gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
4836 commits 5 branches 72 tags 705 MiB
Commit graph

4836 commits

This branch
This branch
All branches
Author SHA1 Message Date
yangdx
a1df76a4ea Optimize LLM/embedding config caching to reduce repeated parsing overhead 
• Add LLMConfigCache class for smart caching
• Pre-process OpenAI/Ollama configurations
• Create optimized function factories
• Reduce redundant option parsing calls
 2025-09-05 16:36:08 +08:00
Daniel.y
dc14623b42
Merge pull request #2064 from danielaskdd/history-message-truncate 
feat: Limit Pipeline Status History Messages to Latest 1000 Entries
 2025-09-05 13:09:39 +08:00
yangdx
17d665c9f3 Limit history messages to latest 1000 entries with truncation indicator 
• Limit history to 1000 latest messages
• Add truncation message when needed
• Show count of truncated messages
• Update API documentation
• Prevent memory issues with large logs
 2025-09-05 12:31:36 +08:00
yangdx
0ccf2036c6 Refactor Docker workflows: rename and clean up build processes 
• Rename workflows for clarity
• Remove debug git commands
 2025-09-05 11:46:56 +08:00
yangdx
cf31d636c2 Add git tag fetching and debug output to Docker workflow 2025-09-05 11:28:28 +08:00
yangdx
9181649bae Add version sync to __init__.py in Docker workflows 2025-09-05 10:56:46 +08:00
yangdx
d85ff5b9d7 Fix variable reference in PyPI publish workflow 2025-09-05 02:37:22 +08:00
yangdx
b88ab7c04e Revert "Remove PyPI environment from publish workflow" 
This reverts commit 688550a9c6.
 2025-09-05 02:00:44 +08:00
yangdx
688550a9c6 Remove PyPI environment from publish workflow 2025-09-05 01:53:20 +08:00
yangdx
ed5b9b414c Add automatic version extraction from git tags to PyPI workflow 
* Fetch full git history for tags
* Extract version from latest git tag
* Update __init__.py with tag version
* Display updated version for verification
 2025-09-05 01:48:53 +08:00
yangdx
09334ca8db Fix git tag detection in Docker publish workflow 
- Fetch full git history for tags
- Add debug output for found tag
- Enable proper tag resolution
 2025-09-05 01:11:48 +08:00
yangdx
e16c302f5f Use git tag for Docker image versioning instead of semver 
• Add step to get latest git tag
• Replace semver with raw tag value
• Maintain latest tag for default branch
• Fix tag resolution in CI pipeline
 2025-09-05 01:00:24 +08:00
yangdx
be3f0ebbe5 Simplify entity extraction prompt instructions and remove delimiter 2025-09-04 23:42:11 +08:00
yangdx
3f56c6820c Reorder language and completion delimiter instructions in prompt 2025-09-04 23:05:16 +08:00
yangdx
2c551cb5db Add support for Chinese book title marks in normalize_extracted_info 2025-09-04 18:51:57 +08:00
Daniel.y
ae65676b4e
Merge pull request #2060 from danielaskdd/fix-worksapce-dir 
Fix incorrect variable name in NetworkXStorage file path
 2025-09-04 18:36:48 +08:00
yangdx
f19cce16be Fix incorrect variable name in NetworkXStorage file path 
- Fix working_dir -> workspace_dir typo
- Correct GraphML file path generation
 2025-09-04 18:31:53 +08:00
yangdx
50adf64fab Fix linting in prompt 2025-09-04 15:22:36 +08:00
yangdx
94114df995 Improve prompt clarity and structure 2025-09-04 14:53:27 +08:00
yangdx
83b54975a2 fix: resolve "Task exception was never retrieved" warnings in async task handling 
- Handle multiple simultaneous exceptions correctly
- Maintain fast-fail behavior while ensuring proper exception cleanup to
  prevent asyncio warnings
 2025-09-04 12:40:41 +08:00
yangdx
c903b14849 Bump AIP version to 0214 and update env.example 2025-09-04 12:04:50 +08:00
yangdx
de972f6222 Rename method for clarity and improve code readability 
- Rename _process_entity_relation_graph to _process_extract_entities
 2025-09-04 11:48:31 +08:00
yangdx
9b516a8a53 Hot Fix: Preserve whitespace chars in text sanitization 
• Keep \t, \n, \r in control char removal
 2025-09-04 10:58:29 +08:00
yangdx
7b35657e32 Refactor entity extraction prompt formatting and clarity 
- Remove quotes from tuple format strings
- Simplify relationship extraction text
- Add relationships to quality guidelines
 2025-09-04 10:47:57 +08:00
Daniel.y
ead821aafa
Merge pull request #2055 from danielaskdd/db-retry 
Add VDB error handling with retries for data consistency
 2025-09-03 21:59:32 +08:00
yangdx
a25ce7f078 Fix linting 2025-09-03 21:58:30 +08:00
yangdx
7ef2f0dff6 Add VDB error handling with retries for data consistency 
- Add safe_vdb_operation_with_exception util
- Wrap VDB ops in entity/relationship code
- Ensure exceptions propagate on failure
- Add retry logic with configurable delays
 2025-09-03 21:15:09 +08:00
Daniel.y
61fb2444f0
Merge pull request #2051 from danielaskdd/extract-result-process 
Enhance KG Extraction for LLM with Small Parameters
 2025-09-03 17:59:09 +08:00
yangdx
0b07c022d6 Update webui assets and bump api version to 0213 2025-09-03 12:51:08 +08:00
yangdx
5a5d5e4a34 Add document translation key to all locale files 2025-09-03 12:50:27 +08:00
yangdx
78abb397bf Reorder entity types and add Document type to extraction 2025-09-03 12:44:40 +08:00
yangdx
95c08cc7dc Improve entity extraction prompt clarity by replacing pronouns with specific nouns 2025-09-03 12:35:52 +08:00
yangdx
c86f863fa4 feat: optimize entity extraction for smaller LLMs 
Simplify entity relationship extraction process to improve compatibility
and performance with smaller, less capable language models.

