Commit graph

  • 6bef40766d style: fix lint errors (trailing whitespace and formatting) BukeLy 2025-11-20 01:41:23 +08:00
  • 65ff9b32bd style: fix lint errors in E2E test file BukeLy 2025-11-20 01:32:42 +08:00
  • 12ab6ebb42
    Add trilingual entity extractor (Chinese/English/Swedish) Claude 2025-11-19 17:29:00 +00:00
  • 088b986ac6 style: fix lint issues (trailing whitespace and formatting) BukeLy 2025-11-20 01:28:39 +08:00
  • e9f6cedff8 fix: use NetworkXStorage for E2E tests (AGE extension not available in CI) BukeLy 2025-11-20 01:15:20 +08:00
  • e842327486 fix: replace db.fetch with db.query for PostgreSQL migration BukeLy 2025-11-20 01:12:27 +08:00
  • 5d9547344a fix: correct Qdrant legacy_namespace for data migration BukeLy 2025-11-20 01:08:15 +08:00
  • fa7a43a6d2 fix: preserve EmbeddingFunc object in global_config BukeLy 2025-11-20 00:55:06 +08:00
  • 519f7f61c4 fix: handle wrapped embedding_func and lock flag logic BukeLy 2025-11-20 00:51:47 +08:00
  • bf176b38ee fix: correct attribute access in E2E tests BukeLy 2025-11-20 00:47:16 +08:00
  • 6737ec00bc fix: improve Qdrant wait strategy in E2E tests BukeLy 2025-11-20 00:38:28 +08:00
  • bef7577fd9 fix: correct PostgreSQL environment variable name in E2E workflow BukeLy 2025-11-20 00:35:03 +08:00
  • 15e5b1f8f4
    Add comprehensive multilingual NER tools comparison guide Claude 2025-11-19 16:34:37 +00:00
  • 38f41daa3d fix: remove non-existent storage kwargs in E2E tests BukeLy 2025-11-20 00:32:16 +08:00
  • 01bdaac180 refactor: optimize batch insert handling in PGVectorStorage BukeLy 2025-11-20 00:27:17 +08:00
  • 722f639fa5 fix: remove Qdrant health check in E2E workflow BukeLy 2025-11-20 00:26:36 +08:00
  • 66a0dfe5b7 fix: resolve E2E test failures in CI BukeLy 2025-11-20 00:25:35 +08:00
  • c7e7b347e9 test: add Qdrant legacy migration E2E test BukeLy 2025-11-20 00:19:21 +08:00
  • dd8ad7c46d
    Add detailed comparison: HanLP vs GLiNER for Chinese entity extraction Claude 2025-11-19 16:16:00 +00:00
  • dc2061583f test: refactor E2E tests using complete LightRAG instances BukeLy 2025-11-20 00:13:00 +08:00
  • 47fd7ea10e fix: add required connection retry configs to E2E tests BukeLy 2025-11-20 00:02:26 +08:00
  • d89849c8a6 fix: E2E test fixture scope mismatch BukeLy 2025-11-19 23:58:32 +08:00
  • c32e6a4e7b test: add E2E tests with real PostgreSQL and Qdrant services BukeLy 2025-11-19 23:41:40 +08:00
  • 209dadc0af ci: add feature branch testing workflow BukeLy 2025-11-19 23:34:45 +08:00
  • 4c12301e81 fix: correct parameter passing in delete_entity_relation BukeLy 2025-11-19 23:31:09 +08:00
  • a0dfb47d0d docs: add multi-model vector storage isolation demo BukeLy 2025-11-19 23:28:35 +08:00
  • d52adb64d7
    Merge pull request #2390 from danielaskdd/fix-pytest-logging-error Daniel.y 2025-11-19 23:09:30 +08:00
  • 7dc1f83efb fix: PostgreSQL read methods and delete_entity_relation bugs BukeLy 2025-11-19 23:01:01 +08:00
  • ad68624d02 feat: PostgreSQL model isolation and auto-migration BukeLy 2025-11-19 22:54:37 +08:00
  • b7de694f48 Add comprehensive error logging across API routes yangdx 2025-11-19 22:50:06 +08:00
  • 0fb2925c6a Remove ascii_colors dependency and fix stream handling errors yangdx 2025-11-19 21:38:17 +08:00
  • ec70d9c857
    Add comprehensive comparison of RAG evaluation methods Claude 2025-11-19 13:36:56 +00:00
  • 9b4831d84e
    Add comprehensive RAGAS evaluation framework guide Claude 2025-11-19 12:52:22 +00:00
  • 362ef56129
    Add comprehensive entity/relation extraction quality evaluation guide Claude 2025-11-19 12:45:31 +00:00
