aman/kg-scr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • c5bf5d2b0c remove notebooks - Delete notebooks/ (personal scratch artifacts; gitignored) - Move nbformat to --extra migrate; lazy imports in migrate.py and cli.py so base CLI loads without it - Restore langchain-text-splitters in core (chunking dependency) main Aman Nalakath 2026-07-21 00:47:52 +02:00
  • 7de0e716eb repo hygiene, tooling config, v0.2.0 - Untrack src/ocr_pipeline.egg-info from git, delete pyproject.toml~, stale run_008/run_009 dirs - Ruff config moved to [tool.ruff.lint] (silences deprecation warning) - Pre-commit: bump revs (ruff v0.14.13, mypy v1.18.1, hooks v6.0.0); drop redundant isort hook (ruff I already sorts imports) - mypy: add ignore_missing_imports for optional deps; types-PyYAML in dev extras; python_version=3.12 for numpy 2.5 stubs compat; CI step - Doctor: suppress paddle ccache UserWarning noise during check - CHANGELOG dated for 0.2.0; README minimal-style rewrite with collapsible details sections - Bump version to 0.2.0 v0.2.0 Aman Nalakath 2026-07-21 00:40:19 +02:00
  • bf968affaa update readme aman 2026-07-20 17:53:52 +00:00
  • 65220d3aca Update README.md aman 2026-07-20 17:53:08 +00:00
  • 7503a441c2 kg: graph build, traversal queries, neo4j export - kg_ocr.graph builds a networkx graph (docs, chunks, entities, citations, co-occurrence) from chunk markdown - analyzer for summaries, top entities/citations, anomaly checks - traversal: chunks_for_entity/citation, related_entities, expand_context - export: JSON round-trip, GraphML, batched MERGE into neo4j - new CLI: ocr-pipeline kg build|stats|query|export - lazy kg_ocr imports, networkx/neo4j behind extras - dropped dead watch.py shim, added KgConfig stub - trimmed README, updated TODO Aman Nalakath 2026-07-20 19:50:38 +02:00
  • 39655fc35f add doctor command, fix ISBN false positives, wire up CI Aman Nalakath 2026-07-20 12:37:26 +02:00
  • a0211155fa refactor: solidify startup UX and engine-aware preprocessing - Slim core deps: move ML stack to optional extras (paddle/tables/figures/scientific/full) - Lazy settings proxy with config search paths (env var, cwd, user dir) - New commands: init, demo, setup [basic|full], first-run guard on run/watch - Engine-aware preprocessing: Paddle gets original image (fixes dark mode 0.83->0.95) - Results table shows Skipped count; lazy run-dir creation - kg_ocr marked experimental with extra, Docker defaults with OCR_PIPELINE_CONFIG - 25/25 tests, ruff clean Aman Nalakath 2026-07-19 22:14:54 +02:00
  • deab02610b update README pyproject & config Aman Nalakath 2026-07-19 20:01:32 +02:00
  • 1cf1c6eeab improve the OCR pipeline processing and outputs formatting Aman Nalakath 2026-07-19 19:54:53 +02:00
  • d375db47c3 platform agnosticity Aman Nalakath 2026-07-19 11:45:08 +02:00
  • 4fe9e76cad add ImagePreprocessor, compute_image_hash, and OutputMetadata Aman 2026-07-19 08:46:53 +00:00
  • bf9e8b8a8f add ImagePreprocessor and compute_image_hash to ocr module Aman 2026-07-19 08:43:20 +00:00
  • a32b7508c7 OCR-to-RAG pipeline for life science screenshots Aman 2026-07-18 19:34:22 +00:00
  • 012549b4bc added llm and rag queries Aman Nalakath 2026-03-24 20:15:22 +01:00
  • cbfcf1e315 added scaffold struct for the prj Aman Nalakath 2026-03-24 14:58:58 +01:00
  • 95655686f9 RAG init using litellm Aman Nalakath 2026-03-21 19:30:04 +01:00
  • 37fc80931f add txtai, miniLM Aman Nalakath 2026-03-19 14:29:38 +01:00
  • 4b25500600 prj init Aman Nalakath 2025-12-09 22:53:41 +01:00