gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
4914 commits 5 branches 72 tags 705 MiB
Commit graph

4914 commits

This branch
This branch
All branches
Author SHA1 Message Date
yangdx
b32bd993e1 Bump API version to 0219 2025-09-11 22:47:22 +08:00
yangdx
4ce823b4dd Handle empty context in mix mode and improve query logging 2025-09-11 18:58:37 +08:00
yangdx
87f1b47218 Update env.examples 2025-09-11 15:50:16 +08:00
yangdx
c8a17f7ea5 Improve extraction failure log message formatting and consistency 2025-09-11 14:03:21 +08:00
yangdx
7f83a58497 Refactor extraction delimiters from ## to newlines and change tuple delimiter to <|SEP|> 
• Add robust delimiter fixing logic
• Update prompts for single-line format
 2025-09-11 13:44:44 +08:00
yangdx
7fe47fac84 Fix linting 2025-09-10 18:38:21 +08:00
yangdx
db6bba80c9 Log all merges at appropriate level 2025-09-10 18:37:13 +08:00
yangdx
a4bfdb7ddf Fix logging condition to show merges even when no fragments exist if LLM is used 2025-09-10 18:22:10 +08:00
yangdx
02e7462645 feat: enhance LLM output format tolerance for bracket processing 
- Expand bracket tolerance to support additional characters: < > " '
- Implement symmetric handling for both leading and trailing characters
- Replace simple string matching with robust regex-based pattern detection
- Maintain full backward compatibility with existing bracket formats
 2025-09-10 18:10:06 +08:00
yangdx
00de0a4be8 Handle backtick-wrapped brackets in extraction result parsing 
* Support `( and `（ start patterns
* Support )` and ）` end patterns
* Graceful fallback to warning logs
* Strip 2 chars for backtick variants
* Maintain existing bracket logic
 2025-09-10 17:15:03 +08:00
yangdx
19014c6471 feat: enhance entity/relationship merging with description length comparison 
- Implement description length comparison in gleaning merge logic (extract_entities)
- Apply same logic to knowledge graph reconstruction (_rebuild_knowledge_from_chunks)
- Prioritize entities/relationships with longer descriptions for better quality
- Use list() instead of extend() for performance optimization when replacing
 2025-09-10 17:06:57 +08:00
yangdx
4a21b7f53f Update OpenAI API config docs for max_tokens and max_completion_tokens 
• Clarify max_tokens vs max_completion_tokens
• Add Gemini exception note
• Update parameter descriptions
• Add new completion tokens option
 2025-09-10 16:23:10 +08:00
yangdx
e3ebf45a18 Add logging for missing brackets in extraction result processing 2025-09-10 16:10:42 +08:00
yangdx
24242c5bb8 Fix indentation for logging and status updates in merge functions 2025-09-10 15:26:35 +08:00
yangdx
c4506438cd Only log merge messages when there are existing fragments to merge 2025-09-10 15:14:33 +08:00
yangdx
50fddeebbf fix: Remove conversation history from prompt template 
- Delete history section from prompt
- Simplify user query response format
- Remove {history} placeholder variable
 2025-09-10 12:07:34 +08:00
yangdx
a49c8e4a0d Refactor JSON serialization to use newline-separated format 
- Replace json.dumps with line-by-line format
- Apply to entities, relations, text units
- Update truncation key functions
- Maintain ensure_ascii=False setting
- Improve context readability
 2025-09-10 11:59:25 +08:00
yangdx
2dd143c935 Refactor conversation history handling to use LLM native message format 
• Remove get_conversation_turns utility
• Pass history_messages to LLM directly
• Clean up prompt template formatting
 2025-09-10 11:56:58 +08:00
yangdx
e078ab7103 Fix cache handling and context return logic for query parameters 
• Skip cache when only_need_prompt is set
• Update only_need_context condition logic
• Prevent cache bypass in prompt-only mode
 2025-09-10 11:31:48 +08:00
yangdx
6774058670 Merge branch 'main' into tongda/main 2025-09-09 22:43:17 +08:00
Daniel.y
9c9d55b697
Merge pull request #2086 from danielaskdd/reasoning_content 
feat: Add Deepseek Sytle CoT Support for Open AI Compatible LLM Provider
 2025-09-09 22:42:09 +08:00
yangdx
077d9be5d7 Add Deepseek Style Chain of Thought (CoT) Support for OpenAI Compatible LLM providers 
- Add enable_cot parameter to all LLM APIs
- Implement CoT for OpenAI with <think> tags
- Log warnings for unsupported providers
- Enable CoT in query operations
