KaifAhmad1 f338b66274 feat: Add provenance metadata and robust fallback chains to semantic extraction ...

- Implemented ML/LLM -> Pattern -> Last Resort fallback chains for NER, Relation, and Triplet extractors to prevent empty results.
- Added provenance metadata (batch_index, document_id) to all extraction schemas (Entity, Relation, Triplet, etc.).
- Unified batch processing API with progress tracking across all extractors.
- Updated documentation (module usage and reference docs) to reflect new features.
- Added robustness and batch provenance tests.

2026-01-10 20:43:09 +05:30

..

conflicts

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

context

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

cookbook

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

core

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

deduplication

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

embeddings

fix: resolve model switching bug and implement intrinsic dimension detection in TextEmbedder

2026-01-08 18:56:42 +05:30

ingest

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

kg

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

normalize

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

ontology

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

parse

docs: add Docling integration guide, clear code example, and fix parser consistency issues

2026-01-08 21:27:48 +05:30

pipeline

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

reasoning

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

seed

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

semantic_extract

feat: Add provenance metadata and robust fallback chains to semantic extraction

2026-01-10 20:43:09 +05:30

split

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

triplet_store

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

utils

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

vector_store

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

visualization

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

__init__.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_all_features.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_amazon_neptune.py

feat: Add Amazon Neptune Database Graph Store Support

2026-01-08 20:13:28 -05:00

test_embedding_providers.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_export_methods_wrapper.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_export_module.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_graph_store_methods.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_graph_store.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_groq_integration.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_import.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_llm_extraction_fixes.py

Fix semantic extraction empty returns, schema validation, and update docs

2026-01-09 18:39:09 +05:30

test_model_selection.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_ner_configurations.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_notebook_15_export.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_notebooks_plain.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_notebooks_repro.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_notebooks_simulation.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_notebooks_verification.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_pipeline_orchestration.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_seed_manager.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_semantic_extract_batch_provenance.py

feat: Add provenance metadata and robust fallback chains to semantic extraction

2026-01-10 20:43:09 +05:30

test_semantic_extract_deepdive_part2.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_semantic_extract_deepdive.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

test_semantic_extract_triplets.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

verify_backends.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30

verify_context_sync.py

fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159

2026-01-08 17:23:31 +05:30