LICENSE
README.md
pyproject.toml
src/nemo_retriever/__init__.py
src/nemo_retriever/__main__.py
src/nemo_retriever/_build_info.py
src/nemo_retriever/config_utils.py
src/nemo_retriever/graph_ingestor.py
src/nemo_retriever/ingest_config.py
src/nemo_retriever/ingest_plans.py
src/nemo_retriever/ingestor.py
src/nemo_retriever/retriever.py
src/nemo_retriever/version.py
src/nemo_retriever.egg-info/PKG-INFO
src/nemo_retriever.egg-info/SOURCES.txt
src/nemo_retriever.egg-info/dependency_links.txt
src/nemo_retriever.egg-info/entry_points.txt
src/nemo_retriever.egg-info/requires.txt
src/nemo_retriever.egg-info/top_level.txt
src/nemo_retriever/adapters/__init__.py
src/nemo_retriever/adapters/cli/__init__.py
src/nemo_retriever/adapters/cli/main.py
src/nemo_retriever/adapters/service/__init__.py
src/nemo_retriever/adapters/service/app.py
src/nemo_retriever/adapters/service/cli.py
src/nemo_retriever/api/__init__.py
src/nemo_retriever/application/__init__.py
src/nemo_retriever/application/modes/__init__.py
src/nemo_retriever/application/pipeline/__init__.py
src/nemo_retriever/application/pipeline/build_plan.py
src/nemo_retriever/application/pipeline/contracts.py
src/nemo_retriever/application/pipeline/run_plan.py
src/nemo_retriever/application/pipeline/stage_registry.py
src/nemo_retriever/audio/__init__.py
src/nemo_retriever/audio/__main__.py
src/nemo_retriever/audio/asr_actor.py
src/nemo_retriever/audio/chunk_actor.py
src/nemo_retriever/audio/cli.py
src/nemo_retriever/audio/media_interface.py
src/nemo_retriever/audio/stage.py
src/nemo_retriever/caption/__init__.py
src/nemo_retriever/caption/caption.py
src/nemo_retriever/chart/__init__.py
src/nemo_retriever/chart/__main__.py
src/nemo_retriever/chart/chart_detection.py
src/nemo_retriever/chart/commands.py
src/nemo_retriever/chart/config.py
src/nemo_retriever/chart/cpu_actor.py
src/nemo_retriever/chart/gpu_actor.py
src/nemo_retriever/chart/processor.py
src/nemo_retriever/chart/shared.py
src/nemo_retriever/config/__init__.py
src/nemo_retriever/dedup/__init__.py
src/nemo_retriever/dedup/dedup.py
src/nemo_retriever/examples/common.py
src/nemo_retriever/examples/graph_pipeline.py
src/nemo_retriever/graph/__init__.py
src/nemo_retriever/graph/abstract_operator.py
src/nemo_retriever/graph/content_operators.py
src/nemo_retriever/graph/content_transforms.py
src/nemo_retriever/graph/cpu_operator.py
src/nemo_retriever/graph/custom_operator.py
src/nemo_retriever/graph/executor.py
src/nemo_retriever/graph/file_loader_operator.py
src/nemo_retriever/graph/gpu_operator.py
src/nemo_retriever/graph/graph_pipeline_registry.py
src/nemo_retriever/graph/ingestor_runtime.py
src/nemo_retriever/graph/multi_type_extract_operator.py
src/nemo_retriever/graph/operator_archetype.py
src/nemo_retriever/graph/operator_resolution.py
src/nemo_retriever/graph/pipeline_graph.py
src/nemo_retriever/graph/store_operator.py
src/nemo_retriever/graph/tabular_fetch_embeddings_operator.py
src/nemo_retriever/graph/tabular_schema_extract_operator.py
src/nemo_retriever/harness/__init__.py
src/nemo_retriever/harness/__main__.py
src/nemo_retriever/harness/artifacts.py
src/nemo_retriever/harness/cli.py
src/nemo_retriever/harness/config.py
src/nemo_retriever/harness/nightly.py
src/nemo_retriever/harness/recall_adapters.py
src/nemo_retriever/harness/reporting.py
src/nemo_retriever/harness/run.py
src/nemo_retriever/harness/slack.py
src/nemo_retriever/html/__init__.py
src/nemo_retriever/html/__main__.py
src/nemo_retriever/html/convert.py
src/nemo_retriever/html/ray_data.py
src/nemo_retriever/image/__init__.py
src/nemo_retriever/image/load.py
src/nemo_retriever/image/ray_data.py
src/nemo_retriever/infographic/__init__.py
src/nemo_retriever/infographic/commands.py
src/nemo_retriever/infographic/config.py
src/nemo_retriever/infographic/infographic_detection.py
src/nemo_retriever/infographic/processor.py
src/nemo_retriever/io/__init__.py
src/nemo_retriever/io/dataframe.py
src/nemo_retriever/io/image_store.py
src/nemo_retriever/io/markdown.py
src/nemo_retriever/io/stage_files.py
src/nemo_retriever/local/__init__.py
