Commit Graph

647 Commits

Author SHA1 Message Date
rinfx
af8748d754 add inject_encoded_data_to_filter_chain_on_header example (#3071) 2025-10-30 10:58:25 +08:00
johnlanni
d386739e48 upgrade wasm-go to 1.0.4 in jsonrpc-converter
Change-Id: I6a5fc136907e9864a6450d53f6ec5b926af8887c
Signed-off-by: johnlanni <zty98751@alibaba-inc.com>
2025-10-29 17:53:50 +08:00
woody
5e4c262814 Feat/vllm provider (#3067) 2025-10-29 14:31:38 +08:00
rinfx
2a320f87a6 [feature] add checking of maliciousUrl & modelHallucination, and adjust consumer specific configs (#3024) 2025-10-28 14:12:54 +08:00
SaladDay
1bcef0c00c feature: support secret reference for Redis password in MCP Server (#3006)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
2025-10-27 13:33:52 +08:00
Libres-coder
7c4899ad38 feat(mcp): add list-plugin-instances tool for AI Agent (#3038) 2025-10-25 20:39:22 +08:00
victorserbu2709
5fc1d6b222 Add ApiNameAnthropicMessages in claude capabilities (#3040) 2025-10-23 09:54:47 +08:00
澄潭
271e6036fa feat(ai-proxy): enable Qwen compatible mode by default and add missing API endpoints (#3032) 2025-10-22 11:17:09 +08:00
澄潭
67b92b76fe fix(jsonrpc-converter): Use raw JSON instead of incorrect JSON string formatting (#2988) 2025-10-16 09:58:06 +08:00
rinfx
6b2d06a330 [bugfix] sometimes bedrock EventStream chunk is not complete (#3010) 2025-10-16 09:52:51 +08:00
韩贤涛
1f301be851 fix: Optimization of Rate Limiting Logic for Cluster, AI Token and WASM Plugin (#2997) 2025-10-15 17:24:42 +08:00
johnlanni
15db773e24 update wasm-go dependency 2025-10-11 16:41:08 +08:00
johnlanni
fe69084c04 enable ai-proxy&ai-statistics rebuild logic with new key 2025-10-11 16:32:32 +08:00
rinfx
fcc7fc0139 record consumer name even the consumer is not allowed (#2992) 2025-10-10 20:00:05 +08:00
rinfx
ac2f7dedaa [key-auth] record consumer name once the consumer name is determined (#2978) 2025-10-09 11:22:09 +08:00
Kent Dong
b351dc45e3 doc: Update the description of azureServiceUrl in ai-proxy README files (#2965) 2025-10-06 15:09:53 +08:00
Jun
aebe354055 add vectordb mapping (#2968) 2025-10-06 15:08:13 +08:00
johnlanni
45a11734bd remove rebuild logic in ai-proxy&ai-statistics 2025-09-26 16:26:06 +08:00
johnlanni
063bfbfcfe fix(ai-proxy): fix streaming process 2025-09-23 19:44:30 +08:00
rinfx
9a3ccff4c8 opt(ai-load-balancer): update global least request lua script for ai-load-balancer (#2945) 2025-09-23 19:24:33 +08:00
澄潭
623c8da8d8 fix(ai-proxy): Fix Azure OpenAI Response API handling and service URL type detection (#2948) 2025-09-23 18:49:55 +08:00
Jun
e2d00da861 fix: llm can be empty and optimize document and prompt (#2942) 2025-09-23 14:03:00 +08:00
rinfx
732aacdbc5 fix(ai-security-guard): compatible with old configs (#2941) 2025-09-23 10:23:25 +08:00
Jun
8b8c8b242b feat: add rag mcp server (#2930) 2025-09-21 14:48:22 +08:00
Jingze
f1345f9973 fix: optimize host pattern matching and fix SSE newline bug (#2899) 2025-09-21 14:34:51 +08:00
