Spaces:
Running on Zero
Running on Zero
File size: 9,981 Bytes
e726170 f7b61d8 dc54127 e726170 f7b61d8 e726170 f7b61d8 e726170 f7b61d8 e726170 f7b61d8 e726170 f7b61d8 e726170 f7b61d8 e726170 5ab38b4 e726170 5ab38b4 e726170 dc54127 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 | """Batch orchestration for the GCMD classifier MVP."""
from __future__ import annotations
import logging
import time
from collections.abc import Callable
from datetime import datetime, timezone
from typing import Any
from pydantic import BaseModel, ConfigDict, Field
from gcmd_classifier.config import ModelSettings
from gcmd_classifier.llm.base import ModelClient
from gcmd_classifier.logging_config import get_logger, log_event
from gcmd_classifier.models import (
ArticleClassificationOutcome,
ArticleLoadResult,
ArticleProcessingStatus,
ArticleRecord,
ArticleResult,
ArticleValidationIssue,
OutputError,
RunSummary,
)
from gcmd_classifier.persistence.cache import (
ArticleResultCache,
build_cache_identity,
)
from gcmd_classifier.persistence.json_store import JsonResultStore
from gcmd_classifier.pipeline.service import (
APPLICATION_VERSION,
classify_article,
failed_article_result,
)
from gcmd_classifier.vocabulary.index import VocabularyIndex
ArticleStartCallback = Callable[[int, int, ArticleRecord], None]
ArticleFinishCallback = Callable[[int, int, ArticleResult, float], None]
class BatchRunResult(BaseModel):
"""Structured batch result with article outputs and run summary."""
model_config = ConfigDict(extra="forbid", frozen=True)
results: tuple[ArticleResult, ...] = Field(default_factory=tuple)
summary: RunSummary
def run_batch(
*,
article_load_result: ArticleLoadResult,
vocabulary: VocabularyIndex,
model_client: ModelClient,
settings: ModelSettings,
store: JsonResultStore,
cache: ArticleResultCache | None = None,
force_reprocess: bool = False,
run_id: str | None = None,
application_version: str = APPLICATION_VERSION,
relevant_config: dict[str, Any] | None = None,
logger: logging.Logger | None = None,
on_article_start: ArticleStartCallback | None = None,
on_article_finish: ArticleFinishCallback | None = None,
) -> BatchRunResult:
"""Process valid articles in source order while preserving completed results."""
active_logger = logger or get_logger(__name__)
started = time.perf_counter()
started_at = _now_iso()
actual_run_id = run_id or f"run-{started_at}"
invalid_errors = tuple(_issue_to_error(issue) for issue in article_load_result.errors)
results: list[ArticleResult] = []
cache_hits = 0
cache_misses = 0
log_event(
active_logger,
"batch_started",
stage="batch",
source_records=article_load_result.source_count,
valid_records=len(article_load_result.articles),
invalid_records=_invalid_record_count(article_load_result.errors),
)
total_articles = len(article_load_result.articles)
for index, article in enumerate(article_load_result.articles):
article_started = time.perf_counter()
if on_article_start is not None:
on_article_start(index, total_articles, article)
try:
result: ArticleResult | None = None
identity = build_cache_identity(
article=article,
vocabulary=vocabulary,
settings=settings,
application_version=application_version,
relevant_config=relevant_config,
)
if cache is not None and not force_reprocess:
result = cache.get(identity)
if result is not None:
cache_hits += 1
log_event(
active_logger,
"cache_hit",
DOI=article.DOI,
index=index,
stage="cache",
cache_key=identity.cache_key,
)
else:
cache_misses += 1
log_event(
active_logger,
"cache_miss",
DOI=article.DOI,
index=index,
stage="cache",
cache_key=identity.cache_key,
)
elif cache is not None:
cache_misses += 1
if result is None:
result = classify_article(
article=article,
vocabulary=vocabulary,
model_client=model_client,
settings=settings,
run_id=actual_run_id,
application_version=application_version,
relevant_config=relevant_config,
logger=active_logger,
)
if cache is not None:
cache.put(identity, result)
else:
result = result.model_copy(
update={
