mengzhx/semantica
1
0
Fork 0
mirror of https://github.com/semantica-agi/semantica.git synced 2026-08-30 04:40:16 +00:00
Code Issues Packages Projects Releases Wiki Activity
737 Commits 43 Branches 23 Tags
parse
Commit Graph
737 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
KaifAhmad1 957c122116 docs: add Docling integration guide, clear code example, and fix parser consistency issues 2026-01-08 21:27:48 +05:30
Mohd Kaif 31ca2e4446 Merge pull request #164 from Hawksight-AI/docs 
docs: update changelog with model switching fixes
 2026-01-08 19:38:01 +05:30
KaifAhmad1 b08c13364b docs: update changelog with model switching fixes and tests 2026-01-08 19:35:24 +05:30
Mohd Kaif 01dd0c97ab Merge pull request #163 from Hawksight-AI/embeddings 
Fix Model Switching and Dynamic Dimension Detection
 2026-01-08 19:00:12 +05:30
KaifAhmad1 2bd1d06eb2 fix: resolve model switching bug and implement intrinsic dimension detection in TextEmbedder 2026-01-08 18:56:42 +05:30
Mohd Kaif 9a2f2cd2d2 Merge pull request #162 from Hawksight-AI/kg 
docs: update changelog with kg module fixes #159
 2026-01-08 17:43:29 +05:30
KaifAhmad1 04a210232e docs: update changelog with kg module fixes #159 2026-01-08 17:42:19 +05:30
Mohd Kaif b3baeaa74e Merge pull request #161 from Hawksight-AI/kg 
Fix 'unhashable type: Entity' in GraphAnalyzer (#159)
 2026-01-08 17:29:31 +05:30
KaifAhmad1 58707ff721 fix(kg): resolve 'unhashable type: Entity' in GraphAnalyzer #159 
- Robust ID extraction in CentralityCalculator, CommunityDetector, and ConnectivityAnalyzer
- Support for direct Entity objects and dictionaries as node identifiers
- Improved Entity hashability in utils/types.py
- Added integration test to verify fix and prevent regression
 2026-01-08 17:23:31 +05:30
Mohd Kaif 9b18bc3da3 Merge pull request #158 from Hawksight-AI/dependabot/pip/protobuf-4.25.8 
chore(deps): bump protobuf from 4.25.3 to 4.25.8
 2026-01-07 19:13:13 +05:30
dependabot[bot] 5764a88d7e chore(deps): bump protobuf from 4.25.3 to 4.25.8 
Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 4.25.3 to 4.25.8.
- [Release notes](https://github.com/protocolbuffers/protobuf/releases)
- [Commits](https://github.com/protocolbuffers/protobuf/compare/v4.25.3...v4.25.8)

