Commit Graph
435 Commits
Author SHA1 Message Date
KaifAhmad1 e7e67bd673 Enhance normalize module: fix recursion, add comprehensive tests (57 passed) 2025-12-11 16:58:14 +05:30
KaifAhmad1 5d5928badf feat: enhance kg module with tests, conflict resolution placeholders, and doc updates 2025-12-11 15:21:39 +05:30
Mohd Kaif 2f94986b01 Merge pull request #74 from Hawksight-AI/ingest
validate and fix ingest module and notebooks
2025-12-11 00:31:15 +05:30
KaifAhmad1 3e7863aa23 feat(ingest): validate and fix ingest module and notebooks
- Fix ProgressTracker usage in MCPIngestor and RepoIngestor
- Fix recursive calls in methods.py
- Add comprehensive test suite for all ingest submodules (tests/ingest/test_submodules.py)
- Add integration tests for key cookbooks (tests/ingest/test_cookbook_integration.py)
- Fix and align existing tests (test_notebook_02.py, test_notebook_06.py)
- Ensure full coverage of all 15 data sources
2025-12-11 00:28:25 +05:30
Mohd Kaif d23ca2d743 Update README.md 2025-12-10 21:56:26 +05:30
Mohd Kaif 507a1f9c71 Merge pull request #73 from Hawksight-AI/graph-store
Remove KuzuDB backend support and cleanup references
2025-12-10 20:33:29 +05:30
KaifAhmad1 afc94ad059 Remove KuzuDB backend support and cleanup references 2025-12-10 20:30:59 +05:30
Mohd Kaif bad6bd0326 Merge pull request #72 from Hawksight-AI/export
Fix export_yaml schema export bug and update docs
2025-12-10 18:43:35 +05:30
KaifAhmad1 3207eb3b41 Fix export_yaml schema export bug and update docs
- Fix YAMLSchemaExporter method call in export_yaml (use export_ontology_schema)
- Add file writing logic to export_yaml for schema method
- Update docs/reference/export.md and semantica/export/export_usage.md with correct method signature
- Add test_export_methods_wrapper.py to verify schema export
- Prevent infinite recursion in method_registry lookups in methods.py
2025-12-10 18:40:32 +05:30
Mohd Kaif 3457f4d7c8 Merge pull request #71 from Hawksight-AI/export
Enhanced Export Module Testing & Notebook Fixes
2025-12-10 18:19:23 +05:30
KaifAhmad1 7bbf8e9881 Enhance export module, fix notebooks, and add tests
- Added comprehensive unit tests for export module (tests/test_export_module.py)

- Added simulation tests for notebooks 15 and 05 (tests/test_notebook*.py)

