yangdx
bb7b360269
Fix linting
2025-05-13 21:35:04 +08:00
yangdx
4d57370c94
Refactor: Move get_env_value from api.config to utils
...
Relocates the `get_env_value` utility function
from `lightrag.api.config` to `lightrag.utils` to decouple
LightRAG core from API Server
2025-05-10 08:58:18 +08:00
yangdx
3025094c62
Add commments for deprecated functions
2025-05-08 09:36:57 +08:00
yangdx
08e532eaf3
Remove unused text_chunks_db param from naive_query
2025-05-08 03:26:14 +08:00
yangdx
156244e260
Refactor: Unify naive context to JSON format
...
- Merges 'mix' mode query handling into 'hybrid' mode, simplifying query logic by removing the dedicated `mix_kg_vector_query` function
- Standardizes vector search result by using JSON string format to build context
- Fixes a bug in `query_with_keywords` ensuring `hl_keywords` and `ll_keywords` are correctly passed to `kg_query_with_keywords`
2025-05-07 17:42:14 +08:00
yangdx
365ef75447
Add deprecating commend to text_chunks storage
2025-05-07 02:03:57 +08:00
yangdx
dbfcf30801
Fix linting
2025-05-06 22:03:40 +08:00
yangdx
c8ecfa2d68
feat: Centralize configuration and update defaults
...
This commit introduces `lightrag/constants.py` to centralize default values for various configurations across the API and core components.
Key changes:
- Added `constants.py` to centralize default values
- Improved the `get_env_value` function in `api/config.py` to correctly handle string "None" as a None value and to catch `TypeError` during value conversion.
- Updated the default `SUMMARY_LANGUAGE` to "English"
- Set default `WORKERS` to 2
2025-05-06 22:00:43 +08:00
yangdx
9a41de51fb
Optimize log message
2025-05-04 22:20:44 +08:00
yangdx
b9b86df786
Persistent LLM cache on error
2025-05-03 23:00:09 +08:00
yangdx
36f8787bc7
Fix linting
2025-05-01 10:04:31 +08:00
yangdx
a561be0cff
Fix time zone problem of doc status
2025-05-01 02:16:19 +08:00
yangdx
0ecae90002
Enhance the function's robustness
2025-04-28 22:52:31 +08:00
yangdx
90a07b0420
Remove unused params
2025-04-28 21:14:19 +08:00
yangdx
ef69009c15
Increase the priority of queries related to LLM requests
2025-04-28 19:36:21 +08:00
yangdx
140b1b3cbb
Add priority control for limited async decorator
2025-04-28 18:12:29 +08:00
yangdx
3e385b5f81
Optimize logger info
2025-04-28 02:39:18 +08:00
yangdx
594e7b751a
Fix linting
2025-04-28 02:15:25 +08:00
yangdx
18040aa95c
Improve parallel handling logic between extraction and merge operation
2025-04-28 01:14:00 +08:00
yangdx
7f09972901
Optimize error log
2025-04-24 15:46:25 +08:00
yangdx
3aab5b41f2
Fix linting
2025-04-24 14:15:10 +08:00
yangdx
4f68f3e410
Using semaphore to control parallel doc processing instead of batching.
2025-04-24 13:45:44 +08:00
earayu
7597a5bdfb
feat: support aget_docs_by_ids
2025-04-21 13:27:16 +08:00
yangdx
733e307a8d
Merge branch 'stevezhangishero/main'
2025-04-20 15:18:36 +08:00
yangdx
cd01ec64d3
Add tokenizer to global_config
2025-04-20 14:51:11 +08:00
drahnreb
de827abcc7
prepare rebase
2025-04-18 16:32:09 +02:00
drahnreb
9c6b5aefcb
fix linting
2025-04-18 16:24:43 +02:00
drahnreb
e71f466910
fix: take global_config from storage class
2025-04-18 16:24:43 +02:00
drahnreb
20ba1eb9c2
add: to optionally replace default tiktoken Tokenizer with a custom one
2025-04-18 16:24:43 +02:00
stevezhang
6a1e9baa24
refactor(lightrag): Optimize error handling and logging
...
[During operation] Failure to properly log exception details
- Use traceback.format_exc() to capture comprehensive error traces when processing documents
- Log verbose error context upon failures in entity/relationship extraction
- Enhance system stability and debuggability by expanding exception catching and structured logging
2025-04-17 16:08:58 +08:00
朱 东
ecd1fc48c2
fix: add miss key for ainsert_custom_chunks
2025-04-17 11:53:01 +08:00
yangdx
5c1d4201f9
Fix linting
2025-04-14 12:08:56 +08:00
yangdx
89d1e68d97
Move graph edit function implemention to a utils_graph.py to educe the size of lightray.py
2025-04-14 03:06:23 +08:00
yangdx
6dd67748ca
Add graph_db_lock to esure consistency across multiple processes for node and edge edition jobs
2025-04-14 00:07:31 +08:00
yangdx
ecfe4209c3
Update log message
2025-04-12 21:34:50 +08:00
yangdx
745301ea13
Deleted node2vec implementation
2025-04-11 18:41:45 +08:00
choizhang
eb3038e55a
docs(locales): Update multilingual files to include descriptions of bypass mode
2025-04-11 15:13:58 +08:00
choizhang
a12d60e4ea
feat: Add query mode 'bypass' to bypass knowledge retrieval and directly use LLM
2025-04-11 02:57:34 +08:00
yangdx
96f439bb52
Optimize pipeline status message
2025-04-10 21:19:26 +08:00
yangdx
3007dff153
Add env FORCE_LLM_SUMMARY_ON_MERGE
2025-04-10 17:29:07 +08:00
yangdx
ac7e275932
Fix linting
2025-04-02 18:36:05 +08:00
yangdx
d7d04a0d94
Update graph retrival api(abandon pydantic model)
2025-04-02 18:32:03 +08:00
yangdx
0981ee1af9
Replace delete() with drop_cache_by_modes() method to implement cache clearing operations
2025-03-31 23:23:31 +08:00
yangdx
1772e7a887
Add delete support to all storage implementation
2025-03-31 16:21:20 +08:00
yangdx
6a51f38cae
Remove namespace_prefix from PostgreSQL, maintain consistency with other storage implementation
2025-03-31 02:59:44 +08:00
yangdx
53ab5e015c
remove check_storage_env_vars from lightrag.py
2025-03-30 15:25:04 +08:00
yangdx
1a25a78e8a
feat: remove check_storage_env_vars and add TODOs
...
- Remove unused check_storage_env_vars method
- Add TODO to check if has_edge works on reverse relation
- Add TODO about entities_vdb.client_storage local storage limitation
2025-03-30 10:25:49 +08:00
yangdx
65574459f9
standardize .env loading behavior across modules
2025-03-29 03:48:38 +08:00
yangdx
46f5c5b47f
Fix linting
2025-03-26 17:30:06 +08:00
yangdx
5c18213b24
fix: optimize job name handling in document processing pipeline
...
- Move job name setting to before batch processing
- Fix document and batch counter accumulation
2025-03-26 16:58:31 +08:00