---
updated-dependencies:
- dependency-name: protobuf
  dependency-version: 4.25.8
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
 2026-01-07 13:41:10 +00:00
Mohd Kaif cc69899b13 Merge pull request #157 from Hawksight-AI/utils 
Dependency Fixes, GraphRAG Alignment, and Orchestrator Improvements
 2026-01-07 19:07:26 +05:30
KaifAhmad1 e3b53998c3 Fix dependency issues, align GraphRAG notebook, and update changelog 2026-01-07 19:00:30 +05:30
Mohd Kaif de3441e76e Merge pull request #156 from Hawksight-AI/docs 
Cookbook Fixes & Repository Optimization
 2026-01-07 16:03:03 +05:30
KaifAhmad1 bd3c258458 chore: add .gitattributes to fix language statistics 2026-01-07 15:59:39 +05:30
Mohd Kaif 51cc445327 Merge pull request #155 from Hawksight-AI/docs 
Cookbook Notebook Cleanup & Fixes
 2026-01-07 15:43:37 +05:30
KaifAhmad1 04c4c9fb4c docs: clean and fix corrupted notebooks in cookbook 2026-01-07 15:41:13 +05:30
Mohd Kaif 010251ac35 Merge pull request #154 from Hawksight-AI/ontology 
Fix KnowledgeGraph Documentation Mismatch
 2026-01-07 15:05:48 +05:30
KaifAhmad1 dcd6f25f87 docs: fix KnowledgeGraph mismatch and update tests for issue #144 2026-01-07 15:01:47 +05:30
Mohd Kaif 55abd52b77 Merge pull request #153 from Hawksight-AI/docs 
docs: improve robustness and data consistency in earnings analysis notebook
 2026-01-07 14:11:41 +05:30
KaifAhmad1 960d7c5f8f docs: improve robustness and fix variable inconsistencies in earnings call notebook 2026-01-07 14:09:22 +05:30
Mohd Kaif 2489ce72b5 Delete GITHUB_ISSUE_LLM_EXTRACTION.md 2026-01-07 03:06:21 +05:30
Mohd Kaif f488dfb82a Delete PR_DESCRIPTION_LLM_EXTRACTION.md 2026-01-07 03:06:06 +05:30
Mohd Kaif 74fdd3330e Merge pull request #150 from Hawksight-AI/semantic-extract 
Robust LLM Extraction - Auto-Chunking, Retries, and Diagnostics
 2026-01-07 03:05:37 +05:30
KaifAhmad1 e712949872 Enhance LLM extraction methods with auto-chunking, robust parsing and improved diagnostics (#149) 2026-01-07 03:03:19 +05:30
Mohd Kaif c208f6b54e Delete PR_DESCRIPTION.md 2026-01-07 01:13:55 +05:30
Mohd Kaif d516ea69dc Merge pull request #148 from Hawksight-AI/semantic-extract 
fix(semantic_extract): Pass API key to Groq LLM provider in extractio…
 2026-01-07 01:11:21 +05:30
KaifAhmad1 2790132e8e fix(semantic_extract): Pass API key to Groq LLM provider in extraction methods 
- Add API key handling in extract_entities_llm(), extract_relations_llm(), and extract_triplets_llm()
- Add explicit api_key handling in NERExtractor and RelationExtractor
- Add llm_model parameter support in extract_triplets_llm() for consistency
- Fix relation extraction bug with type checking for subject_text/object_text
- Add environment variable fallback for API keys
- Update notebook with standard API key pattern

Fixes #147
 2026-01-07 01:07:56 +05:30
Mohd Kaif 1e22ff3a75 Merge pull request #146 from Hawksight-AI/semantic-extract 
fix(semantic_extract): Pass API key to Groq LLM provider in extractio…
 2026-01-06 22:43:59 +05:30
KaifAhmad1 9c59f97542 fix(semantic_extract): Pass API key to Groq LLM provider in extraction methods 
- Add API key handling in extract_entities_llm(), extract_relations_llm(), and extract_triplets_llm()
- Add llm_model parameter support in extract_triplets_llm() for consistency
- Fix relation extraction bug with type checking for subject_text/object_text
- Add environment variable fallback for API keys
- Include providers.py for context (GroqProvider implementation)

Fixes #145
 2026-01-06 22:37:57 +05:30
Mohd Kaif 4eb69e5048 Merge pull request #143 from Hawksight-AI/docs 
Refreshed Metadata, Analytics & Community Links
 2026-01-06 12:04:53 +05:30
KaifAhmad1 2b43fa4699 fix: update discord badge to a reliable static version 2026-01-06 12:00:23 +05:30
Mohd Kaif 9fb18e3ec6 Merge pull request #142 from Hawksight-AI/docs 
Update Badges, Discord Links, and Version Metadata
 2026-01-06 11:57:37 +05:30
KaifAhmad1 7f7c36f94d docs: update badges, discord links, and version mentions 2026-01-06 11:54:17 +05:30
Mohd Kaif 2e2f19f43d Merge pull request #141 from Hawksight-AI/docs 
Release v0.1.1: Docling Integration & 2026 Sync
 2026-01-06 00:28:15 +05:30
KaifAhmad1 d7b686f32a Release v0.1.1: Docling support, version bump, and documentation updates 2026-01-06 00:21:20 +05:30
Mohd Kaif e89e707e49 Merge pull request #140 from Hawksight-AI/utils 
Fix DoclingParser Integration and Confirm Cross-Platform Compatibility
 2026-01-05 22:31:57 +05:30
KaifAhmad1 a441e935f9 Fix DoclingParser integration and align with docling API 
- Fix import logic in __init__.py to properly export DoclingParser
- Rewrite docling_parser.py to use docling's native API (direct attribute access)
- Remove unsupported features (table_extraction_mode, invalid format_options)
- Use doc.tables, doc.pictures, doc.pages directly instead of dict parsing
- Update notebook with improved code and documentation
- Add proper error handling for when docling is not available

