4671 Commits

Author SHA1 Message Date
yangdx
d97913873b Update logger message 2025-07-24 03:44:02 +08:00
yangdx
3075691f72 Refactor: move reranking utilities from operate.py to utils.py
• Move apply_rerank_if_enabled to utils
• Move process_chunks_unified to utils
2025-07-24 03:33:38 +08:00
yangdx
2c940f0728 reduce RELATED_CHUNK_NUMBER from 10 to 5 2025-07-24 02:49:05 +08:00
yangdx
5a5d32dc32 Optimize logger message 2025-07-24 02:13:39 +08:00
yangdx
42710221f5 Update log messages 2025-07-24 01:31:49 +08:00
yangdx
02f79508e0 Optimize context building with weighted polling and round-robin data selection 2025-07-24 01:18:21 +08:00
Daniel.y
0009a37efb
Merge pull request #1844 from AkosLukacs/patch-1
Fix "A Simple Program" example in README.md
2025-07-23 18:08:45 +08:00
yangdx
958151e610 Merge branch 'main' into context-builder 2025-07-23 16:17:11 +08:00
yangdx
7d96ca98f7 Fix linting 2025-07-23 16:16:37 +08:00
yangdx
00d7bc80bf Merge branch 'context-builder' 2025-07-23 16:14:44 +08:00
yangdx
75fd6c73ea Merge branch 'main' into context-builder 2025-07-23 16:14:14 +08:00
yangdx
6cc9411c86 fix: handle empty tasks list in merge_nodes_and_edges to prevent ValueError
- Add empty tasks check before calling asyncio.wait()
- Return early with logging when no entities/relationships to process
2025-07-23 16:06:47 +08:00
yangdx
2d41e5313a Remove redundant tokenizer checks 2025-07-23 10:19:45 +08:00
Ákos Lukács
75beaf249e
Better prompt for entity description extraction to avoid hallucinations 2025-07-22 20:40:46 +02:00
Ákos Lukács
f115661e16
Fix "A Simple Program" example in README.md
The example should use ainsert and aquery. Fixes #1723
2025-07-22 14:37:15 +02:00
zrguo
681d43bb32 fix typo 2025-07-22 15:34:51 +08:00
yangdx
ce9dac9bcf vdb does not store rank any more 2025-07-21 17:04:23 +08:00
Daniel.y
ae582f63a3
Merge pull request #1834 from danielaskdd/postgres-ssl
feat: Add SSL support for PostgreSQL database connections
2025-07-21 02:07:49 +08:00
Daniel.y
74e0989a49
Merge pull request #1833 from danielaskdd/postgres-extensions-init
Feat: add PostgreSQL extensions for vector and AGE
2025-07-21 02:06:24 +08:00
yangdx
df8b4202f3 feat: Add SSL support for PostgreSQL database connections
- Add SSL configuration options (ssl_mode, ssl_cert, ssl_key, ssl_root_cert, ssl_crl)
- Support all PostgreSQL SSL modes (disable, allow, prefer, require, verify-ca, verify-full)
- Add SSL context creation with certificate validation
- Update initdb() method to handle SSL connection parameters
- Add SSL environment variables to env.example
- Maintain backward compatibility with existing non-SSL configurations
2025-07-21 02:03:06 +08:00
yangdx
19a38d9310 Feat: add PostgreSQL extensions for vector and AGE
- Ensure VECTOR extension is available when PostgreSQL init
- Ensure AGE extension is available when PGGraphStorage init
2025-07-21 01:46:41 +08:00
yangdx
e6de125eb4 Fix linting 2025-07-20 08:20:53 +08:00
yangdx
9f670fcc72 Add workflow to mark stale issues and PRs
- Runs daily at 22:30 UTC+08
- Marks issues stale after 90 days
- Closes stale issues after 7 more days
2025-07-20 08:20:21 +08:00
yangdx
88bf695de5 Update doc for rerank 2025-07-20 00:37:36 +08:00
Daniel.y
b40fafba73
Merge pull request #1815 from danielaskdd/rerank-top-n
Fix: rename rerank parameter from top_k to top_n
2025-07-20 00:30:43 +08:00
yangdx
cb3bf3291c Fix: rename rerank parameter from top_k to top_n
The change aligns with the API parameter naming used by Jina and Cohere rerank services, ensuring consistency and clarity.
