors(home / "data" / "ely_eye.sqlite")
|
|
if vectors == 0 and any(config["dense"] for config in CONFIGS):
|
|
raise SystemExit(
|
|
f"{home}: the store carries no dense vectors, so a dense arm here would rank an empty "
|
|
"index and the 24-minute build would hide outside the measured latency. Build them with "
|
|
"python -m bench.dense_scale, or point --home at a store that already has them."
|
|
)
|
|
|
|
arms: list[dict[str, Any]] = []
|
|
picture: dict[str, Any] | None = None
|
|
rate: dict[str, Any] | None = None
|
|
schema = 0
|
|
for config in CONFIGS:
|
|
print(f" {config['label']}: dense={config['dense']} visual={config['visual']}", flush=True)
|
|
copy_home = prepare(
|
|
home,
|
|
scratch,
|
|
objects,
|
|
clip_index,
|
|
dense=config["dense"],
|
|
visual=config["visual"],
|
|
clip_model=models["clip"],
|
|
embedding_model=models["embedding"],
|
|
)
|
|
schema = _schema(copy_home)
|
|
if config["visual"]:
|
|
picture = picture_facts(clip_index)
|
|
if rate is None:
|
|
rate = encode_rate(models["clip"], objects, ENCODE_SAMPLE)
|
|
settings = Settings(
|
|
home=copy_home,
|
|
dense_embeddings_enabled=config["dense"],
|
|
embedding_model_dir=models["embedding"] if config["dense"] else None,
|
|
clip_model_dir=models["clip"] if config["visual"] else None,
|
|
)
|
|
database = Database(settings)
|
|
service = RetrievalService(settings=settings, database=database)
|
|
ids = _source_ids(database)
|
|
rankings, distinct, timings = rank_all(service, ids, answerable, int(config["top_k"]))
|
|
scores = [
|
|
score_query(query.query_id, ranking, set(query.gold), query.holder)
|
|
for query, ranking in zip(answerable, rankings, strict=True)
|
|
]
|
|
summary = aggregate(scores)
|
|
timing = latency(timings)
|
|
memory_rankings, _, _ = rank_all(service, ids, memory, int(config["top_k"]))
|
|
memory_scores = [
|
|
score_query(query.query_id, ranking, set(query.gold), query.holder)
|
|
for query, ranking in zip(memory, memory_rankings, strict=True)
|
|
]
|
|
memory_summary = aggregate(memory_scores)
|
|
arms.append(
|
|
{
|
|
"label": config["label"],
|
|
"top_k": config["top_k"],
|
|
"dense": config["dense"],
|
|
"visual": config["visual"],
|
|
"recall_at_10": summary["recall_at_10"],
|
|
"mrr": summary["mrr"],
|
|
"hit_at_10": summary["hit_at_10"],
|
|
"wilson_lower": summary["hit_at_10_wilson_lower"],
|
|
"p50_seconds": timing["p50"],
|
|
"p95_seconds": timing["p95"],
|
|
"median_distinct_sources": statistics.median(distinct),
|
|
**_groups(answerable, scores, rankings, times),
|
|
"memory": {
|
|
"queries": len(memory),
|
|
"recall_at_10": memory_summary["recall_at_10"],
|
|
"mrr": memory_summary["mrr"],
|
|
"hit_at_10": memory_summary["hit_at_10"],
|
|
"wilson_lower": memory_summary["hit_at_10_wilson_lower"],
|
|
**_groups(memory, memory_scores, memory_rankings, times),
|
|
},
|
|
}
|
|
)
|
|
print(
|
|
f" recall@10 {summary['recall_at_10']:.3f}, mrr {summary['mrr']:.3f}, "
|
|
f"p50 {timing['p50'] * 1000:.1f}ms",
|
|
flush=True,
|
|
)
|
|
return {
|
|
"commit": git_commit(),
|
|
"schema_version": schema,
|
|
"store": str(scratch / "data" / "ely_eye.sqlite"),
|
|
"source_store": str(home),
|
|
"dense_vectors": vectors,
|
|
"picture_index": picture,
|
|
"encode_rate": rate,
|
|
"probes": len(answerable),
|
|
"memory_queries": len(memory),
|
|
"memory_modality": MEMORY_MODALITY,
|
|
"arms": arms,
|
|
"machine": machine_facts(),
|
|
}
|
|
|
|
|
|
def _source_ids(database: Any) -> dict[str, str]:
|
|
"""Store source id to benchmark source id, the same mapping every other arm uses."""
|
|
from bench.systems import _corpus_ids
|
|
|
|
return _corpus_ids(database)
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(description=__doc__)
|
|
parser.add_argument("--home", type=Path, default=DEFAULT_HOME)
|
|
parser.add_argument("--scratch", type=Path, default=DEFAULT_SCRATCH)
|
|
parser.add_argument("--objects", type=Path, default=DEFAULT_OBJECTS)
|
|
parser.add_argument("--clip-index", type=Path, default=DEFAULT_CLIP_INDEX)
|
|
parser.add_argument("--clip-model", type=Path, default=DEFAULT_CLIP_MODEL)
|
|
parser.add_argument("--embedding-model", type=Path, default=DEFAULT_EMBEDDING_MODEL)
|
|
parser.add_argument("--probes", type=int, default=300)
|
|
parser.add_argument("--out", type=Path, default=Path("bench/reports/LEGS.md"))
|
|
parser.add_argument("--json-out", type=Path, default=Path("bench/reports/leg_check.json"))
|
|
args = parser.parse_args()
|
|
|
|
report = measure(
|
|
args.home,
|
|
args.scratch,
|
|
args.objects,
|
|
args.clip_index,
|
|
args.probes,
|
|
{"clip": args.clip_model, "embedding": args.embedding_model},
|
|
)
|
|
args.json_out.parent.mkdir(parents=True, exist_ok=True)
|
|
args.json_out.write_text(json.dumps(report, indent=2, ensure_ascii=False), encoding="utf-8")
|
|
write_markdown(report, args.out)
|
|
print(f"wrote {args.out}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
if sys.version_info < (3, 11):
|
|
raise SystemExit("bench needs Python 3.11+")
|
|
main()
|