Commit Graph

  • 46dc4342ee
    Merge 780a46d1b1 into 710fdad6f0 Nathan Evans 2026-01-13 02:00:28 +0000
  • 780a46d1b1 Push drift_k_followups through to prompt drift-fixes Nathan Evans 2026-01-12 18:00:21 -0800
  • a380a58f4b Fix DRIFT notebook Nathan Evans 2026-01-12 17:22:48 -0800
  • 3d6b182a46 Fix mock embedder to match default embedding length Nathan Evans 2026-01-12 16:38:39 -0800
  • 1fcb5cfaad Add drift back to smoke tests Nathan Evans 2026-01-12 16:01:33 -0800
  • 7ccf8d43a8 Fix lancedb insertion Nathan Evans 2026-01-12 15:27:02 -0800
  • f4a20cd73d Remove embedding column from df loaders Nathan Evans 2026-01-12 14:41:04 -0800
  • a8c1772340 Remove deprecated title from embedding flow Nathan Evans 2026-01-12 14:40:46 -0800
  • a4d1278c2a Use stable ids for community reports Nathan Evans 2026-01-12 14:40:30 -0800
  • 710fdad6f0
    Input factory (#2168) v3/main Nathan Evans 2026-01-12 12:47:57 -0800
  • ad76163581 Format Nathan Evans 2026-01-12 10:51:32 -0800
  • 89a5223249 Fix BOM in csv smoke Nathan Evans 2026-01-12 10:29:35 -0800
  • ade3a6f77d Fix smoke tests Nathan Evans 2026-01-12 08:52:08 -0800
  • febfd13acf
    Merge 281b8e84b7 into fdb7e3835b dependabot[bot] 2026-01-12 08:08:40 +0000
  • 281b8e84b7
    Bump JamesIves/github-pages-deploy-action from 4.6.4 to 4.8.0 dependabot/github_actions/JamesIves/github-pages-deploy-action-4.8.0 dependabot[bot] 2026-01-12 08:08:36 +0000
  • e170124d39 Add empty objects for NaN raw_data Nathan Evans 2026-01-09 16:55:41 -0800
  • 7ce10306ee Separate storage from input config Nathan Evans 2026-01-09 16:40:52 -0800
  • c974970e83 Update verb tests Nathan Evans 2026-01-09 15:33:18 -0800
  • 6fba8d005a Format Nathan Evans 2026-01-09 12:02:35 -0800
  • e19501d937 Remove plugins flag (implicit disabled) Nathan Evans 2026-01-09 11:57:06 -0800
  • 6fbf26c091 Remove pattern default from MarkItDown reader Nathan Evans 2026-01-09 11:56:09 -0800
  • 6d5076aa51 Add MarkItDown support Nathan Evans 2026-01-09 11:54:59 -0800
  • a671aa4fe4 Align input config type name with other factory configs Nathan Evans 2026-01-08 15:41:28 -0800
  • 2f6d075b97 Back-compat comment Nathan Evans 2026-01-08 12:13:11 -0800
  • 39125b2b13 Rename ChunkResult to TextChunk and add transformer support Nathan Evans 2026-01-07 17:43:34 -0800
  • e8e316f291 Extract input module into new graphrag-input monorepo package Nathan Evans 2026-01-07 16:40:18 -0800
  • 868fde1c22 Update structured_file_reader to use get_property utility Nathan Evans 2026-01-07 16:22:00 -0800
  • 164c5e1188 Add get_property utility for nested dictionary access with dot notation Nathan Evans 2026-01-07 16:21:21 -0800
  • 9d161bdd9f Typo Nathan Evans 2026-01-07 14:10:48 -0800
  • 36b7be72f1 Nicer automatic title Nathan Evans 2026-01-06 16:48:14 -0800
  • e2395e97ba Move metadata handling entirely to chunking Nathan Evans 2026-01-06 16:45:29 -0800
  • fb9a92464b Fix merge imports Nathan Evans 2026-01-06 15:48:06 -0800
  • 8e3c7170f7 Merge branch 'v3/main' into input-factory Nathan Evans 2026-01-06 15:42:16 -0800