- Fixed GraphBuilder.build() signature usage in notebooks and simulations

- Fixed CSVExporter file path handling and CSV content verification

- Fixed VectorExporter data format in notebooks

- Updated YAMLSchemaExporter usage

- Fixed conflict detection in GraphBuilder

- Verified all export formats (JSON, CSV, RDF, GraphML, YAML, OWL, Vector, LPG)
2025-12-10 18:15:04 +05:30
Mohd Kaif a163a46c56 Merge pull request #70 from Hawksight-AI/embeddings
Dynamic Embedding Model Switching & Enhanced Testing
2025-12-10 17:37:17 +05:30
KaifAhmad1 6ee19d971e feat: enhance embeddings with dynamic model switching, updated docs and tests 2025-12-10 17:32:43 +05:30
Mohd Kaif 0f48b5bc87 Merge pull request #69 from Hawksight-AI/conflicts
`fix(conflicts/deduplication): Fix critical bugs and add comprehensive verification for Conflict and Deduplication modules`
2025-12-10 16:11:05 +05:30
KaifAhmad1 e7bf664868 Update PR description 2025-12-10 16:07:01 +05:30
KaifAhmad1 ff7768f1ad Fix deduplication/conflict bugs and add verification scripts 2025-12-10 16:05:46 +05:30
Mohd Kaif e0fce67ab2 Merge pull request #68 from Hawksight-AI/core
`test(core/pipeline): Add comprehensive unit tests and fix pipeline validation logic`
2025-12-10 15:31:20 +05:30
KaifAhmad1 926c518bd7 feat: comprehensive testing and fixes for Core, KG, Conflicts, and Pipeline modules 2025-12-10 15:26:05 +05:30
Mohd Kaif ea477f9b32 Merge pull request #67 from Hawksight-AI/context-engineering
Context Module Testing & Validation
2025-12-10 14:07:21 +05:30
KaifAhmad1 a7106f810f feat(context): Add comprehensive tests and fix dependencies
- Added unit tests for Context module (AgentContext, AgentMemory, ContextGraph, EntityLinker)
- Fixed Tuple import error in deduplication/merge_strategy.py
- Verified notebook examples via test conversion
2025-12-10 14:05:05 +05:30
Mohd Kaif 36e94cdbbc Merge pull request #66 from Hawksight-AI/conflicts
fix(conflicts): fix recursion bug in methods module and add comprehensive unit tests
2025-12-10 13:39:27 +05:30
KaifAhmad1 b169ce6253 fix(conflicts): fix recursion bug in methods.py and add comprehensive tests
- Fix infinite recursion in semantica/conflicts/methods.py by removing redundant registration
- Update 04_Conflict_Resolution_Strategies.ipynb to use correct API
- Add unit tests for conflicts module in tests/conflicts/test_conflicts.py
- Add __init__.py files to tests/ and tests/conflicts/ for package structure
2025-12-10 13:36:05 +05:30
Mohd Kaif 845de6a0d0 Remove code style badge from README
Removed the badge for code style 'black' from README.
2025-12-10 11:46:06 +05:30
KaifAhmad1 4900285dc4 docs(readme): update badge label color for better contrast 2025-12-09 21:49:19 +05:30
KaifAhmad1 50b6be4081 docs(readme): improve badge spacing and alignment 2025-12-09 21:46:40 +05:30
KaifAhmad1 49dd4ef819 docs(readme): add support stickers and star badge 2025-12-09 21:42:44 +05:30
KaifAhmad1 732729e707 refactor(docs): improve format and organization of context and embeddings reference 2025-12-09 21:08:55 +05:30
KaifAhmad1 9445d96fff docs: Update context and embeddings reference docs with grid cards 2025-12-09 20:23:12 +05:30
KaifAhmad1 da08354a96 Refactor Context Module: Architecture 2.0, Hierarchical Memory, and Doc Updates 2025-12-09 18:43:27 +05:30
KaifAhmad1 cf56dad82a docs: update cookbook links to absolute GitHub URLs in reference docs 2025-12-09 16:51:28 +05:30
KaifAhmad1 45556563f0 docs: Add missing notebook links to README 2025-12-09 13:09:09 +05:30
KaifAhmad1 dec98bcee5 docs: Update broken notebook links in README 2025-12-09 12:44:18 +05:30
KaifAhmad1 d5cb9b2d34 Update visualization notebooks: temporal snapshot comparison and version history; align APIs (KGVisualizer.visualize_network, EmbeddingVisualizer.visualize_2d_projection); add semantic network and multimodal/quality examples; refresh docs references 2025-12-08 23:17:03 +05:30
KaifAhmad1 c932d59b4b docs(vector_store): add VectorManager section to usage guide
- Added VectorManager usage examples
- Shows store creation, registration, and management
- Demonstrates listing stores and getting statistics
- Completes vector_store_usage.md documentation (100% coverage)
2025-12-08 20:02:50 +05:30
KaifAhmad1 06145fd4b9 docs(vector_store): finalize documentation with simplified notebooks
- Enhanced docs/reference/vector_store.md (~575 lines)
  - All 32 classes documented
  - All 10 convenience functions
  - Complete adapter documentation

- Updated cookbook/introduction/13_Vector_Store.ipynb
  - 10-step comprehensive guide

- Created cookbook/advanced/Advanced_Vector_Store_and_Search.ipynb
  - 4 focused parts (removed error handling per user request)
  - Part 1: Index selection (Flat, HNSW, IVF)
  - Part 2: Smart filtering with metadata
  - Part 3: Result fusion (RRF, weighted)
  - Part 4: Multi-tenant data isolation
  - Beginner-friendly with clear examples
  - Quick reference guide included

All vector_store documentation complete and production-ready.
2025-12-08 19:55:23 +05:30
KaifAhmad1 6c555b49a0 docs(triple_store): add dataclass documentation to usage guide
- Added Dataclasses section to triple_store_usage.md
  - TripleStore dataclass with usage example
  - QueryResult dataclass with usage example
  - QueryPlan dataclass with usage example
  - All attributes documented with types and descriptions

Now triple_store_usage.md is 100% complete with all classes and dataclasses documented.
2025-12-08 19:03:57 +05:30
KaifAhmad1 9fcb1c5410 docs(triple_store): complete documentation and add comprehensive notebook
- Enhanced docs/reference/triple_store.md
  - Added RDF4JAdapter section with features and transaction examples
  - Added VirtuosoAdapter section with named graphs and SQL integration
  - Added TripleStore dataclass documentation with attributes
  - Added QueryResult dataclass documentation with usage examples
  - Added QueryPlan dataclass documentation with optimization details
  - Added LoadProgress dataclass documentation with progress tracking

- Created comprehensive introduction notebook
  - Added cookbook/introduction/20_Triple_Store.ipynb
  - 10 comprehensive steps covering all triple_store functionality
  - All 11 classes demonstrated with examples
    - TripleManager, QueryEngine, BulkLoader
    - BlazegraphAdapter, JenaAdapter, RDF4JAdapter, VirtuosoAdapter
  - All 13 functions covered with practical examples
  - Multi-backend examples for all 4 store types
  - SPARQL query execution and optimization examples
  - Bulk loading with progress tracking
  - Multi-store operations and replication
  - Best practices and backend selection guide