Changes:
- Remove iterative gleaning loop with LLM-based continuation decisions
- Simplify to single gleaning pass when entity_extract_max_gleaning > 0
- Streamline entity extraction prompts with clearer instructions
- Add explicit completion delimiter signals in all examples
 2025-09-03 10:33:01 +08:00
yangdx
9d81cd724a Fix typo: change "Equiment" to "Equipment" in entity types 2025-09-02 03:19:31 +08:00
yangdx
476b64c9d4 Update webui assets 2025-09-02 03:03:19 +08:00
yangdx
4e37ff5f2f Bump API verstion to 0212 2025-09-02 03:02:39 +08:00
yangdx
4db43c43f3 Add product and other entity type translations 
- Add "product" translations
- Add "other" translations
- Update 5 locale files
- Extend entity type coverage
 2025-09-02 03:01:59 +08:00
yangdx
5b2deccbef Improve text normalization and add entity type capitalization 
- Capitalize entity types with .title()
- Add non-breaking space handling
- Add narrow non-breaking space regex
 2025-09-02 02:51:41 +08:00
yangdx
29f0ecc88c Refactor entity extraction prompts and remove completion delimiter 
• Update prompt structure and wording
• Remove deprecated completion delimiter
• Add quality guidelines section
• Improve instruction clarity
• Enhance continue extraction prompt
 2025-09-02 02:14:14 +08:00
yangdx
3f8a9abe7e Refactor extraction result processing to reduce code duplication 
• Extract shared processing logic
• Add delimiter pattern fixes
• Improve bracket standardization
 2025-09-02 01:22:29 +08:00
yangdx
3cdc98f366 Improve extraction parsing with better bracket handling and delimiter fixes 
• Standardize Chinese/English brackets
• Fix incomplete tuple delimiters
• Remove duplicate delimiter fix code
• Support mixed bracket formats
• Enhance record parsing robustness
 2025-09-02 00:26:04 +08:00
yangdx
8bbf307aeb Fix regex to match multiline content in extraction parsing 
• Remove non-greedy quantifier
• Add DOTALL flag for multiline matching
• Apply to both parsing functions
• Enable cross-line content extraction
 2025-09-01 10:35:06 +08:00
yangdx
7baeb186c6 Fix regex to use non-greedy matching for parentheses extraction 2025-09-01 10:10:45 +08:00
yangdx
692357fbf3 Add conflict resolution instruction to entity summarization prompt 
- Add conflict handling step
- Handle entities with same name
- Separate then consolidate summaries
 2025-09-01 08:51:19 +08:00
yangdx
e95622ca7b fix(utils): enhance remove_think_tags to handle orphaned </think> closing tags 
The function now properly handles cases where text contains </think> closing tags
without corresponding <think> opening tags, which can occur due to content
truncation or processing errors.
 2025-09-01 07:17:30 +08:00
Daniel.y
5e73896c40
Merge pull request #2035 from danielaskdd/fix-llm-output 
Fix LLM output instability for <|> tuple delimiter
 2025-09-01 01:25:24 +08:00
yangdx
30be70991d Bump API version to 0211 2025-09-01 01:23:22 +08:00
yangdx
5fd7682f16 Fix LLM output instability for <|> tuple delimiter 
- Replace <||> with <|>
- Replace < | > with <|>
- Apply fix in both functions
- Handle delimiter variations
- Improve parsing reliability
 2025-09-01 01:22:27 +08:00
Daniel.y
cdc4570cfe
Merge pull request #2034 from danielaskdd/fix-entity-type-env 
Fix ENTITY_TYPES Environment Variable Handling
 2025-09-01 00:43:46 +08:00
yangdx
ec059d1b5d Fix typo and clarify delimiter formatting in relationship extraction Prompt 
- Fix "feild" → "field" typo
- Clarify delimiter spacing rules
 2025-09-01 00:42:59 +08:00