LICENSE
MANIFEST.in
README.md
THIRD_PARTY_NOTICES.md
pyproject.toml
datasets/wikipedia_mini.json
datasets/extraction_lab/labels.json
docs/ANALYSIS.md
docs/ARCHITECTURE.md
docs/BACKENDS.md
docs/CONTEXT_PACK.md
docs/CORPUS.md
docs/CORPUS_DESIGN.md
docs/DEMOS.md
docs/EXTRACTION.md
docs/EXTRACTION_EVALUATION.md
docs/FEATURE_INDEX.md
docs/KNOWLEDGE_BASE.md
docs/PROFILING.md
docs/RETRIEVAL.md
docs/RETRIEVAL_EVALUATION.md
docs/RETRIEVAL_QUALITY.md
docs/ROADMAP.md
docs/STT.md
docs/TESTING.md
docs/TOPIC_MODELING.md
docs/USER_CONFIGURATION.md
docs/api.rst
docs/conf.py
docs/index.rst
docs/backends/index.md
docs/backends/scan.md
docs/backends/sqlite-full-text-search.md
docs/backends/vector.md
docs/extractors/index.md
docs/extractors/ocr/index.md
docs/extractors/ocr/paddleocr-vl.md
docs/extractors/ocr/rapidocr.md
docs/extractors/pipeline-utilities/index.md
docs/extractors/pipeline-utilities/pipeline.md
docs/extractors/pipeline-utilities/select-longest.md
docs/extractors/pipeline-utilities/select-override.md
docs/extractors/pipeline-utilities/select-smart-override.md
docs/extractors/pipeline-utilities/select-text.md
docs/extractors/speech-to-text/deepgram.md
docs/extractors/speech-to-text/index.md
docs/extractors/speech-to-text/openai.md
docs/extractors/text-document/index.md
docs/extractors/text-document/markitdown.md
docs/extractors/text-document/metadata.md
docs/extractors/text-document/pass-through.md
docs/extractors/text-document/pdf.md
docs/extractors/text-document/unstructured.md
docs/extractors/vlm-document/docling-granite.md
docs/extractors/vlm-document/docling-smol.md
docs/extractors/vlm-document/index.md
features/analysis_schema.feature
features/backend_validation.feature
features/biblicus_corpus.feature
features/cli_entrypoint.feature
features/cli_parsing.feature
features/cli_step_spec_parsing.feature
features/content_sniffing.feature
features/context_pack.feature
features/context_pack_cli.feature
features/context_pack_policies.feature
features/corpus_edge_cases.feature
features/corpus_identity.feature
features/corpus_purge.feature
features/crawl.feature
features/docling_granite_extractor.feature
features/docling_smol_extractor.feature
features/environment.py
features/error_cases.feature
features/evaluation.feature
features/evidence_processing.feature
features/extraction_error_handling.feature
features/extraction_evaluation.feature
features/extraction_evaluation_lab.feature
features/extraction_run_lifecycle.feature
features/extraction_selection.feature
features/extraction_selection_longest.feature
features/extractor_pipeline.feature
features/extractor_validation.feature
features/frontmatter.feature
features/hook_config_validation.feature
features/hook_error_handling.feature
features/import_tree.feature
features/inference_backend.feature
features/ingest_sources.feature
features/integration_audio_samples.feature
features/integration_image_samples.feature
features/integration_mixed_corpus.feature
features/integration_mixed_extraction.feature
features/integration_ocr_image_extraction.feature
features/integration_pdf_retrieval.feature
features/integration_pdf_samples.feature
features/integration_unstructured_extraction.feature
features/integration_wikipedia.feature
features/knowledge_base.feature
features/lifecycle_hooks.feature
features/markitdown_extractor.feature
features/model_validation.feature
features/ocr_extractor.feature
features/paddleocr_vl_extractor.feature
features/paddleocr_vl_parse_api_response.feature
features/pdf_text_extraction.feature
features/profiling.feature
features/python_api.feature
features/python_hook_logging.feature
features/query_processing.feature
features/recipe_file_extraction.feature
features/retrieval_budget.feature
features/retrieval_quality.feature
features/retrieval_scan.feature
features/retrieval_sqlite_full_text_search.feature
features/retrieval_uses_extraction_run.feature
features/retrieval_utilities.feature
features/select_override.feature
features/smart_override_selection.feature
features/source_loading.feature
features/streaming_ingest.feature
features/stt_deepgram_extractor.feature