Fixes #138
 2026-01-05 22:27:15 +05:30
Mohd Kaif 3fb98aa0ed Merge pull request #139 from Hawksight-AI/utils 
Resolve DoclingParser Exports, Windows Progress Encoding, and Finance Cookbook Update (#138)
 2026-01-05 20:10:45 +05:30
KaifAhmad1 4e0c3bc361 Resolve DoclingParser exports, fix Windows progress encoding, and update finance cookbook #138 2026-01-05 20:04:59 +05:30
Mohd Kaif ef2c3dc841 Merge pull request #137 from Hawksight-AI/utils 
feat: Add pipeline_id support and fix parsing table display
 2026-01-05 18:17:24 +05:30
KaifAhmad1 96604ae398 feat: Add pipeline_id support and fix parsing table display 
- Add pipeline_id parameter to all trackers, batch processors, parsers, and extractors
- Fix DoclingParser to show extraction counts in progress display
- Add 'Extracted' column showing tables, images, pages
- Emphasize Docling as core dependency in messages

Closes #136
 2026-01-05 18:15:12 +05:30
Mohd Kaif 88a4b9f1d2 Merge pull request #134 from Hawksight-AI/parse 
feat(parse): add progress tracking to DoclingParser and update earnin…
 2026-01-05 14:46:12 +05:30
KaifAhmad1 ea02896617 feat(parse): add progress tracking to DoclingParser and update earnings call notebook 
- Add 8-stage progress tracking (0-100%) with ETA to DoclingParser
- Update earnings call analysis notebook with MDA Space Q3 2025 example
- Simplify notebook code structure
- Add real-time progress visibility for PDF parsing

Closes #133
 2026-01-05 14:42:12 +05:30
Mohd Kaif 01808728f4 Merge pull request #132 from Hawksight-AI/docs 
[DOCS] Fix Discord invite link and reorganize README sections
 2026-01-04 19:58:02 +05:30
KaifAhmad1 b03ab2458d docs: Fix Discord invite link and reorganize README sections 
- Update Discord invite link from https://discord.gg/semantica to https://discord.gg/pMHguUzG
- Move Contributors section inside Contributing section (following open source best practices)
- Update Enterprise Support section to indicate future availability
- Add Evals to roadmap

Fixes #127
 2026-01-04 19:56:10 +05:30
Mohd Kaif f8551c5dfb Merge pull request #131 from Hawksight-AI/utils 
Fix: Handle OSError for Optional Dependencies and Make DoclingParser Standalone
 2026-01-04 17:56:39 +05:30
KaifAhmad1 e7f713d43b Fix: Handle OSError for optional dependencies and make DoclingParser standalone 
- Add safe_import utility in semantica/utils/helpers.py for graceful optional dependency handling
- Update all optional imports (spacy, docling, etc.) to handle OSError (Windows DLL issues)
- Make DoclingParser standalone with docling as core dependency
- Remove DoclingParser integration from DocumentParser
- Implement lazy initialization for DoclingParser (fails on parse(), not init())
- Fix DocumentConverter initialization (remove unsupported pipeline_options parameter)
- Preserve original error messages without modification
- Update semantic_extract, split, parse, embeddings, vector_store, visualization modules
- Fix OSError handling across entire codebase for Windows compatibility
- Update 60+ files with proper optional dependency handling
 2026-01-04 17:44:14 +05:30
Mohd Kaif 6595f1918c Merge pull request #130 from Hawksight-AI/llms 
Fix: Make PyTorch import lazy to avoid DLL errors on Windows
 2026-01-03 20:43:43 +05:30
KaifAhmad1 47809f2ef9 Fix: Make PyTorch import lazy to avoid DLL errors on Windows 
- Remove top-level torch import from providers.py
- Add lazy imports in HuggingFaceLLMProvider and HuggingFaceModelLoader
- Remove hardcoded API key from notebook
- PyTorch now only loads when HuggingFace providers are instantiated

Fixes #129
 2026-01-03 20:39:37 +05:30