Commit Graph

162 Commits

Author SHA1 Message Date
澄潭
29079f4e2a Support set buffer limit (#1153) 2024-07-25 20:42:39 +08:00
Kent Dong
b6d07a157c feat: Always buffer request body in ai-proxy plugin (#1155) 2024-07-25 19:35:39 +08:00
澄潭
10569f49ae support keep original auth header (#1151) 2024-07-24 19:31:38 +08:00
Kent Dong
0cfef34bff feat: Support fallback route in ai-proxy plugin (#1123) 2024-07-24 19:25:32 +08:00
rinfx
5c2b5d5750 potential bug fix (#1141) 2024-07-24 19:24:47 +08:00
rinfx
8f483518a9 support take effect on api level (#1150) 2024-07-24 19:23:55 +08:00
Kent Dong
f6ee4ed166 fix: Bypass the response body processing in ai-proxy if it is returned internally (#1149) 2024-07-24 16:18:00 +08:00
rinfx
8c48fcb423 update template decorator (#1142) 2024-07-22 17:04:55 +08:00
007gzs
ef31e09310 feat: add rust demo plugin request block (#1091)
Co-authored-by: Yi <lynskylate@gmail.com>
2024-07-22 15:49:06 +08:00
韩贤涛
c0f2cafdc8 feat: support ext_auth wasmplugin (#1103) 2024-07-17 15:30:32 +08:00
Kent Dong
d5a9ff3a98 fix: Fix possible type-casting related panics in ai-proxy plugin (#1127) 2024-07-16 18:38:43 +08:00
Kent Dong
f069ad5b0d feat: Add statusCodeDetails info when returning response in Wasm plugins directly (#1116) 2024-07-16 09:52:46 +08:00
mamba
5041277be3 feat: 🎸 add frontend gray plugin (#1120)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-07-15 15:47:04 +08:00
rinfx
c00c8827f9 support service-level match config (#1112) 2024-07-15 14:00:02 +08:00
rinfx
46218058d1 token-ratelimit crash bugfix (#1119) 2024-07-12 15:05:15 +08:00
Kent Dong
5306385e6b feat: Support loading custom parameters in build-and-push-wasm-plugin-image.yaml (#1118) 2024-07-12 14:23:12 +08:00
Se7en
4e881fdd3f doc: update cluster-key-rate-limit doc (#1113)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-07-11 17:31:14 +08:00
Kent Dong
5a2c6835f7 feat: Support embeddings API for Qwen in the ai-proxy plugin (#1079) 2024-07-08 19:37:08 +08:00
Kent Dong
12a5612450 feat: Support model prefix mapping in ai-proxy (#1097) 2024-07-08 19:33:08 +08:00
nohup
b9f5c4d1f2 feat: support Cloudflare Workers AI (#1068)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-07-08 19:27:11 +08:00
pepesi
e0159f501a fix jwt-auth plugin claims_to_headers failed (#1075) 2024-07-03 10:11:17 +08:00
pepesi
086a9cc973 fixed ai-statistics plugin statistics error (#1060) 2024-07-02 20:35:12 +08:00
澄潭
f64c601264 compatiable with openai sdk (#1061)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-06-27 09:30:52 +08:00
Se7en
51dca7055a feat: support claude ai model (#969)
Signed-off-by: chengzw <chengzw258@163.com>
2024-06-19 13:53:21 +08:00
Chi Kai
ab1bc0a73a feat: support stepfun model (#1012)
Co-authored-by: Kent Dong <kentstl@163.com>
2024-06-19 13:51:02 +08:00
Kent Dong
ffee7dc5ea fix: Accommodate the incomplete function name in the initial event from Qwen (#1045) 2024-06-19 13:48:20 +08:00
rinfx
1ea87f0e7a add plugin: ai-token-ratelimit (#1015) 2024-06-19 13:46:59 +08:00
rinfx
7164653446 ai rag updates (#1046) 2024-06-19 13:46:17 +08:00
rinfx
0785d4aac4 add plugin: ai-statistics (#1011) 2024-06-18 17:53:04 +08:00
rinfx
4ca4bec2b5 add plugin: ai-transformer (#1035) 2024-06-18 17:51:38 +08:00
rinfx
174350d3fb add plugin: ai-rag (#1038) 2024-06-17 15:37:00 +08:00
rinfx
0380cb03d3 add plugin: ai-prompt-template (#1019) 2024-06-17 15:33:05 +08:00
rinfx
15d9f76ff9 add plugin: ai-prompt-decorator (#1021) 2024-06-17 15:31:34 +08:00
rinfx
5f15017963 add plugin: ai-security-guard (#1034) 2024-06-17 10:41:46 +08:00
韩贤涛
634de3f7f8 feat: cluster key rate limit enhancement (#1036) 2024-06-17 10:37:03 +08:00
韩贤涛
12cc44b324 feat: cluster key rate limit (#1002) 2024-06-12 14:51:46 +08:00
韩贤涛
d53c713561 feat: support minimax ai model (#1033) 2024-06-09 21:01:31 +08:00
韩贤涛
2db0b60a98 feat: support baidu ernie bot ai model (#1024)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-06-06 18:19:55 +08:00
nash5
c6e3db95e0 feature: add hunyuan llm support for plugins/ai-proxy (#1018)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-06-06 18:11:51 +08:00
Ink33
ed976c6d06 feat(plugin): implement golang version of plugin jwt-auth (#743)
Signed-off-by: Ink33 <Ink33@smlk.org>
2024-06-06 10:22:51 +08:00
Kent Dong
6e4ade05a8 doc: Add instructions of how to build ai-proxy plugin (#1005) 2024-05-31 13:59:43 +08:00
Kent Dong
bdd050b926 fix: Fix tool_calls compatibility issues with LobeChat (#1009) 2024-05-30 19:20:48 +08:00
澄潭
38ddc49360 Optimize the method for judging streaming responses (#1017) 2024-05-30 17:50:28 +08:00
澄潭
909f8bc719 Update main.go 2024-05-30 10:26:52 +08:00
澄潭
863d0e5872 Update main.go 2024-05-30 09:53:48 +08:00
澄潭
812edf1490 add ai cache plugin (#1010) 2024-05-29 21:10:22 +08:00
Yang Beining
51b9d9ec4b feat: Add the ZhipuAI (ChatGLM) provider to the ai-proxy wasm plugin #950 (#1007)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-05-28 11:29:36 +08:00
Yifan Gao
50f79c9099 feat: support ollama ai model (#1001)
Co-authored-by: Kent Dong <ch3cho@qq.com>
2024-05-28 10:55:59 +08:00
澄潭
ca1ad1dc73 Fixed the issue where an empty string system prompt would be set when enabling file id. (#999) 2024-05-24 16:27:02 +08:00
澄潭
e09edff827 Fix the issue with multiple system prompts when using qwen-long file id mode. (#994)
Signed-off-by: johnlanni <zty98751@alibaba-inc.com>
2024-05-24 14:43:34 +08:00