  • 6ac0b582ed Store raw data Nathan Evans 2026-01-06 15:39:58 -0800
  • 8fd7730067
    Chunker factory (#2156) Nathan Evans 2026-01-06 15:39:44 -0800
  • 8b45208ba9 Add json lines (jsonl) input support Nathan Evans 2026-01-06 14:59:49 -0800
  • a03df1b350 Throw if empty documents Nathan Evans 2026-01-06 14:29:11 -0800
  • 2b83d661f9 Remove pandas from input loading Nathan Evans 2026-01-06 14:18:57 -0800
  • f066080ef0 Combine structured data extraction Nathan Evans 2026-01-06 13:03:04 -0800
  • b265612828 Clean up optional column configs Nathan Evans 2026-01-06 10:51:37 -0800
  • c73263d02c Set encoding default Nathan Evans 2026-01-06 10:13:36 -0800
  • 2b893840c0 Move file pattern logic into InputReader Nathan Evans 2026-01-06 10:11:38 -0800
  • aa7ecec286
    Merge a9746b4a1e into fdb7e3835b priya-madraslabs 2026-01-06 13:24:21 +0000
  • a9746b4a1e feat: Add Neo4j + GraphQL POC integration ajee-cmd 2026-01-06 18:50:11 +0530
  • efaaa1f1d0 Move input config alongside input readers Nathan Evans 2026-01-05 17:49:39 -0800
  • 99aea5226e Update input factory to match other factories Nathan Evans 2026-01-05 16:35:14 -0800
  • fde14b63e5
    Mismatch between header in community report generation prompt examples and input data (id vs human_readable_id) (#2161) gaudyb 2025-12-30 18:08:51 -0600
  • 66d41e7e0a
    Merge branch 'v3/main' into issue-860-id-mismatch gaudyb 2025-12-30 18:08:40 -0600
  • c649d9f6ee
    Issue #2004 fix (#2159) gaudyb 2025-12-30 18:08:10 -0600
  • 391858d4d9 fix format Gaudy Blanco 2025-12-30 13:02:20 -0600
  • 1922f5fde7 fix issue #860 for mismatch in prompts and input Gaudy Blanco 2025-12-30 13:00:51 -0600
  • c6920de967
    Merge 6b1d1aba8c into fdb7e3835b priya-madraslabs 2025-12-30 14:45:52 +0000
  • 6b1d1aba8c Verify Gemini usage via LiteLLM and add runtime logging ajee-cmd 2025-12-30 19:27:00 +0530
  • 1a25bf845d Add missing version updates for graphrag_chunking Nathan Evans 2025-12-29 15:59:36 -0800
  • a3fcf95a25 add unit test for dynamic community selection implementing #2158 logic Gaudy Blanco 2025-12-29 16:51:43 -0600
  • a817dbcd7c add unit test for dynamic community selection Gaudy Blanco 2025-12-29 16:49:52 -0600
  • 5793486e95 fix issue #2004 using KeenhoChu idea in his PR Gaudy Blanco 2025-12-29 16:16:10 -0600
  • 6cb803c878
    Fix DynamicCommunitySelection type mismatch for children IDs majiayu000 2025-12-28 10:38:15 +0800
  • d79c496f39 launch.json changes issue_1965_prompt_tuning_sample Gaudy Blanco 2025-12-24 11:30:22 -0600
  • 7748493fdf Streamline chunking config Nathan Evans 2025-12-23 10:28:14 -0800
  • a741bfb8d7 Add ChunkResult model Nathan Evans 2025-12-22 14:18:21 -0800
  • ee20153d8c Typo Nathan Evans 2025-12-22 12:48:25 -0800
  • 88af7f8dc2 Format Nathan Evans 2025-12-22 12:13:02 -0800
  • bd968f2710 Move chunking to monorepo package Nathan Evans 2025-12-22 11:57:12 -0800
  • d9ba63f4d6 Set defaults for chunking config Nathan Evans 2025-12-22 11:25:53 -0800
  • b32f403e8f Fix tokenizer removal from chunker Nathan Evans 2025-12-22 11:20:43 -0800