  • f72f435cef
    Merge pull request #2389 from danielaskdd/fix-chunk-size Daniel.y 2025-11-19 20:34:11 +08:00
  • 49a485b414
    Add gleaning configuration display to frontend status Claude 2025-11-19 12:13:56 +00:00
  • 63e928d75c
    Add comprehensive guide explaining gleaning concept in LightRAG Claude 2025-11-19 11:45:07 +00:00
  • fec7c67f45 Add comprehensive chunking tests with multi-token tokenizer edge cases yangdx 2025-11-19 19:31:36 +08:00
  • 5733292557 Add comprehensive tests for chunking with recursive splitting yangdx 2025-11-19 19:08:50 +08:00
  • 17df3be7f9
    Add comprehensive self-hosted LLM optimization guide for LightRAG Claude 2025-11-19 10:53:48 +00:00
  • 6fea68bff9 Fix ChunkTokenLimitExceededError message formatting yangdx 2025-11-19 18:50:45 +08:00
  • df5aacb545 feat: Qdrant model isolation and auto-migration BukeLy 2025-11-19 18:47:38 +08:00
  • f988a22652 Add token limit validation for character-only chunking yangdx 2025-11-19 18:32:43 +08:00
  • d78a8cb9df
    Add comprehensive performance FAQ addressing max_async, LLM selection, and database optimization Claude 2025-11-19 10:21:58 +00:00
  • 6a56829e69
    Add performance optimization guide and configuration for LightRAG indexing Claude 2025-11-19 09:55:28 +00:00
  • 5cc916861f Expand AGENTS.md with testing controls and automation guidelines yangdx 2025-11-19 11:30:54 +08:00
  • af4d2a3dcc
    Merge pull request #2386 from danielaskdd/excel-optimization Daniel.y 2025-11-19 10:26:32 +08:00
  • 95cd0ece74 Fix DOCX table extraction by escaping special characters in cells yangdx 2025-11-19 09:54:35 +08:00
  • 87de2b3e9e Update XLSX extraction documentation to reflect current implementation yangdx 2025-11-19 04:26:41 +08:00
  • 0244699d81 Optimize XLSX extraction by using sheet.max_column instead of two-pass scan yangdx 2025-11-19 04:02:39 +08:00
  • 2b16016312 Optimize XLSX extraction to avoid storing all rows in memory yangdx 2025-11-19 03:48:36 +08:00
  • ef659a1e09 Preserve column alignment in XLSX extraction with two-pass processing yangdx 2025-11-19 03:34:22 +08:00
  • 3efb1716b4 Enhance XLSX extraction with structured tab-delimited format and escaping yangdx 2025-11-19 03:06:29 +08:00
  • efbbaaf7f9
    Merge pull request #2383 from danielaskdd/doc-table Daniel.y 2025-11-19 02:26:02 +08:00
  • 13f2440bbf feat: enhance BaseVectorStorage for model isolation BukeLy 2025-11-19 02:15:22 +08:00
  • 35612af9a2
    Update Step_1.py Menish Chandra 2025-11-18 23:44:19 +05:30
  • b2888d7292
    Update Step_0.py Menish Chandra 2025-11-18 23:43:57 +05:30
  • e7d2803a65 Remove text stripping in DOCX extraction to preserve whitespace yangdx 2025-11-19 02:12:27 +08:00
  • 5c10d3d58e feat: enhance EmbeddingFunc with model_name support BukeLy 2025-11-19 02:11:39 +08:00
  • 186c8f0e16 Preserve blank paragraphs in DOCX extraction to maintain spacing yangdx 2025-11-19 02:03:10 +08:00
  • fa887d811b Fix table column structure preservation in DOCX extraction yangdx 2025-11-19 01:52:02 +08:00
  • 4438ba41a3 Enhance DOCX extraction to preserve document order with tables yangdx 2025-11-19 01:31:33 +08:00
  • d16c7840ab Bump API version to 0256 yangdx 2025-11-18 23:15:31 +08:00
  • e77340d4a1 Adjust chunking parameters to match the default environment variable settings yangdx 2025-11-18 23:14:50 +08:00
  • 24423c9215 Merge branch 'fix_chunk_comment' yangdx 2025-11-18 22:47:23 +08:00
  • 1bfa1f81cb Merge branch 'main' into fix_chunk_comment yangdx 2025-11-18 22:38:50 +08:00
  • 9c10c87554 Fix linting yangdx 2025-11-18 22:38:43 +08:00
