KaifAhmad1
adabdd283f
Refactor imports to use submodule-specific paths and remove generic exports
2025-12-16 17:49:41 +05:30
KaifAhmad1
96702923de
Remove QA components (OntologyValidator, ConflictDetector, etc) and fix residual references
2025-12-16 17:25:15 +05:30
KaifAhmad1
bfd4bd60e5
fix(split): add id field to Chunk class and update provenance tracking logic in notebook
2025-12-15 23:16:11 +05:30
KaifAhmad1
e211a7bf57
Fix Chunking Notebook errors and Windows Unicode encoding issues
...
- Fix AttributeError in SlidingWindowChunker notebook example by using correct chunk attributes (start_index/end_index).
- Update SlidingWindowChunker initialization in notebook (window_size->chunk_size, step_size->stride).
- Fix UnicodeEncodeError in progress_tracker.py by adding fallback encoding for Windows console output.
- Minor updates to chunk validator and table chunker.
2025-12-15 22:22:13 +05:30
KaifAhmad1
30e2645a98
Remove temporary output files
2025-12-15 21:18:39 +05:30
KaifAhmad1
e5e8823423
Fix relation extraction for dependency method
2025-12-15 21:14:08 +05:30
KaifAhmad1
b5c91a90a3
fix(split): populate entities/relations in chunk metadata and reload modules in notebook
2025-12-15 19:30:49 +05:30
KaifAhmad1
569fdc31f1
fix(kg): update GraphAnalyzer metrics keys and fix notebook usage
2025-12-15 19:11:04 +05:30
KaifAhmad1
bdcaab92b0
docs(cookbook): update Neo4j connection details in 09_Graph_Store.ipynb
2025-12-15 18:36:41 +05:30
KaifAhmad1
3f4e6f831f
fix(cookbook): fix missing graph visualization in 08_Your_First_Knowledge_Graph.ipynb
2025-12-15 17:57:38 +05:30
KaifAhmad1
52aa1a6896
Enhance KG notebooks and fix GraphBuilder data processing bug
2025-12-15 17:10:35 +05:30
KaifAhmad1
d34731d687
fix(cookbook): resolve syntax and API usage errors in KG notebook
...
- Fix indentation error in GraphBuilder loop
- Update EntityResolver.resolve to resolve_entities
- Update GraphValidator result access to use dataclass attributes
- Fix deduplication logic to preserve unmerged entities
2025-12-15 16:33:42 +05:30
Mohd Kaif
8dace2f078
Merge pull request #89 from Hawksight-AI/triplet-store
...
Refactor: Standardize "Triple" to "Triplet" Terminology
2025-12-15 16:13:14 +05:30
KaifAhmad1
4fdc483935
Refactor terminology: Triple -> Triplet across codebase, docs, and notebooks
2025-12-15 16:09:20 +05:30
KaifAhmad1
d042054f9a
Fix relation extraction methods and resolve AttributeError in Knowledge Graph notebook
...
- Fixed pattern-based relation extraction by using entity patterns for subjects to ensure validity.
- Improved dependency-based relation extraction to handle nested prepositional phrases and passive voice.
- Increased cooccurrence confidence threshold to meet defaults.
- Fixed AttributeError in 07_Building_Knowledge_Graphs.ipynb by replacing dict.get() with direct attribute access for Entity/Relation dataclasses.
2025-12-15 00:28:01 +05:30
KaifAhmad1
c2d7d92a53
Fix relation extraction methods: dependency and cooccurrence
...
- Fix cooccurrence method confidence score to meet default threshold (0.5 -> 0.6)
- Fix dependency method to handle passive voice and better token-to-entity mapping
2025-12-14 23:55:48 +05:30
KaifAhmad1
b6e27b7d71
Improve relation extraction: expand patterns and fix regex subject matching
2025-12-14 23:20:09 +05:30
KaifAhmad1
444746de02
fix(normalize): handle currency symbols in number normalizer
2025-12-14 22:41:59 +05:30
KaifAhmad1
e8655a97ed
Fix NumberNormalizer suffix support and update Normalization cookbook
2025-12-14 20:51:25 +05:30
KaifAhmad1
f15ab2a327
Fix XMLData attribute error in Document Parsing notebook
2025-12-14 20:37:07 +05:30
KaifAhmad1
2f9ad467f0
Fix bugs in Ingestion module and update Data Ingestion cookbook
2025-12-14 18:03:25 +05:30
KaifAhmad1
253d35ee31
Fix NameError and enhance sample file generation in Data Ingestion cookbook
2025-12-14 15:31:52 +05:30
KaifAhmad1
09e7e61111
Fix GraphExporter to support output_path argument in export method
2025-12-14 14:53:00 +05:30
KaifAhmad1
05f553271d
Fix TextSplitter error, GraphExporter usage, and general improvements
2025-12-14 14:16:49 +05:30
KaifAhmad1
ccb3f43104
Update cookbooks: remove version checks and ensure pip install
2025-12-13 23:03:29 +05:30
Mohd Kaif
6be868e067
Delete cookbook/introduction/welcome_docs directory
2025-12-13 21:56:01 +05:30
KaifAhmad1
7b7d3fa8ad
Refactor modules for pipeline API compatibility and fix bugs
2025-12-13 21:54:48 +05:30
KaifAhmad1
c178b8dead
Enhance Welcome notebook: validate pipeline, refine docs, and ensure full module coverage
2025-12-13 19:24:50 +05:30
KaifAhmad1
8b9f6dbd09
Update Welcome notebook: Fix opening issue and add comprehensive module reference tables
2025-12-13 18:52:12 +05:30
KaifAhmad1
096ad31f77
Add runnable Semantica install cells to cookbook notebooks
2025-12-13 17:13:43 +05:30
KaifAhmad1
4b7cc5a359
chore: sync cookbook notebook updates
2025-12-13 15:59:49 +05:30
Mohd Kaif
c41f2951b2
Merge pull request #88 from Hawksight-AI/pipeline
...