  • 90479c0b1c Move Tokenizer back to GR core Nathan Evans 2025-12-22 11:18:42 -0800
  • 247547f5bc Move metadata prepending to a util Nathan Evans 2025-12-22 11:10:39 -0800
  • c8dbb029f4 Revert ChunkingDocument interface Nathan Evans 2025-12-22 10:17:27 -0800
  • 026474a073 Remove chunk_size_includes_metadata config Nathan Evans 2025-12-19 17:39:42 -0800
  • 780a03827c Add prepending tests Nathan Evans 2025-12-19 16:36:30 -0800
  • eb22d7a61b Fix defaults construction Nathan Evans 2025-12-18 17:20:04 -0800
  • 9aa94dfd86 Streamline config Nathan Evans 2025-12-18 17:15:04 -0800
  • 896a48ce1e Move pre-pending into chunkers Nathan Evans 2025-12-18 16:38:34 -0800
  • b7c06730d7 Move Tokenizer base class to common package Nathan Evans 2025-12-18 13:56:32 -0800
  • e5c1aa7d52 Restore create_base_text_units parameterization Nathan Evans 2025-12-18 13:46:22 -0800
  • a20dbdb795 Collapse token splitting functionality into one class/function Nathan Evans 2025-12-18 13:22:18 -0800
  • b63f747d44 Co-locate chunking/splitting Nathan Evans 2025-12-18 11:58:53 -0800
  • 461291706f Split apart chunker module Nathan Evans 2025-12-17 16:12:25 -0800
  • 81240ab2e3 Merge v3/main into chunker-factory Nathan Evans 2025-12-17 15:21:51 -0800
  • 9e8c900dd4 Add base chunking factory and migrate workflow to use it Nathan Evans 2025-12-17 15:15:35 -0800
  • c296f1ae15
    Fix a bunch of module comments and function visibility (#2154) Nathan Evans 2025-12-17 10:55:26 -0800
  • 76f9862465 Fix a bunch of module comments and function visibility Nathan Evans 2025-12-16 15:22:58 -0800
  • bdc2485433 Delete unused check_token_limit Nathan Evans 2025-12-16 14:43:54 -0800
  • 8bf28187da Delete NoopTextSplitter Nathan Evans 2025-12-16 14:38:35 -0800
  • 3201f28bea
    Add GraphRAG Cache package. (#2153) Derek Worthen 2025-12-16 06:37:28 -0800
  • 96f05f986f Merge branch 'v3/main' into graphrag-cache Derek Worthen 2025-12-16 06:00:21 -0800
  • 85418ca73d Update docs. Derek Worthen 2025-12-16 05:52:54 -0800
  • bffa400c89
    Python update (3.13) (#2149) Nathan Evans 2025-12-15 15:39:38 -0800
  • 18e95140c6 Fix integration tests. Derek Worthen 2025-12-15 14:32:18 -0800
  • 9fed90c9b4 Update cache config to support storage. Derek Worthen 2025-12-15 14:18:48 -0800
  • d39d975d52 update vsts.yml python version Nathan Evans 2025-12-15 14:09:26 -0800
  • f998d373ad Update numpy to 2.1+ and pandas to 2.3+ for Python 3.13 Windows compatibility Nathan Evans 2025-12-15 14:09:13 -0800
  • f6935a3ab1 Update Python support to 3.11-3.13 with compatible dependencies Nathan Evans 2025-12-15 14:00:46 -0800
  • 8ae99bb9db update uv lock Nathan Evans 2025-12-15 13:20:52 -0800
  • 5e3c0b4899 Add scipy>=1.15.0 for numpy 2.x compatibility Nathan Evans 2025-12-15 13:18:45 -0800
  • 71f9c09f3f Add GraphRAG Cache package. Derek Worthen 2025-10-22 10:19:10 -0700
  • f44ad83b7e update uv.lock Nathan Evans 2025-12-15 11:37:16 -0800
  • 3bbaaca126 Update pandas to >=2.3.0 for numpy 2.x compatibility Nathan Evans 2025-12-15 11:36:49 -0800
  • fbe007f228 update uv lock Nathan Evans 2025-12-15 10:54:53 -0800