81 Commits

Author SHA1 Message Date
Yasiru Rangana
e70cf8d38a fix: use DocStatus.PROCESSED enum instead of hardcoded uppercase string
## Problem

Status comparisons used hardcoded uppercase string "PROCESSED" which
didn't match LightRAG's DocStatus enum that stores lowercase "processed".
This caused text_processed to always return False even when documents
were successfully processed.

**Evidence:**
- LightRAG's DocStatus enum (lightrag/base.py): PROCESSED = "processed"
- RAGAnything's DocStatus enum (raganything/base.py:11): PROCESSED = "processed"
- Current code checked: doc_status == "PROCESSED" (uppercase) 
- Actual value from LightRAG: "processed" (lowercase) ✓

**Impact:**
- is_document_fully_processed() always returned False
- get_document_processing_status() showed text_processed as False
- Multimodal processing logic incorrectly detected status

## Solution

Replace hardcoded string literals with DocStatus.PROCESSED enum constant
(already imported at line 14).

**Changes:**
- Line 481: doc_status == "PROCESSED" → DocStatus.PROCESSED
- Line 486: doc_status == "PROCESSED" → DocStatus.PROCESSED
- Line 1355: doc_status.get("status") == "PROCESSED" → DocStatus.PROCESSED
- Line 1387: doc_status.get("status") == "PROCESSED" → DocStatus.PROCESSED
- Updated comments (lines 463, 478) for consistency

**Benefits:**
1.  Fixes case mismatch bug - enum auto-converts to lowercase
2.  Type-safe - IDE/linter catches errors
3.  Maintainable - single source of truth (no magic strings)
4.  Future-proof - if enum changes, code updates automatically
5.  Follows Python best practices

**Compatibility:**
- Works with LightRAG v1.4.9.2+
- Compatible with LightRAG v1.4.9.3 (which added PREPROCESSED status)
- No breaking changes

**References:**
- LightRAG DocStatus: lightrag/base.py
- RAGAnything DocStatus: raganything/base.py:11
- Related: LightRAG v1.4.9.3 added PREPROCESSED = "multimodal_processed"
2025-10-19 23:36:54 +11:00
laansdole
0f6d3ea83a feat: implement tiktoken env variables 2025-10-04 21:26:59 +07:00
zrguo
214eb0f94d update 2025-09-22 11:11:40 +08:00
zrguo
1d48f24b4a fix lint 2025-09-22 10:42:35 +08:00
hongdongjian
7e5e691650 feat: Add support for Chinese characters in PDF generation 2025-09-16 16:20:43 +08:00
zrguo
8d170e52c8 fix lint 2025-09-16 15:48:20 +08:00
zrguo
ba3f737c87 Merge pull request #106 from liz-in-tech/fix-cleanup-warning
fix: replace __del__ with atexit to fix RAGAnything cleanup warning
2025-09-16 15:40:18 +08:00
zrguo
48087eac78 Add log info 2025-09-16 15:32:12 +08:00
zrguo
d63798f05c fix lint 2025-09-16 11:31:35 +08:00
zrguo
991794361f Compatible with new fields 2025-09-16 11:10:26 +08:00
hzywhite
ba3c0154dd Update processor.py 2025-09-11 22:35:19 +08:00
liz
260044f449 fix: replace __del__ with atexit to fix RAGAnything cleanup warning 2025-09-09 17:10:36 +08:00
hzywhite
bcd6cc16c0 Update processor.py 2025-09-05 20:30:47 +08:00
hzywhite
de2824f816 summary 2025-09-05 14:57:00 +08:00
hzywhite
9872b86d13 summary 2025-09-05 14:56:35 +08:00
hzywhite
6877983a71 summary 2025-09-02 18:19:56 +08:00
hzywhite
92cf72fe8a summary 2025-09-02 16:38:41 +08:00
hzywhite
c6d805005e Update processor.py 2025-09-02 06:18:52 +08:00
hzywhite
ec858868ee Update processor.py 2025-09-02 06:17:27 +08:00
hzywhite
6781662a3e summary 2025-09-01 23:04:03 +08:00
hzywhite
dc3a46f247 summary 2025-09-01 22:14:07 +08:00
hzywhite
a87166814c summary 2025-09-01 21:57:31 +08:00
hzywhite
2addb7b799 summary 2025-09-01 21:30:36 +08:00
hzywhite
e5a3d0cfae summary 2025-09-01 15:39:34 +08:00
zrguo
d031468437 Update query.py 2025-08-12 19:17:27 +08:00
zrguo
801f276d82 update debug log 2025-08-12 17:46:36 +08:00
zrguo
dfd9ec855e vlm_enhanced_query 2025-08-12 15:59:50 +08:00
zrguo
cf2aa70cfd Add MinerU log 2025-08-06 18:13:20 +08:00
zrguo
0f6f41aafb Update parser.py 2025-08-06 17:31:57 +08:00
zrguo
9649e31d1a Update _ensure_lightrag_initialized 2025-08-06 17:09:02 +08:00
zrguo
d7eaa8642b Update processor.py 2025-07-31 18:51:48 +08:00
zrguo
380e3cdf3c Update __init__.py 2025-07-31 18:35:06 +08:00
zrguo
d5ff598a9b Add finalize_storages 2025-07-31 18:34:36 +08:00
zrguo
bc7d5ec0b3 fix lint 2025-07-29 21:36:23 +08:00
zzhtx258
c31610200c Merge branch 'main' of https://github.com/HKUDS/RAG-Anything 2025-07-29 20:20:37 +08:00
zzhtx258
d858eabaf9 Fixed docling parser 2025-07-29 19:54:55 +08:00
Shorthills AI
a7c46d5e55 Merge pull request #5 from MinalMahalaShorthillsAI/my-feature-branch
Improvised version
2025-07-28 10:24:51 +05:30
Shorthills AI
336ae09177 Merge branch 'HKUDS:main' into main 2025-07-28 10:23:59 +05:30
MinalMahalaShorthillsAI
60f05e04cf improvised version 2025-07-28 10:08:54 +05:30
MinalMahalaShorthillsAI
1764e1ee8d corrected the linting errors 2025-07-24 15:07:33 +05:30
MinalMahalaShorthillsAI
5b44298214 Merge remote-tracking branch 'upstream/main' 2025-07-24 15:00:42 +05:30
MinalMahalaShorthillsAI
356f26a390 Restrored previous version along with new features 2025-07-24 14:22:10 +05:30
MinalMahalaShorthillsAI
0653b0c7f0 Fixed Lint and formatting errors 2025-07-24 14:20:50 +05:30
zrguo
7775bb35ea Update __init__.py 2025-07-24 15:00:48 +08:00
zrguo
fd418b69f6 Update processor.py 2025-07-24 14:10:16 +08:00
zrguo
1d40425c81 update multimodal process pipeline 2025-07-24 14:09:26 +08:00
Shorthills AI
2056c358ac Merge pull request #1 from MinalMahalaShorthillsAI/batch-markdown-enhancements
Add batch processing and enhanced markdown features
2025-07-24 10:48:28 +05:30
zrguo
710ed38d88 direct content list insertion 2025-07-23 19:01:26 +08:00
MinalMahalaShorthillsAI
a1a783b481 Add batch processing and enhanced markdown features 2025-07-23 13:23:22 +05:30
zrguo
905466436d Update lightrag_kwargs 2025-07-22 19:23:17 +08:00