Daniel.y
79a2007f1f
Merge pull request #1552 from danielaskdd/ollama-user-prompt
...
Add user prompt support for Ollama api
2025-05-09 11:53:55 +08:00
yangdx
8145b436c8
Fix linting
2025-05-09 11:52:10 +08:00
yangdx
0751382e65
Update README.md
2025-05-09 11:51:22 +08:00
yangdx
fb4f12ba8e
Add user prompt support for Ollama api
2025-05-09 11:37:43 +08:00
yangdx
4e1caf1e40
Fix lingting
2025-05-09 10:43:37 +08:00
yangdx
11fa70f7d1
Update README.md
2025-05-09 10:43:19 +08:00
Arjun Rao
6ebd76d5da
bugfix: convert config val to int
2025-05-09 04:22:46 +10:00
Daniel.y
0e3ecbfd6c
Merge pull request #1550 from danielaskdd/keyword-join-with-comma
...
Deduplicate merged relation keywords
2025-05-08 16:10:41 +08:00
yangdx
b8e88cfc6d
Merge branch 'keyword-join-with-comma' of github.com:danielaskdd/LightRAG into keyword-join-with-comma
2025-05-08 16:06:53 +08:00
yangdx
d2d755db7b
Normalize keyword extration result
2025-05-08 16:05:52 +08:00
yangdx
2fefb57356
Normalize keyword extration result
2025-05-08 16:05:08 +08:00
yangdx
de40f1b5b3
Deduplicate merged relation keywords
2025-05-08 15:52:18 +08:00
yangdx
b92f9b9453
Optimizing query prompt
2025-05-08 12:53:28 +08:00
Arjun Rao
b7eae4d7c0
Use the context manager for the openai client
...
This avoids issues of resource cleanup (too many open files) when dealing with massively parallel calls to the openai API since RAII in python is highly unreliable in such contexts.
2025-05-08 11:42:53 +10:00
yangdx
2bafc87a80
Add comment for deprecated PROMPT template
2025-05-08 09:40:38 +08:00
yangdx
3025094c62
Add commments for deprecated functions
2025-05-08 09:36:57 +08:00
Arjun Rao
f2c522ce7a
Allow max_connections to be configured in postgres
2025-05-08 11:00:56 +10:00
yangdx
4a03218450
Update README.md
2025-05-08 05:26:59 +08:00
Daniel.y
f9d2415108
Merge pull request #1546 from danielaskdd/user-prompt
...
Feat: Add user prompt to QueryParam
2025-05-08 04:38:32 +08:00
Daniel.y
606df5fe68
Merge pull request #1545 from danielaskdd/change-naive-context-to-json
...
Optimize query context format for mix and naive mode query
2025-05-08 04:30:01 +08:00
yangdx
10dbbe4ebf
Fix linting
2025-05-08 04:29:43 +08:00
yangdx
45d4db1eff
Update webui assets
2025-05-08 04:18:19 +08:00
yangdx
12a8caa6ed
Remove unsed i18n translate key
2025-05-08 04:17:25 +08:00
yangdx
d914de441e
Add user_prompt to WebUI
2025-05-08 04:15:21 +08:00
yangdx
a359414931
Remove CardDescription
2025-05-08 03:47:13 +08:00
yangdx
ae1c9f8d10
Add user_prompt the QueryParam
2025-05-08 03:38:47 +08:00
yangdx
08e532eaf3
Remove unused text_chunks_db param from naive_query
2025-05-08 03:26:14 +08:00
yangdx
147f73002d
Remove ll-keywords and hl-keywords from WebUI
2025-05-07 19:07:31 +08:00
yangdx
474b77c43e
Remove deprecated mix_rag_response prompt template
2025-05-07 18:11:35 +08:00
yangdx
1c5bbe396a
Optimize prompt template for naive query
2025-05-07 18:11:12 +08:00
yangdx
3eb3b170ab
Remove list_of_list_to_dict function
2025-05-07 18:01:23 +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
59771b60df
Optimize relationship title to entity1 and entity2
2025-05-07 13:02:22 +08:00
yangdx
1e03888cef
Change function name get_kg_context to _get_kg_context
2025-05-07 10:57:33 +08:00
yangdx
3146309fde
Change function name from list_of_list_to_json to list_of_list_to_dict
2025-05-07 10:52:26 +08:00
yangdx
edb3d6ac11
Improve query context format for mix mode
2025-05-07 10:51:44 +08:00
Daniel.y
ade1425f1f
Merge pull request #1539 from danielaskdd/json-code-block-freezing
...
Resolve json code block freezing issue in WebUI
2025-05-07 04:45:42 +08:00
yangdx
ee420f135a
Bump api version to 0168
2025-05-07 04:37:20 +08:00
yangdx
217d80bfd8
Update webui assets
2025-05-07 04:36:48 +08:00
yangdx
1509e3985e
Resolve json code block freezing issue
2025-05-07 04:35:53 +08:00
Daniel.y
7ff23dded1
Merge pull request #1538 from danielaskdd/ignore-chat-history-in-vector-search
...
Ignore chat history in vector search
2025-05-07 04:03:14 +08:00
yangdx
2485bfe53c
Fix linting
2025-05-07 03:57:14 +08:00
yangdx
910a7a8936
Unified vector retrieval logic for mix and naive queries
2025-05-07 03:47:09 +08:00
yangdx
1794b57b43
Ignore chat history in vector search
2025-05-07 03:20:39 +08:00
yangdx
c984ebd462
Improve mix query context format
2025-05-07 03:11:59 +08:00
yangdx
098846b651
Improve naive query context format
2025-05-07 02:52:05 +08:00
Daniel.y
a26c5d1644
Merge pull request #1537 from danielaskdd/redundant-chunk-fetch
...
Eliminate redundant chunk data fetching in naive and mix query mode
2025-05-07 02:05:05 +08:00
yangdx
365ef75447
Add deprecating commend to text_chunks storage
2025-05-07 02:03:57 +08:00
yangdx
0e3e936e1a
Bump api version to 0167
2025-05-07 01:52:29 +08:00
yangdx
b1f874b489
Fix linting
2025-05-07 01:51:58 +08:00