src/nemo_retriever/local/__main__.py
src/nemo_retriever/local/stages/__init__.py
src/nemo_retriever/local/stages/stage1_pdf_extraction.py
src/nemo_retriever/local/stages/stage2_infographic_extraction.py
src/nemo_retriever/local/stages/stage3_table_extractor.py
src/nemo_retriever/local/stages/stage4_chart_extractor.py
src/nemo_retriever/local/stages/stage5_text_embeddings.py
src/nemo_retriever/local/stages/stage6_vdb_upload.py
src/nemo_retriever/local/stages/stage7_vdb_query.py
src/nemo_retriever/local/stages/stage999_post_mortem_analysis.py
src/nemo_retriever/model/__init__.py
src/nemo_retriever/model/model.py
src/nemo_retriever/model/local/__init__.py
src/nemo_retriever/model/local/llama_nemotron_embed_1b_v2_embedder.py
src/nemo_retriever/model/local/llama_nemotron_embed_vl_1b_v2_embedder.py
src/nemo_retriever/model/local/nemotron_graphic_elements_v1.py
src/nemo_retriever/model/local/nemotron_ocr_v1.py
src/nemo_retriever/model/local/nemotron_page_elements_v3.py
src/nemo_retriever/model/local/nemotron_parse_v1_2.py
src/nemo_retriever/model/local/nemotron_rerank_v2.py
src/nemo_retriever/model/local/nemotron_rerank_vl_v2.py
src/nemo_retriever/model/local/nemotron_table_structure_v1.py
src/nemo_retriever/model/local/nemotron_vlm_captioner.py
src/nemo_retriever/model/local/parakeet_ctc_1_1b_asr.py
src/nemo_retriever/nim/__init__.py
src/nemo_retriever/nim/chat_completions.py
src/nemo_retriever/nim/nim.py
src/nemo_retriever/ocr/__init__.py
src/nemo_retriever/ocr/cpu_ocr.py
src/nemo_retriever/ocr/cpu_parse.py
src/nemo_retriever/ocr/gpu_ocr.py
src/nemo_retriever/ocr/gpu_parse.py
src/nemo_retriever/ocr/ocr.py
src/nemo_retriever/ocr/shared.py
src/nemo_retriever/online/__init__.py
src/nemo_retriever/online/__main__.py
src/nemo_retriever/operators/__init__.py
src/nemo_retriever/operators/base.py
src/nemo_retriever/operators/content.py
src/nemo_retriever/operators/embedding.py
src/nemo_retriever/page_elements/__init__.py
src/nemo_retriever/page_elements/cpu_actor.py
src/nemo_retriever/page_elements/gpu_actor.py
src/nemo_retriever/page_elements/local.py
src/nemo_retriever/page_elements/page_elements.py
src/nemo_retriever/page_elements/shared.py
src/nemo_retriever/params/__init__.py
src/nemo_retriever/params/models.py
src/nemo_retriever/params/utils.py
src/nemo_retriever/parse/__init__.py
src/nemo_retriever/parse/nemotron_parse.py
src/nemo_retriever/parse/nemotron_parse_postprocessing.py
src/nemo_retriever/pdf/__init__.py
src/nemo_retriever/pdf/__main__.py
src/nemo_retriever/pdf/config.py
src/nemo_retriever/pdf/extract.py
src/nemo_retriever/pdf/io.py
src/nemo_retriever/pdf/split.py
src/nemo_retriever/pdf/stage.py
src/nemo_retriever/recall/__init__.py
src/nemo_retriever/recall/__main__.py
src/nemo_retriever/recall/beir.py
src/nemo_retriever/recall/core.py
src/nemo_retriever/recall/vdb_recall.py
src/nemo_retriever/rerank/__init__.py
src/nemo_retriever/rerank/rerank.py
src/nemo_retriever/table/__init__.py
src/nemo_retriever/table/commands.py
src/nemo_retriever/table/config.py
src/nemo_retriever/table/cpu_actor.py
src/nemo_retriever/table/gpu_actor.py
src/nemo_retriever/table/processor.py
src/nemo_retriever/table/shared.py
src/nemo_retriever/table/table_detection.py
src/nemo_retriever/tabular_data/__init__.py
src/nemo_retriever/tabular_data/sql_database.py
src/nemo_retriever/tabular_data/ingestion/__init__.py
src/nemo_retriever/tabular_data/ingestion/embeddings.py
src/nemo_retriever/tabular_data/ingestion/extract_data.py
src/nemo_retriever/tabular_data/ingestion/indexes.py
src/nemo_retriever/tabular_data/ingestion/utils.py
src/nemo_retriever/tabular_data/ingestion/write_to_graph.py
src/nemo_retriever/tabular_data/ingestion/dal/__init__.py
src/nemo_retriever/tabular_data/ingestion/dal/db_dal.py
src/nemo_retriever/tabular_data/ingestion/dal/schemas_dal.py
src/nemo_retriever/tabular_data/ingestion/dal/utils_dal.py
src/nemo_retriever/tabular_data/ingestion/model/__init__.py
src/nemo_retriever/tabular_data/ingestion/model/neo4j_node.py
src/nemo_retriever/tabular_data/ingestion/model/reserved_words.py