- Handle streaming and non-streaming CoT
 2025-09-09 22:34:36 +08:00
yangdx
3477e9f919 Merge branch 'main' into tongda/main 2025-09-09 18:27:56 +08:00
yangdx
09abb656b8 Improve log message formatting for better readability 2025-09-09 17:41:09 +08:00
Daniel.y
f064b950fc
Merge pull request #2027 from Matt23-star/main 
Refactor: PostgreSQL
 2025-09-09 15:12:35 +08:00
Daniel.y
92058187f7
Merge pull request #2082 from danielaskdd/prompt-optimization 
Prompt Optimization: remove angle brackets from entity and relationship output formats
 2025-09-09 12:11:39 +08:00
yangdx
564850aa9d Update webui assets and bump api version to 0218 2025-09-09 11:41:02 +08:00
yangdx
f1d6d949f1 Fix assistant message display content fallback logic 
- Handle undefined vs empty string cases
- Prevent COT content keep rendering before </think> tag recieved
 2025-09-09 11:39:59 +08:00
yangdx
06db511f3b Remove angle brackets from entity and relationship output formats 2025-09-09 09:21:23 +08:00
Daniel.y
569ed94d15
Merge pull request #2079 from danielaskdd/fix-cot-render-fall-back 
Fix assistant message display with content fallback
 2025-09-08 23:48:07 +08:00
yangdx
6157318408 Update webui assets and bump api to 0217 2025-09-08 23:37:34 +08:00
yangdx
3912b7d281 Fix assistant message display with content fallback 
• Add content fallback for compatibility
• Update comment for clarity
• Prevent empty assistant messages
 2025-09-08 23:35:31 +08:00
yangdx
ff6c061aa9 Remove conditional check for latest Docker tag 
- Remove is_default_branch condition
- Always apply latest tag
 2025-09-08 23:23:13 +08:00
yangdx
3059089e7d Fix logging order in pipeline history trimming 2025-09-08 23:00:44 +08:00
yangdx
d57fce1aac Add manual trigger to PyPI publish workflow 2025-09-08 22:03:54 +08:00
Daniel.y
14eb3d6a16
Merge pull request #2078 from danielaskdd/update-cons 
Increase default Gunicorn worker timeout from 210 to 300 seconds
 2025-09-08 20:12:58 +08:00
yangdx
8ad7109313 Fix linting 2025-09-08 20:11:21 +08:00
yangdx
8d53ef7ff0 Increase default Gunicorn worker timeout from 210 to 300 seconds 2025-09-08 20:03:21 +08:00
Daniel.y
5f349d507c
Merge pull request #2077 from danielaskdd/render-thinking-block 
Feature: Add LLM COT Rendering support for WebUI
 2025-09-08 19:47:47 +08:00
yangdx
56df4ac4b1 Update webui assets and bump api version to 0216 2025-09-08 19:36:49 +08:00
yangdx
4346846e5a Fix thinking content extraction to prevent duplication and overwriting 
- Add thinkingProcessed ref to track state
- Extract thinking content only once
- Preserve real-time thinking updates
- Reset processed flag on new queries
- Always update display content stream
 2025-09-08 19:34:05 +08:00
yangdx
eeff0d5c67 Fix thinking state management and UI improvements for chat messages 
- Reset expansion state on new thinking
- Prevent content leakage during thinking
- Update thinkingTime type to allow null
- Add memory leak prevention cleanup
- Add missing i18n translations
 2025-09-08 18:47:41 +08:00
yangdx
2ba10dbb5b Add AI thinking process display with expandable UI and timing 
- Add thinking fields to Message type
- Create expandable thinking section
- Track thinking time during streaming
 2025-09-08 18:09:04 +08:00
yangdx
de4fe8bc7d Improve uvicorn workers warning message clarity 2025-09-08 16:05:51 +08:00
yangdx
9437df83cc Add memory management for pipeline history messages 
- Trim history at 10k messages
- Keep latest 5k messages
- Prevent memory growth
- Add logging for trim events
 2025-09-08 15:56:35 +08:00
Daniel.y
298037d8f7
Merge pull request #2076 from danielaskdd/prompt-refactor 
refactor: Optimize Entity Extraction for Small Parameter LLMs with Enhanced Prompt Caching
 2025-09-08 15:40:13 +08:00
yangdx
d218f15a62 Refactor entity extraction with system prompts and output limits 
- Add system/user prompt separation
- Set max tokens for endless output fix
- Improve extraction error logging
- Update cache type from extract to summary
 2025-09-08 15:20:45 +08:00
Daniel.y
c568e2a972
Merge pull request #2075 from k-shlomi/patch-1 
fix env file example
 2025-09-08 14:17:51 +08:00
Shlomi
8d7ef07bbf
fix env file example 2025-09-07 15:22:24 +03:00
yangdx
451f488f72 Add debug logging for client configs in OpenAI LLM function 2025-09-07 02:29:37 +08:00