gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
5238 commits 5 branches 72 tags 705 MiB
Commit graph

3365 commits

Author SHA1 Message Date
yangdx
b3ed264707 Refactor PostgreSQL retry config to use centralized configuration 
• Move retry config to ClientManager
• Remove env var parsing from PostgreSQLDB
• Add config params to test setup
 2025-10-10 03:44:13 +08:00
yangdx
e758204ab2 Add PostgreSQL connection retry mechanism with comprehensive error handling 
• Implement connection retry with backoff
• Add transient error detection
• Pool management with timeout guards
 2025-10-10 03:06:01 +08:00
Yasiru Rangana
ae9f4ae73f fix: Remove trailing whitespace for pre-commit linting 2025-10-09 15:01:53 +11:00
Yasiru Rangana
ec40b17eea feat: Add token tracking support to openai_embed function 
- Add optional token_tracker parameter to openai_embed()
- Track prompt_tokens and total_tokens for embedding API calls
- Enables monitoring of embedding token usage alongside LLM calls
- Maintains backward compatibility with existing code
 2025-10-08 14:36:08 +11:00
yangdx
f1e0110716 Merge branch 'kevinnkansah/main' 2025-10-07 23:04:59 +08:00
yangdx
f2c0b41e78 Make PostgreSQL statement_cache_size configuration optional 
• Remove forced int conversion
• Allow None values for cache size
• Add conditional parameter setting
 2025-10-07 22:57:21 +08:00
Aleks Vujić
dd8f44e621
Fixed typo in log message when creating new graph file 2025-10-07 14:30:05 +02:00
kevinnkansah
fdcb034da0 chore: distinguish settings 2025-10-06 12:01:40 +02:00
kevinnkansah
22a7b482c5 fix: renamed PostGreSQL options env variable and allowed LRU cache to be an optional env variable 2025-10-06 11:56:09 +02:00
kevinnkansah
d8a9617c0e fix: fix: asyncpg bouncer connection pool error 
Prepared statement caching is disabled by setting
`statement_cache_size=0` in the `asyncpg` connection pool parameters.
This is necessary to prevent
`asyncpg.exceptions.InvalidSQLStatementNameError` when using
transaction-level connection poolers like Supabase Supavisor or
pgbouncer, which do not support prepared statements.
 2025-10-06 00:36:25 +02:00
kevinnkansah
108cdbe133 feat: add options for PostGres connection 2025-10-05 23:29:04 +02:00
yangdx
d473f635d8 Update webui assets 2025-10-05 14:02:18 +08:00
yangdx
aac787bafb Clarify chunk tracking log message in _build_llm_context 2025-10-05 13:33:55 +08:00
yangdx
457d51952e Add doc_name field to full docs storage 
- Store file_path in full_docs storage
- Update PostgreSQL implementation by map file_path to doc_name
- Other storage implementation automatically handles the new field
 2025-10-05 11:44:27 +08:00
yangdx
1574fec7f0 Update webui assets 2025-10-05 10:41:46 +08:00
yangdx
b5f8376756 Update webui assets 2025-10-05 09:27:38 +08:00
yangdx
dde728a32f Bump core version to 1.5.0 and API to 0236 2025-10-05 09:25:57 +08:00
Jon
cf2a024e37 feat: Add endpoint and UI to retry failed documents 
Add a new `/documents/reprocess_failed` API endpoint and corresponding
UI button to retry processing of failed and pending documents. This
addresses a common recovery scenario when document processing fails due
to server crashes, network errors, or LLM service outages.

Backend changes:
- Add ReprocessResponse model with status, message, and track_id fields
- Add POST /documents/reprocess_failed endpoint that triggers background
  reprocessing of FAILED, PENDING, and interrupted PROCESSING documents
- Reuses existing apipeline_process_enqueue_documents for consistency
- Includes comprehensive docstring and logging for observability

Frontend changes:
- Add TypeScript types and API function for the new endpoint
- Add retry handler with intelligent polling (fast refresh → normal)
- Add "Retry Failed" button in Documents page toolbar
- Button disabled when pipeline is busy to prevent duplicate operations
- Complete i18n support (English and Chinese translations)

