Commit Graph

44 Commits

Author SHA1 Message Date
Andy Lee
e595bbb5fb feat: hint for users about wrong model name 2025-07-15 22:40:40 -07:00
Andy Lee
6a1dc895fb feat: disable warmup by default 2025-07-15 22:16:02 -07:00
yichuan520030910320
e5a9ca8787 fix mem compare 2025-07-14 22:55:10 -07:00
Andy Lee
baa60b40d1 fix: smaller warmup id 2025-07-14 15:20:45 -07:00
Andy Lee
3da5b44d7f fix: mlx when searching, added to embedding_server 2025-07-14 01:11:21 -07:00
Andy Lee
8b4654921b fix: run faiss in subprocess to prevent kmp 2025-07-14 00:29:21 -07:00
Andy Lee
3b5a185e60 refactor: check if current emb_server has correct passages/embedder 2025-07-13 22:43:51 -07:00
Andy Lee
fddc61df5e chore: reset to latest version 2025-07-13 17:06:48 -07:00
yichuan520030910320
c69afb56e4 Resolve submodule conflict - update to af2a264 2025-07-13 17:03:42 -07:00
yichuan520030910320
0fa8a9191f add wechat history extract app 2025-07-13 16:52:08 -07:00
Andy Lee
48dda1cb5b feat: mlx 2025-07-13 02:13:04 -07:00
Andy Lee
71ef4b7d4c fix: reproducible dpr on mac 2025-07-12 18:13:22 -07:00
Fangzhou66
88ca09440d fix some hf problem 2025-07-12 16:13:15 -07:00
Andy Lee
8e0ab4a28d chore: update deps 2025-07-12 22:48:13 +00:00
yichuan520030910320
9b8c5041dc update readme 2025-07-12 13:01:11 -07:00
yichuan520030910320
74ffd7ec64 add email test code 2025-07-11 23:59:47 -07:00
Andy Lee
eb6f504789 Datastore reproduce (#3)
* fix: diskann zmq port and passages

* feat: auto discovery of packages and fix passage gen for diskann

* docs: embedding pruning

* refactor: passage structure

* feat: reproducible research datas, rpj_wiki & dpr

* refactor: chat and base searcher

* feat: chat on mps
2025-07-11 23:37:23 -07:00
Andy Lee
27b3a26e75 fix(deps): Update DiskANN with cleaned up CMake configuration 2025-07-08 23:27:05 +00:00
Andy Lee
41d872504e feat(deps): Update DiskANN to use system-installed Boost and Protobuf 2025-07-08 23:13:36 +00:00
Andy Lee
963cd05273 chore: diskann modules 2025-07-08 21:57:38 +00:00
Andy Lee
09b6e67baf chore: diskann upg boost 2025-07-08 21:44:44 +00:00
yichuan520030910320
dafb2aacab update macos env 2025-07-08 14:37:41 -07:00
Andy Lee
a6c400cd4f chroe: linux boost and protobuf 2025-07-08 21:25:43 +00:00
Andy Lee
c013e5ccce chore: linux deps 2025-07-08 13:55:39 -07:00
Andy Lee
f25a1a3840 chore: macos compatible 2025-07-08 13:32:00 -07:00
yichuan520030910320
6497e17671 add gpu chunk embedd and add complexity in hnsw 2025-07-08 18:40:52 +00:00
yichuan520030910320
44369a8138 update diskann module 2025-07-07 18:27:07 -07:00
yichuan520030910320
637dab379e add workaround code 2025-07-07 23:13:47 +00:00
yichuan520030910320
6fc57eb48e add reuse code 2025-07-07 21:07:00 +00:00
yichuan520030910320
95a653993a rm useless 2025-07-06 06:47:20 +00:00
yichuan520030910320
af0959818d rm useless 2025-07-06 05:21:05 +00:00
Andy Lee
cf17c85607 Make DiskANN and HNSW work on main example (#2)
* fix: diskann zmq port and passages

* feat: auto discovery of packages and fix passage gen for diskann
2025-07-05 22:18:12 -07:00
Andy Lee
a38bc0a3fc refactor: embedding server manager 2025-07-06 01:54:46 +00:00
yichuan520030910320
df63526503 merge main 2025-07-06 00:50:58 +00:00
yichuan520030910320
e92deee1e8 fix larger file read and add faq 2025-07-06 00:48:57 +00:00
Andy Lee
910927a405 feat: support more embedders 2025-07-06 00:35:07 +00:00
Andy Lee
0aa84e147b feat: hnsw embedding server and csr format 2025-07-05 23:04:41 +00:00
yichuan520030910320
368474d036 fix larger file read and add faq 2025-07-03 23:25:36 +00:00
yichuan520030910320
a627abe794 fix file path bug still compatiable bug in hnsw search 2025-07-03 02:02:42 +00:00
yichuan520030910320
44815ee7fd add configuable funcname 2025-07-02 05:18:00 +00:00
yichuan520030910320
371e3de04e add configuable funcname 2025-07-01 05:02:01 +00:00
yichuan520030910320
b81b5d0f86 256 cannot work but increase chunk size can 2025-07-01 04:09:18 +00:00
yichuan520030910320
a075fd6f47 Add DiskANN and faiss as submodules 2025-06-30 10:11:39 +00:00
yichuan520030910320
46f6cc100b Initial commit 2025-06-30 09:05:05 +00:00