features/stt_extractor.feature
features/text_extraction_runs.feature
features/token_budget.feature
features/topic_modeling.feature
features/unstructured_extractor.feature
features/user_config.feature
features/steps/analysis_steps.py
features/steps/backend_steps.py
features/steps/cli_parsing_steps.py
features/steps/cli_steps.py
features/steps/context_pack_steps.py
features/steps/crawl_steps.py
features/steps/deepgram_steps.py
features/steps/docling_steps.py
features/steps/evidence_processing_steps.py
features/steps/extraction_evaluation_lab_steps.py
features/steps/extraction_evaluation_steps.py
features/steps/extraction_run_lifecycle_steps.py
features/steps/extraction_steps.py
features/steps/extractor_steps.py
features/steps/frontmatter_steps.py
features/steps/inference_steps.py
features/steps/knowledge_base_steps.py
features/steps/markitdown_steps.py
features/steps/model_steps.py
features/steps/openai_steps.py
features/steps/paddleocr_mock_steps.py
features/steps/paddleocr_vl_steps.py
features/steps/paddleocr_vl_unit_steps.py
features/steps/pdf_steps.py
features/steps/profiling_steps.py
features/steps/python_api_steps.py
features/steps/rapidocr_steps.py
features/steps/requests_mock_steps.py
features/steps/retrieval_quality_steps.py
features/steps/retrieval_steps.py
features/steps/stt_deepgram_steps.py
features/steps/stt_steps.py
features/steps/topic_modeling_steps.py
features/steps/unstructured_steps.py
features/steps/user_config_steps.py
scripts/download_ag_news.py
scripts/download_audio_samples.py
scripts/download_image_samples.py
scripts/download_mixed_samples.py
scripts/download_pdf_samples.py
scripts/download_wikipedia.py
scripts/extraction_evaluation_demo.py
scripts/extraction_evaluation_lab.py
scripts/profiling_demo.py
scripts/readme_end_to_end_demo.py
scripts/test.py
scripts/topic_modeling_integration.py
scripts/wikipedia_rag_demo.py
src/biblicus/__init__.py
src/biblicus/__main__.py
src/biblicus/cli.py
src/biblicus/constants.py
src/biblicus/context.py
src/biblicus/corpus.py
src/biblicus/crawl.py
src/biblicus/errors.py
src/biblicus/evaluation.py
src/biblicus/evidence_processing.py
src/biblicus/extraction.py
src/biblicus/extraction_evaluation.py
src/biblicus/frontmatter.py
src/biblicus/hook_logging.py
src/biblicus/hook_manager.py
src/biblicus/hooks.py
src/biblicus/ignore.py
src/biblicus/inference.py
src/biblicus/knowledge_base.py
src/biblicus/models.py
src/biblicus/retrieval.py
src/biblicus/sources.py
src/biblicus/time.py
src/biblicus/uris.py
src/biblicus/user_config.py
src/biblicus.egg-info/PKG-INFO
src/biblicus.egg-info/SOURCES.txt
src/biblicus.egg-info/dependency_links.txt
src/biblicus.egg-info/entry_points.txt
src/biblicus.egg-info/requires.txt
src/biblicus.egg-info/top_level.txt
src/biblicus/_vendor/dotyaml/__init__.py
src/biblicus/_vendor/dotyaml/interpolation.py
src/biblicus/_vendor/dotyaml/loader.py
src/biblicus/_vendor/dotyaml/transformer.py
src/biblicus/analysis/__init__.py
src/biblicus/analysis/base.py
src/biblicus/analysis/llm.py
src/biblicus/analysis/models.py
src/biblicus/analysis/profiling.py
src/biblicus/analysis/schema.py
src/biblicus/analysis/topic_modeling.py
src/biblicus/backends/__init__.py
src/biblicus/backends/base.py
src/biblicus/backends/hybrid.py
src/biblicus/backends/scan.py
src/biblicus/backends/sqlite_full_text_search.py
src/biblicus/backends/vector.py
src/biblicus/extractors/__init__.py
src/biblicus/extractors/base.py
src/biblicus/extractors/deepgram_stt.py
src/biblicus/extractors/docling_granite_text.py
src/biblicus/extractors/docling_smol_text.py
src/biblicus/extractors/markitdown_text.py
src/biblicus/extractors/metadata_text.py
src/biblicus/extractors/openai_stt.py
src/biblicus/extractors/paddleocr_vl_text.py
src/biblicus/extractors/pass_through_text.py
src/biblicus/extractors/pdf_text.py
src/biblicus/extractors/pipeline.py
src/biblicus/extractors/rapidocr_text.py
src/biblicus/extractors/select_longest_text.py
src/biblicus/extractors/select_override.py
src/biblicus/extractors/select_smart_override.py
src/biblicus/extractors/select_text.py
src/biblicus/extractors/unstructured_text.py