mengzhx/semantica
1
0
Fork 0
mirror of https://github.com/semantica-agi/semantica.git synced 2026-09-13 04:04:09 +00:00
Code Issues Packages Projects Releases Wiki Activity
647 Commits 61 Branches 24 Tags
2ecebf1003fb4e95c72d2d3771e4cc0a36931e45
Commit Graph
647 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
KaifAhmad1 2ecebf1003 Jpdate pytoml 2025-12-27 23:32:33 +05:30
KaifAhmad1 94ddcc4d33 Fix blockchain transaction network analysis notebook 
- Fix TemporalGraphQuery: Change detect_temporal_patterns to query_temporal_pattern
- Fix GraphAnalyzer: Replace find_paths with direct relationship queries and BFS implementation
- Fix KGVisualizer: Change visualize() to visualize_network() with interactive visualization
- Fix GraphExporter: Remove unsupported CSV format, use export_csv for CSV export
- Add proper imports and improve error handling
- Enhance visualization with force-directed layout and better interactivity
 2025-12-27 21:48:35 +05:30
KaifAhmad1 7a652cf227 Fix GraphBuilder progress tracking for list of dict sources 
- Added support for detecting and merging list of dict sources with entities/relationships
- Progress tracking now shows ETA and remaining items when sources is a list
- Fixes issue where progress wasn't displayed when passing list of dicts to build()
 2025-12-27 19:21:07 +05:30
KaifAhmad1 f53935e0a1 Add progress tracking and ETA to GraphBuilder 
- Enhanced GraphBuilder with real-time progress updates showing percentage, ETA, and processing rate
- Added time tracking for entity processing, relationship processing, entity resolution, and graph structure building
- Added final summary with total build time
- Simplified notebook cell to rely on Semantica's built-in progress tracking instead of manual Python code
 2025-12-27 18:46:27 +05:30
KaifAhmad1 b9ffba67ea Update DeFi Protocol Intelligence notebook: 
- Use ML-only approach for entity extraction (spaCy)
- Improve knowledge graph visualization with interactive layout
- Fix ontology export to use RDFExporter for TTL format
- Enhance visualization with better interactivity and explanations
 2025-12-27 16:57:24 +05:30
KaifAhmad1 d4f008a183 Fix AttributeError issues in TripletStore and ContextRetriever 
- Fix LoadProgress attribute access in TripletStore (use loaded_triplets instead of processed_triplets)
- Fix None source handling in ContextRetriever RetrievedContext objects
- Add error handling for Blazegraph connection in notebook
- Ensure source field always has a default value in vector/memory retrieval
 2025-12-27 15:34:04 +05:30
KaifAhmad1 f7fcfa3691 Fix LLM-based entity and relation extraction 
- Updated extract_entities_llm to use custom entity_types in prompts
- Updated extract_relations_llm to use custom relation_types in prompts
- Made entity type filtering case-insensitive and flexible
- Added verbose mode to RelationExtractor for progress tracking
- Improved error handling and progress reporting in notebook
- Made prompts more flexible to accept variations of entity/relation types
 2025-12-26 23:00:14 +05:30
KaifAhmad1 8289d56d89 Update notebook and other changes 2025-12-26 19:41:55 +05:30
KaifAhmad1 bde4ef18a3 Update Genomic Variant Analysis notebook and fix temporal query issues 
- Fixed analyze_evolution metrics None handling in temporal_query.py
- Updated 02_Genomic_Variant_Analysis.ipynb with simplified code using Semantica effectively
- Added temporal visualization support
- Fixed GraphBuilder conflict resolution (set resolve_conflicts=False when conflicts already handled)
- Simplified pathway analysis and disease association cells
- Updated visualization to use interactive Plotly graphs instead of HTML
- Added temporal dashboard visualization
 2025-12-26 19:01:32 +05:30
KaifAhmad1 1542b2dafb Improve GraphRAG accuracy with semantic matching and domain-agnostic query intent 
- Replace keyword matching with semantic similarity using embeddings
- Add domain-agnostic query intent extraction
- Improve ranking with hybrid_alpha weighting and context boosting
- Enhance content generation from graph structures
- Update ContextRetriever documentation
- Fix KGVisualizer method call in notebook
 2025-12-26 18:07:44 +05:30
KaifAhmad1 76def647d8 Fix Drug Discovery Pipeline notebook: resolve conflicts, simplify GraphBuilder, update documentation 
- Fixed NameError: Changed merged_entities to all_entities in conflict detection and GraphBuilder cells
- Fixed TypeError: Updated conflict detection to use detect_relationship_conflicts() directly
- Simplified code: Reduced manual Python code, better utilize Semantica's built-in features
- Updated markdown: Converted to bullet points, reflect credibility-weighted strategy
- Improved GraphBuilder: Use automatic object handling instead of manual conversion
 2025-12-26 13:13:23 +05:30
KaifAhmad1 c15ee40cdf feat: Diversify deduplication and conflict resolution across 16 use case notebooks 
Implement domain-appropriate strategies for all notebooks:

Deduplication Methods (9): pairwise, batch, incremental, group, graph_based,
hierarchical, exact, semantic, fuzzy

Merge Strategies (5): keep_first, keep_last, keep_most_complete,
keep_highest_confidence, merge_all

Conflict Detection (6): value, type, entity, relationship, temporal, logical

Conflict Resolution (6): voting, credibility_weighted, most_recent,
first_seen, highest_confidence, expert_review

Key patterns:
- Real-time: pairwise + keep_first + first_seen
- Time-sensitive: temporal + most_recent
- Multi-source: batch + merge_all + voting
- Medical/Research: credibility_weighted
- Fraud/Security: graph_based + logical + expert_review

Added STRATEGIES_SUMMARY.md documentation.
