yangdx
c95656ca87
feat: improve debug message handling with better truncation and formatting
2025-02-21 16:28:08 +08:00
yangdx
8164c57b7e
Fix linting
2025-02-21 14:59:50 +08:00
yangdx
cff229a806
fix: respect user-specified log level in set_logger
...
Previously, the set_logger function would always set the log level to DEBUG, overriding any user-specified log level.
2025-02-21 14:46:27 +08:00
Yannick Stephan
c7bc2c63cf
cleanup storages
2025-02-20 13:21:41 +01:00
Yannick Stephan
32e489865c
cleanup code
2025-02-20 13:18:17 +01:00
Yannick Stephan
2524e02428
remove tqdm and cleaned readme and ollama
2025-02-18 19:58:03 +01:00
Yannick Stephan
24ae083284
removed never used method
2025-02-18 19:38:04 +01:00
Yannick Stephan
161baa6f08
pm bs4 when ollama
2025-02-18 17:11:17 +01:00
zrguo
fce24f7611
Merge pull request #797 from danielaskdd/add-env-settings
...
Add the token size truncation for local query and token size setting by env
2025-02-17 15:00:07 +08:00
ArnoChen
6da53a302a
add api tab in webui and handle invalid num_turns
2025-02-17 12:32:04 +08:00
yangdx
9963fb7ff4
Make VERBOSE_DEBUG configurable via environment variable
...
- Adds environment variable support
- Defaults to "false" if not set
- Case-insensitive check for "true"
- Simplifies debugging configuration
- Maintains backward compatibility
2025-02-17 11:37:38 +08:00
yangdx
806eadf5dc
Add verbose debug option to control detailed debug output level
...
• Added VERBOSE env var & CLI flag
• Implemented verbose_debug() function
• Added verbose option to splash screen
• Reduced default debug output length
• Modified LLM debug logging behavior
2025-02-17 01:38:18 +08:00
Yannick Stephan
3319db0dba
cleaned code
2025-02-15 22:37:32 +01:00
Yannick Stephan
eaf1d553d2
improved typing
2025-02-15 22:37:12 +01:00
Yannick Stephan
621540a54e
cleaned code
2025-02-15 00:23:14 +01:00
Yannick Stephan
66f555677a
cleaning the message and project no needed
2025-02-14 23:31:27 +01:00
yangdx
cdd52809b0
Fix linting
2025-02-13 14:07:36 +08:00
yangdx
e5adb2e0f3
Improve cache logging and add more detailed log messages
...
• Add cache type to log data structure
• Make debug logs more detailed
• Add high-level info logs for cache hits
• Add null check for best_response
• Improve log message readability
2025-02-13 13:53:52 +08:00
Yannick Stephan
1f8fc44591
cleaned type
2025-02-09 11:46:01 +01:00
ultrageopro
19ee3d109c
feat: trimming the model’s reasoning
2025-02-06 22:56:17 +03:00
yangdx
0a693dbfda
Fix linting
2025-02-02 04:27:55 +08:00
yangdx
8484564f50
Fix llm_model_func retrieval error.
2025-02-02 03:54:41 +08:00
yangdx
873b52d2e4
Add debug logging for cache response retrieval
2025-02-02 03:15:43 +08:00
yangdx
bed5a97ae2
Fix prompt respond cache fail when is_embedding_cache_enabled is true
2025-02-02 03:09:06 +08:00
yangdx
5d14ab03eb
Fix linting
2025-02-02 01:56:32 +08:00
yangdx
b45ae1567c
Refactor LLM cache handling and entity extraction
...
- Removed custom LLM function in entity extraction
- Simplified cache handling logic
- Added `force_llm_cache` parameter
- Updated cache handling conditions
2025-02-02 01:28:46 +08:00
yangdx
6c7d7c25d3
Refactor cache handling logic for better readability, keep function unchanged.
2025-02-02 00:10:21 +08:00
yangdx
c9481c81b9
Add cache type "extract" for entity extraction
2025-02-01 23:05:02 +08:00
yangdx
3c3cdba499
Fix typo error
2025-02-01 22:27:49 +08:00
yangdx
3bc7c4d8f1
Save cache_type to llm_response_cache
2025-02-01 22:18:59 +08:00
yangdx
c3942077a9
Use direct embedding_func from hashing_kv (do not by pass maxiumu async control)
2025-02-01 22:12:45 +08:00
yangdx
c98a675b6c
remove unused parm
2025-02-01 22:07:12 +08:00
yangdx
95edf8a51e
Fix linting
2025-02-01 15:22:40 +08:00
yangdx
b109f57ddd
Refactor async call limiting to use asyncio.Semaphore for better performance.
...
- Replace custom counter with asyncio.Semaphore
- The existing implementation cannot follow the FIFO order
2025-02-01 10:36:25 +08:00
yangdx
2ba36f87e3
Add support for list input in quantize_embedding function
...
- Convert list to numpy array if needed
- Maintain existing functionality
2025-02-01 10:36:25 +08:00
yangdx
1192727be7
remove semaphore logic from EmbeddingFunc(cause num of instances is already control by limit_async_func_call)
2025-02-01 10:36:25 +08:00
yangdx
b0d87b2e29
Fix linting
2025-01-31 15:33:50 +08:00
yangdx
54b68074a1
Merge branch 'main' into fix-extract-entity-concurrent-problem
2025-01-31 01:19:44 +08:00
yangdx
3150c2812f
Fix loop step from 1 to 2 in get_conversation_turns, ensure user-assistant pairing
2025-01-30 13:08:27 +08:00
yangdx
cc50ade14e
Fix concurrent problem on extract_entities function.
...
- Abandon the approach of temporarily replacing the global llm_model_func configuration
- Introduce custom_llm function with new_config for handle_cache while extracting entities
- Update handle_cache to accept custom_llm
2025-01-30 02:45:33 +08:00
zrguo
80451af839
fix linting errors
2025-01-27 23:21:34 +08:00
Saifeddine ALOUI
16d1ae77ee
fixed csv_string_to_list when data contains null
2025-01-27 10:15:30 +01:00
Saifeddine ALOUI
315f0bf5f9
Added escaping to list_of_list_to_csv
2025-01-27 10:13:06 +01:00
Saifeddine ALOUI
06c9e4e454
Fixed missing imports bug and fixed linting
2025-01-25 00:55:07 +01:00
Saifeddine ALOUI
34018cb1e0
Separated llms from the main llm.py file and fixed some deprication bugs
2025-01-25 00:11:00 +01:00
Magic_yuan
5719aa8882
支持多轮对话
2025-01-24 19:03:36 +08:00
Magic_yuan
f6d29e1793
修复缓存处理的运行时错误
...
].func # ["func"]
^^^^
AttributeError: 'dict' object has no attribute 'func'
2025-01-24 11:01:32 +08:00
jin
6ae8647285
support pipeline mode
2025-01-16 12:58:15 +08:00
jin
d5ae6669ea
support pipeline mode
2025-01-16 12:52:37 +08:00
jin
85331e3fa2
update Oracle support
...
add cache support, fix bug
2025-01-10 11:36:28 +08:00
