Some checks failed
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-school (push) Successful in 39s
CI / test-go-edu-search (push) Successful in 29s
CI / test-python-klausur (push) Failing after 2m34s
CI / test-python-agent-core (push) Successful in 20s
CI / test-nodejs-website (push) Successful in 26s
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
47 lines
1.2 KiB
Python
47 lines
1.2 KiB
Python
"""
|
|
Multi-pass OCR, line matching, LLM/spell review, and pipeline orchestration.
|
|
|
|
Re-export facade -- all logic lives in the sub-modules:
|
|
|
|
cv_review_pipeline Stages 6-8: OCR, line alignment, orchestrator
|
|
cv_review_spell Rule-based spell-checker OCR correction
|
|
cv_review_llm LLM-based OCR correction, prompt building, streaming
|
|
|
|
Lizenz: Apache 2.0 (kommerziell nutzbar)
|
|
DATENSCHUTZ: Alle Verarbeitung erfolgt lokal.
|
|
"""
|
|
|
|
# Re-export everything for backward compatibility
|
|
from .pipeline import ( # noqa: F401
|
|
ocr_region,
|
|
run_multi_pass_ocr,
|
|
match_lines_to_vocab,
|
|
llm_post_correct,
|
|
run_cv_pipeline,
|
|
)
|
|
|
|
from .spell import ( # noqa: F401
|
|
_SPELL_AVAILABLE,
|
|
_spell_dict_knows,
|
|
_spell_fix_field,
|
|
_spell_fix_token,
|
|
_try_split_merged_word,
|
|
_normalize_page_ref,
|
|
spell_review_entries_sync,
|
|
spell_review_entries_streaming,
|
|
)
|
|
|
|
from .llm import ( # noqa: F401
|
|
OLLAMA_REVIEW_MODEL,
|
|
REVIEW_ENGINE,
|
|
_REVIEW_BATCH_SIZE,
|
|
_build_llm_prompt,
|
|
_diff_batch,
|
|
_entry_needs_review,
|
|
_is_spurious_change,
|
|
_parse_llm_json_array,
|
|
_sanitize_for_json,
|
|
llm_review_entries,
|
|
llm_review_entries_streaming,
|
|
)
|