src/nemo_retriever/tabular_data/ingestion/model/schema.py
src/nemo_retriever/tabular_data/ingestion/parsers/__init__.py
src/nemo_retriever/tabular_data/ingestion/parsers/schemas_parser.py
src/nemo_retriever/tabular_data/ingestion/services/__init__.py
src/nemo_retriever/tabular_data/ingestion/services/schema.py
src/nemo_retriever/tabular_data/neo4j/__init__.py
src/nemo_retriever/tabular_data/neo4j/neo4j_connection.py
src/nemo_retriever/tabular_data/retrieval/__init__.py
src/nemo_retriever/tabular_data/retrieval/generate_sql.py
src/nemo_retriever/text_embed/__init__.py
src/nemo_retriever/text_embed/commands.py
src/nemo_retriever/text_embed/config.py
src/nemo_retriever/text_embed/cpu_operator.py
src/nemo_retriever/text_embed/gpu_operator.py
src/nemo_retriever/text_embed/main_text_embed.py
src/nemo_retriever/text_embed/operators.py
src/nemo_retriever/text_embed/processor.py
src/nemo_retriever/text_embed/runtime.py
src/nemo_retriever/text_embed/shared.py
src/nemo_retriever/text_embed/stage.py
src/nemo_retriever/text_embed/text_embed.py
src/nemo_retriever/txt/__init__.py
src/nemo_retriever/txt/__main__.py
src/nemo_retriever/txt/ray_data.py
src/nemo_retriever/txt/split.py
src/nemo_retriever/utils/__init__.py
src/nemo_retriever/utils/detection_summary.py
src/nemo_retriever/utils/hf_cache.py
src/nemo_retriever/utils/hf_model_registry.py
src/nemo_retriever/utils/input_files.py
src/nemo_retriever/utils/ray_resource_hueristics.py
src/nemo_retriever/utils/remote_auth.py
src/nemo_retriever/utils/table_and_chart.py
src/nemo_retriever/utils/benchmark/__init__.py
src/nemo_retriever/utils/benchmark/__main__.py
src/nemo_retriever/utils/benchmark/all_actor.py
src/nemo_retriever/utils/benchmark/audio_extract_actor.py
src/nemo_retriever/utils/benchmark/common.py
src/nemo_retriever/utils/benchmark/extract_actor.py
src/nemo_retriever/utils/benchmark/ocr_actor.py
src/nemo_retriever/utils/benchmark/page_elements_actor.py
src/nemo_retriever/utils/benchmark/split_actor.py
src/nemo_retriever/utils/compare/__init__.py
src/nemo_retriever/utils/compare/__main__.py
src/nemo_retriever/utils/convert/__init__.py
src/nemo_retriever/utils/convert/to_pdf.py
src/nemo_retriever/utils/image/__init__.py
src/nemo_retriever/utils/image/__main__.py
src/nemo_retriever/utils/image/render.py
src/nemo_retriever/utils/pipeline/__init__.py
src/nemo_retriever/utils/pipeline/content.py
src/nemo_retriever/utils/pipeline/embedding.py
src/nemo_retriever/vector_store/__init__.py
src/nemo_retriever/vector_store/__main__.py
src/nemo_retriever/vector_store/lancedb_store.py
src/nemo_retriever/vector_store/lancedb_utils.py
src/nemo_retriever/vector_store/stage.py
tests/test_actor_operators.py
tests/test_asr_actor.py
tests/test_audio_benchmark.py
tests/test_audio_chunk_actor.py
tests/test_audio_pipeline_batch.py
tests/test_audio_stage.py
tests/test_batch_pipeline.py
tests/test_beir_evaluation.py
tests/test_caption.py
tests/test_chart_graphic_elements.py
tests/test_cpu_module_import_safety.py
tests/test_create_local_embedder.py
tests/test_dedup.py
tests/test_detection_summary.py
tests/test_doc_to_pdf_actor.py
tests/test_embed_params.py
tests/test_graph_pipeline_registry.py
tests/test_harness_config.py
tests/test_harness_nightly.py
tests/test_harness_recall_adapters.py
tests/test_harness_reporting.py
tests/test_harness_run.py
tests/test_html_convert.py
tests/test_image_load.py
tests/test_ingest_config.py
tests/test_ingest_interface.py
tests/test_ingest_plans.py
tests/test_io_dataframe.py
tests/test_io_image_store.py
tests/test_io_markdown.py
tests/test_lancedb_row_metadata.py
tests/test_multimodal_embed.py
tests/test_nemotron_rerank_v2.py
tests/test_nemotron_rerank_vl_v2.py
tests/test_operator_flags_and_cpu_actors.py
tests/test_params_utils.py
tests/test_pdf_render_scale.py
tests/test_pipeline_graph.py
tests/test_recall_core.py
tests/test_resource_heuristics.py
tests/test_retriever_queries.py
tests/test_store_pipeline_stages.py
tests/test_table_structure.py
tests/test_tabular_pipeline.py
tests/test_txt_split.py