Commit Graph

142 Commits

Author SHA1 Message Date
zrguo
f3ae4fccfa Merge pull request #383 from MRX760/main
added nvidia text-embedding API and example of using nvidia API llm a…
2024-12-04 11:21:46 +08:00
zrguo
cf11401ab3 Merge pull request #384 from Ecocytus/main
fix examples' prompt bug
2024-12-04 11:17:07 +08:00
zrguo
c2e73de88c Merge pull request #378 from doosenn/main
fix neo4jstorage bug
2024-12-04 11:11:19 +08:00
zrguo
ae920fe43b Merge pull request #375 from partoneplay/main
Ollama `embedding` deprecated in favor of `embed`
2024-12-04 11:09:44 +08:00
yuanxiaobin
4a866f3084 修改日志文件路径
- 因为LightRAG的几乎都是导入的utils中的全局logger对象,当多个rag实例的时候并无法完全把日志记录到对应的working_dir,并且应用中删除working_dir时会由于logger的句柄无法删除
- 此修改简化了日志文件的路径,不再依赖于 working_dir 属性,日志文件独立于working_dir
2024-12-04 08:44:13 +08:00
Yizhi Zhang
380a1d1bc3 fix bug of example prompt 2024-12-03 22:25:50 +08:00
MRX760
0b87e4649f added nvidia text-embedding API and example of using nvidia API llm and text-embedding 2024-12-03 17:15:10 +07:00
zuoluo
2786004972 fix neo4jstorage bug 2024-12-03 16:04:58 +08:00
partoneplay
18e86a1825 embedding deprecated in favor of embed 2024-12-03 08:42:36 +08:00
zrguo
608c7ff956 Merge pull request #368 from AdityaKalraShorthillsAI/main
Added embedding_func argument in Neo4JStorage class's __init__ method in neo4j implementation
2024-12-02 16:02:53 +08:00
zrguo
1420669891 Merge pull request #360 from ahmadhatahet/azure_openai_embedding
Azure OpenAI Embedding
2024-12-02 16:02:13 +08:00
zrguo
66cf15e7f1 Merge pull request #354 from TashaSkyUp/patch-1
fix for #209
2024-12-02 15:53:08 +08:00
AdityaKalraShorthillsAI
8d5af931d7 Added embedding_func argument in Neo4JStorage class's __init__ method in neo4j implementation 2024-12-02 02:44:47 +05:30
b10902118
3f9d19401f fix with ruff (unused import) 2024-12-01 16:09:24 +08:00
Ahmad Hatahet
137315ec18 add api_version to azure_openai_complete_if_cache 2024-11-30 17:47:33 +01:00
Ahmad Hatahet
9b92d425f6 update max_token_size according to openai doc 2024-11-30 17:16:07 +01:00
Ahmad Hatahet
38c8a6e97c add api_version to args 2024-11-30 17:11:38 +01:00
Tasha Upchurch
f0ea55d709 fix for #209
function was returning a closed event loop.
2024-11-29 13:27:08 -07:00
b10902118
2e95c633cf fix error and tested 2024-11-30 00:00:51 +08:00
b10902118
b0dd600429 support JSON output for ollama and openai 2024-11-29 21:41:37 +08:00
Sebastian Schramm
ba25614423 fix templating of language in prompts 2024-11-28 14:28:29 +01:00
jin
a88908009c Merge branch 'HKUDS:main' into main 2024-11-27 15:16:28 +08:00
jin
28bc45c8f5 fix formate 2024-11-26 10:21:39 +08:00
jin
5bde05ed53 add LightRAG init parameters in readme
also fix some error
2024-11-26 10:19:28 +08:00
Larfii
abc56d68a2 Add custom KG insertion 2024-11-25 18:06:19 +08:00
Larfii
ac1587ad2a Add a progress bar 2024-11-25 15:04:38 +08:00
jin
0ffd44b79c Update oracle_impl.py 2024-11-25 14:21:01 +08:00
jin
b5050ba80c Update oracle_impl.py 2024-11-25 14:15:10 +08:00
jin
21f161390a Logic Optimization 2024-11-25 13:40:38 +08:00
jin
bf5815be8f Merge branch 'main' of https://github.com/jin38324/LightRAG 2024-11-25 13:32:33 +08:00
jin
af3aef5d88 Optimization logic 2024-11-25 13:29:55 +08:00
zrguo
6aeb2cf09a Merge pull request #320 from Lizidong01/main
删除Neo4JStorage.has_edge中定义的没有用到的同步close函数
2024-11-22 15:14:25 +08:00
lzd
e6f380fc7a 删除Neo4JStorage.has_edge中定义的没有用到的同步close函数 2024-11-22 13:59:14 +08:00
zzzcccxx
116e1d20a9 修改了relation_counts计数规则 2024-11-21 14:35:18 +08:00
LarFii
bcaaaad959 Update 2024-11-19 16:52:26 +08:00
zrguo
14cd7bad24 Merge pull request #302 from Luobots/main
A more robust approach for result to json.
2024-11-19 16:26:29 +08:00
zrguo
93e0dcfd59 Merge pull request #286 from Sucran/main
fix neo4j bug
2024-11-19 15:25:49 +08:00
luoyifan
c9becdf5f4 A more robust approach for result to json. 2024-11-19 14:02:38 +08:00
tmuife
89d7967349 use pre-commit reformat 2024-11-18 13:52:49 +08:00
tmuife
8e16f0815c change the type of binding parameters in Oracle23AI 2024-11-18 10:00:06 +08:00
Richard
5661d76860 fix neo4j bug 2024-11-15 13:11:43 +08:00
jin
d6589684ef use oracle bind variables to avoid error 2024-11-15 12:57:01 +08:00
LarFii
30cf5a62ee fix cache bug 2024-11-14 15:59:37 +08:00
zrguo
87aad3554e Merge pull request #266 from davidleon/fix_hf_embedding_device
fix hf embedding to support loading to different device
2024-11-14 07:50:52 +08:00
david
38e1956395 fix hf embedding to support loading to different device 2024-11-13 14:20:36 +08:00
Rick Battle
83f8a5139c Only update storage if there was something to insert
Before, the `finally` block would always call `_insert_done()`, which writes out the `vdb_*` and `kv_store_*` files ... even if there was nothing to insert (because all docs had already been inserted).  This was causing the speed of skippable inserts to become very slow as the graph grew.
2024-11-12 09:30:21 -07:00
jin
33caba3e12 fix pre commit 2024-11-12 13:32:40 +08:00
jin
90790747ee Update oracle_impl.py 2024-11-12 13:23:03 +08:00
jin
66799fb685 Update oracle_impl.py 2024-11-12 13:03:03 +08:00
jin
5dce625464 Update oracle_impl.py 2024-11-12 12:02:24 +08:00