aman pushed to main at aman/kg-scr 2026-07-20 22:48:01 +00:00
c5bf5d2b0c remove notebooks
aman pushed tag v0.2.0 to aman/kg-scr 2026-07-20 22:40:49 +00:00
aman pushed to main at aman/kg-scr 2026-07-20 22:40:48 +00:00
7de0e716eb repo hygiene, tooling config, v0.2.0
aman pushed to main at aman/kg-scr 2026-07-20 17:53:54 +00:00
bf968affaa update readme
aman pushed to main at aman/kg-scr 2026-07-20 17:53:10 +00:00
65220d3aca Update README.md
aman pushed to main at aman/kg-scr 2026-07-20 17:50:53 +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 pushed to main at aman/kg-scr 2026-07-20 10:37:34 +00:00
39655fc35f add doctor command, fix ISBN false positives, wire up CI
aman pushed to main at aman/kg-scr 2026-07-19 20:15:11 +00:00
a0211155fa refactor: solidify startup UX and engine-aware preprocessing
aman pushed to main at aman/kg-scr 2026-07-19 18:01:39 +00:00
deab02610b update README pyproject & config
aman pushed to main at aman/kg-scr 2026-07-19 17:55:04 +00:00
1cf1c6eeab improve the OCR pipeline processing and outputs formatting
aman pushed to main at aman/kg-scr 2026-07-19 09:45:15 +00:00
d375db47c3 platform agnosticity
aman pushed to main at aman/kg-scr 2026-07-19 08:47:02 +00:00
4fe9e76cad add ImagePreprocessor, compute_image_hash, and OutputMetadata
aman pushed to main at aman/kg-scr 2026-07-19 08:43:31 +00:00
bf9e8b8a8f add ImagePreprocessor and compute_image_hash to ocr module
aman pushed to main at aman/kg-scr 2026-07-18 19:38:43 +00:00
a32b7508c7 OCR-to-RAG pipeline for life science screenshots
aman pushed to main at aman/kg-scr 2026-03-24 19:15:29 +00:00
012549b4bc added llm and rag queries
aman pushed to main at aman/kg-scr 2026-03-24 13:59:06 +00:00
cbfcf1e315 added scaffold struct for the prj
aman pushed to main at aman/kg-scr 2026-03-21 18:31:19 +00:00
95655686f9 RAG init using litellm
aman pushed to main at aman/kg-scr 2026-03-19 13:29:48 +00:00
37fc80931f add txtai, miniLM