Commit graph

2620 commits

Author SHA1 Message Date
zrguo
b0479c078a fix process_chunks_unified() 2025-07-09 15:55:38 +08:00
yangdx
9aa2ed0837 Merge branch 'main' into rerank 2025-07-09 15:33:39 +08:00
zrguo
e1541caea9 Update webui setting 2025-07-09 12:10:06 +08:00
Anton Vice
b192f8c9a3 Fix: Handle NoneType error when processing documents without a file path
The document processing pipeline would crash with a TypeError when a document was submitted as raw text via the API, as the file_path attribute would be None. This change adds a check to handle the None case gracefully, preventing the crash and allowing text-based documents to be indexed correctly.
2025-07-08 19:35:22 -03:00
yangdx
4705a22861 Bump core version to 1.4.0 2025-07-09 04:43:20 +08:00
yangdx
2056c3c809 Increase default CHUNK_TOP_K from 5 to 15 2025-07-09 04:41:51 +08:00
yangdx
e9c3503f77 Update logger info 2025-07-09 04:36:52 +08:00
yangdx
5d4484882a Merge branch 'main' into rerank 2025-07-09 03:59:04 +08:00
yangdx
14d51518dd Merge branch 'add-Memgraph-graph-db' into memgraph 2025-07-09 03:38:07 +08:00
DavIvek
08eb68b8ed run pre-commit 2025-07-08 20:21:20 +02:00
yangdx
75ce636084 Merge branch 'main' into add-Memgraph-graph-db 2025-07-09 02:09:35 +08:00
DavIvek
4438897b6b add changes based on review 2025-07-08 16:28:06 +02:00
zrguo
d4651d59c1 Add rerank to server 2025-07-08 21:44:20 +08:00
yangdx
b6ab69e25d Merge branch 'main' into fix-issue-1746 2025-07-08 18:20:02 +08:00
yangdx
2a0cff3ed6 Fix linting 2025-07-08 18:17:21 +08:00
zrguo
71cb3adb4f Merge branch 'main' into rerank 2025-07-08 15:10:23 +08:00
zrguo
c295d355a0 fix chunk_top_k limiting 2025-07-08 15:05:30 +08:00
SLKun
5f330ec11a remove <think> tag for entities and keywords extraction 2025-07-08 14:59:15 +08:00
zrguo
04a57445da update chunks truncation method 2025-07-08 13:31:05 +08:00
Molion Surya
8cbba6e9db Fix #1746: [openai.py logic for streaming complete] 2025-07-08 13:25:52 +08:00
zrguo
f5c80d7cde Simplify Configuration 2025-07-08 11:16:34 +08:00
yangdx
9b7b2a9b0f Reduce default embedding batch size from 32 to 10 2025-07-08 11:00:09 +08:00
yangdx
2670f8dc98 Merge branch 'main' into add-Memgraph-graph-db 2025-07-08 00:31:46 +08:00
yangdx
a1bbf367ad Update webui assets 2025-07-08 00:22:14 +08:00
zrguo
75dd4f3498 add rerank model 2025-07-07 22:44:59 +08:00
yangdx
ef79088f60 Move max_graph_nodes to global config 2025-07-07 21:53:57 +08:00
yangdx
cb14ce6ff3 Bump api version to 0180 2025-07-07 18:14:31 +08:00
yangdx
f417118e27 Center banner text dynamically 2025-07-07 17:28:59 +08:00
yangdx
f86ae6df0a Update api server README 2025-07-07 17:16:14 +08:00
yangdx
7a7a01b68b Fix linting 2025-07-07 04:44:06 +08:00
yangdx
9e823de74e Exit program on vector index creation failure for MongoDB 2025-07-07 04:43:46 +08:00
yangdx
809f839c07 Merge branch 'main' into add-Memgraph-graph-db 2025-07-07 04:29:12 +08:00
yangdx
4632adb355 Add NEO4J_WORKSPACE env var override support
- Allow workspace override via NEO4J_WORKSPACE
- Update env.example with new config option
2025-07-07 04:16:44 +08:00
yangdx
7916b3d18f Update webui assets 2025-07-07 03:45:19 +08:00
yangdx
da8655002a Add composite indexes for workspace+id columns for PostgreSQL 2025-07-07 03:36:49 +08:00
yangdx
907f2313cd Improve MongoDB vector index handling with workspace support
- Add workspace-specific index naming
- Store index name as instance variable
2025-07-07 03:19:41 +08:00
yangdx
1d24e8ca3c Bump api version to 0179 2025-07-07 01:40:26 +08:00
yangdx
db22cad2c8 feat: add workspace and MAX_GRAPH_NODES to /health endpoint and webui 2025-07-07 01:39:48 +08:00
yangdx
253833475f Add workspace info to splash screen display 2025-07-07 01:26:27 +08:00
yangdx
033098c1bc Feat: Add WORKSPACE support to all storage types 2025-07-07 00:57:21 +08:00
yangdx
1b2d295a4f Remove namespace_prefix 2025-07-06 00:16:47 +08:00
yangdx
98150e80b8 Improved empty/whitespace file handling
- Better detection of whitespace-only files
- Changed error to warning for empty chunks
2025-07-05 23:16:39 +08:00
xuewei
648a87653f 文本块是空白 2025-07-05 14:28:42 +08:00
xuewei
49cb51b5dc PDF文件解析不到内容 2025-07-05 13:47:47 +08:00
yangdx
a567601da2 Merge branch 'main' into add-Memgraph-graph-db 2025-07-05 13:14:39 +08:00
yangdx
706da5ad23 Merge branch 'main' of github.com:HKUDS/LightRAG 2025-07-05 13:12:27 +08:00
yangdx
86a00ed333 Remove deprecated storage type 2025-07-05 13:11:32 +08:00
yangdx
fe13475234 Fix linting 2025-07-05 12:07:37 +08:00
yangdx
a2e59dd078 fix: prevent empty entity names after normalization in extraction
Added validation checks in entity and relationship extraction functions to filter out entities that become empty strings after normalize_extracted_info processing. This prevents empty labels from appearing in get_all_labels() results and maintains knowledge graph data integrity.
2025-07-05 12:06:34 +08:00
yangdx
bdfd2d53c7 Fix linting 2025-07-05 11:43:45 +08:00