This feature provides a convenient way to recover from processing
failures without requiring a full filesystem rescan.
 2025-10-04 16:46:29 -04:00
yangdx
b9c37bd937 Fix linting 2025-10-03 02:10:02 +08:00
yangdx
112349ed5b Modernize type hints and remove Python 3.8 compatibility code 
• Use collections.abc.AsyncIterator only
• Remove sys.version_info checks
• Use union syntax for None types
• Simplify string emptiness checks
 2025-10-02 23:15:42 +08:00
yangdx
cec784f60e Update webui assets 2025-10-02 22:02:42 +08:00
yangdx
a250d881f2 Update webui assets 2025-10-02 21:24:39 +08:00
yangdx
6bf6f43d96 Remove bold formatting from instruction headers in prompts 2025-10-02 00:58:03 +08:00
yangdx
bb6138e748 fix(prompt): Clarify reference section restrictions in prompt templates 2025-10-01 22:35:26 +08:00
yangdx
37e8898cf6 Simplify reference formatting in LLM context generation 
- Remove extra newlines in reference lists
- Change code block type from text to generic
 2025-10-01 22:20:58 +08:00
yangdx
f83cde14df fix(prompt): Improve markdown formatting requirements and reference style 2025-10-01 21:41:12 +08:00
yangdx
83d99e1424 fix(OllamaAPI): Add validation to ensure last message is from user role 
• Validate last message role is "user"
• Raise 400 error for invalid role
• Improve API request validation
• Prevent invalid message sequences
 2025-10-01 20:48:37 +08:00
yangdx
df43afc89b Relax conversation history role validation requirements 
• Remove strict role value checking
• Allow any non-empty string roles
 2025-09-29 13:10:15 +08:00
yangdx
ba216787c1 Update webui assets 2025-09-28 22:51:06 +08:00
yangdx
6e3e67fc24 Update webui assets 2025-09-28 21:34:09 +08:00
yangdx
81bc1ba025 Update webui assets and bump API version to 0235 2025-09-28 21:05:40 +08:00
yangdx
42d1d04147 Fix boolean parser problem for for LLM environment variable 
• Add custom boolean parser for argparse in BindingOptions
 2025-09-28 19:23:57 +08:00
yangdx
4957f4f017 Bump core version to 1.4.9.1 2025-09-28 15:25:02 +08:00
yangdx
978f154680 Update webui assets and bump API version to 0234 2025-09-28 15:14:05 +08:00
yangdx
0fd0186414 Improve prompt clarity by standardizing terminology and formatting 
• Replace "Source Data" with "Context"
• Add bold formatting for key sections
• Clarify reference_id usage
• Improve JSON/text block formatting
• Standardize data source naming
 2025-09-28 13:31:55 +08:00
yangdx
7cba458f22 Limit deprecated documents endpoint to 1000 records with fair distribution 2025-09-28 11:18:10 +08:00
yangdx
fcbab77613 docs: add API key usage example and security guidance 2025-09-28 10:56:52 +08:00
yangdx
2ce6a022ac Fix documentation for user_prompt parameter in QueryParam 2025-09-27 23:41:17 +08:00
yangdx
91be53ffd2 Fix linting 2025-09-27 22:36:38 +08:00
yangdx
e0ac05db90 Simplify query route documentation and clarify conversation history 2025-09-27 22:36:16 +08:00
yangdx
f66a0aad8b Update query streaming endpoint docs to clarify behavior 2025-09-27 22:27:49 +08:00
yangdx
3ca2165c69 Bump API version to 0233 2025-09-27 15:31:30 +08:00
yangdx
dbb0b3afb4 Fix hl_keywords and ll_keywords cache logic 
- Remove hl_keywords and ll_keywords from keywork extracht cache
- Add hl_keywords and ll_keywords to LLM query cache
 2025-09-27 15:26:52 +08:00
yangdx
e7948df541 Fix linting 2025-09-27 15:13:07 +08:00
yangdx
1766cddd6c Fix mode parameter serialization error in Ollama chat API 
• Use mode.value for API requests
• Add debug logging in aquery_llm
 2025-09-27 15:11:51 +08:00
yangdx
81caee3498 Enhance query API with streaming control and comprehensive documentation 
- Add stream parameter to QueryRequest
- Support non-streaming in /query/stream
- Add detailed OpenAPI response schemas
- Expand endpoint documentation
- Include usage examples and error handling
 2025-09-27 11:53:31 +08:00
yangdx
f43eb00e6c Update webui assets 2025-09-26 20:06:08 +08:00
yangdx
a528213210 Fix logging filter logic 
• Fix boolean operator precedence in filter
• Consolidate GET/POST condition logic
 2025-09-26 19:42:33 +08:00
yangdx
3ba06478a8 fix http log message order for streaming respond 
- Move aquery_llm call outside generator
- Execute query before stream starts
 2025-09-26 19:27:44 +08:00
yangdx
8cd4139cbf refactor: fix double query problem by add aquery_llm function for consistent response handling 
- Add new aquery_llm/query_llm methods providing structured responses
- Consolidate /query and /query/stream endpoints to use unified aquery_llm
- Optimize cache handling by moving cache checks before LLM calls
 2025-09-26 19:05:03 +08:00