Removed temporary update scripts.
 2025-12-25 22:38:03 +05:30
KaifAhmad1 068d0d489a refactor(trading): rebuild risk assessment and sentiment analysis notebooks 
- Refactor 01_Risk_Assessment.ipynb with GraphStore, DBIngestor, conflict detection
- Refactor 02_News_Sentiment_Analysis.ipynb with TripletStore, StreamIngestor, deduplication
- Complete all 8 phases in both notebooks with different module approaches
- Add comprehensive graph analytics, ontology generation, and export functionality
 2025-12-25 16:54:35 +05:30
KaifAhmad1 7a82b7b597 docs(supply-chain): update risk management notebook 2025-12-25 16:30:23 +05:30
KaifAhmad1 96e784509e Refactor renewable energy notebooks: modular architecture with unique module combinations 
- Rebuilt 01_Energy_Market_Analysis.ipynb with temporal pattern detection, trend prediction, and seed data integration
- Rebuilt 02_Smart_Grid_Management.ipynb with stream processing, real-time monitoring, and anomaly detection
- Removed core orchestrator usage, implemented cell-specific imports
- Added comprehensive data sources and Mermaid pipeline diagrams
- Minimal print statements, proper error handling with redirect_stderr
- Unique module combinations per use case for differentiation
 2025-12-25 15:51:54 +05:30
KaifAhmad1 bd594f9c41 Refactor intelligence notebooks: Use modular architecture with unique approaches per use case 
- Rebuilt 01_Criminal_Network_Analysis.ipynb with graph analytics and centrality focus (31 cells)
- Rebuilt 02_Intelligence_Analysis_Orchestrator_Worker.ipynb with multi-source integration and temporal analysis focus (31 cells)
- Added comprehensive data sources (OSINT feeds, threat intelligence, geospatial data, intelligence agency feeds)
- Implemented cell-specific imports and minimal print statements
- Each notebook uses different module combinations to showcase uniqueness:
  - Criminal Network: CentralityCalculator, CommunityDetector, GraphAnalyzer, entity-aware chunking
  - Intelligence Analysis: StreamIngestor, ConflictDetector, Reasoner, TemporalGraphQuery, sentence chunking
- Removed empty markdown cells
- Added Mermaid pipeline flow diagrams
- No phase/step numbers - descriptive section headers
 2025-12-25 15:19:31 +05:30
KaifAhmad1 b5f895e289 Refactor healthcare notebooks: Use modular architecture with unique approaches per use case 
- Rebuilt 01_Clinical_Reports_Processing.ipynb with EHR integration and triplet store focus (32 cells)
- Rebuilt 02_Drug_Interactions_Analysis.ipynb with ontology generation and reasoning focus (35 cells)
- Added comprehensive data sources (EHR APIs, HL7/FHIR feeds, FDA RSS, PubMed, drug databases)
- Implemented cell-specific imports and minimal print statements
- Each notebook uses different module combinations to showcase uniqueness:
  - Clinical Reports: TripletStore, SeedDataManager, TemporalGraphQuery, DocumentParser
  - Drug Interactions: OntologyGenerator, Reasoner, ConflictDetector, TemporalPatternDetector, CommunityDetector
- Removed empty markdown cells
- Added Mermaid pipeline flow diagrams
- No phase/step numbers - descriptive section headers
 2025-12-25 14:40:58 +05:30
KaifAhmad1 7d07691d99 Refactor finance notebooks: Use modular architecture with unique approaches per use case 
- Rebuilt 01_Financial_Data_Integration_MCP.ipynb with MCP and seed data focus (31 cells)