Fix pipeline orchestration and add E2E tests
2025-12-13 15:09:53 +05:30
KaifAhmad1
a047ebf74f
Merge main into pipeline and resolve visualization conflicts
2025-12-13 15:08:47 +05:30
KaifAhmad1
88c12b1867
Add pipeline orchestration fixes and E2E tests
2025-12-13 15:03:34 +05:30
KaifAhmad1
094bb8d82b
Recommit pipeline orchestration and e2e tests
2025-12-13 15:01:37 +05:30
Mohd Kaif
7ff2fd9981
Merge pull request #87 from Hawksight-AI/visualization
...
Enhancement of Visualization Module & Comprehensive Testing Suite
2025-12-12 23:14:00 +05:30
KaifAhmad1
0a555145e4
Enhance visualization module with comprehensive testing and robust dependency handling
2025-12-12 23:10:17 +05:30
Mohd Kaif
994e58a170
Delete PR_DESCRIPTION.md
2025-12-12 20:24:25 +05:30
Mohd Kaif
244144dee3
Merge pull request #86 from Hawksight-AI/vector-store
...
Refactor: Remove Pinecone and Enhance Vector Store Backend Support
2025-12-12 20:23:51 +05:30
KaifAhmad1
5dfca85500
Merge branch 'main' into vector-store: Resolve PR_DESCRIPTION.md modify/delete conflict by keeping local version
2025-12-12 20:23:15 +05:30
KaifAhmad1
f3dd7a05bd
Refactor: Remove Pinecone and enhance vector store backend support
...
- Removed all Pinecone references, adapters, and documentation to align with open-source, self-hosted focus.
- Removed PineconeAdapter and related dependencies.
- Updated VectorStore to enforce supported backends (FAISS, Weaviate, Qdrant, Milvus, InMemory).
- Updated cookbooks (e.g., 13_Vector_Store.ipynb) to use Weaviate/FAISS examples instead of Pinecone.
- Updated core documentation (modules.md, rchitecture.md, etc.) to reflect backend changes.
- Added new tests ( est_pinecone_removal.py, est_vector_store_deepdive.py) to verify removal and validate remaining backends.
- Verified all vector store tests pass.
2025-12-12 20:19:17 +05:30
Mohd Kaif
d03a237278
Delete PR_DESCRIPTION.md
2025-12-12 18:50:33 +05:30
Mohd Kaif
f3ac9fbffa
Merge pull request #85 from Hawksight-AI/triplet-store
...
Refactor: Rename `triple_store` to `triplet_store`
2025-12-12 18:48:41 +05:30
KaifAhmad1
6856580a7a
Refactor: Rename triple_store to triplet_store across codebase
...
- Renamed semantica/triple_store to semantica/triplet_store
- Updated all imports and class references in core modules and adapters
- Refactored Jupyter notebooks in cookbook/
- Updated documentation files (README, docs/, etc.)
- Updated tests and verified passing status
2025-12-12 18:45:00 +05:30
KaifAhmad1
4a282628ea
Merge branch 'main' of https://github.com/Hawksight-AI/semantica
2025-12-12 16:31:43 +05:30
KaifAhmad1
c73e35a2fe
docs: update chunking cookbook and PR description
2025-12-12 16:30:59 +05:30
Mohd Kaif
a99f18b71b
Merge pull request #84 from Hawksight-AI/split
...
Fix & Align Split Module with Documentation
2025-12-12 16:21:55 +05:30
KaifAhmad1
84b90b45a2
fix: align split methods with documentation and registry
2025-12-12 16:15:57 +05:30
Mohd Kaif
d7d589f64e
Merge pull request #83 from Hawksight-AI/semantic-extract
...
Refactor Semantic Extract Module to Class-Based Interfaces
2025-12-12 13:25:58 +05:30
KaifAhmad1
d3366bbcf0
Refactor Semantic Extract module: Update notebooks, docs, and implementation to use class-based interfaces
2025-12-12 13:23:37 +05:30
KaifAhmad1