韩贤涛
de8a9c539b doc: optimize the documentation for hmac-auth-apisix (#2912) 2025-09-21 14:34:07 +08:00
aias00
88a679ee07 feat(ai-proxy): add Fireworks AI support (#2917) 2025-09-21 14:32:04 +08:00
Xijun Dai
47827ad271 refactor(v2): upgrade module to github.com/alibaba/higress/v2 (#2922)
Signed-off-by: Xijun Dai <daixijun1990@gmail.com>
2025-09-21 14:29:07 +08:00
woody
cd2082033c fix: add AttackLevel field support for MultiModalGuard prompt attack detection (#2938) 2025-09-21 14:25:36 +08:00
rinfx
ef12f40c0e deduplicate think tag for bedrock and vertex (#2933) 2025-09-18 14:35:36 +08:00
rinfx
caae3ee068 [feature] bedrock provider support multimodal and thinking (#2897) 2025-09-18 14:22:37 +08:00
rinfx
d7bebf79e1 vertex support multi-modal, function call and thinking (#2926) 2025-09-18 14:22:22 +08:00
rinfx
e70b9ec437 update ai-security-guard test (#2928) 2025-09-17 16:13:24 +08:00
rinfx
7e9f98d14b [ai-statistics] update logic of api extraction (#2927) 2025-09-16 19:51:18 +08:00
BlueSi1ence
42a74449f7 ai-security-guard compatible with MultiModalGuard interfaces (#2806)
Co-authored-by: rinfx <yucheng.lxr@alibaba-inc.com>
2025-09-15 11:50:38 +08:00
johnlanni
1cc977c6d4 add RebuildAfterRequests config for some plugins 2025-09-12 17:31:46 +08:00
aias00
c1b4cd6644 update(wasm-go): upgrade wasm-go for supporting outputSchema (#2907) 2025-09-12 09:39:03 +08:00
澄潭
89d414e49a fix(ai-proxy): Avoid overwriting the existing original auth header (#2904) 2025-09-11 16:54:26 +08:00
澄潭
e2011cb805 fix(claude): support array content format in tool_result and remove duplicate structs (#2892) 2025-09-10 14:18:44 +08:00
johnlanni
4edf79a1f6 Revert "remove qwen Anthropic compatiable mode"
This reverts commit f7d80373f9.
2025-09-09 21:35:31 +08:00
johnlanni
3ed70b2a1e more compatiable fix for SAA 2025-09-09 20:05:39 +08:00
johnlanni
3e9a3623a1 compatiable for SAA 2025-09-09 17:43:52 +08:00
rinfx
9f0f3de540 support consumer specific check service || =support consumer specific check service (#2891) 2025-09-09 17:35:05 +08:00
澄潭
5384481704 refactor(mcp-server): improve host matching logic using HostMatcher p… (#2890) 2025-09-09 16:14:33 +08:00
johnlanni
f7d80373f9 remove qwen Anthropic compatiable mode 2025-09-09 11:12:49 +08:00
aias00
91a44ea7aa feat(provider): add support for meituan longcat || feat(provider): add support for meituan longcat (#2883) 2025-09-08 13:38:40 +08:00
xingpiaoliang
d053e01540 feat(ai-proxy): Add provider: nvidia's triton-server (#2843) 2025-09-08 13:37:30 +08:00
澄潭
4a429bf147 fix(ai-proxy): resolve Claude streaming response conversion and SSE event chunking issues (#2882) 2025-09-08 09:54:18 +08:00
lvshui
039c6615a9 fix: When the sse event is divided into multiple chunks, the sse connection is blocked (#2865)
Co-authored-by: 澄潭 <zty98751@alibaba-inc.com>
2025-09-05 14:48:35 +08:00
韩贤涛
7e74eeb333 feat(wasm-plugin): add tests and docs for hmac-auth-apisix (#2842) 2025-09-01 14:07:57 +08:00