"processing_metadata": result.processing_metadata.model_copy(
update={"run_id": actual_run_id}
)
}
)
except Exception as exc:
result = failed_article_result(
article=article,
error=OutputError(
code=exc.__class__.__name__,
message=str(exc),
stage="batch",
DOI=article.DOI,
),
vocabulary=vocabulary,
settings=settings,
run_id=actual_run_id,
application_version=application_version,
relevant_config=relevant_config,
)
log_event(
active_logger,
"article_failed",
DOI=article.DOI,
index=index,
stage="batch",
error_code=exc.__class__.__name__,
)
store.save_article_result(result)
results.append(result)
if on_article_finish is not None:
on_article_finish(index, total_articles, result, time.perf_counter() - article_started)
summary = _run_summary(
run_id=actual_run_id,
started_at=started_at,
completed_at=_now_iso(),
duration_seconds=time.perf_counter() - started,
article_load_result=article_load_result,
results=tuple(results),
invalid_errors=invalid_errors,
cache_hits=cache_hits,
cache_misses=cache_misses,
)
store.write_consolidated(results=tuple(results), summary=summary)
log_event(
active_logger,
"batch_finished",
stage="batch",
run_id=actual_run_id,
processed_articles=len(results),
cache_hits=cache_hits,
cache_misses=cache_misses,
errors=summary.total_errors,
)
return BatchRunResult(results=tuple(results), summary=summary)
def _run_summary(
*,
run_id: str,
started_at: str,
completed_at: str,
duration_seconds: float,
article_load_result: ArticleLoadResult,
results: tuple[ArticleResult, ...],
invalid_errors: tuple[OutputError, ...],
cache_hits: int,
cache_misses: int,
) -> RunSummary:
warnings_count = sum(len(result.warnings) for result in results) + sum(
len(record.warnings) for result in results for record in result.classifications
)
result_errors = tuple(error for result in results for error in result.errors)
errors = (*invalid_errors, *result_errors)
completed = sum(
result.processing_status is ArticleProcessingStatus.COMPLETED for result in results
)
partial = sum(result.processing_status is ArticleProcessingStatus.PARTIAL for result in results)
failed = sum(result.processing_status is ArticleProcessingStatus.FAILED for result in results)
skipped = sum(result.processing_status is ArticleProcessingStatus.SKIPPED for result in results)
classifications = sum(len(result.classifications) for result in results)
processed = len(results)
return RunSummary(
run_id=run_id,
started_at=started_at,
completed_at=completed_at,
articles_received=article_load_result.source_count,
valid_article_records=len(article_load_result.articles),
invalid_source_records=_invalid_record_count(article_load_result.errors),
processed_articles=processed,
cache_hits=cache_hits,
cache_misses=cache_misses,
total_warnings=warnings_count,
total_errors=len(errors),
duration_seconds=duration_seconds,
articles_completed=completed,
articles_partial=partial,
articles_failed=failed,
articles_skipped=skipped,
articles_not_classified=sum(
result.classification_outcome is ArticleClassificationOutcome.NOT_CLASSIFIED
for result in results
),
articles_requiring_review=sum(
any(record.review_required for record in result.classifications) for result in results
),
accepted_classifications=classifications,
average_classifications_per_article=(classifications / processed if processed else None),
average_processing_time_seconds=(duration_seconds / processed if processed else None),
total_model_calls=sum(
result.processing_metadata.model_calls or 0
for result in results
if not result.processing_metadata.cache_used
),
errors=errors,
)
def _issue_to_error(issue: ArticleValidationIssue) -> OutputError:
return OutputError(
code=issue.code,
message=issue.message,
stage="article_loading",
details={"field": issue.field},
index=issue.index,
DOI=issue.DOI,
)
def _invalid_record_count(issues: tuple[ArticleValidationIssue, ...]) -> int:
indices = {issue.index for issue in issues if issue.index is not None}
return len(indices)
def _now_iso() -> str:
return datetime.now(timezone.utc).isoformat() # noqa: UP017
|