Yannick Stephan
db5159fc24
added missing type
2025-02-20 14:47:31 +01:00
Yannick Stephan
c4562f71b9
cleanup extraction
2025-02-20 14:17:26 +01:00
Yannick Stephan
98d005dc1c
updated paralle
2025-02-19 23:32:21 +01:00
Yannick Stephan
8958046b74
cleaned code
2025-02-19 22:07:25 +01:00
Yannick Stephan
2524e02428
remove tqdm and cleaned readme and ollama
2025-02-18 19:58:03 +01:00
Yannick Stephan
613b748dfa
cleaned code
2025-02-18 09:09:12 +01:00
Yannick Stephan
53384e9a46
fixed keywords
2025-02-18 09:06:25 +01:00
Yannick Stephan
0ab8eeed14
cleaned code
2025-02-17 23:29:25 +01:00
Yannick Stephan
ba65329898
cleanup
2025-02-17 23:23:30 +01:00
Yannick Stephan
80272cbf16
fixed edge
2025-02-17 23:20:10 +01:00
Yannick Stephan
efb28c8003
fixed already edge
2025-02-17 23:16:37 +01:00
MdNazishArmanShorthillsAI
c2ff17d343
Added system prompt support in all modes
2025-02-17 16:45:00 +05:30
zrguo
fc6dff04ff
fix logger level
2025-02-17 15:10:15 +08:00
yangdx
ae37454c42
Replace verbose_debug with logger.debug for token logging.
...
- Removed unused verbose_debug import
- Updated debug logging in kg_query
- Updated debug logging in mix_kg_vector_query
- Updated debug logging in kg_query_with_keywords
2025-02-17 12:28:49 +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
yangdx
b450430109
Change log level from info to debug for token count logging
2025-02-16 22:42:53 +08:00
yangdx
8f6e9fcf50
Merge branch 'main' into add-env-settings
2025-02-16 22:34:39 +08:00
yangdx
41cbecdbe6
Add token size limit truncation for node data retrieval
...
• Add truncate_list_by_token_size function
• Limit max tokens for local context
• Add logging for truncation info
• Apply truncation to node_datas list
2025-02-16 21:26:29 +08:00
yangdx
36ff0bfa85
Improve logging message clarity by including max tokens info for truncation
2025-02-16 19:47:20 +08:00
zrguo
f868c1da78
Merge branch 'main' into code-cleaning
2025-02-16 19:41:05 +08:00
yangdx
601df31edf
feat: move query-related settings to env file for better configuration
...
• Add env vars for token and chunk settings
• Add token count logging for prompts
• Add token count logging for context
• Move hardcoded values to env variables
• Improve logging clarity and consistency
2025-02-16 19:26:57 +08:00
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
e6520ad6a2
added typing
2025-02-14 23:49:39 +01:00
Yannick Stephan
66f555677a
cleaning the message and project no needed
2025-02-14 23:31:27 +01:00
Pankaj Kaushal
cd81312659
Enhance Neo4j graph storage with error handling and label validation
...
- Add label existence check and validation methods in Neo4j implementation
- Improve error handling in get_node, get_edge, and upsert methods
- Add default values and logging for missing edge properties
- Ensure consistent label processing across graph storage methods
2025-02-14 16:07:41 +01:00
yangdx
ed73ea4076
Fix linting
2025-02-13 04:12:00 +08:00
yangdx
11c7af7fd8
refactor: use vdb instance's cosine threshold instead of global constant
...
• Remove global COSINE_THRESHOLD
• Use instance-level threshold config
• Update logging statements
• Reference vdb threshold directly
2025-02-13 03:34:31 +08:00
yangdx
3308ecfa69
Refactor logging for vector similarity search with configurable threshold
2025-02-13 02:14:32 +08:00
zrguo
0c3b754108
Fix bugs
2025-02-11 11:42:46 +08:00
Yannick Stephan
acbe3e2ff2
cleaned code
2025-02-09 13:18:47 +01:00
Yannick Stephan
1f8fc44591
cleaned type
2025-02-09 11:46:01 +01:00
Yannick Stephan
f4287804ce
added typing
2025-02-09 10:39:48 +01:00
Yannick Stephan
020fdecc73
cleaned typed not useful
2025-02-08 23:33:11 +01:00
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
c9481c81b9
Add cache type "extract" for entity extraction
2025-02-01 23:05:02 +08:00
yangdx
2d387fa6de
Save keywords to cache only when it's no empty
2025-02-01 22:54:23 +08:00
yangdx
b22a8b216c
Fix linting
2025-02-01 10:36:25 +08:00
yangdx
2a010c985e
Add logging for chunk truncation in mix_kg_vector_query
2025-02-01 10:36:25 +08:00
yangdx
b0d87b2e29
Fix linting
2025-01-31 15:33:50 +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
yangdx
90c765c724
Fix linting
2025-01-29 22:14:18 +08:00
yangdx
4302c65a04
Avoid unnecessary LLM response generation
2025-01-29 21:01:35 +08:00
yangdx
c423f37f62
Lower log level for keyword outputs
2025-01-29 21:00:42 +08:00
MdNazishArmanShorthillsAI
f0b2024667
Query with your custom prompts
2025-01-27 10:32:22 +05:30
yangdx
86282ba434
Fix history_context handling error in kg_query
2025-01-25 22:54:12 +08:00
yangdx
06673b6fb2
Add logging for high and low-level keywords
2025-01-25 20:11:52 +08:00
yangdx
cf2f83377c
fix linting
2025-01-25 16:57:47 +08:00
yangdx
d1969515d3
Add conversation history to naive_query prompt
2025-01-25 16:29:18 +08:00
