hzywhite
0dc11e0794
summary
2025-09-05 19:31:00 +08:00
hzywhite
8620ce0b01
Update __init__.py
2025-09-05 17:38:34 +08:00
Daniel.y
8fd7bca8d7
Merge pull request #2068 from danielaskdd/fix-llm-option
...
refact: Smart Configuration Caching and Conditional Logging
2025-09-05 17:19:44 +08:00
yangdx
385668dec5
Fix malformed tuple delimiters in extraction result processing
2025-09-05 17:14:42 +08:00
yangdx
2db7e4a3e8
Update env.example
2025-09-05 17:13:29 +08:00
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
hzywhite
8bd8888506
summary
2025-09-05 16:18:17 +08:00
hzywhite
8d4ef251c7
summary
2025-09-05 16:17:39 +08:00
hzywhite
27845023e6
summary
2025-09-05 16:17:20 +08:00
hzywhite
a33484bdb7
merge
2025-09-05 15:04:34 +08:00
hzywhite
e07d4bb70b
merge
2025-09-05 15:04:04 +08:00
hzywhite
482a09d397
merge
2025-09-05 15:03:19 +08:00
hzywhite
8d800239d6
merge
2025-09-05 15:02:49 +08:00
hzywhite
e3ea87da24
merge
2025-09-05 15:01:50 +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
hzywhite
2a453fbe37
webui
2025-09-04 11:24:06 +08:00
hzywhite
7c8db78057
merge
2025-09-04 11:05:22 +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
hzywhite
82a0f8cc1f
merge
2025-09-04 10:57:41 +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
hzywhite
e27031587d
merge
2025-09-04 10:27:38 +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