2025-07-20 00:26:27 +08:00
yangdx
4d8eda5ce3 Merge branch 'find_text_unit' 2025-07-19 21:09:50 +08:00
yangdx
7e3914052d Optimize text chunk retrieval with batch fetching
- Replace individual chunk fetches with batch get
- Simplify deduplication logic
- Improve error handling for missing data
2025-07-19 21:01:03 +08:00
xuewei
7acca59dfb Improve query for find_text_unit 2025-07-19 17:27:28 +08:00
yangdx
8d8f9e411e Bump core verion to 1.4.4 and api version to 0187 2025-07-19 13:28:39 +08:00
yangdx
2c7d2b3f5f Increase Neo4j connection pool size and timeouts
- Bump default connection pool size to 100
- Add new Neo4j timeout env variables to env.example
2025-07-19 13:27:34 +08:00
Daniel.y
0171e0ce20
Merge pull request #1811 from danielaskdd/fix-keyed-lock
Fix: implemented entity-keyed locks for edge merging operations to ensure robust race condition protection
v1.4.3
2025-07-19 12:22:49 +08:00
yangdx
cba97c62fe Merge branch 'fix-memgraph' into fix-keyed-lock 2025-07-19 11:55:24 +08:00
Daniel.y
66967c3802
Merge pull request #1810 from danielaskdd/fix-memgraph
Fix: add retry mechanism for Memgraph transient errors
2025-07-19 11:54:34 +08:00
Daniel.y
678da3e398
Merge pull request #1809 from danielaskdd/fix-redis
Enhance Redis connection handling with retries and timeouts
2025-07-19 11:52:25 +08:00
yangdx
2d3a530ce8 Fix: Implemented entity-keyed locks for edge merging operations to ensure robust race condition protection
- Replacing string concatenation with direct list passing for lock keys
- Eliminating deadlock risks by removing the lock around node insertion within the edge merge
2025-07-19 11:48:19 +08:00
yangdx
9f5399c2f1 Replace tenacity retries with manual Memgraph transaction retries
- Implement manual retry logic
- Add exponential backoff with jitter
- Improve error handling for transient errors
2025-07-19 11:31:21 +08:00
yangdx
99e58ac752 fix: add retry mechanism for Memgraph transient errors
- Implement exponential backoff retry for transaction conflicts
- Add tenacity-based retry decorator with 5 attempts
- Handle TransientError in upsert_node and upsert_edge operations
- Resolve "Cannot resolve conflicting transactions" errors
- Improve system reliability under concurrent load
2025-07-19 10:34:35 +08:00
yangdx
aea18d7b80 Merge branch 'fix-redis' into fix-keyed-lock 2025-07-19 10:26:08 +08:00
yangdx
6e1657a771 Improve thread safety for relationship rebuilding
- Sort src and tgt for consistent lock keys
- Maintain order-independent locking
2025-07-19 10:25:48 +08:00
yangdx
96b94acc83 Enhance Redis connection handling with retries and timeouts
- Added Redis connection timeout configurations
- Implemented retry logic for Redis operations
- Updated error handling for timeout cases
- Improved connection pool management
- Added environment variable support
2025-07-19 10:15:26 +08:00
yangdx
05bc5cfb64 Improve task execution with early failure detection
- Add early failure detection for async tasks
- Cancel pending tasks on first exception
2025-07-19 10:14:22 +08:00
yangdx
12d4f12e57 fix: sort edge_key components in _locked_process_edges for consistent locking
- Ensures bidirectional relationships use same lock key
- Maintains thread safety for knowledge graph edge operations
2025-07-19 07:36:50 +08:00
Daniel.y
801bdc520e
Merge pull request #1801 from Chida82/main
fix Azure deployment
2025-07-18 16:00:09 +08:00
Daniel.y
1c870454f1
Merge pull request #1802 from danielaskdd/fix-agtype-parsing
fix(postgres): improve AGE agtype parsing and simplify error logging
2025-07-18 08:52:59 +08:00
yangdx
f033fd6f87 fix(postgres): improve AGE agtype parsing and simplify error logging
- Fix JSON parsing errors caused by :: characters in data content
- Implement precise agtype string parsing using rfind() to separate JSON content from type identifiers
- Add robust error handling for malformed JSON in graph data
2025-07-18 08:50:47 +08:00
Dario Chini
5b28233903 fix Azure deployment 2025-07-17 23:11:07 +02:00
Daniel.y
83c8691221
Merge pull request #1799 from danielaskdd/remove-requirements
Remove separate requirements.txt and update Dockerfile to use pip install
2025-07-18 02:11:39 +08:00
yangdx
488028b9e2 Remove separate requirements.txt and update Dockerfile to use pip install 2025-07-18 01:58:46 +08:00
Daniel.y
03cd40d00d
Merge pull request #1797 from danielaskdd/defaul-query-mode
feat: change default query mode from hybrid to mix
2025-07-17 19:23:24 +08:00