  • 9109509b1a Merge branch 'dev-postgres-vchordrq' yangdx 2025-11-18 22:25:35 +08:00
  • dbae327a17 Merge branch 'main' into dev-postgres-vchordrq yangdx 2025-11-18 22:13:27 +08:00
  • b583b8a59d Merge branch 'feature/postgres-vchordrq-indexes' into dev-postgres-vchordrq yangdx 2025-11-18 22:05:48 +08:00
  • 3096f844fb fix(postgres): allow vchordrq.epsilon config when probes is empty yangdx 2025-11-18 21:58:36 +08:00
  • 23e7ffbe1c Reformat Tom Aarsen 2025-11-18 12:19:55 +01:00
  • 835edda6fc Add embeddings & reranking via Sentence Transformers Tom Aarsen 2025-11-18 12:18:56 +01:00
  • dacca334e0 refactor(chunking): rename params and improve docstring for chunking_by_token_size EightyOliveira 2025-11-18 15:46:28 +08:00
  • f4bf5d279c
    fix: add logger to configure_vchordrq() and format code wmsnp 2025-11-18 15:31:08 +08:00
  • dfbc97363c
    Merge pull request #2369 from HKUDS/workspace-isolation Daniel.y 2025-11-18 15:21:10 +08:00
  • 702cfd2981 Fix document deletion concurrency control and validation logic yangdx 2025-11-18 13:59:24 +08:00
  • 656025b75e Rename GitHub workflow from "Tests" to "Offline Unit Tests" yangdx 2025-11-18 13:36:00 +08:00
  • 7e9c8ed1e8 Rename test classes to prevent warning from pytest yangdx 2025-11-18 13:33:05 +08:00
  • 4048fc4b89 Fix: auto-acquire pipeline when idle in document deletion yangdx 2025-11-18 13:25:13 +08:00
  • 1745b30a5f Fix missing workspace parameter in update flags status call yangdx 2025-11-18 12:55:48 +08:00
  • f8dd2e0724 Fix namespace parsing when workspace contains colons yangdx 2025-11-18 12:23:05 +08:00
  • 472b498ade Replace pytest group reference with explicit dependencies in evaluation yangdx 2025-11-18 12:17:21 +08:00
  • a11912ffa5 Add testing workflow guidelines to basic development rules yangdx 2025-11-18 11:54:19 +08:00
  • 41bf6d0283 Fix test to use default workspace parameter behavior yangdx 2025-11-18 11:51:17 +08:00
  • d07023c962
    feat(postgres_impl): add vchordrq vector index support and unify vector index creation logic wmsnp 2025-11-18 11:45:16 +08:00
  • 4ea2124001 Add GitHub CI workflow and test markers for offline/integration tests yangdx 2025-11-18 11:36:10 +08:00
  • 5e1b3f9c75 Initial plan copilot-swe-agent[bot] 2025-11-18 02:41:49 +00:00
  • 4fef731f37 Standardize test directory creation and remove tempfile dependency yangdx 2025-11-18 10:39:54 +08:00
  • 1fe05df211 Refactor test configuration to use pytest fixtures and CLI options yangdx 2025-11-18 10:31:53 +08:00
  • 56fe7bcfb8 Initial plan copilot/enhance-cosine-similarity copilot-swe-agent[bot] 2025-11-18 02:20:24 +00:00
  • 6ae0c14438 test: add concurrent execution to workspace isolation test yangdx 2025-11-18 10:17:34 +08:00
  • 6cef8df159 Reduce log level and improve workspace mismatch message clarity yangdx 2025-11-18 08:25:21 +08:00
  • fc9f7c705e Fix linting yangdx 2025-11-18 08:07:54 +08:00
  • 98f5b401f4
    Merge c0df9447e8 into f83b475ab1 Hammton 2025-11-18 01:58:22 +08:00
  • f83b475ab1 Remove Dependabot configuration file yangdx 2025-11-18 01:42:15 +08:00
  • 21ad990e36 Improve workspace isolation tests with better parallelism checks and cleanup yangdx 2025-11-18 01:38:31 +08:00
  • 455d23ed69
    Update numpy requirement from <2.0.0,>=1.24.0 to >=1.24.0,<3.0.0 dependabot[bot] 2025-11-17 17:29:57 +00:00
  • 5da82bb096 Add pre-commit to pytest dependencies and format test code yangdx 2025-11-18 00:42:04 +08:00
  • 99262adaaa Enhance workspace isolation test with distinct mock data and persistence yangdx 2025-11-18 00:38:31 +08:00