All triple_store module exports (11 classes, 13 functions, 4 config items) now fully documented.
Documentation is 100% consistent with actual module exports.
2025-12-08 19:00:52 +05:30
KaifAhmad1 f5dfe426e9 docs(split): complete split module documentation and add comprehensive notebook
- Enhanced split_usage.md with missing class examples
  - Added OntologyAwareChunker with detailed parameters
  - Added SlidingWindowChunker with window_size and step_size
  - Added TableChunker with all configuration options
  - Updated 'Using Existing Chunkers' section with all 9 chunkers

- Enhanced docs/reference/split.md with complete class documentation
  - Added OntologyAwareChunker section (methods, parameters, examples)
  - Added SlidingWindowChunker section (methods, parameters, examples)
  - Added TableChunker section (methods, parameters, examples)
  - All sections include parameter tables and detailed examples

- Created comprehensive introduction notebook
  - Added cookbook/introduction/11_Chunking_and_Splitting.ipynb
  - 14 comprehensive steps covering all functionality
  - All 13 classes demonstrated (TextSplitter, SemanticChunker, EntityAwareChunker, etc.)
  - All 15 splitting functions covered with examples
  - Best practices, method comparisons, and performance tips included

- Removed duplicate advanced notebook
  - Deleted cookbook/advanced/11_Text_Chunking_Strategies.ipynb
  - Consolidated into comprehensive introduction notebook

All split module exports (13 classes, 15 functions, 4 config items) now fully documented.
Documentation is 100% consistent with actual module exports.
2025-12-08 18:06:08 +05:30
KaifAhmad1 31da5731b1 refactor(semantic_extract): remove build function and enhance documentation
BREAKING CHANGE: Removed build() convenience function from semantic_extract module

- Removed build() function from semantic_extract/__init__.py
- Updated __all__ exports to remove 'build'
- Resolved merge conflicts in named_entity_recognizer.py, relation_extractor.py, triple_extractor.py
- Updated semantic_extract_usage.md with class-based examples
- Updated docs/reference/semantic_extract.md with detailed parameter documentation
- Fixed 01_GraphRAG_Complete.ipynb to use individual extractor classes
- Enhanced 05_Entity_Extraction.ipynb with comprehensive examples (9 sections)
- Enhanced 06_Relation_Extraction.ipynb with complete pipeline examples (9 sections)

Users should now use individual classes (NERExtractor, RelationExtractor, TripleExtractor, etc.)
instead of the build() function for better control and flexibility.

Migration guide available in documentation.
2025-12-08 17:33:45 +05:30
KaifAhmad1 7b4b822553 Refactor seed module to class-based API, update docs and cookbooks 2025-12-08 16:14:24 +05:30
KaifAhmad1 a33e7ecb51 Cookbook: deep dive reasoning module; Rete stress test; performance comparison; mixed ReteInferenceExplanation workflow 2025-12-08 14:29:28 +05:30
KaifAhmad1 68f4eb6d2d chore: align reasoning module documentation and notebooks with implementation 2025-12-08 13:29:45 +05:30
KaifAhmad1 75ffcb1031 Standardize notebooks to handler-based pipeline API: add explicit step dependencies, use data injection for inputs, remove legacy func/args usage; update supply chain, intelligence, forensics, healthcare examples; refresh pipeline docs. 2025-12-07 23:03:39 +05:30
KaifAhmad1 902b332d9b cookbook(trading): migrate to StructuredDataParser.parse_data and dict access; fix backtesting notebook parsing and iteration; minor doc updates 2025-12-07 20:43:05 +05:30
KaifAhmad1 9837feec9b Refactor Unstructured Cookbook imports for better modularity 2025-12-07 16:15:50 +05:30
KaifAhmad1 1829b46340 Enhance Unstructured to Ontology Cookbook with LLM and Visualization 2025-12-07 16:14:11 +05:30
KaifAhmad1 694141297f Enhance Ontology Cookbook with visualization and advanced features 2025-12-07 15:58:53 +05:30
Semantica Bot 7878b4a222 cookbook/ontology: add worked example for object vs data properties; align worksFor to Schema.org; add optional hierarchy visualization; plus commit pending changes across notebooks, docs, and ontology modules 2025-12-07 15:21:16 +05:30
KaifAhmad1 6b7f230b37 docs(normalize): standardize docs to class usage; update cookbook notebooks; fix Colab link; correct text_normalizer.normalize → normalize_text 2025-12-07 00:17:57 +05:30
Mohd Kaif 4c98802cef Update README.md 2025-12-06 18:13:03 +05:30