- Rebuilt 02_Fraud_Detection.ipynb with temporal analysis and pattern detection focus (38 cells)
- Added comprehensive data sources (APIs, RSS feeds, streams, databases)
- Implemented cell-specific imports and minimal print statements
- Each notebook uses different module combinations to showcase uniqueness:
  - Financial Data Integration: MCPIngestor, SeedDataManager, GraphAnalyzer, CentralityCalculator
  - Fraud Detection: StreamIngestor, TemporalGraphQuery, TemporalPatternDetector, ConflictDetector
- Removed empty markdown cells
- Added Mermaid pipeline flow diagrams
- No phase/step numbers - descriptive section headers
 2025-12-25 14:12:27 +05:30
KaifAhmad1 8740379df6 Refactor cybersecurity notebooks: Use modular architecture with comprehensive data sources and all Semantica modules 
- Rebuilt 01_Real_Time_Anomaly_Detection.ipynb with 20+ sections
- Rebuilt 02_Threat_Intelligence_Hybrid_RAG.ipynb with 20+ sections
- Added comprehensive data sources (RSS feeds, APIs, databases, IOC sources)
- Implemented cell-specific imports and minimal print statements
- Integrated all relevant Semantica modules (parse, embeddings, vector_store, graph_store, temporal queries, etc.)
- Removed empty markdown cells
- Added Mermaid pipeline flow diagrams
- No phase/step numbers - descriptive section headers
 2025-12-25 13:38:35 +05:30
KaifAhmad1 5e220dc341 Refactor blockchain notebooks: Use modular architecture with comprehensive data sources and all Semantica modules 
- Rebuilt 01_DeFi_Protocol_Intelligence.ipynb with 20+ sections
- Rebuilt 02_Transaction_Network_Analysis.ipynb with 21+ sections
- Added comprehensive data sources (RSS feeds, APIs, databases)
- Implemented cell-specific imports and minimal print statements
- Integrated all relevant Semantica modules (parse, embeddings, vector_store, graph_store, triplet_store, context, etc.)
- Removed empty markdown cells
- Added Mermaid pipeline flow diagrams
- No phase/step numbers - descriptive section headers
 2025-12-25 13:08:13 +05:30
KaifAhmad1 3f74040509 Refactor biomedical notebooks: Use modular architecture with cell-specific imports and comprehensive data sources 2025-12-25 12:48:51 +05:30
KaifAhmad1 a54959d277 Refactor Drug Discovery Pipeline notebook: break down dense cells, remove unnecessary markdown headings, add bullet points 2025-12-25 00:20:06 +05:30
KaifAhmad1 7c5ee9fb10 Merge branch 'main' of https://github.com/Hawksight-AI/semantica 2025-12-24 18:02:34 +05:30
KaifAhmad1 6155a28d9f Update documentation layout and spacing adjustments 2025-12-24 18:02:16 +05:30
Mohd Kaif 2bbe36400a Delete cookbook/use_cases/USE_CASES_CATALOG.md 2025-12-24 16:48:07 +05:30
KaifAhmad1 106e817ad8 docs: Update all documentation with 18 enhanced domain-specific cookbooks 
- Enhanced 18 cookbooks across 9 domains with real data sources, advanced chunking, temporal KGs, and GraphRAG
- Updated docs/cookbook.md with all 18 cookbook links and enhanced descriptions
- Updated docs/use-cases.md with corrected links and removed duplicates
- Updated README.md with comprehensive Industry Use Cases section
- Fixed all outdated notebook links and ensured consistency across all docs
- Added real data ingestion (RSS feeds, APIs, MCP servers, streams)
- Integrated advanced chunking strategies (entity-aware, relation-aware, ontology-aware, semantic_transformer, etc.)
- Added temporal knowledge graphs, GraphRAG, deduplication, conflict detection, and other Semantica modules
 2025-12-24 16:33:36 +05:30
KaifAhmad1 d5ec639d3c Fix GraphRAG notebooks: update LLM model to llama-3.3-70b-versatile, fix embedding dimension check, fix file ingestion, fix graph metrics access, fix export methods, fix conflict detection, and add side-by-side comparison 2025-12-24 13:37:17 +05:30
KaifAhmad1 cd437a9cfb Fix GraphRAG notebook: embedding dimension check, update LLM model to llama-3.3-70b-versatile, fix file ingestion, graph metrics access, and export methods 2025-12-24 13:00:10 +05:30
KaifAhmad1 bd466b6016 Fix GraphRAG notebook issues: embedding dimension check, update LLM model to llama-3.3-70b-versatile, fix file ingestion, and fix graph metrics access 2025-12-24 12:52:55 +05:30
KaifAhmad1 ef0797e03e Fix semantic extraction pipeline errors and enhance LLM JSON parsing 
Summary of changes:
- Fixed TripletExtractor method name (extract -> extract_triplets)
- Fixed Event attribute name (type -> event_type)
- Improved LLM JSON parsing in providers.py (handles trailing commas, unclosed structures)
- Fixed CentralityCalculator TypeError in GraphRAG notebook
- Corrected CommunityDetector logic and imports in notebook
 2025-12-23 23:23:46 +05:30
KaifAhmad1 eaa1fbefa6 feat(reasoning): add dedicated reasoning tests and fix critical reasoning bugs 
- Added tests/reasoning/ directory with unit and integration tests
- Fixed indentation bug in Reasoner.add_fact for dictionary-based relationships
- Fixed regex variable matching in Reasoner._match_pattern
- Fixed variable handling in SPARQLReasoner query expansion
- Cleaned up cookbook and documentation references
 2025-12-23 21:26:26 +05:30
KaifAhmad1 9cc096dcd5 Refactor GraphRAG notebooks: remove empty cells, step numbers, reorganize imports, and make markdown concise 2025-12-23 18:19:23 +05:30
KaifAhmad1 07bd371e7d Expand GraphRAG notebooks with more cells, less dense code, and improved markdown documentation 2025-12-23 17:10:28 +05:30
Mohd Kaif e24ee50a0d Merge pull request #116 from Hawksight-AI/reasoning 
Reasoning Module Refactor & Synchronization
 2025-12-23 15:24:40 +05:30
KaifAhmad1 7046c92b3a Merge main and resolve conflicts by prioritizing audited reasoning refactor 2025-12-23 15:24:07 +05:30
KaifAhmad1 1ca83dd3c9 Comprehensive reasoning module cleanup: removed InferenceEngine, updated documentation, and synchronized cookbooks project-wide 2025-12-23 15:14:52 +05:30
Mohd Kaif b2925ed773 Delete restructure_utf8.py 2025-12-23 13:47:17 +05:30
Mohd Kaif 4524f071e1 Delete Traeresourcesappoutvsworkbenchcontribterminalcommonscriptssafe_rm_aliases.ps1 } catch{} ; Write-Output [Trae] Safe Rm alias is not enabled, try to fix it now. 2025-12-23 13:46:33 +05:30
KaifAhmad1 644314e976 feat: enhance GraphRAG notebooks with AgentContext and improve VectorStore API 2025-12-23 13:45:13 +05:30
KaifAhmad1 65cb229ed5 Update GraphRAG cookbook notebook 2025-12-23 00:22:41 +05:30
KaifAhmad1 ab4fa0e4c5 fix(cookbook): resolve AttributeError and update imports in GraphRAG notebook 2025-12-22 23:44:22 +05:30
KaifAhmad1 ab9624fb39 feat: expand real-world data sources and add web ingestion to advanced RAG notebooks 2025-12-22 23:11:28 +05:30
KaifAhmad1 323a788288 Remove hardcoded API keys and finalize Colab badges in notebooks 2025-12-22 22:11:08 +05:30
KaifAhmad1 e92bf0e872 Move Colab badges to the top of notebooks for better visibility 2025-12-22 22:06:10 +05:30
KaifAhmad1 995c1f27eb Add 'Open in Colab' badges to notebooks 2025-12-22 21:59:05 +05:30
KaifAhmad1 fcd61772b2 Update notebooks for local embeddings and interactive multi-hop queries, fix FalkorDB integration, and add docker-compose 2025-12-22 21:52:22 +05:30
KaifAhmad1 2cf2733d5b fix: Update ingestion URLs and logic in GraphRAG notebook and restructure script 2025-12-22 20:43:51 +05:30
KaifAhmad1 b07b1d58f7 feat: professional restructure of comparison notebook and core API enhancements 2025-12-22 20:22:05 +05:30
KaifAhmad1 e91cc315ec Cleanup temporary fix script 2025-12-22 20:09:17 +05:30
KaifAhmad1 5b14f1cc4a Fix Phase 5 config and cleanup debug scripts 2025-12-22 20:08:16 +05:30